megadetector 5.0.23__py3-none-any.whl → 5.0.25__py3-none-any.whl

megadetector/visualization/visualization_utils.py

@@ -15,7 +15,7 @@ import os
 import cv2
 
 from io import BytesIO
-from PIL import Image, ImageFile, ImageFont, ImageDraw
+from PIL import Image, ImageFile, ImageFont, ImageDraw, ImageFilter
 from multiprocessing.pool import ThreadPool
 from multiprocessing.pool import Pool
 from tqdm import tqdm
@@ -25,6 +25,7 @@ from megadetector.utils.path_utils import find_images
 from megadetector.data_management.annotations import annotation_constants
 from megadetector.data_management.annotations.annotation_constants import \
     detector_bbox_category_id_to_name
+from megadetector.utils.ct_utils import sort_list_of_dicts_by_key
 
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 
@@ -352,13 +353,14 @@ def resize_image(image, target_width=-1, target_height=-1, output_file=None,
 def crop_image(detections, image, confidence_threshold=0.15, expansion=0):
     """
     Crops detections above [confidence_threshold] from the PIL image [image],
-    returning a list of PIL Images.
+    returning a list of PIL Images, preserving the order of [detections].
 
     Args:
         detections (list): a list of dictionaries with keys 'conf' and 'bbox';
             boxes are length-four arrays formatted as [x,y,w,h], normalized, 
             upper-left origin (this is the standard MD detection format)
-        image (Image): the PIL Image object from which we should crop detections
+        image (Image or str): the PIL Image object from which we should crop detections,
+            or an image filename
         confidence_threshold (float, optional): only crop detections above this threshold
         expansion (int, optional): a number of pixels to include on each side of a cropped
             detection
@@ -369,6 +371,9 @@ def crop_image(detections, image, confidence_threshold=0.15, expansion=0):
 
     ret_images = []
 
+    if isinstance(image,str):
+        image = load_image(image)
+        
     for detection in detections:
 
         score = float(detection['conf'])
@@ -405,12 +410,54 @@ def crop_image(detections, image, confidence_threshold=0.15, expansion=0):
 
     return ret_images
 
+# ...def crop_image(...)
 
+
+def blur_detections(image,detections,blur_radius=40):
+    """
+    Blur the regions in [image] corresponding to the MD-formatted list [detections].
+    [image] is modified in place.
+    
+    Args:
+        image (PIL.Image.Image): image in which we should blur specific regions
+        detections (list): list of detections in the MD output format, see render
+            detection_bounding_boxes for more detail.
+    """
+    
+    img_width, img_height = image.size
+    
+    for d in detections:
+        
+        bbox = d['bbox']
+        x_norm, y_norm, width_norm, height_norm = bbox
+
+        # Calculate absolute pixel coordinates
+        x = int(x_norm * img_width)
+        y = int(y_norm * img_height)
+        width = int(width_norm * img_width)
+        height = int(height_norm * img_height)
+        
+        # Calculate box boundaries
+        left = max(0, x)
+        top = max(0, y)
+        right = min(img_width, x + width)
+        bottom = min(img_height, y + height)
+        
+        # Crop the region, blur it, and paste it back
+        region = image.crop((left, top, right, bottom))
+        blurred_region = region.filter(ImageFilter.GaussianBlur(radius=blur_radius))
+        image.paste(blurred_region, (left, top))
+
+    # ...for each detection
+        
+# ...def blur_detections(...)
+
+        
 def render_detection_bounding_boxes(detections, 
                                     image,
                                     label_map='show_categories',
                                     classification_label_map=None, 
-                                    confidence_threshold=0.15, 
+                                    confidence_threshold=0, 
                                     thickness=DEFAULT_BOX_THICKNESS, 
                                     expansion=0,
                                     classification_confidence_threshold=0.3,
@@ -419,7 +466,9 @@ def render_detection_bounding_boxes(detections,
                                     textalign=TEXTALIGN_LEFT,
                                     vtextalign=VTEXTALIGN_TOP,
                                     label_font_size=DEFAULT_LABEL_FONT_SIZE,
-                                    custom_strings=None):
+                                    custom_strings=None,
+                                    box_sort_order='confidence',
+                                    verbose=False):
     """
     Renders bounding boxes (with labels and confidence values) on an image for all
     detections above a threshold.
@@ -497,6 +546,9 @@ def render_detection_bounding_boxes(detections,
         label_font_size (float, optional): font size for labels        
         custom_strings: optional set of strings to append to detection labels, should have the
             same length as [detections].  Appended before any classification labels.
+        box_sort_order (str, optional): sorting scheme for detection boxes, can be None, "confidence", or 
+            "reverse_confidence".
+        verbose (bool, optional): enable additional debug output
     """
 
