change the ffmpeg config for global defaults and overrides

.gitignore

@@ -1,2 +1,4 @@
 *.pyc 
 debug
+.vscode
+config/config.yml

README.md

@@ -1,9 +1,9 @@
 <a href='https://ko-fi.com/P5P7XGO9' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://az743702.vo.msecnd.net/cdn/kofi4.png?v=2' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
 
-# Frigate - Realtime Object Detection for RTSP Cameras
+# Frigate - Realtime Object Detection for IP Cameras
 **Note:** This version requires the use of a [Google Coral USB Accelerator](https://coral.withgoogle.com/products/accelerator/)
 
-Uses OpenCV and Tensorflow to perform realtime object detection locally for RTSP cameras. Designed for integration with HomeAssistant or others via MQTT.
+Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras. Designed for integration with HomeAssistant or others via MQTT.
 
 - Leverages multiprocessing and threads heavily with an emphasis on realtime over processing every frame
 - Allows you to define specific regions (squares) in the image to look for objects
@@ -32,8 +32,9 @@ docker run --rm \
 --privileged \
 -v /dev/bus/usb:/dev/bus/usb \
 -v <path_to_config_dir>:/config:ro \
+-v /etc/localtime:/etc/localtime:ro \
 -p 5000:5000 \
--e RTSP_PASSWORD='password' \
+-e FRIGATE_RTSP_PASSWORD='password' \
 frigate:latest
 ```
 
@@ -46,14 +47,15 @@ Example docker-compose:
     image: frigate:latest
     volumes:
       - /dev/bus/usb:/dev/bus/usb
+      - /etc/localtime:/etc/localtime:ro
       - <path_to_config>:/config
     ports:
       - "5000:5000"
     environment:
-      RTSP_PASSWORD: "password"
+      FRIGATE_RTSP_PASSWORD: "password"
 ```
 
-A `config.yml` file must exist in the `config` directory. See example [here](config/config.yml).
+A `config.yml` file must exist in the `config` directory. See example [here](config/config.yml) and device specific info can be found [here](docs/DEVICES.md).
 
 Access the mjpeg stream at `http://localhost:5000/<camera_name>` and the best person snapshot at `http://localhost:5000/<camera_name>/best_person.jpg`
 
