filter-frame-dedup 1.1.1__py3-none-any.whl

filter_frame_dedup/__init__.py

@@ -0,0 +1,4 @@
+from filter_frame_dedup.filter import FilterFrameDedupConfig, FilterFrameDedup
+
+
+__all__ = ["FilterFrameDedupConfig", "FilterFrameDedup"]

filter_frame_dedup/filter.py

@@ -0,0 +1,265 @@
+import logging, os, cv2, time
+from openfilter.filter_runtime.filter import FilterConfig, Filter, Frame
+from filter_frame_dedup.hash_processor import HashFrameProcessor
+from filter_frame_dedup.ssim_processor import SSIMProcessor
+
+__all__ = ["FilterFrameDedupConfig", "FilterFrameDedup"]
+
+logger = logging.getLogger(__name__)
+
+
+class FilterFrameDedupConfig(FilterConfig):
+    """
+    Configuration for the Frame Deduplication filter, loaded typically from environment variables.
+    """
+    hash_threshold:                     int = 5                             # Threshold for hash difference
+    motion_threshold:                   int = 1200                          # Threshold for motion detection
+    min_time_between_frames:            float = 1.0                         # Minimum time between saved frames
+    ssim_threshold:                     float = 0.90                        # Threshold for SSIM comparison
+    roi:                                tuple | None                        # Region of interest (x, y, width, height) or None for full image
+    output_folder:                      str = "/output"                     # Output folder for saved frames
+    save_images:                        bool = True                         # Whether to save images to disk
+    debug:                              bool = False                        # Enable debug logging
+    forward_deduped_frames:             bool = False                       # Forward deduplicated frames in a side channel
+    forward_upstream_data:              bool = True                         # Forward data from upstream filters
+
+
+class FilterFrameDedup(Filter):
+    """
+    A filter that:
+    1) Detects duplicate frames using multiple methods (hash-based and SSIM)
+    2) Saves only unique frames based on configurable thresholds
+    3) Supports ROI-based processing (or full image when ROI is None)
+    4) Maintains minimum time between saved frames
+    """
+    
+    @classmethod
+    def normalize_config(cls, config: FilterFrameDedupConfig):
+        """
+        Convert environment variables to correct data types, apply checks, etc.
+        """
+        # Call parent class normalize_config first to handle sources/outputs parsing
+        config = super().normalize_config(config)
+        
+        # Handle nested config structure
+        if isinstance(config, dict) and 'config' in config:
+            config = config['config']
+
+        # Convert string values to proper types before creating FilterFrameDedupConfig
+        if isinstance(config, dict):
+            # Convert numeric strings to proper types
+            if 'hash_threshold' in config and isinstance(config['hash_threshold'], str):
+                config['hash_threshold'] = int(config['hash_threshold'])
+            if 'motion_threshold' in config and isinstance(config['motion_threshold'], str):
+                config['motion_threshold'] = int(config['motion_threshold'])
+            if 'min_time_between_frames' in config and isinstance(config['min_time_between_frames'], str):
+                config['min_time_between_frames'] = float(config['min_time_between_frames'])
+            if 'ssim_threshold' in config and isinstance(config['ssim_threshold'], str):
+                config['ssim_threshold'] = float(config['ssim_threshold'])
+            if 'roi' in config and isinstance(config['roi'], str):
+                # Parse tuple string like "(100, 100, 200, 200)"
+                roi_str = config['roi'].strip('()')
+                config['roi'] = tuple(map(int, roi_str.split(', ')))
+
+        # Convert to FilterFrameDedupConfig
+        config = FilterFrameDedupConfig(**config)
+        
+        # Validate debug mode
+        if isinstance(config.debug, str):   
+            debug_str = config.debug.lower()
+            if debug_str in ['true', 'false']:
+                config.debug = debug_str == 'true'
+            else:
+                raise ValueError(f"Invalid debug mode: {config.debug}. It should be True or False.")
+        elif not isinstance(config.debug, bool):
+            raise ValueError(f"Invalid debug mode: {config.debug}. It should be True or False.")
+        
+        # Validate forward_deduped_frames mode
+        if isinstance(config.forward_deduped_frames, str):   
+            config.forward_deduped_frames = config.forward_deduped_frames.lower() == 'true'
+        elif not isinstance(config.forward_deduped_frames, bool):
+            raise ValueError(f"Invalid forward_deduped_frames mode: {config.forward_deduped_frames}. It should be True or False.")
+        
+        # Validate forward_upstream_data mode
+        if isinstance(config.forward_upstream_data, str):   
+            config.forward_upstream_data = config.forward_upstream_data.lower() == 'true'
+        elif not isinstance(config.forward_upstream_data, bool):
+            raise ValueError(f"Invalid forward_upstream_data mode: {config.forward_upstream_data}. It should be True or False.")
+        
+        # Validate save_images mode
+        if isinstance(config.save_images, str):   
+            config.save_images = config.save_images.lower() == 'true'
+        elif not isinstance(config.save_images, bool):
+            raise ValueError(f"Invalid save_images mode: {config.save_images}. It should be True or False.")
+
+        # Validate thresholds
+        if config.hash_threshold < 0:
+            raise ValueError("Hash threshold must be non-negative")
+        if config.motion_threshold < 0:
+            raise ValueError("Motion threshold must be non-negative")
+        if config.min_time_between_frames < 0:
+            raise ValueError("Minimum time between frames must be non-negative")
+        if not 0 <= config.ssim_threshold <= 1:
+            raise ValueError("SSIM threshold must be between 0 and 1")
+
+        # Validate ROI if provided
+        if config.roi is not None:
+            if len(config.roi) != 4:
+                raise ValueError("ROI must be a tuple of 4 values (x, y, width, height)")
+            x, y, w, h = config.roi
+            if w <= 0 or h <= 0:
+                raise ValueError("ROI width and height must be positive")
+
+        return config
+
+    def setup(self, config: FilterFrameDedupConfig):
+        """
+        Called once at the start of the filter's lifecycle.
