fix process clip

process_clip.py → frigate/process_clip.py

@@ -1,25 +1,68 @@
-import sys
-import click
-import os
 import datetime
-from unittest import TestCase, main
-from frigate.video import process_frames, start_or_restart_ffmpeg, capture_frames, get_frame_shape
-from frigate.util import DictFrameManager, SharedMemoryFrameManager, EventsPerSecond, draw_box_with_label
-from frigate.motion import MotionDetector
-from frigate.edgetpu import LocalObjectDetector
-from frigate.objects import ObjectTracker
+import json
+import logging
 import multiprocessing as mp
-import numpy as np
+import os
+import subprocess as sp
+import sys
+from unittest import TestCase, main
+
+import click
 import cv2
+import numpy as np
+
+from frigate.config import FRIGATE_CONFIG_SCHEMA, FrigateConfig
+from frigate.edgetpu import LocalObjectDetector
+from frigate.motion import MotionDetector
 from frigate.object_processing import COLOR_MAP, CameraState
+from frigate.objects import ObjectTracker
+from frigate.util import (DictFrameManager, EventsPerSecond,
+                          SharedMemoryFrameManager, draw_box_with_label)
+from frigate.video import (capture_frames, process_frames,
+                           start_or_restart_ffmpeg)
+
+logging.basicConfig()
+logging.root.setLevel(logging.DEBUG)
+
+logger = logging.getLogger(__name__)
+
+def get_frame_shape(source):
+    ffprobe_cmd = " ".join([
+        'ffprobe',
+        '-v',
+        'panic',
+        '-show_error',
+        '-show_streams',
+        '-of',
+        'json',
+        '"'+source+'"'
+    ])
+    p = sp.Popen(ffprobe_cmd, stdout=sp.PIPE, shell=True)
+    (output, err) = p.communicate()
+    p_status = p.wait()
+    info = json.loads(output)
+
+    video_info = [s for s in info['streams'] if s['codec_type'] == 'video'][0]
+
+    if video_info['height'] != 0 and video_info['width'] != 0:
+        return (video_info['height'], video_info['width'], 3)
+    
+    # fallback to using opencv if ffprobe didnt succeed
+    video = cv2.VideoCapture(source)
+    ret, frame = video.read()
+    frame_shape = frame.shape
+    video.release()
+    return frame_shape
 
 class ProcessClip():
-    def __init__(self, clip_path, frame_shape, config):
+    def __init__(self, clip_path, frame_shape, config: FrigateConfig):
         self.clip_path = clip_path
-        self.frame_shape = frame_shape
         self.camera_name = 'camera'
-        self.frame_manager = DictFrameManager()
-        # self.frame_manager = SharedMemoryFrameManager()
+        self.config = config
+        self.camera_config = self.config.cameras['camera']
+        self.frame_shape = self.camera_config.frame_shape
+        self.ffmpeg_cmd = [c['cmd'] for c in self.camera_config.ffmpeg_cmds if 'detect' in c['roles']][0]
+        self.frame_manager = SharedMemoryFrameManager()
         self.frame_queue = mp.Queue()
         self.detected_objects_queue = mp.Queue()
         self.camera_state = CameraState(self.camera_name, config, self.frame_manager)
@@ -27,12 +70,11 @@ class ProcessClip():
     def load_frames(self):
         fps = EventsPerSecond()
         skipped_fps = EventsPerSecond()
-        stop_event = mp.Event()
-        detection_frame = mp.Value('d', datetime.datetime.now().timestamp()+100000)
         current_frame = mp.Value('d', 0.0)
-        ffmpeg_cmd = f"ffmpeg -hide_banner -loglevel panic -i {self.clip_path} -f rawvideo -pix_fmt rgb24 pipe:".split(" ")
-        ffmpeg_process = start_or_restart_ffmpeg(ffmpeg_cmd, self.frame_shape[0]*self.frame_shape[1]*self.frame_shape[2])
-        capture_frames(ffmpeg_process, self.camera_name, self.frame_shape, self.frame_manager, self.frame_queue, 1, fps, skipped_fps, stop_event, detection_frame, current_frame)
+        frame_size = self.camera_config.frame_shape_yuv[0] * self.camera_config.frame_shape_yuv[1]
+        ffmpeg_process = start_or_restart_ffmpeg(self.ffmpeg_cmd, logger, sp.DEVNULL, frame_size)
+        capture_frames(ffmpeg_process, self.camera_name, self.camera_config.frame_shape_yuv, self.frame_manager, 
+            self.frame_queue, fps, skipped_fps, current_frame)
         ffmpeg_process.wait()
         ffmpeg_process.communicate()
     