     # Input validation
@@ -516,6 +568,15 @@ def render_detection_bounding_boxes(detections,
     # for color selection
     classes = []  
 
+    if box_sort_order is not None:
+        
+        if box_sort_order == 'confidence':            
+            detections = sort_list_of_dicts_by_key(detections,k='conf',reverse=False)
+        elif box_sort_order == 'reverse_confidence':
+            detections = sort_list_of_dicts_by_key(detections,k='conf',reverse=True)
+        else:
+            raise ValueError('Unrecognized sorting scheme {}'.format(box_sort_order))
+            
     for i_detection,detection in enumerate(detections):
 
         score = detection['conf']
@@ -536,8 +597,9 @@ def render_detection_bounding_boxes(detections,
             # category or on the most confident classification category.
             clss = detection['category']
             
-            # {} is the default, which means "show labels with no mapping", so don't use "if label_map" here
-            # if label_map:                
+            # This will be a list of strings that should be rendered above/below this box            
+            displayed_label = []
+            
             if label_map is not None:
                 label = label_map[clss] if clss in label_map else clss
                 if score is not None:
@@ -545,17 +607,14 @@ def render_detection_bounding_boxes(detections,
                 else:
                     displayed_label = ['{}'.format(label)]
             else:
-                displayed_label = ''
+                displayed_label = ['']
 
             if custom_strings is not None:
                 custom_string = custom_strings[i_detection]
                 if custom_string is not None and len(custom_string) > 0:
-                    if isinstance(displayed_label,str):
-                        displayed_label += ' ' + custom_string
-                    else:
-                        assert len(displayed_label) == 1
-                        displayed_label[0] += ' ' + custom_string
-                                    
+                    assert len(displayed_label) == 1
+                    displayed_label[0] += ' ' + custom_string
+
             if ('classifications' in detection) and len(detection['classifications']) > 0:
 
                 classifications = detection['classifications']
@@ -597,6 +656,7 @@ def render_detection_bounding_boxes(detections,
                 
             # ...if we have classification results
                         
+            # display_strs is a list of labels for each box
             display_strs.append(displayed_label)
             classes.append(clss)
 
@@ -606,6 +666,9 @@ def render_detection_bounding_boxes(detections,
     
     display_boxes = np.array(display_boxes)
 
+    if verbose:
+        print('Rendering {} of {} detections'.format(len(display_boxes),len(detections)))
+        
     draw_bounding_boxes_on_image(image, display_boxes, classes,
                                  display_strs=display_strs, thickness=thickness, 
                                  expansion=expansion, colormap=colormap, 
@@ -953,7 +1016,8 @@ def render_db_bounding_boxes(boxes,
                              textalign=TEXTALIGN_LEFT,
                              vtextalign=VTEXTALIGN_TOP,
                              text_rotation=None,
-                             label_font_size=DEFAULT_LABEL_FONT_SIZE):
+                             label_font_size=DEFAULT_LABEL_FONT_SIZE,
+                             tags=None):
     """
     Render bounding boxes (with class labels) on an image.  This is a wrapper for
     draw_bounding_boxes_on_image, allowing the caller to operate on a resized image
@@ -981,6 +1045,8 @@ def render_db_bounding_boxes(boxes,
         vtextalign (int, optional): VTEXTALIGN_TOP or VTEXTALIGN_BOTTOM
         text_rotation (float, optional): rotation to apply to text
         label_font_size (float, optional): font size for labels
+        tags (list, optional): list of strings of length len(boxes) that should be appended
+            after each class name (e.g. to show scores)
     """
 