+        """
+        logger.info("========= Setting up FilterFrameDedup =========")
+        self.config = config
+        
+        # Initialize processors
+        self.hash_processor = HashFrameProcessor(config)
+        self.ssim_processor = SSIMProcessor(config)
+        
+        # Initialize counters
+        self.processed_frame_count = 0
+        self.frame_count = 1
+        
+        # Create output folder if it doesn't exist and save_images is enabled
+        if config.save_images and not os.path.exists(config.output_folder):
+            os.makedirs(config.output_folder)
+            
+        logger.info(f"FilterFrameDedup setup completed. Config: {config.__dict__}")
+
+    def process(self, frames: dict[str, Frame]) -> dict[str, Frame]:
+        """
+        Process frames and determine if they should be saved based on motion detection and hash changes.
+
+        Args:
+            frames: Dictionary containing frames
+
+        Returns:
+            Updated frames dictionary with selected frame and optional side channels
+        """
+        # Get the main frame from the frames dictionary
+        main_frame = frames.get('main')
+        if main_frame is None or not main_frame.has_image:
+            if self.config.debug:
+                logger.info("No valid frame received")
+            return frames
+
+        # Increment the frame counter
+        self.processed_frame_count += 1
+        if self.config.debug:
+            logger.info(f"Processing frame {self.processed_frame_count}")
+
+        # Access the raw BGR image from the frame and create a copy for processing
+        processed_image = main_frame.rw_bgr.image.copy()
+
+        # Initialize output frames dictionary
+        output_frames = {}
+        
+        # Always forward the main frame with the processed image first
+        # Create a new frame with the processed image to maintain the original frame data
+        processed_main_frame = Frame(
+            image=processed_image,
+            data=main_frame.data,
+            format='BGR'
+        )
+        self.frame_count += 1
+        output_frames['main'] = processed_main_frame
+        
+        # Forward upstream data if enabled
+        if self.config.forward_upstream_data:
+            # Copy all non-main frames from upstream
+            for key, frame in frames.items():
+                if key != 'main':
+                    output_frames[key] = frame
+
+        # First check if frame should be processed based on hash and motion
+        if self.hash_processor.should_process_frame(processed_image):
+            if self.config.debug:
+                logger.info("Frame passed hash/motion check")
+            # Then check if frame should be saved based on SSIM
+            if self.ssim_processor.should_save_frame(processed_image):
+                frame_path = None
+                
+                # Save frame to disk only if save_images is enabled
+                if self.config.save_images:
+                    frame_path = os.path.join(self.config.output_folder, f"frame_{self.frame_count:06d}.jpg")
+                    lock_path = frame_path + '.lock'
+
+                    try:
+                        # Create lock file
+                        with open(lock_path, 'x') as _:
+                            # Write the processed image
+                            cv2.imwrite(frame_path, processed_image)
+                            # time.sleep(30) # for testing
+                    finally:
+                        # Always remove the lock file, even if writing fails
+                        try:
+                            os.remove(lock_path)
+                        except:
+                            pass
+                    
+                    if self.config.debug:
+                        logger.info(f"Saved frame to {frame_path}")
+                else:
+                    if self.config.debug:
+                        logger.info("Frame passed deduplication criteria but not saved (save_images=False)")
+                
+                # Update the last saved time only when frame is actually saved
+                self.hash_processor.update_last_saved_time()
+                
+                # Forward deduplicated frame in side channel if enabled
+                if self.config.forward_deduped_frames:
+                    # Create a frame with the actual deduplicated image (the one that was saved)
+                    # This creates an asynchronous channel that only contains frames that passed deduplication
+                    deduped_frame = Frame(
+                        image=processed_image,  # Use the processed image that was saved
+                        data=main_frame.data.copy() if main_frame.data else {},
+                        format='BGR'
+                    )
+                    # Add metadata about the deduplication
+                    if deduped_frame.data is None:
+                        deduped_frame.data = {}
+                    deduped_frame.data['deduped'] = True
+                    deduped_frame.data['frame_number'] = self.frame_count - 1
+                    if frame_path:
+                        deduped_frame.data['saved_path'] = frame_path
+                    else:
+                        deduped_frame.data['saved_path'] = None
+                    deduped_frame.data['original_frame_id'] = getattr(main_frame.data, 'id', None) if main_frame.data else None
+                    
+                    output_frames['deduped'] = deduped_frame
+                    
+                    if self.config.debug:
+                        logger.info("Forwarded deduplicated frame in side channel")
+            else:
+                if self.config.debug:
+                    logger.info("Skipping frame due to high SSIM score")
+        else:
+            if self.config.debug:
+                logger.info("Frame did not pass hash/motion check")
+
+        # Ensure main topic comes first in the output dictionary
+        if 'main' in output_frames:
+            main_frame = output_frames.pop('main')
+            return {'main': main_frame, **output_frames}
+        
+        return output_frames
+
+    def shutdown(self):
+        """
+        Called once when the filter is shutting down.
+        """
+        logger.info("========= Shutting down FilterFrameDedup =========")
+        logger.info(f"Total frames processed: {self.processed_frame_count}")
+        logger.info(f"Total frames saved: {self.frame_count - 1}")
+        logger.info("FilterFrameDedup shutdown complete.")
+
+
+if __name__ == "__main__":
+    FilterFrameDedup.run()