@@ -43,23 +85,28 @@ class ProcessClip():
 
         object_detector = LocalObjectDetector(labels='/labelmap.txt')
         object_tracker = ObjectTracker(10)
-        process_fps = mp.Value('d', 0.0)
-        detection_fps = mp.Value('d', 0.0)
-        current_frame = mp.Value('d', 0.0)
+        process_info = {
+            'process_fps': mp.Value('d', 0.0),
+            'detection_fps': mp.Value('d', 0.0),
+            'detection_frame': mp.Value('d', 0.0)
+        }
         stop_event = mp.Event()
+        model_shape = (self.config.model.height, self.config.model.width)
 
-        process_frames(self.camera_name, self.frame_queue, self.frame_shape, self.frame_manager, motion_detector, object_detector, object_tracker, self.detected_objects_queue, 
-            process_fps, detection_fps, current_frame, objects_to_track, object_filters, mask, stop_event, exit_on_empty=True)
+        process_frames(self.camera_name, self.frame_queue, self.frame_shape, model_shape, 
+            self.frame_manager, motion_detector, object_detector, object_tracker, 
+            self.detected_objects_queue, process_info, 
+            objects_to_track, object_filters, mask, stop_event, exit_on_empty=True)
     
     def objects_found(self, debug_path=None):
         obj_detected = False
         top_computed_score = 0.0
-        def handle_event(name, obj):
+        def handle_event(name, obj, frame_time):
             nonlocal obj_detected
             nonlocal top_computed_score
-            if obj['computed_score'] > top_computed_score:
-                top_computed_score = obj['computed_score']
-            if not obj['false_positive']:
+            if obj.computed_score > top_computed_score:
+                top_computed_score = obj.computed_score
+            if not obj.false_positive:
                 obj_detected = True
         self.camera_state.on('new', handle_event)
         self.camera_state.on('update', handle_event)
@@ -71,7 +118,8 @@ class ProcessClip():
 
             self.camera_state.update(frame_time, current_tracked_objects)
             for obj in self.camera_state.tracked_objects.values():
-                print(f"{frame_time}: {obj['id']} - {obj['computed_score']} - {obj['score_history']}")
+                obj_data = obj.to_dict()
+                print(f"{frame_time}: {obj_data['id']} - {obj_data['label']} - {obj_data['score']} - {obj.score_history}")
         
         self.frame_manager.delete(self.camera_state.previous_frame_id)
         
@@ -81,7 +129,7 @@ class ProcessClip():
         }
     
     def save_debug_frame(self, debug_path, frame_time, tracked_objects):
-        current_frame = self.frame_manager.get(f"{self.camera_name}{frame_time}", self.frame_shape)
+        current_frame = cv2.cvtColor(self.frame_manager.get(f"{self.camera_name}{frame_time}", self.camera_config.frame_shape_yuv), cv2.COLOR_YUV2BGR_I420)
         # draw the bounding boxes on the frame
         for obj in tracked_objects:
             thickness = 2
@@ -95,12 +143,12 @@ class ProcessClip():
 