     display_boxes = []
@@ -993,8 +1059,11 @@ def render_db_bounding_boxes(boxes,
 
     img_width, img_height = image_size
 
-    for box, clss in zip(boxes, classes):
+    for i_box in range(0,len(boxes)):
 
+        box = boxes[i_box]
+        clss = classes[i_box]
+        
         x_min_abs, y_min_abs, width_abs, height_abs = box[0:4]
 
         ymin = y_min_abs / img_height
@@ -1008,9 +1077,17 @@ def render_db_bounding_boxes(boxes,
         if label_map:
             clss = label_map[int(clss)]
             
+        display_str = str(clss)
+    
+        # Do we have a tag to append to the class string?
+        if tags is not None and tags[i_box] is not None and len(tags[i_box]) > 0:
+            display_str += ' ' + tags[i_box]
+            
         # need to be a string here because PIL needs to iterate through chars
-        display_strs.append([str(clss)])  
+        display_strs.append([display_str])
 
+    # ...for each box
+    
     display_boxes = np.array(display_boxes)
     
     draw_bounding_boxes_on_image(image, 
@@ -1706,7 +1783,7 @@ if False:
         TEXTALIGN_LEFT,TEXTALIGN_RIGHT,VTEXTALIGN_BOTTOM,VTEXTALIGN_TOP, \
         DEFAULT_LABEL_FONT_SIZE
         
-    fn = os.path.expanduser('~\AppData\Local\Temp\md-tests\md-test-images\ena24_7904.jpg')
+    fn = os.path.expanduser('~/AppData/Local/Temp/md-tests/md-test-images/ena24_7904.jpg')
     output_fn = r'g:\temp\test.jpg'
     
     image = load_image(fn)

megadetector/visualization/visualize_db.py

@@ -167,7 +167,7 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
         options (DbVizOptions, optional): See DbVizOptions for details
     
     Returns:
-        tuple: A length-two tuple containing (the html filename) and (the loaded database).        
+        tuple: A length-two tuple containing (the html filename) and (the loaded database).
     """    
     
     if options is None:
@@ -315,6 +315,7 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
     
         bboxes = []
         box_classes = []
+        box_score_strings = []
         
         # All the class labels we've seen for this image (with out without bboxes)
         image_categories = set()
@@ -363,12 +364,19 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
             image_categories.add(category_name)
             
             if 'bbox' in anno:
-                bbox = anno['bbox']        
+                bbox = anno['bbox']                
                 if isinstance(bbox,float):
                     assert math.isnan(bbox), "I shouldn't see a bbox that's neither a box nor NaN"
                     continue
                 bboxes.append(bbox)
                 box_classes.append(anno['category_id'])
+                
+                box_score_string = ''
+                if options.confidence_field_name is not None and \
+                   options.confidence_field_name in anno:
+                       score = anno[options.confidence_field_name]
+                       box_score_string = '({}%)'.format(round(100 * score))
+                box_score_strings.append(box_score_string)
         
         # ...for each of this image's annotations
         
@@ -382,8 +390,12 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
         for c in illegal_characters:
             file_name = file_name.replace(c,'~')
         
