matrice 1.0.99252__tar.gz → 1.0.99254__tar.gz

{matrice-1.0.99252/src/matrice.egg-info → matrice-1.0.99254}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice
-Version: 1.0.99252
+Version: 1.0.99254
 Summary: SDK for connecting to matrice.ai services
 Home-page: https://github.com/matrice-ai/python-sdk
 Author: Matrice.ai

{matrice-1.0.99252 → matrice-1.0.99254}/setup.py

@@ -14,7 +14,7 @@ long_description = (here / "README.md").read_text(encoding="utf-8")
 setup(
     name="matrice",
 
-    version = "1.0.99252",
+    version = "1.0.99254",
     
     description="SDK for connecting to matrice.ai services",
     long_description=long_description,

{matrice-1.0.99252 → matrice-1.0.99254}/src/matrice/deploy/utils/post_processing/usecases/crop_weed_detection.py

@@ -1,8 +1,7 @@
 """
-Crop Weed Detection Post-Processing Use Case
-========================================================
-This module implements the Crop weed detection use case for crop weed detection.
-It processes detection results, applies category mapping, performs bbox smoothing, and generates alerts for detected weeds (yet to be implemented).
+Crop weed detection usecase
+This module provides functionality for detecting crops in images or video streams.
+
 """
 
 from typing import Any, Dict, List, Optional
@@ -29,7 +28,7 @@ from ..core.config import BaseConfig, AlertConfig, ZoneConfig
 
 @dataclass
 class CropWeedDetectionConfig(BaseConfig):
-    """Configuration for crop weed detection use case in crop weed detection."""
+    """Configuration for crop weed detection use case."""
     # Smoothing configuration
     enable_smoothing: bool = True
     smoothing_algorithm: str = "observability"  # "window" or "observability"
@@ -38,7 +37,7 @@ class CropWeedDetectionConfig(BaseConfig):
     smoothing_confidence_range_factor: float = 0.5
 
     # confidence thresholds
-    confidence_threshold: float = 0.5
+    confidence_threshold: float = 0.4
 
     usecase_categories: List[str] = field(
         default_factory=lambda: ['plants', 'BroWeed', 'Maize', 'NarWeed']
@@ -52,20 +51,21 @@ class CropWeedDetectionConfig(BaseConfig):
 
     index_to_category: Optional[Dict[int, str]] = field(
         default_factory=lambda: {
-            0: 'plants', 
-            1: 'BroWeed', 
-            2: 'Maize', 
+            0: 'plants',
+            1: 'BroWeed',
+            2: 'Maize',
             3: 'NarWeed'
         }
     )
 
+
 class CropWeedDetectionUseCase(BaseProcessor):
     # Human-friendly display names for categories
     CATEGORY_DISPLAY = {
-        "weed": "weed",
-        "BroWeed": "BroWeed",
+        "plants": "Plants",
+        "BroWeed": "Bro Weed",
         "Maize": "Maize",
-        "NarWeed": "NarWeed"
+        "NarWeed": "Nar Weed"
     }
     def __init__(self):
         super().__init__("crop_weed_detection")
@@ -77,6 +77,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
         # List of  categories to track
         self.target_categories = ['plants', 'BroWeed', 'Maize', 'NarWeed']
 
+
         # Initialize smoothing tracker
         self.smoothing_tracker = None
 
@@ -99,6 +100,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
         self._ascending_alert_list: List[int] = []
         self.current_incident_end_timestamp: str = "N/A"
 
+
     def process(self, data: Any, config: ConfigProtocol, context: Optional[ProcessingContext] = None,
                 stream_info: Optional[Dict[str, Any]] = None) -> ProcessingResult:
         """
@@ -124,7 +126,6 @@ class CropWeedDetectionUseCase(BaseProcessor):
             self.logger.debug(f"Applied confidence filtering with threshold {config.confidence_threshold}")
         else:
             processed_data = data
-            
             self.logger.debug(f"Did not apply confidence filtering with threshold since nothing was provided")
 