@@ -94,7 +96,7 @@ automation:
 ```
 
 ## Tips
-- Lower the framerate of the RTSP feed on the camera to reduce the CPU usage for capturing the feed
+- Lower the framerate of the video feed on the camera to reduce the CPU usage for capturing the feed
 
 ## Future improvements
 - [x] Remove motion detection for now

config/config.example.yml

@@ -0,0 +1,110 @@
+web_port: 5000
+
+mqtt:
+  host: mqtt.server.com
+  topic_prefix: frigate
+#  client_id: frigate # Optional -- set to override default client id of 'frigate' if running multiple instances
+#  user: username # Optional -- Uncomment for use
+#  password: password # Optional -- Uncomment for use
+
+#################
+# Default ffmpeg args. Optional and can be overwritten per camera.
+# Should work with most RTSP cameras that send h264 video
+# Built from the properties below with:
+# "ffmpeg" + global_args + input_args + "-i" + input + output_args
+#################
+# ffmpeg:
+#   global_args:
+#     - -hide_banner
+#     - -loglevel
+#     - panic
+#   hwaccel_args: []
+#   input_args:
+#     - -avoid_negative_ts
+#     - make_zero
+#     - -fflags
+#     - nobuffer
+#     - -flags
+#     - low_delay
+#     - -strict
+#     - experimental
+#     - -fflags
+#     - +genpts+discardcorrupt
+#     - -vsync
+#     - drop
+#     - -rtsp_transport
+#     - tcp
+#     - -stimeout
+#     - '5000000'
+#     - -use_wallclock_as_timestamps
+#     - '1'
+#   output_args:
+#     - -vf
+#     - mpdecimate
+#     - -f
+#     - rawvideo
+#     - -pix_fmt
+#     - rgb24
+  
+cameras:
+  back:
+    ffmpeg:
+      ################
+      # Source passed to ffmpeg after the -i parameter. Supports anything compatible with OpenCV and FFmpeg.
+      # Environment variables that begin with 'FRIGATE_' may be referenced in {}
+      ################
+      input: rtsp://viewer:{FRIGATE_RTSP_PASSWORD}@10.0.10.10:554/cam/realmonitor?channel=1&subtype=2
+      #################
+      # These values will override default values for just this camera
+      #################
+      # global_args: []
+      # hwaccel_args: []
+      # input_args: []
+      # output_args: []
+
+    ################
+    ## Optional mask. Must be the same dimensions as your video feed.
+    ## The mask works by looking at the bottom center of the bounding box for the detected
+    ## person in the image. If that pixel in the mask is a black pixel, it ignores it as a
+    ## false positive. In my mask, the grass and driveway visible from my backdoor camera 
+    ## are white. The garage doors, sky, and trees (anywhere it would be impossible for a 
+    ## person to stand) are black.
+    ################
+    # mask: back-mask.bmp
+
+    ################
+    # Allows you to limit the framerate within frigate for cameras that do not support
+    # custom framerates. A value of 1 tells frigate to look at every frame, 2 every 2nd frame, 
+    # 3 every 3rd frame, etc.
+    ################
+    take_frame: 1
+    
+    ################
+    # size: size of the region in pixels
+    # x_offset/y_offset: position of the upper left corner of your region (top left of image is 0,0)
+    # min_person_area (optional): minimum width*height of the bounding box for the detected person
+    # max_person_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
+    # Tips: All regions are resized to 300x300 before detection because the model is trained on that size.
+    #       Resizing regions takes CPU power. Ideally, all regions should be as close to 300x300 as possible.
+    #       Defining a region that goes outside the bounds of the image will result in errors.
+    ################
+    regions:
+      - size: 350
+        x_offset: 0
+        y_offset: 300
+        min_person_area: 5000
+        max_person_area: 100000
+        threshold: 0.5
+      - size: 400
+        x_offset: 350
+        y_offset: 250
+        min_person_area: 2000
+        max_person_area: 100000
+        threshold: 0.5
+      - size: 400
+        x_offset: 750
+        y_offset: 250
+        min_person_area: 2000
+        max_person_area: 100000
+        threshold: 0.5

config/config.yml

@@ -1,82 +0,0 @@
-web_port: 5000
-
-mqtt:
-  host: mqtt.server.com
-  topic_prefix: frigate
-#  user: username # Optional -- Uncomment for use
-#  password: password # Optional -- Uncomment for use
-
-cameras:
-  back:
-    rtsp:
-      user: viewer
-      host: 10.0.10.10
-      port: 554
-      # values that begin with a "$" will be replaced with environment variable
-      password: $RTSP_PASSWORD
-      path: /cam/realmonitor?channel=1&subtype=2
-
-    ################
-    ## Optional mask. Must be the same dimensions as your video feed.