-        rendering_info.append({'bboxes':bboxes, 'box_classes':box_classes, 'img_path':img_path,
-                               'output_file_name':file_name})
+        rendering_info_this_image = {'bboxes':bboxes,
+                                     'box_classes':box_classes,
+                                     'tags':box_score_strings,
+                                     'img_path':img_path,
+                                     'output_file_name':file_name}
+        rendering_info.append(rendering_info_this_image)
                 
         label_level_string = ''
         if len(annotation_level_for_image) > 0:
@@ -442,6 +454,9 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
         img_path = rendering_info['img_path']
         bboxes = rendering_info['bboxes']
         bbox_classes = rendering_info['box_classes']
+        bbox_tags = None
+        if 'tags' in rendering_info:
+            bbox_tags = rendering_info['tags']            
         output_file_name = rendering_info['output_file_name']
         output_full_path = os.path.join(output_dir, 'rendered_images', output_file_name)
         
@@ -467,11 +482,14 @@ def visualize_db(db_path, output_dir, image_base_dir, options=None):
             print('Image {} failed to open, error: {}'.format(img_path, e))
             return False
             
-        vis_utils.render_db_bounding_boxes(boxes=bboxes, classes=bbox_classes,
-                                           image=image, original_size=original_size,
+        vis_utils.render_db_bounding_boxes(boxes=bboxes, 
+                                           classes=bbox_classes,
+                                           image=image, 
+                                           original_size=original_size,
                                            label_map=label_map,
                                            thickness=options.box_thickness,
-                                           expansion=options.box_expansion)
+                                           expansion=options.box_expansion,
+                                           tags=bbox_tags)
         
         image.save(output_full_path)
                 

megadetector/visualization/visualize_detector_output.py

@@ -22,6 +22,7 @@ from tqdm import tqdm
 
 from megadetector.data_management.annotations.annotation_constants import detector_bbox_category_id_to_name
 from megadetector.visualization import visualization_utils as vis_utils
+from megadetector.visualization.visualization_utils import blur_detections
 from megadetector.utils.ct_utils import get_max_conf
 from megadetector.utils import write_html_image_list
 from megadetector.detection.run_detector import get_typical_confidence_threshold_from_results
@@ -38,10 +39,17 @@ DEFAULT_DETECTOR_LABEL_MAP = {
 #%% Support functions
 
 def _render_image(entry,
-                 detector_label_map,classification_label_map,
-                 confidence_threshold,classification_confidence_threshold,
-                 render_detections_only,preserve_path_structure,out_dir,images_dir,
-                 output_image_width):
+                  detector_label_map,
+                  classification_label_map,
+                  confidence_threshold,
+                  classification_confidence_threshold,
+                  render_detections_only,
+                  preserve_path_structure,
+                  out_dir,
+                  images_dir,
+                  output_image_width,
+                  box_sort_order=None,
+                  category_names_to_blur=None):
     """
     Internal function for rendering a single image.
     """
@@ -65,22 +73,43 @@ def _render_image(entry,
         rendering_result['skipped_image'] = True
         return rendering_result
     
-    image_obj = os.path.join(images_dir, image_id)
-    if not os.path.exists(image_obj):
+    image_filename_in_abs = os.path.join(images_dir, image_id)
+    if not os.path.exists(image_filename_in_abs):
         print(f'Image {image_id} not found in images_dir')
         rendering_result['missing_image'] = True
         return rendering_result
 
+    # Load the image
+    image = vis_utils.open_image(image_filename_in_abs)
+    
+    # Find categories we're supposed to blur
+    category_ids_to_blur = []
+    if category_names_to_blur is not None:
+        if isinstance(category_names_to_blur,str):
+            category_names_to_blur = [category_names_to_blur]
+        for category_id in detector_label_map:
+            if detector_label_map[category_id] in category_names_to_blur:
+                category_ids_to_blur.append(category_id)
+    
+    detections_to_blur = []
+    for d in entry['detections']:
+        if d['conf'] >= confidence_threshold and d['category'] in category_ids_to_blur:
+            detections_to_blur.append(d)
+    if len(detections_to_blur) > 0:
+        blur_detections(image,detections_to_blur)
+        
+    # Resize if necessary
+    #
     # If output_image_width is -1 or None, this will just return the original image
-    image = vis_utils.resize_image(
-        vis_utils.open_image(image_obj), output_image_width)
+    image = vis_utils.resize_image(image, output_image_width)
 