         # Step 2: Apply category mapping if provided
@@ -150,11 +151,13 @@ class CropWeedDetectionUseCase(BaseProcessor):
                 self.smoothing_tracker = BBoxSmoothingTracker(smoothing_config)
             processed_data = bbox_smoothing(processed_data, self.smoothing_tracker.config, self.smoothing_tracker)
 
+
         # Advanced tracking (BYTETracker-like)
         try:
             from ..advanced_tracker import AdvancedTracker
             from ..advanced_tracker.config import TrackerConfig
 
+            # Create tracker instance if it doesn't exist (preserves state across frames)
             
             if self.tracker is None:
                 if config.confidence_threshold is not None:
@@ -445,22 +448,20 @@ class CropWeedDetectionUseCase(BaseProcessor):
 
         # Prepare detections without confidence scores (as per eg.json)
         detections = []
+
         for detection in counting_summary.get("detections", []):
-            bbox = detection.get("bounding_box", {})
-            category = detection.get("category", "person")
+            detection_data = {
+                "category": detection.get("category"),
+                "bounding_box": detection.get("bounding_box", {})
+            }
             # Include segmentation if available (like in eg.json)
             if detection.get("masks"):
-                segmentation= detection.get("masks", [])
-                detection_obj = self.create_detection_object(category, bbox, segmentation=segmentation)
-            elif detection.get("segmentation"):
-                segmentation= detection.get("segmentation")
-                detection_obj = self.create_detection_object(category, bbox, segmentation=segmentation)
-            elif detection.get("mask"):
-                segmentation= detection.get("mask")
-                detection_obj = self.create_detection_object(category, bbox, segmentation=segmentation)
-            else:
-                detection_obj = self.create_detection_object(category, bbox)
-            detections.append(detection_obj)
+                detection_data["masks"] = detection.get("masks", [])
+            if detection.get("segmentation"):
+                detection_data["segmentation"] = detection.get("segmentation")
+            if detection.get("mask"):
+                detection_data["mask"] = detection.get("mask")
+            detections.append(detection_data)
 
         # Build alert_settings array in expected format
         alert_settings = []
@@ -511,7 +512,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
 
         tracking_stats.append(tracking_stat)
         return tracking_stats
-
+    
     def _generate_business_analytics(self, counting_summary: Dict, alerts:Any, config: CropWeedDetectionConfig, stream_info: Optional[Dict[str, Any]] = None, is_empty=False) -> List[Dict]:
         """Generate standardized business analytics for the agg_summary structure."""
         if is_empty:
@@ -596,7 +597,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
         """
         return {cat: len(ids) for cat, ids in getattr(self, '_per_category_total_track_ids', {}).items()}
 
-    
+
     def _format_timestamp_for_stream(self, timestamp: float) -> str:
         """Format timestamp for streams (YYYY:MM:DD HH:MM:SS format)."""
         dt = datetime.fromtimestamp(timestamp, tz=timezone.utc)
@@ -683,8 +684,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
             # Reset minutes and seconds to 00:00 for "TOTAL SINCE" format
             dt = dt.replace(minute=0, second=0, microsecond=0)
             return dt.strftime('%Y:%m:%d %H:%M:%S')
-
-
+    
     def _count_categories(self, detections: list, config: CropWeedDetectionConfig) -> dict:
         """
         Count the number of detections per category and return a summary dict.
@@ -711,6 +711,7 @@ class CropWeedDetectionUseCase(BaseProcessor):
             ]
         }
 
+
     def _extract_predictions(self, detections: list) -> List[Dict[str, Any]]:
         """
         Extract prediction details for output (category, confidence, bounding box).