             # draw the bounding boxes on the frame
             box = obj['box']
-            draw_box_with_label(current_frame, box[0], box[1], box[2], box[3], obj['label'], f"{int(obj['score']*100)}% {int(obj['area'])}", thickness=thickness, color=color)
+            draw_box_with_label(current_frame, box[0], box[1], box[2], box[3], obj['id'], f"{int(obj['score']*100)}% {int(obj['area'])}", thickness=thickness, color=color)
             # draw the regions on the frame
             region = obj['region']
             draw_box_with_label(current_frame, region[0], region[1], region[2], region[3], 'region', "", thickness=1, color=(0,255,0))
         
-        cv2.imwrite(f"{os.path.join(debug_path, os.path.basename(self.clip_path))}.{int(frame_time*1000000)}.jpg", cv2.cvtColor(current_frame, cv2.COLOR_RGB2BGR))
+        cv2.imwrite(f"{os.path.join(debug_path, os.path.basename(self.clip_path))}.{int(frame_time*1000000)}.jpg", current_frame)
 
 @click.command()
 @click.option("-p", "--path", required=True, help="Path to clip or directory to test.")
@@ -116,29 +164,37 @@ def process(path, label, threshold, debug_path):
     elif os.path.isfile(path):  
         clips.append(path)
 
-    config = {
-        'snapshots': {
-            'show_timestamp': False, 
-            'draw_zones': False
+    json_config = {
+        'mqtt': {
+            'host': 'mqtt'
         },
-        'zones': {},
-        'objects': {
-            'track': [label],
-            'filters': {
-                'person': {
-                    'threshold': threshold
-                }
+        'cameras': {
+            'camera': {
+                'ffmpeg': {
+                    'inputs': [
+                        { 'path': 'path.mp4', 'global_args': '', 'input_args': '', 'roles': ['detect'] }
+                    ]
+                },
+                'height': 1920,
+                'width': 1080
             }
         }
     }
 
     results = []
     for c in clips:
+        logger.info(c)
         frame_shape = get_frame_shape(c)
-        config['frame_shape'] = frame_shape
+        
+        json_config['cameras']['camera']['height'] = frame_shape[0]
+        json_config['cameras']['camera']['width'] = frame_shape[1]
+        json_config['cameras']['camera']['ffmpeg']['inputs'][0]['path'] = c
+
+        config = FrigateConfig(config=FRIGATE_CONFIG_SCHEMA(json_config))
+
         process_clip = ProcessClip(c, frame_shape, config)
         process_clip.load_frames()
-        process_clip.process_frames(objects_to_track=config['objects']['track'])
+        process_clip.process_frames(objects_to_track=[label])
 
         results.append((c, process_clip.objects_found(debug_path)))
 
@@ -149,4 +205,4 @@ def process(path, label, threshold, debug_path):
     print(f"Objects were detected in {positive_count}/{len(results)}({positive_count/len(results)*100:.2f}%) clip(s).")
 
 if __name__ == '__main__':
-    process()
+    process()

frigate/video.py

@@ -112,16 +112,15 @@ def capture_frames(ffmpeg_process, camera_name, frame_shape, frame_manager: Fram
         frame_name = f"{camera_name}{current_frame.value}"
         frame_buffer = frame_manager.create(frame_name, frame_size)
         try:
-          frame_buffer[:] = ffmpeg_process.stdout.read(frame_size)
-        except:
-          logger.info(f"{camera_name}: ffmpeg sent a broken frame. something is wrong.")
-
-          if ffmpeg_process.poll() != None:
-              logger.info(f"{camera_name}: ffmpeg process is not running. exiting capture thread...")
-              frame_manager.delete(frame_name)
-              break
-          
-          continue
+            frame_buffer[:] = ffmpeg_process.stdout.read(frame_size)
+        except Exception as e:
+            logger.info(f"{camera_name}: ffmpeg sent a broken frame. {e}")
+
+            if ffmpeg_process.poll() != None:
+                logger.info(f"{camera_name}: ffmpeg process is not running. exiting capture thread...")
+                frame_manager.delete(frame_name)
+                break
+            continue
 
         frame_rate.update()