-    ## The mask works by looking at the bottom center of the bounding box for the detected
-    ## person in the image. If that pixel in the mask is a black pixel, it ignores it as a
-    ## false positive. In my mask, the grass and driveway visible from my backdoor camera 
-    ## are white. The garage doors, sky, and trees (anywhere it would be impossible for a 
-    ## person to stand) are black.
-    ################
-    # mask: back-mask.bmp
-
-    ################
-    # Allows you to limit the framerate within frigate for cameras that do not support
-    # custom framerates. A value of 1 tells frigate to look at every frame, 2 every 2nd frame, 
-    # 3 every 3rd frame, etc.
-    ################
-    take_frame: 1
-
-    ################
-    # Optional hardware acceleration parameters for ffmpeg. If your hardware supports it, it can
-    # greatly reduce the CPU power used to decode the video stream. You will need to determine which
-    # parameters work for your specific hardware. These may work for those with Intel hardware that
-    # supports QuickSync.
-    ################
-    # ffmpeg_hwaccel_args:
-    #   - -hwaccel
-    #   - vaapi
-    #   - -hwaccel_device
-    #   - /dev/dri/renderD128
-    #   - -hwaccel_output_format
-    #   - yuv420p
-
-    ################
-    # FFmpeg log level. Default is "panic". https://ffmpeg.org/ffmpeg.html#Generic-options
-    ################
-    # ffmpeg_log_level: panic
-
-    ################
-    # Optional custom input args. Some cameras may need custom ffmpeg params to work reliably. Specifying
-    # these will replace the default input params.
-    ################
-    # ffmpeg_input_args: []
-
-    ################
-    # Optional custom output args. Some cameras may need custom ffmpeg params to work reliably. Specifying
-    # these will replace the default output params.
-    ################
-    # ffmpeg_output_args: []
-    
-    regions:
-      - size: 350
-        x_offset: 0
-        y_offset: 300
-        min_person_area: 5000
-        threshold: 0.5
-      - size: 400
-        x_offset: 350
-        y_offset: 250
-        min_person_area: 2000
-        threshold: 0.5
-      - size: 400
-        x_offset: 750
-        y_offset: 250
-        min_person_area: 2000
-        threshold: 0.5

detect_objects.py

@@ -17,6 +17,30 @@ MQTT_PORT = CONFIG.get('mqtt', {}).get('port', 1883)
 MQTT_TOPIC_PREFIX = CONFIG.get('mqtt', {}).get('topic_prefix', 'frigate')
 MQTT_USER = CONFIG.get('mqtt', {}).get('user')
 MQTT_PASS = CONFIG.get('mqtt', {}).get('password')
+MQTT_CLIENT_ID = CONFIG.get('mqtt', {}).get('client_id', 'frigate')
+
+# Set the default FFmpeg config
+FFMPEG_CONFIG = CONFIG.get('ffmpeg', {})
+FFMPEG_DEFAULT_CONFIG = {
+    'global_args': FFMPEG_CONFIG.get('global_args', 
+        ['-hide_banner','-loglevel','panic']),
+    'hwaccel_args': FFMPEG_CONFIG.get('hwaccel_args', 
+        []),
+    'input_args': FFMPEG_CONFIG.get('input_args',
+        ['-avoid_negative_ts', 'make_zero',
+         '-fflags', 'nobuffer',
+         '-flags', 'low_delay',
+         '-strict', 'experimental',
+         '-fflags', '+genpts+discardcorrupt',
+         '-vsync', 'drop',
+         '-rtsp_transport', 'tcp',
+         '-stimeout', '5000000',
+         '-use_wallclock_as_timestamps', '1']),
+    'output_args': FFMPEG_CONFIG.get('output_args',
+        ['-vf', 'mpdecimate',
+         '-f', 'rawvideo',
+         '-pix_fmt', 'rgb24'])
+}
 
 WEB_PORT = CONFIG.get('web_port', 5000)
 DEBUG = (CONFIG.get('debug', '0') == '1')
@@ -36,7 +60,7 @@ def main():
                 print ("Unable to connect to MQTT: Connection refused. Error code: " + str(rc))
         # publish a message to signal that the service is running
         client.publish(MQTT_TOPIC_PREFIX+'/available', 'online', retain=True)
-    client = mqtt.Client(client_id="frigate")
+    client = mqtt.Client(client_id=MQTT_CLIENT_ID)
     client.on_connect = on_connect
     client.will_set(MQTT_TOPIC_PREFIX+'/available', payload='offline', qos=1, retain=True)
     if not MQTT_USER is None:
@@ -50,7 +74,7 @@ def main():
 
     cameras = {}
     for name, config in CONFIG['cameras'].items():
-        cameras[name] = Camera(name, config, prepped_frame_queue, client, MQTT_TOPIC_PREFIX)
+        cameras[name] = Camera(name, FFMPEG_DEFAULT_CONFIG, config, prepped_frame_queue, client, MQTT_TOPIC_PREFIX)
 
     prepped_queue_processor = PreppedQueueProcessor(
         cameras,
@@ -65,21 +89,32 @@ def main():
     # create a flask app that encodes frames a mjpeg on demand
     app = Flask(__name__)
 
+    @app.route('/')
+    def ishealthy():