filter_frame_dedup/hash_processor.py

@@ -0,0 +1,164 @@
+import cv2
+import numpy as np
+import time
+from openfilter.filter_runtime.filter import FilterConfig
+
+
+class HashFrameProcessor:
+    """
+    A class that handles hash-based frame processing and motion detection.
+    """
+    def __init__(self, config: FilterConfig):
+        self.config = config
+        self.prev_phash = None
+        self.prev_ahash = None
+        self.prev_dhash = None
+        self.prev_frame = None
+        self.last_saved_time = 0  # Initialize to 0 instead of current time
+
+    def extract_roi(self, image: np.ndarray) -> np.ndarray:
+        """
+        Extract the region of interest (ROI) from the image.
+        If ROI is None, returns the entire image.
+
+        Args:
+            image: Input image in BGR format
+
+        Returns:
+            Extracted ROI from the image or entire image if ROI is None
+        """
+        if self.config.roi is None:
+            return image
+        x, y, w, h = self.config.roi
+        return image[y:y+h, x:x+w]
+
+    def compute_phash(self, image: np.ndarray, hash_size: int = 8) -> np.ndarray:
+        """
+        Compute the perceptual hash (phash) of the image.
+
+        Args:
+            image: Input image in BGR format
+            hash_size: Size of the hash
+
+        Returns:
+            Computed phash of the image
+        """
+        roi = self.extract_roi(image)
+        gray_image = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+        resized_image = cv2.resize(gray_image, (32, 32), interpolation=cv2.INTER_AREA)
+        dct_image = cv2.dct(np.float32(resized_image))
+        dct_low_freq = dct_image[:hash_size, :hash_size]
+        dct_mean = np.mean(dct_low_freq)
+        return (dct_low_freq > dct_mean).flatten()
+
+    def compute_ahash(self, image: np.ndarray, hash_size: int = 8) -> np.ndarray:
+        """
+        Compute the average hash (ahash) of the image.
+
+        Args:
+            image: Input image in BGR format
+            hash_size: Size of the hash
+
+        Returns:
+            Computed ahash of the image
+        """
+        roi = self.extract_roi(image)
+        gray_image = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+        resized_image = cv2.resize(gray_image, (hash_size, hash_size), interpolation=cv2.INTER_AREA)
+        avg = resized_image.mean()
+        return (resized_image > avg).flatten()
+
+    def compute_dhash(self, image: np.ndarray, hash_size: int = 8) -> np.ndarray:
+        """
+        Compute the difference hash (dhash) of the image.
+
+        Args:
+            image: Input image in BGR format
+            hash_size: Size of the hash
+
+        Returns:
+            Computed dhash of the image
+        """
+        roi = self.extract_roi(image)
+        gray_image = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
+        resized_image = cv2.resize(gray_image, (hash_size + 1, hash_size), interpolation=cv2.INTER_AREA)
+        diff = resized_image[:, 1:] > resized_image[:, :-1]
+        return diff.flatten()
+
+    def is_motion_detected(self, prev_frame: np.ndarray, curr_frame: np.ndarray) -> bool:
+        """
+        Detect motion between two frames by calculating their absolute differences.
+
+        Args:
+            prev_frame: Previous frame in BGR format
+            curr_frame: Current frame in BGR format
+
+        Returns:
+            True if motion is detected, False otherwise
+        """
+        prev_roi = self.extract_roi(prev_frame)
+        curr_roi = self.extract_roi(curr_frame)
+        gray_prev = cv2.cvtColor(prev_roi, cv2.COLOR_BGR2GRAY)
+        gray_curr = cv2.cvtColor(curr_roi, cv2.COLOR_BGR2GRAY)
+        diff = cv2.absdiff(gray_prev, gray_curr)
+        _, thresh = cv2.threshold(diff, 25, 255, cv2.THRESH_BINARY)
+        non_zero_count = np.count_nonzero(thresh)
+        return non_zero_count > self.config.motion_threshold
+
+    def should_process_frame(self, image: np.ndarray) -> bool:
+        """
+        Determine if a frame should be processed based on hash changes and motion detection.
+
+        Args:
+            image: Current frame in BGR format
+
+        Returns:
+            True if frame should be processed, False otherwise
+        """
+        # Calculating hash values
+        phash = self.compute_phash(image)
+        ahash = self.compute_ahash(image)
+        dhash = self.compute_dhash(image)
+
+        # Check motion detection
+        motion_detected = self.prev_frame is None or self.is_motion_detected(self.prev_frame, image)
+
+        # Check if there are significant changes in hash values
+        hash_changed = (
+            self.prev_phash is None or
+            np.count_nonzero(self.prev_phash != phash) > self.config.hash_threshold or
+            np.count_nonzero(self.prev_ahash != ahash) > self.config.hash_threshold or
+            np.count_nonzero(self.prev_dhash != dhash) > self.config.hash_threshold
+        )
+
+        current_time = time.time()
+        time_elapsed = current_time - self.last_saved_time
+
+        # Debug logging
+        if self.config.debug:
+            print(f"Hash differences - pHash: {np.count_nonzero(self.prev_phash != phash) if self.prev_phash is not None else 'None'}, "
+                  f"aHash: {np.count_nonzero(self.prev_ahash != ahash) if self.prev_ahash is not None else 'None'}, "
+                  f"dHash: {np.count_nonzero(self.prev_dhash != dhash) if self.prev_dhash is not None else 'None'}")
+            print(f"Motion detected: {motion_detected}")
+            print(f"Hash changed: {hash_changed}")
+            print(f"Time elapsed since last save: {time_elapsed:.2f}s")
+            print(f"Should process: {(hash_changed or motion_detected) and (time_elapsed >= self.config.min_time_between_frames)}")
+
+        # Update previous values
+        self.prev_phash = phash
+        self.prev_ahash = ahash
+        self.prev_dhash = dhash
+        self.prev_frame = image
+
+        # For the first frame (when last_saved_time is 0), always process if there are changes
+        if self.last_saved_time == 0:
+            return hash_changed or motion_detected
+
+        return (hash_changed or motion_detected) and (time_elapsed >= self.config.min_time_between_frames)
+
+    def update_last_saved_time(self):
+        """
+        Update the last saved time when a frame is actually saved.
+        This should be called by the filter after successfully saving a frame.
+        """
+        self.last_saved_time = time.time() 

