fix multiple object type tracking

frigate/objects.py

@@ -4,7 +4,9 @@ import threading
 import cv2
 import prctl
 import itertools
+import copy
 import numpy as np
+import multiprocessing as mp
 from collections import defaultdict
 from scipy.spatial import distance as dist
 from frigate.util import draw_box_with_label, LABELS, compute_intersection_rectangle, compute_intersection_over_union, calculate_region
@@ -24,6 +26,14 @@ class ObjectCleaner(threading.Thread):
             for frame_time in list(self.camera.detected_objects.keys()).copy():
                 if not frame_time in self.camera.frame_cache:
                     del self.camera.detected_objects[frame_time]
+            
+            with self.camera.object_tracker.tracked_objects_lock:
+                now = datetime.datetime.now().timestamp()
+                for id, obj in list(self.camera.object_tracker.tracked_objects.items()):
+                    # if the object is more than 10 seconds old
+                    # and not in the most recent frame, deregister
+                    if (now - obj['frame_time']) > 10 and self.camera.object_tracker.most_recent_frame_time > obj['frame_time']:
+                        self.camera.object_tracker.deregister(id)
 
 class DetectedObjectsProcessor(threading.Thread):
     def __init__(self, camera):
@@ -222,15 +232,17 @@ class ObjectTracker(threading.Thread):
         threading.Thread.__init__(self)
         self.camera = camera
         self.tracked_objects = {}
-        self.disappeared = {}
-        self.max_disappeared = max_disappeared
+        self.tracked_objects_lock = mp.Lock()
+        self.most_recent_frame_time = None
     
     def run(self):
         prctl.set_name(self.__class__.__name__)
         while True:
             frame_time = self.camera.refined_frame_queue.get()
-            self.match_and_update(self.camera.detected_objects[frame_time])
-            self.camera.frame_output_queue.put(frame_time)
+            with self.tracked_objects_lock:
+                self.match_and_update(self.camera.detected_objects[frame_time])
+                self.most_recent_frame_time = frame_time
+                self.camera.frame_output_queue.put((frame_time, copy.deepcopy(self.tracked_objects)))
             if len(self.tracked_objects) > 0:
                 with self.camera.objects_tracked:
                     self.camera.objects_tracked.notify_all()
@@ -241,10 +253,8 @@ class ObjectTracker(threading.Thread):
         obj['top_score'] = obj['score']
         self.add_history(obj)
         self.tracked_objects[id] = obj
-        self.disappeared[id] = 0
 
     def deregister(self, id):
-        del self.disappeared[id]
         del self.tracked_objects[id]
     
     def update(self, id, new_obj):
@@ -267,22 +277,7 @@ class ObjectTracker(threading.Thread):
             obj['history'] = [entry]
 
     def match_and_update(self, new_objects):
-        # check to see if the list of input bounding box rectangles
-        # is empty
         if len(new_objects) == 0:
-            # loop over any existing tracked objects and mark them
-            # as disappeared
-            for objectID in list(self.disappeared.keys()):
-                self.disappeared[objectID] += 1
-
-                # if we have reached a maximum number of consecutive
-                # frames where a given object has been marked as
-                # missing, deregister it
-                if self.disappeared[objectID] > self.max_disappeared:
-                    self.deregister(objectID)
-
-            # return early as there are no centroids or tracking info
-            # to update
             return
             
         # group by name
@@ -291,13 +286,12 @@ class ObjectTracker(threading.Thread):
             new_object_groups[obj['name']].append(obj)
         
         # track objects for each label type
-        # TODO: this is going to miss deregistering objects that are not in the new groups
         for label, group in new_object_groups.items():
             current_objects = [o for o in self.tracked_objects.values() if o['name'] == label]
             current_ids = [o['id'] for o in current_objects]
             current_centroids = np.array([o['centroid'] for o in current_objects])
 
-            # compute centroids
+            # compute centroids of new objects
             for obj in group:
                 centroid_x = int((obj['box']['xmin']+obj['box']['xmax']) / 2.0)
                 centroid_y = int((obj['box']['ymin']+obj['box']['ymax']) / 2.0)
@@ -339,7 +333,6 @@ class ObjectTracker(threading.Thread):
             for (row, col) in zip(rows, cols):
                 # if we have already examined either the row or
                 # column value before, ignore it
-                # val
                 if row in usedRows or col in usedCols:
                     continue
 