+        # return a healh
+        return "Frigate is running. Alive and healthy!"
+
     @app.route('/<camera_name>/best_person.jpg')
     def best_person(camera_name):
-        best_person_frame = cameras[camera_name].get_best_person()
-        if best_person_frame is None:
-            best_person_frame = np.zeros((720,1280,3), np.uint8)
-        ret, jpg = cv2.imencode('.jpg', best_person_frame)
-        response = make_response(jpg.tobytes())
-        response.headers['Content-Type'] = 'image/jpg'
-        return response
+        if camera_name in cameras:
+            best_person_frame = cameras[camera_name].get_best_person()
+            if best_person_frame is None:
+                best_person_frame = np.zeros((720,1280,3), np.uint8)
+            ret, jpg = cv2.imencode('.jpg', best_person_frame)
+            response = make_response(jpg.tobytes())
+            response.headers['Content-Type'] = 'image/jpg'
+            return response
+        else:
+            return f'Camera named {camera_name} not found', 404
 
     @app.route('/<camera_name>')
     def mjpeg_feed(camera_name):
-        # return a multipart response
-        return Response(imagestream(camera_name),
-                        mimetype='multipart/x-mixed-replace; boundary=frame')
+        if camera_name in cameras:
+            # return a multipart response
+            return Response(imagestream(camera_name),
+                            mimetype='multipart/x-mixed-replace; boundary=frame')
+        else:
+            return f'Camera named {camera_name} not found', 404
 
     def imagestream(camera_name):
         while True:

docs/DEVICES.md

@@ -0,0 +1,74 @@
+# Configuration Examples
+
+### Default (most RTSP cameras)
+This is the default ffmpeg command and should work with most RTSP cameras that send h264 video
+```yaml
+ffmpeg:
+  global_args:
+    - -hide_banner
+    - -loglevel
+    - panic
+  hwaccel_args: []
+  input_args:
+    - -avoid_negative_ts
+    - make_zero 
+    - -fflags
+    - nobuffer
+    - -flags
+    - low_delay
+    - -strict
+    - experimental
+    - -fflags
+    - +genpts+discardcorrupt
+    - -vsync
+    - drop
+    - -rtsp_transport
+    - tcp
+    - -stimeout
+    - '5000000' 
+    - -use_wallclock_as_timestamps
+    - '1'
+  output_args:
+    - -vf
+    - mpdecimate
+    - -f
+    - rawvideo
+    - -pix_fmt
+    - rgb24
+```
+
+### RTMP Cameras
+The input parameters need to be adjusted for RTMP cameras
+```yaml
+ffmpeg:
+input_args:
+    - -avoid_negative_ts
+    - make_zero
+    - -fflags
+    - nobuffer
+    - -flags
+    - low_delay
+    - -strict
+    - experimental
+    - -fflags
+    - +genpts+discardcorrupt
+    - -vsync
+    - drop
+    - -use_wallclock_as_timestamps
+    - '1'
+```
+
+
+### Hardware Acceleration
+
+Intel Quicksync
+```yaml
+ffmpeg:
+  hwaccel_args:
+    - -hwaccel
+    - vaapi
+    - -hwaccel_device
+    - /dev/dri/renderD128
+    - -hwaccel_output_format
+    - yuv420p
+```

frigate/objects.py

@@ -85,4 +85,8 @@ class BestPersonFrame(threading.Thread):
                 draw_box_with_label(best_frame, self.best_person['xmin'], self.best_person['ymin'], 
                     self.best_person['xmax'], self.best_person['ymax'], label)
                 
+                # print a timestamp
+                time_to_show = datetime.datetime.fromtimestamp(self.best_person['frame_time']).strftime("%m/%d/%Y %H:%M:%S")
+                cv2.putText(best_frame, time_to_show, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=.8, color=(255, 255, 255), thickness=2)
+                
                 self.best_frame = cv2.cvtColor(best_frame, cv2.COLOR_RGB2BGR)

frigate/video.py

@@ -46,21 +46,18 @@ class FrameTracker(threading.Thread):
                 if (now - k) > 2:
                     del self.recent_frames[k]
 
-def get_frame_shape(rtsp_url):
+def get_frame_shape(source):
     # capture a single frame and check the frame shape so the correct array
     # size can be allocated in memory
-    video = cv2.VideoCapture(rtsp_url)
+    video = cv2.VideoCapture(source)
     ret, frame = video.read()
     frame_shape = frame.shape
     video.release()
     return frame_shape
 
-def get_rtsp_url(rtsp_config):
-    if (rtsp_config['password'].startswith('$')):
-        rtsp_config['password'] = os.getenv(rtsp_config['password'][1:])
-    return 'rtsp://{}:{}@{}:{}{}'.format(rtsp_config['user'], 
-        rtsp_config['password'], rtsp_config['host'], rtsp_config['port'],
-        rtsp_config['path'])
+def get_ffmpeg_input(ffmpeg_input):
+    frigate_vars = {k: v for k, v in os.environ.items() if k.startswith('FRIGATE_')}
+    return ffmpeg_input.format(**frigate_vars)
 