filter_frame_dedup/ssim_processor.py

@@ -0,0 +1,47 @@
+import cv2
+import numpy as np
+from skimage.metrics import structural_similarity as ssim
+from openfilter.filter_runtime.filter import FilterConfig
+
+
+class SSIMProcessor:
+    """
+    A class that handles SSIM-based frame processing.
+    """
+    def __init__(self, config: FilterConfig):
+        self.config = config
+        self.prev_frame = None
+
+    def compute_ssim(self, frame1: np.ndarray, frame2: np.ndarray) -> float:
+        """
+        Compute the Structural Similarity Index (SSIM) between two frames.
+
+        Args:
+            frame1: First frame in BGR format
+            frame2: Second frame in BGR format
+
+        Returns:
+            SSIM score between the two frames
+        """
+        gray1 = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)
+        gray2 = cv2.cvtColor(frame2, cv2.COLOR_BGR2GRAY)
+        score, _ = ssim(gray1, gray2, full=True)
+        return score
+
+    def should_save_frame(self, image: np.ndarray) -> bool:
+        """
+        Determine if a frame should be saved based on SSIM comparison.
+
+        Args:
+            image: Current frame in BGR format
+
+        Returns:
+            True if frame should be saved, False otherwise
+        """
+        if self.prev_frame is None:
+            self.prev_frame = image
+            return True
+
+        ssim_score = self.compute_ssim(self.prev_frame, image)
+        self.prev_frame = image
+        return ssim_score <= self.config.ssim_threshold 