@@ -347,43 +340,22 @@ class ObjectTracker(threading.Thread):
                 # set its new centroid, and reset the disappeared
                 # counter
                 objectID = current_ids[row]
-                self.update(objectID, new_objects[col])
-                self.disappeared[objectID] = 0
+                self.update(objectID, group[col])
 
                 # indicate that we have examined each of the row and
                 # column indexes, respectively
                 usedRows.add(row)
                 usedCols.add(col)
 
-            # compute both the row and column index we have NOT yet
-            # examined
-            unusedRows = set(range(0, D.shape[0])).difference(usedRows)
+            # compute the column index we have NOT yet examined
             unusedCols = set(range(0, D.shape[1])).difference(usedCols)
 
-            # in the event that the number of object centroids is
-            # equal or greater than the number of input centroids
-            # we need to check and see if some of these objects have
-            # potentially disappeared
-            if D.shape[0] >= D.shape[1]:
-                # loop over the unused row indexes
-                for row in unusedRows:
-                    # grab the object ID for the corresponding row
-                    # index and increment the disappeared counter
-                    objectID = current_ids[row]
-                    self.disappeared[objectID] += 1
-
-                    # check to see if the number of consecutive
-                    # frames the object has been marked "disappeared"
-                    # for warrants deregistering the object
-                    if self.disappeared[objectID] > self.max_disappeared:
-                        self.deregister(objectID)
-
-            # otherwise, if the number of input centroids is greater
+            # if the number of input centroids is greater
             # than the number of existing object centroids we need to
             # register each new input centroid as a trackable object
-            else:
-                for col in unusedCols:
-                    self.register(col, new_objects[col])
+            # if D.shape[0] < D.shape[1]:
+            for col in unusedCols:
+                self.register(col, group[col])
 
 # Maintains the frame and object with the highest score
 class BestFrames(threading.Thread):
@@ -400,18 +372,18 @@ class BestFrames(threading.Thread):
             with self.camera.objects_tracked:
                 self.camera.objects_tracked.wait()
 
-            # make a copy of detected objects
-            detected_objects = list(self.camera.object_tracker.tracked_objects.values()).copy()
+            # make a copy of tracked objects
+            tracked_objects = list(self.camera.object_tracker.tracked_objects.values())
 
-            for obj in detected_objects:
+            for obj in tracked_objects:
                 if obj['name'] in self.best_objects:
                     now = datetime.datetime.now().timestamp()
                     # if the object is a higher score than the current best score 
                     # or the current object is more than 1 minute old, use the new object
                     if obj['score'] > self.best_objects[obj['name']]['score'] or (now - self.best_objects[obj['name']]['frame_time']) > 60:
-                        self.best_objects[obj['name']] = obj
+                        self.best_objects[obj['name']] = copy.deepcopy(obj)
                 else:
-                    self.best_objects[obj['name']] = obj
+                    self.best_objects[obj['name']] = copy.deepcopy(obj)
             
             for name, obj in self.best_objects.items():
                 if obj['frame_time'] in self.camera.frame_cache:

frigate/util.py

@@ -75,12 +75,13 @@ def compute_intersection_over_union(box_a, box_b):
 def tonumpyarray(mp_arr):
     return np.frombuffer(mp_arr.get_obj(), dtype=np.uint8)
 
-def draw_box_with_label(frame, x_min, y_min, x_max, y_max, label, info):
-    color = COLOR_MAP[label]
+def draw_box_with_label(frame, x_min, y_min, x_max, y_max, label, info, thickness=2, color=None):
+    if color is None:
+        color = COLOR_MAP[label]
     display_text = "{}: {}".format(label, info)
     cv2.rectangle(frame, (x_min, y_min), 
         (x_max, y_max), 
-        color, 2)
+        color, thickness)
     font_scale = 0.5
     font = cv2.FONT_HERSHEY_SIMPLEX
     # get the width and height of the text box

frigate/video.py

@@ -9,6 +9,7 @@ import multiprocessing as mp
 import subprocess as sp
 import numpy as np
 import prctl
+import copy
 import itertools
 from collections import defaultdict
 from frigate.util import tonumpyarray, LABELS, draw_box_with_label, calculate_region, EventsPerSecond
@@ -64,7 +65,7 @@ class CameraWatchdog(threading.Thread):
             # wait a bit before checking
             time.sleep(10)
 