     vis_utils.render_detection_bounding_boxes(
         entry['detections'], image, 
         label_map=detector_label_map,
         classification_label_map=classification_label_map,
         confidence_threshold=confidence_threshold,
-        classification_confidence_threshold=classification_confidence_threshold)
+        classification_confidence_threshold=classification_confidence_threshold,
+        box_sort_order=box_sort_order)
 
     if not preserve_path_structure:
         for char in ['/', '\\', ':']:
@@ -113,7 +142,9 @@ def visualize_detector_output(detector_output_path,
                               preserve_path_structure=False,
                               parallelize_rendering=False,
                               parallelize_rendering_n_cores=10,
-                              parallelize_rendering_with_threads=True):
+                              parallelize_rendering_with_threads=True,
+                              box_sort_order=None,
+                              category_names_to_blur=None):
     
     """
     Draws bounding boxes on images given the output of a detector.
@@ -145,6 +176,10 @@ def visualize_detector_output(detector_output_path,
         parallelize_rendering_with_threads (bool, optional): determines whether we use
             threads (True) or processes (False) for parallelization (ignored if parallelize_rendering 
             is False)
+        box_sort_order (str, optional): sorting scheme for detection boxes, can be None, "confidence", or
+            "reverse_confidence"
+        category_names_to_blur (list of str, optional): category names for which we should blur detections,
+            most commonly ['person']
 
     Returns:
         list: list of paths to annotated images
@@ -235,7 +270,9 @@ def visualize_detector_output(detector_output_path,
                                          preserve_path_structure=preserve_path_structure,
                                          out_dir=out_dir,
                                          images_dir=images_dir,
-                                         output_image_width=output_image_width),
+                                         output_image_width=output_image_width,
+                                         box_sort_order=box_sort_order,
+                                         category_names_to_blur=category_names_to_blur),
                                  images), total=len(images)))
         
     else:
@@ -245,7 +282,8 @@ def visualize_detector_output(detector_output_path,
             rendering_result = _render_image(entry,detector_label_map,classification_label_map,
                                             confidence_threshold,classification_confidence_threshold,
                                             render_detections_only,preserve_path_structure,out_dir,
-                                            images_dir,output_image_width)
+                                            images_dir,output_image_width,box_sort_order,
+                                            category_names_to_blur=category_names_to_blur)
             rendering_results.append(rendering_result)
         
     # ...for each image
@@ -334,12 +372,20 @@ def main():
     parser.add_argument(
         '-pps', '--preserve_path_structure', action='store_true',
         help='Preserve relative image paths (otherwise flattens and assigns unique file names)')
+    parser.add_argument(
+        '--category_names_to_blur', default=None, type=str,
+        help='Comma-separated list of category names to blur (or a single category name, typically "person")')
 
     if len(sys.argv[1:]) == 0:
         parser.print_help()
         parser.exit()
 
     args = parser.parse_args()
+    
+    category_names_to_blur = args.category_names_to_blur
+    if category_names_to_blur is not None:
+        category_names_to_blur = category_names_to_blur.split(',')
+    
     visualize_detector_output(
         detector_output_path=args.detector_output_path,
         out_dir=args.out_dir,
@@ -350,7 +396,8 @@ def main():
         random_seed=args.random_seed,
         render_detections_only=args.detections_only,
         preserve_path_structure=args.preserve_path_structure,
-        html_output_file=args.html_output_file)
+        html_output_file=args.html_output_file,
+        category_names_to_blur=category_names_to_blur)
 
     if args.html_output_file is not None and args.open_html_output_file:
         from megadetector.utils.path_utils import open_file