filter_frame_dedup-1.1.1.dist-info/METADATA

@@ -0,0 +1,389 @@
+Metadata-Version: 2.4
+Name: filter_frame_dedup
+Version: 1.1.1
+License-Expression: Apache-2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: <3.14,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: scikit-image==0.25.2
+Requires-Dist: openfilter[all]<0.2.0,>=0.1.0
+Provides-Extra: dev
+Requires-Dist: build==1.2.1; extra == "dev"
+Requires-Dist: setuptools==72.2.0; extra == "dev"
+Requires-Dist: twine<7,>=6.1.0; extra == "dev"
+Requires-Dist: wheel==0.44.0; extra == "dev"
+Requires-Dist: pytest==8.3.4; extra == "dev"
+Requires-Dist: pytest-cov==6.0.0; extra == "dev"
+Dynamic: license-file
+
+# FrameSelect
+
+FrameSelect is a sophisticated OpenFilter component that intelligently reduces redundant frames in video streams. It uses multiple detection methods (hashing, motion analysis, and SSIM comparison) to identify and save only frames that represent significant visual changes, making it ideal for keyframe extraction, storage optimization, and intelligent video sampling.
+
+## Features
+
+- **Multi-Method Detection**: Uses perceptual hashing (pHash, aHash, dHash), motion analysis, and SSIM comparison
+- **Intelligent Filtering**: Configurable thresholds for fine-tuning sensitivity
+- **Side Channel Support**: Forward deduplicated frames in separate channels (accessible via `localhost:8000/deduped`)
+- **Upstream Data Forwarding**: Preserve metadata from upstream filters
+- **ROI Processing**: Focus on specific regions of interest
+- **Performance Optimized**: Lightweight processing with minimal overhead
+
+## Quick Start
+
+### Basic Usage
+
+```bash
+# Set environment variables
+export VIDEO_INPUT="../data/sample-video.mp4"
+export OUTPUT_FOLDER="./output"
+export HASH_THRESHOLD="5"
+export MOTION_THRESHOLD="1200"
+
+# Run the filter
+python scripts/filter_usage.py
+```
+
+### Docker Usage
+
+```bash
+# Build and run with Docker Compose
+docker-compose up
+```
+
+## Configuration
+
+### Environment Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `VIDEO_INPUT` | `../data/sample-video.mp4` | Input video file path |
+| `OUTPUT_FOLDER` | `./output` | Directory to save deduplicated frames |
+| `SAVE_IMAGES` | `true` | Whether to save images to disk |
+| `HASH_THRESHOLD` | `5` | Minimum hash difference to consider unique |
+| `MOTION_THRESHOLD` | `1200` | Minimum motion intensity threshold |
+| `MIN_TIME_BETWEEN_FRAMES` | `1.0` | Minimum time between saved frames (seconds) |
+| `SSIM_THRESHOLD` | `0.90` | SSIM score threshold (lower = more dissimilar) |
+| `ROI` | `None` | Region of interest as `(x, y, width, height)` |
+| `DEBUG` | `false` | Enable debug logging |
+| `FORWARD_DEDUPED_FRAMES` | `false` | Forward deduplicated frames in side channel |
+| `FORWARD_UPSTREAM_DATA` | `true` | Forward data from upstream filters |
+
+### Configuration Examples
+
+#### High Sensitivity (Detailed Keyframes)
+```python
+{
+    "hash_threshold": 3,
+    "motion_threshold": 800,
+    "min_time_between_frames": 0.5,
+    "ssim_threshold": 0.85,
+    "forward_deduped_frames": True
+}
+```
+
+#### Security Surveillance
+```python
+{
+    "hash_threshold": 5,
+    "motion_threshold": 1200,
+    "min_time_between_frames": 2.0,
+    "ssim_threshold": 0.90,
+    "debug": True
+}
+```
+
+#### Storage Optimization
+```python
+{
+    "hash_threshold": 10,
+    "motion_threshold": 2000,
+    "min_time_between_frames": 5.0,
+    "ssim_threshold": 0.95
+}
+```
+
+#### Detection-Only Mode (No Disk Saving)
+```python
+{
+    "hash_threshold": 5,
+    "motion_threshold": 1200,
+    "min_time_between_frames": 1.0,
+    "ssim_threshold": 0.90,
+    "save_images": False,
+    "forward_deduped_frames": True
+}
+```
+
+## Sample Pipelines
+
+### 1. Security Camera Keyframe Extraction
+
+```python
+from openfilter import Filter
+
+# Pipeline: VideoIn → FilterFrameDedup → Webvis
+filters = [
+    Filter("VideoIn", {
+        "sources": "rtsp://security-camera.company.com:554/stream",