-            if (datetime.datetime.now().timestamp() - self.camera.frame_time.value) > 300:
+            if self.camera.frame_time.value != 0.0 and (datetime.datetime.now().timestamp() - self.camera.frame_time.value) > 300:
                 print("last frame is more than 5 minutes old, restarting camera capture...")
                 self.camera.start_or_restart_capture()
                 time.sleep(5)
@@ -116,12 +117,12 @@ class VideoWriter(threading.Thread):
     def run(self):
         prctl.set_name(self.__class__.__name__)
         while True:
-            frame_time = self.camera.frame_output_queue.get()
-            if len(self.camera.object_tracker.tracked_objects) == 0:
-                continue
-            f = open(f"/debug/{self.camera.name}-{str(frame_time)}.jpg", 'wb')
-            f.write(self.camera.frame_with_objects(frame_time))
-            f.close()
+            (frame_time, tracked_objects) = self.camera.frame_output_queue.get()
+            # if len(self.camera.object_tracker.tracked_objects) == 0:
+            #     continue
+            # f = open(f"/debug/output/{self.camera.name}-{str(format(frame_time, '.8f'))}.jpg", 'wb')
+            # f.write(self.camera.frame_with_objects(frame_time, tracked_objects))
+            # f.close()
 
 class Camera:
     def __init__(self, name, ffmpeg_config, global_objects_config, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
@@ -195,6 +196,14 @@ class Camera:
         for obj in objects_with_config:
             self.object_filters[obj] = {**global_object_filters.get(obj, {}), **camera_object_filters.get(obj, {})}
 
+        # start a thread to track objects
+        self.object_tracker = ObjectTracker(self, 10)
+        self.object_tracker.start()
+
+        # start a thread to write tracked frames to disk
+        self.video_writer = VideoWriter(self)
+        self.video_writer.start()
+
         # start a thread to queue resize requests for regions
         self.region_requester = RegionRequester(self)
         self.region_requester.start()
@@ -222,14 +231,6 @@ class Camera:
         self.region_refiner.start()
         self.dynamic_region_fps.start()
 
-        # start a thread to track objects
-        self.object_tracker = ObjectTracker(self, 10)
-        self.object_tracker.start()
-
-        # start a thread to write tracked frames to disk
-        self.video_writer = VideoWriter(self)
-        self.video_writer.start()
-
         # start a thread to publish object scores
         mqtt_publisher = MqttObjectPublisher(self.mqtt_client, self.mqtt_topic_prefix, self)
         mqtt_publisher.start()
@@ -312,8 +313,9 @@ class Camera:
             'dynamic_regions_per_sec': self.dynamic_region_fps.eps()
         }
     
-    def frame_with_objects(self, frame_time):
+    def frame_with_objects(self, frame_time, tracked_objects=None):
         frame = self.frame_cache[frame_time].copy()
+        detected_objects = self.detected_objects[frame_time].copy()
 
         for region in self.regions:
             color = (255,255,255)
@@ -322,13 +324,17 @@ class Camera:
                 color, 2)
 
         # draw the bounding boxes on the screen
-        for id, obj in list(self.object_tracker.tracked_objects.items()):
-        # for obj in detected_objects[frame_time]:
-            cv2.rectangle(frame, (obj['region']['xmin'], obj['region']['ymin']), 
-                (obj['region']['xmax'], obj['region']['ymax']), 
-                (0,255,0), 1)
-            draw_box_with_label(frame, obj['box']['xmin'], obj['box']['ymin'], obj['box']['xmax'], obj['box']['ymax'], obj['name'], f"{int(obj['score']*100)}% {obj['area']} {id}")
-            
+
+        if tracked_objects is None:
+            tracked_objects = copy.deepcopy(self.object_tracker.tracked_objects)
+
+        for obj in detected_objects:
+            draw_box_with_label(frame, obj['box']['xmin'], obj['box']['ymin'], obj['box']['xmax'], obj['box']['ymax'], obj['name'], f"{int(obj['score']*100)}% {obj['area']}", thickness=3)
+        
+        for id, obj in tracked_objects.items():
+            color = (0, 255,0) if obj['frame_time'] == frame_time else (255, 0, 0)
+            draw_box_with_label(frame, obj['box']['xmin'], obj['box']['ymin'], obj['box']['xmax'], obj['box']['ymax'], obj['name'], f"{int(obj['score']*100)}% {obj['area']} {id}", color=color, thickness=1)
+
         # print a timestamp
         time_to_show = datetime.datetime.fromtimestamp(frame_time).strftime("%m/%d/%Y %H:%M:%S")
         cv2.putText(frame, time_to_show, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=.8, color=(255, 255, 255), thickness=2)