{megadetector-5.0.23.dist-info → megadetector-5.0.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: megadetector
-Version: 5.0.23
+Version: 5.0.25
 Summary: MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.
 Author-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
 Maintainer-email: Your friendly neighborhood MegaDetector team <cameratraps@lila.science>
@@ -29,26 +29,27 @@ Project-URL: Documentation, https://megadetector.readthedocs.io
 Project-URL: Bug Reports, https://github.com/agentmorris/MegaDetector/issues
 Project-URL: Source, https://github.com/agentmorris/MegaDetector
 Keywords: camera traps,conservation,wildlife,ai,megadetector
-Classifier: Development Status :: 3 - Alpha
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Requires-Python: <=3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: mkl==2024.0; sys_platform != "darwin"
+Requires-Dist: numpy<2.0,>=1.26.4
 Requires-Dist: Pillow>=9.5
 Requires-Dist: tqdm>=4.64.0
 Requires-Dist: jsonpickle>=3.0.2
 Requires-Dist: humanfriendly>=10.0
-Requires-Dist: numpy<2.0,>=1.26.4
 Requires-Dist: matplotlib>=3.8.0
 Requires-Dist: opencv-python>=4.8.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: pyqtree>=1.0.0
-Requires-Dist: seaborn>=0.12.2
 Requires-Dist: scikit-learn>=1.3.1
 Requires-Dist: pandas>=2.1.1
-Requires-Dist: PyYAML>=6.0.1
+Requires-Dist: python-dateutil
+Requires-Dist: send2trash
+Requires-Dist: dill
 Requires-Dist: ultralytics-yolov5==0.1.1
+Requires-Dist: yolov9pip==0.0.4
 Requires-Dist: python-dateutil
 
 # MegaDetector
@@ -57,28 +58,15 @@ This package is a pip-installable version of the support/inference code for [Meg
 
 If you aren't looking for the Python package specifically, and you just want to learn more about what MegaDetector is all about, head over to the [MegaDetector repo](https://github.com/agentmorris/MegaDetector/?tab=readme-ov-file#megadetector).
 
+If you don't want to run MegaDetector, and you just want to use the utilities in this package - postprocessing, manipulating large volumes of camera trap images, etc. - you may want to check out the [megadetector-utils](https://pypi.org/project/megadetector-utils/) package, which is identical to this one, but excludes all of the PyTorch/YOLO dependencies, and is thus approximately one zillion times smaller.
 
-## Reasons you might not be looking for this package
-
-### If you are an ecologist...
-
-If you are an ecologist looking to use MegaDetector to help you get through your camera trap images, you probably don't want this package, or at least you probably don't want to start at this page.  We recommend starting with our "[Getting started with MegaDetector](https://github.com/agentmorris/MegaDetector/blob/main/getting-started.md)" page, then digging in to the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md), which will walk you through the process of using MegaDetector.
-
-### If you are a computer-vision-y type...
-
-If you are a computer-vision-y person looking to run or fine-tune MegaDetector programmatically, you probably don't want this package.  MegaDetector is just a fine-tuned version of [YOLOv5](https://github.com/ultralytics/yolov5), and the [ultralytics](https://github.com/ultralytics/ultralytics/) package (from the developers of YOLOv5) has a zillion bells and whistles for both inference and fine-tuning that this package doesn't.
-
-## Reasons you might want to use this package
-
-If you want to programmatically interact with the postprocessing tools from the MegaDetector repo, or programmatically run MegaDetector in a way that produces [Timelapse](https://saul.cpsc.ucalgary.ca/timelapse)-friendly output (i.e., output in the standard [MegaDetector output format](https://github.com/agentmorris/MegaDetector/tree/main/megadetector/api/batch_processing#megadetector-batch-output-format)), this package might be for you.
-
-## If I haven't talked you out of using this package...
+## Installation
 
-To install:
+Install with:
 
 `pip install megadetector`
 
-MegaDetector model weights aren't downloaded at pip-install time, but they will be (optionally) automatically downloaded the first time you run the model.
+MegaDetector model weights aren't downloaded at the time you install the package, but they will be (optionally) automatically downloaded the first time you run the model.
 
 ## Package reference