 class CameraWatchdog(threading.Thread):
     def __init__(self, camera):
@@ -114,32 +111,22 @@ class CameraCapture(threading.Thread):
                 self.camera.frame_ready.notify_all()
 
 class Camera:
-    def __init__(self, name, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
+    def __init__(self, name, ffmpeg_config, config, prepped_frame_queue, mqtt_client, mqtt_prefix):
         self.name = name
         self.config = config
         self.detected_objects = []
         self.recent_frames = {}
-        self.rtsp_url = get_rtsp_url(self.config['rtsp'])
+
+        self.ffmpeg = config.get('ffmpeg', {})
+        self.ffmpeg_input = get_ffmpeg_input(self.ffmpeg['input'])
+        self.ffmpeg_global_args = self.ffmpeg.get('global_args', ffmpeg_config['global_args'])
+        self.ffmpeg_hwaccel_args = self.ffmpeg.get('hwaccel_args', ffmpeg_config['hwaccel_args'])
+        self.ffmpeg_input_args = self.ffmpeg.get('input_args', ffmpeg_config['input_args'])
+        self.ffmpeg_output_args = self.ffmpeg.get('output_args', ffmpeg_config['output_args'])
+
         self.take_frame = self.config.get('take_frame', 1)
-        self.ffmpeg_log_level = self.config.get('ffmpeg_log_level', 'panic')
-        self.ffmpeg_hwaccel_args = self.config.get('ffmpeg_hwaccel_args', [])
-        self.ffmpeg_input_args = self.config.get('ffmpeg_input_args', [
-            '-avoid_negative_ts', 'make_zero', 
-            '-fflags', 'nobuffer',
-            '-flags', 'low_delay',
-            '-strict', 'experimental',
-            '-fflags', '+genpts+discardcorrupt',
-            '-vsync', 'drop',
-            '-rtsp_transport', 'tcp', 
-            '-stimeout', '5000000', 
-            '-use_wallclock_as_timestamps', '1'
-        ])
-        self.ffmpeg_output_args = self.config.get('ffmpeg_output_args', [
-            '-f', 'rawvideo',
-            '-pix_fmt', 'rgb24'
-        ])
         self.regions = self.config['regions']
-        self.frame_shape = get_frame_shape(self.rtsp_url)
+        self.frame_shape = get_frame_shape(self.ffmpeg_input)
         self.frame_size = self.frame_shape[0] * self.frame_shape[1] * self.frame_shape[2]
         self.mqtt_client = mqtt_client
         self.mqtt_topic_prefix = '{}/{}'.format(mqtt_prefix, self.name)
@@ -225,7 +212,7 @@ class Camera:
             self.ffmpeg_process = None
             self.capture_thread = None
             
-        # create the process to capture frames from the RTSP stream and store in a shared array
+        # create the process to capture frames from the input stream and store in a shared array
         print("Creating a new ffmpeg process...")
         self.start_ffmpeg()
         
@@ -235,15 +222,11 @@ class Camera:
         self.capture_thread.start()
     
     def start_ffmpeg(self):
-        ffmpeg_global_args = [
-            '-hide_banner', '-loglevel', self.ffmpeg_log_level
-        ]
-
         ffmpeg_cmd = (['ffmpeg'] +
-            ffmpeg_global_args +
+            self.ffmpeg_global_args +
             self.ffmpeg_hwaccel_args +
             self.ffmpeg_input_args +
-            ['-i', self.rtsp_url] +
+            ['-i', self.ffmpeg_input] +
             self.ffmpeg_output_args +
             ['pipe:'])
 
@@ -289,6 +272,11 @@ class Camera:
                 # detected person, don't add it to detected objects
                 if region and 'min_person_area' in region and region['min_person_area'] > obj['area']:
                     continue
+                
+                # if the detected person is larger than the
+                # max person area, don't add it to detected objects
+                if region and 'max_person_area' in region and region['max_person_area'] < obj['area']:
+                    continue
             
                 # compute the coordinates of the person and make sure
                 # the location isnt outside the bounds of the image (can happen from rounding)
@@ -313,6 +301,7 @@ class Camera:
         # lock and make a copy of the current frame
         with self.frame_lock:
             frame = self.current_frame.copy()
+            frame_time = self.frame_time.value
 
         # draw the bounding boxes on the screen
         for obj in detected_objects:
@@ -324,6 +313,10 @@ class Camera:
             cv2.rectangle(frame, (region['x_offset'], region['y_offset']), 
                 (region['x_offset']+region['size'], region['y_offset']+region['size']), 
                 color, 2)
+        
+        # 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)
 
         # convert to BGR
         frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)