+        "outputs": "tcp://127.0.0.1:5550"
+    }),
+    Filter("FilterFrameDedup", {
+        "sources": "tcp://127.0.0.1:5550",
+        "outputs": "tcp://127.0.0.1:5551",
+        "hash_threshold": 5,
+        "motion_threshold": 1200,
+        "min_time_between_frames": 2.0,
+        "ssim_threshold": 0.90,
+        "output_folder": "/security_keyframes",
+        "forward_deduped_frames": True,
+        "debug": True
+    }),
+    Filter("Webvis", {
+        "sources": "tcp://127.0.0.1:5551",
+        "outputs": "tcp://127.0.0.1:8080"
+    })
+]
+
+Filter.run_multi(filters, exit_time=3600.0)  # 1 hour
+
+# View results in Webvis:
+# - http://localhost:8080/main (all processed frames)
+# - http://localhost:8080/deduped (only saved keyframes)
+```
+
+### 2. Content Analysis with ROI
+
+```python
+# Pipeline: VideoIn → FilterFrameDedup → FilterCrop → Webvis
+filters = [
+    Filter("VideoIn", {
+        "sources": "file://content_video.mp4",
+        "outputs": "tcp://127.0.0.1:5550"
+    }),
+    Filter("FilterFrameDedup", {
+        "sources": "tcp://127.0.0.1:5550",
+        "outputs": "tcp://127.0.0.1:5551",
+        "hash_threshold": 3,
+        "motion_threshold": 800,
+        "min_time_between_frames": 0.5,
+        "ssim_threshold": 0.85,
+        "roi": (100, 100, 800, 600),
+        "output_folder": "/content_keyframes",
+        "forward_deduped_frames": True
+    }),
+    Filter("FilterCrop", {
+        "sources": "tcp://127.0.0.1:5551",
+        "outputs": "tcp://127.0.0.1:5552",
+        "polygon_points": "[[(100, 100), (700, 100), (700, 500), (100, 500)]]",
+        "output_prefix": "thumbnail_",
+        "topic_mode": "main_only"
+    }),
+    Filter("Webvis", {
+        "sources": "tcp://127.0.0.1:5552",
+        "outputs": "tcp://127.0.0.1:8080"
+    })
+]
+
+Filter.run_multi(filters, exit_time=1800.0)  # 30 minutes
+
+# View results in Webvis:
+# - http://localhost:8080/thumbnail_main (cropped frames)
+# - http://localhost:8080/deduped (keyframes before cropping)
+```
+
+## Use Cases
+
+### 1. Security Surveillance
+Extract meaningful keyframes from 24/7 security camera footage for efficient storage and review.
+
+**Configuration:**
+```bash
+export HASH_THRESHOLD="5"
+export MOTION_THRESHOLD="1200"
+export MIN_TIME_BETWEEN_FRAMES="2.0"
+export FORWARD_DEDUPED_FRAMES="true"
+```
+
+### 2. Content Analysis
+Extract keyframes from video content for automated thumbnail generation and scene analysis.
+
+**Configuration:**
+```bash
+export HASH_THRESHOLD="3"
+export MOTION_THRESHOLD="800"
+export MIN_TIME_BETWEEN_FRAMES="0.5"
+export ROI="(100, 100, 800, 600)"
+```
+
+### 3. Live Stream Processing
+Process live video streams with real-time deduplication and analytics.
+
+**Configuration:**
+```bash
+export HASH_THRESHOLD="4"
+export MOTION_THRESHOLD="1000"
+export MIN_TIME_BETWEEN_FRAMES="1.0"
+export FORWARD_UPSTREAM_DATA="true"
+export DEBUG="true"
+```
+
+### 4. Storage Optimization
+Process large video files to extract only unique frames for storage optimization.
+
+**Configuration:**
+```bash
+export HASH_THRESHOLD="10"
+export MOTION_THRESHOLD="2000"
+export MIN_TIME_BETWEEN_FRAMES="5.0"
+export SSIM_THRESHOLD="0.95"
+```
+
+## Side Channel: Deduplicated Frames
+
+The filter supports a special **side channel** called `deduped` that contains only the frames that were actually saved. This channel is **asynchronous** - it only emits data when a frame meets all deduplication criteria and gets saved to disk.
+
+### Key Features:
+
+- **Asynchronous Operation**: Only emits when frames are actually saved, not for every input frame
+- **Webvis Visualization**: Access at `http://localhost:8000/deduped`
+- **Rich Metadata**: Each frame includes deduplication status, frame number, and saved path
+- **Real-time Monitoring**: Perfect for monitoring keyframe extraction
+
+### Channel Comparison:
+
+| Channel | Content | Frequency | Webvis URL |
+|---------|---------|-----------|------------|
+| `main` | All processed frames | Every input frame | `localhost:8000/main` |