{matrice-1.0.99252 → matrice-1.0.99254}/src/matrice/deploy/utils/post_processing/usecases/fire_detection.py

@@ -191,6 +191,18 @@ class FireSmokeUseCase(BaseProcessor):
                     frame_number = start_frame
 
              # Step 7: alerts
+            print("-----------------------------------------------")
+            print(config.confidence_threshold)
+            print(config.fire_smoke_categories)
+            print(config.index_to_category)
+            print(config.target_categories)
+            print(config.threshold_area)
+            print(config.alert_config)
+            print(config.alert_config.count_thresholds)
+            print(config.alert_config.alert_type)
+            print(config.alert_config.alert_value)
+            print(config.alert_config.alert_incident_category)
+            print("-----------------------------------------------")
 
             alerts = self._check_alerts(fire_smoke_summary, frame_number, config, stream_info)
 
@@ -282,7 +294,11 @@ class FireSmokeUseCase(BaseProcessor):
         if hasattr(config.alert_config, 'count_thresholds') and config.alert_config.count_thresholds:
             alert_id = self._get_alert_incident_ids(self._ascending_alert_list[-1:])
 
-            for category, threshold in config.alert_config.count_thresholds.items():
+            count_thresholds = {}
+            if config.alert_config and hasattr(config.alert_config, "count_thresholds"):
+                count_thresholds = config.alert_config.count_thresholds or {}
+
+            for category, threshold in count_thresholds.items():
                 if category == "all" and total > threshold:  
                     
                     alerts.append({
@@ -360,8 +376,14 @@ class FireSmokeUseCase(BaseProcessor):
         if total > 0:
            # Calculate total bbox area
             total_area = 0.0
-        
-            for category, threshold in config.alert_config.count_thresholds.items():
+            # Safely retrieve count thresholds. If alert_config is None (e.g., when it
+            # is not provided or failed to parse) we default to an empty mapping so
+            # the subsequent logic can still execute without raising an AttributeError.
+            count_thresholds = {}
+            if config.alert_config and hasattr(config.alert_config, "count_thresholds"):
+                count_thresholds = config.alert_config.count_thresholds or {}
+
+            for category, threshold in count_thresholds.items():
                 if category in summary.get("per_category_count", {}):
                     
                     #count = summary.get("per_category_count", {})[category]
@@ -583,6 +605,26 @@ class FireSmokeUseCase(BaseProcessor):
 
 
         tracking_stats.append(tracking_stat)
+
+        if len(self.id_hit_list)==1:
+            last_ending_id = self._get_alert_incident_ids("")
+            if last_ending_id==5:
+                tracking_stats.append({
+                            "alert_type": getattr(config.alert_config, 'alert_type', ['Default']) if hasattr(config.alert_config, 'alert_type') else ['Default'],
+                            "alert_id": "alert_"+category+'_'+str(last_ending_id),
+                            "incident_category": self.CASE_TYPE,
+                            "threshold_level": 0,
+                            "ascending": False,
+                            "settings": {t: v for t, v in zip(getattr(config.alert_config, 'alert_type', ['Default']) if hasattr(config.alert_config, 'alert_type') else ['Default'],
+                                     getattr(config.alert_config, 'alert_value', ['JSON']) if hasattr(config.alert_config, 'alert_value') else ['JSON'])
+                                    }       
+                        })
+                tracking_stats.append(self.create_incident(incident_id=self.CASE_TYPE+'_'+str(last_ending_id), incident_type=self.CASE_TYPE,
+                            severity_level='info', human_text='Event Over', camera_info=camera_info, alerts=alerts, alert_settings=alert_settings,
+                            start_time=start_timestamp, end_time='Incident still active',
+                            level_settings= {"low": 3, "medium": 5, "significant":15, "critical": 30}))
+                
+        
         return tracking_stats
 
     def _generate_summary(
@@ -952,6 +994,9 @@ class FireSmokeUseCase(BaseProcessor):
             if len(self.id_hit_list)==1:
                 self.id_hit_counter+=1
                 if self.id_hit_counter>120:
+                    self.id_hit_list = ["low","medium","significant","critical","low"]
+                    self.id_hit_counter = 0
+                    self.latest_stack = None
                     return int(5)
                 if sev_level==self.latest_stack:
                     return int(5-len(self.id_hit_list))

{matrice-1.0.99252 → matrice-1.0.99254/src/matrice.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: matrice
-Version: 1.0.99252
+Version: 1.0.99254
 Summary: SDK for connecting to matrice.ai services
 Home-page: https://github.com/matrice-ai/python-sdk
 Author: Matrice.ai