refactor and reduce false positives

Dockerfile

@@ -31,6 +31,7 @@ RUN apt -qq update && apt -qq install --no-install-recommends -y \
         PyYAML \
         matplotlib \
         pyarrow \
+        click \
     && echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" > /etc/apt/sources.list.d/coral-edgetpu.list \
     && wget -q -O - https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key add - \
     && apt -qq update \
@@ -46,7 +47,7 @@ RUN apt -qq update && apt -qq install --no-install-recommends -y \
 
 # get model and labels
 RUN wget -q https://github.com/google-coral/edgetpu/raw/master/test_data/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite -O /edgetpu_model.tflite --trust-server-names
-RUN wget -q https://dl.google.com/coral/canned_models/coco_labels.txt -O /labelmap.txt --trust-server-names
+COPY labelmap.txt /labelmap.txt
 RUN wget -q https://github.com/google-coral/edgetpu/raw/master/test_data/ssd_mobilenet_v2_coco_quant_postprocess.tflite -O /cpu_model.tflite 
 
 

README.md

@@ -342,5 +342,17 @@ cameras:
     width: 1920
 ```
 - Additional logging is available in the docker container - You can view the logs by running `docker logs -t frigate`
-- Object configuration - Tracked objects types, sizes and thresholds can be defined globally and/or on a per camera basis. The global and camera object configuration is *merged*. For example, if you defined tracking person, car, and truck globally but modified your backyard camera to only track person, the global config would merge making the effective list for the backyard camera still contain person, car and truck. If you want precise object tracking per camera, best practice to put a minimal list of objects at the global level and expand objects on a per camera basis. Object threshold and area configuration will be used first from the camera object config (if defined) and then from the global config.  See the [example config](config/config.example.yml) for more information. 
+- Object configuration - Tracked objects types, sizes and thresholds can be defined globally and/or on a per camera basis. The global and camera object configuration is *merged*. For example, if you defined tracking person, car, and truck globally but modified your backyard camera to only track person, the global config would merge making the effective list for the backyard camera still contain person, car and truck. If you want precise object tracking per camera, best practice to put a minimal list of objects at the global level and expand objects on a per camera basis. Object threshold and area configuration will be used first from the camera object config (if defined) and then from the global config.  See the [example config](config/config.example.yml) for more information.
+
+## Troubleshooting
+
+### "ffmpeg didnt return a frame. something is wrong"
+Turn on logging for the camera by overriding the global_args and setting the log level to `info`:
+```yaml
+ffmpeg:
+  global_args:
+    - -hide_banner
+    - -loglevel
+    - panic
+```
 

config/config.example.yml

@@ -53,9 +53,10 @@ mqtt:
 # unless overridden at the camera levels.
 # Keys must be valid labels. By default, the model uses coco (https://dl.google.com/coral/canned_models/coco_labels.txt).
 # All labels from the model are reported over MQTT. These values are used to filter out false positives.
-# min_area (optional): minimum width*height of the bounding box for the detected person
-# max_area (optional): maximum width*height of the bounding box for the detected person
-# threshold (optional): The minimum decimal percentage (50% hit = 0.5) for the confidence from tensorflow
+# min_area (optional): minimum width*height of the bounding box for the detected object
+# max_area (optional): maximum width*height of the bounding box for the detected object
+# min_score (optional): minimum score for the object
+# threshold (optional): The minimum decimal percentage for tracked object's computed score to considered a true positive
 ####################
 objects:
   track:
@@ -66,7 +67,8 @@ objects:
     person:
       min_area: 5000
       max_area: 100000
-      threshold: 0.8
+      min_score: 0.5
+      threshold: 0.85
 
 zones:
   #################
@@ -184,4 +186,5 @@ cameras:
         person:
           min_area: 5000
           max_area: 100000
-          threshold: 0.8
+          min_score: 0.5
+          threshold: 0.85

detect_objects.py

@@ -120,7 +120,7 @@ def run(self):
                     process = mp.Process(target=track_camera, args=(name, self.config[name], GLOBAL_OBJECT_CONFIG, camera_process['frame_queue'],
                         camera_process['frame_shape'], self.tflite_process.detection_queue, self.tracked_objects_queue, 
                         camera_process['process_fps'], camera_process['detection_fps'],
-                        camera_process['read_start'], camera_process['detection_frame']))
+                        camera_process['read_start'], camera_process['detection_frame'], self.stop_event))
                     process.daemon = True
                     camera_process['process'] = process
                     process.start()
@@ -135,7 +135,7 @@ def run(self):
                     camera_capture.start()
                     camera_process['ffmpeg_process'] = ffmpeg_process
                     camera_process['capture_thread'] = camera_capture
-                elif now - camera_process['capture_thread'].current_frame > 5:
+                elif now - camera_process['capture_thread'].current_frame.value > 5:
                     print(f"No frames received from {name} in 5 seconds. Exiting ffmpeg...")
                     ffmpeg_process = camera_process['ffmpeg_process']
                     ffmpeg_process.terminate()
@@ -181,6 +181,7 @@ def on_connect(client, userdata, flags, rc):
             'show_timestamp': config.get('snapshots', {}).get('show_timestamp', True),
             'draw_zones': config.get('snapshots', {}).get('draw_zones', False)
         }
+        config['zones'] = {}
 
     # Queue for cameras to push tracked objects to
     tracked_objects_queue = mp.Queue()
@@ -259,7 +260,23 @@ def on_connect(client, userdata, flags, rc):
             'capture_thread': camera_capture
         }
 
-        camera_process = mp.Process(target=track_camera, args=(name, config, GLOBAL_OBJECT_CONFIG, frame_queue, frame_shape,
+        # merge global object config into camera object config
+        camera_objects_config = config.get('objects', {})
+        # get objects to track for camera
+        objects_to_track = camera_objects_config.get('track', GLOBAL_OBJECT_CONFIG.get('track', ['person']))
+        # merge object filters
+        global_object_filters = GLOBAL_OBJECT_CONFIG.get('filters', {})
+        camera_object_filters = camera_objects_config.get('filters', {})
+        objects_with_config = set().union(global_object_filters.keys(), camera_object_filters.keys())
+        object_filters = {}
+        for obj in objects_with_config:
+            object_filters[obj] = {**global_object_filters.get(obj, {}), **camera_object_filters.get(obj, {})}
+        config['objects'] = {
+            'track': objects_to_track,
+            'filters': object_filters
+        }
+
+        camera_process = mp.Process(target=track_camera, args=(name, config, frame_queue, frame_shape,
             tflite_process.detection_queue, tracked_objects_queue, camera_processes[name]['process_fps'], 
             camera_processes[name]['detection_fps'], 
             camera_processes[name]['read_start'], camera_processes[name]['detection_frame'], stop_event))
@@ -340,7 +357,7 @@ def stats():
                 'pid': camera_stats['process'].pid,
                 'ffmpeg_pid': camera_stats['ffmpeg_process'].pid,
                 'frame_info': {
-                    'read': capture_thread.current_frame,
+                    'read': capture_thread.current_frame.value,
                     'detect': camera_stats['detection_frame'].value,
                     'process': object_processor.camera_data[name]['current_frame_time']
                 }