+| `deduped` | Only saved frames | Only when saved | `localhost:8000/deduped` |
+
+### Enable Side Channel:
+
+```python
+{
+    "forward_deduped_frames": True,  # Enable side channel
+    "output_folder": "/keyframes"
+}
+```
+
+## How It Works
+
+The filter uses a multi-stage approach:
+
+1. **Hash Analysis**: Computes perceptual, average, and difference hashes
+2. **Motion Detection**: Analyzes pixel-level differences between frames
+3. **SSIM Comparison**: Uses Structural Similarity Index for detailed comparison
+4. **Frame Selection**: Saves frames that meet all criteria:
+   - Hash differences exceed threshold OR motion is detected
+   - SSIM score is below threshold
+   - Minimum time has elapsed since last save
+5. **Side Channel Output**: If enabled, forwards saved frames to `deduped` channel
+
+## Output
+
+### Saved Frames (when `save_images=True`)
+Frames are saved to the specified directory with sequential naming:
+```
+/output/
+├── frame_000001.jpg
+├── frame_000002.jpg
+└── ...
+```
+
+### Detection-Only Mode (when `save_images=False`)
+When `save_images=False`, the filter operates in detection-only mode:
+- No files are written to disk
+- Deduplication logic still runs and updates timing
+- Side channels (`deduped`) still work and contain frames that would have been saved
+- Useful for real-time processing without storage overhead
+
+### Side Channels
+When `forward_deduped_frames` is enabled:
+- **Main channel**: All processed frames (accessible via `localhost:8000/main`)
+- **Deduped channel**: Only saved frames with metadata (accessible via `localhost:8000/deduped`)
+  - **Asynchronous**: Only emits when frames are actually saved
+  - **Rich Metadata**: Includes frame number, saved path, and deduplication status
+  - **Real-time Monitoring**: Perfect for monitoring keyframe extraction
+
+### Metadata
+Deduplicated frames include:
+- `deduped`: Boolean flag indicating frame was saved
+- `frame_number`: Sequential frame number
+- `saved_path`: Path to saved file
+- `original_frame_id`: Original frame identifier
+
+## Debug Mode
+
+Enable debug mode for detailed processing information:
+```bash
+export DEBUG="true"
+```
+
+Debug output shows:
+- Hash differences between frames
+- Motion detection results
+- SSIM scores
+- Frame acceptance/rejection decisions
+- Timing information
+
+## Performance Tuning
+
+### Threshold Guidelines
+
+| Use Case | Hash Threshold | Motion Threshold | SSIM Threshold | Time Between |
+|----------|----------------|------------------|----------------|--------------|
+| High Detail Keyframes | 3-4 | 800-1000 | 0.85-0.88 | 0.5-1.0s |
+| Security Surveillance | 5-6 | 1200-1500 | 0.90-0.92 | 2.0-3.0s |
+| Content Analysis | 4-5 | 1000-1200 | 0.88-0.90 | 1.0-2.0s |
+| Storage Optimization | 8-10 | 2000+ | 0.95+ | 5.0s+ |
+
+### Performance Tips
+
+- Use ROI to focus on important areas and reduce processing time
+- Lower thresholds for detailed analysis, higher for storage optimization
+- Enable `forward_deduped_frames` for side channel access to keyframes
+- Use `debug` mode to tune parameters for your specific use case
+
+## Troubleshooting
+
+### Common Issues
+
+**Too many saved frames:**
+- Increase `ssim_threshold` (closer to 1.0)
+- Increase `min_time_between_frames`
+- Increase `hash_threshold`
+
+**Too few saved frames:**
+- Decrease `ssim_threshold` (closer to 0.0)
+- Decrease `hash_threshold` and `motion_threshold`
+- Decrease `min_time_between_frames`
+
+**High CPU usage:**
+- Increase `hash_threshold` and `motion_threshold`
+- Use ROI to reduce processing area
+- Increase `min_time_between_frames`
+
+## Requirements
+
+Install dependencies:
+```bash
+make run
+```
+
+Or install manually:
+```bash
+pip install -r requirements.txt
+```
+
+## Documentation
+
+For more detailed information, configuration examples, and advanced usage scenarios, see the [comprehensive documentation](docs/overview.md).
+
+## License
+
+See LICENSE file for details.

filter_frame_dedup-1.1.1.dist-info/RECORD

@@ -0,0 +1,9 @@
+filter_frame_dedup/__init__.py,sha256=5nGHWwb-mYLO_8Ek6bXp6KPgxo2lOABOhfAPs_NkUJU,137
+filter_frame_dedup/filter.py,sha256=z2y6KAl_oOIzzWrXxEPH0X9iF_xUc2fczoNG-a6nxZA,12759
+filter_frame_dedup/hash_processor.py,sha256=rsRWrpXamE4rW1J6L9SnnT8_681xj4fq2lCW5RLmIDM,6299
+filter_frame_dedup/ssim_processor.py,sha256=Q8W6V_xKs0jfaYaDHSne9igY9BrAdtnkE7COQv4dRBk,1421
+filter_frame_dedup-1.1.1.dist-info/licenses/LICENSE,sha256=Hun-T5YKdxKbQ1lfbGCu8YiknxeFsTnWAuSWz6CKQAQ,11343
+filter_frame_dedup-1.1.1.dist-info/METADATA,sha256=--ECaRVWMj8oy0KhJiiqNtBpuG4CeqkRPVOVWJLr6_k,11882
+filter_frame_dedup-1.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+filter_frame_dedup-1.1.1.dist-info/top_level.txt,sha256=i5zhda0eEhLy1waCqjsILVaIXWtLtAlblt_Wx_-vAN4,19
+filter_frame_dedup-1.1.1.dist-info/RECORD,,

filter_frame_dedup-1.1.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

filter_frame_dedup-1.1.1.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2025] [Plainsight]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

filter_frame_dedup-1.1.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+filter_frame_dedup