update docs and add back benchmark

Dockerfile

@@ -55,5 +55,6 @@ RUN wget -q https://storage.googleapis.com/download.tensorflow.org/models/tflite
 WORKDIR /opt/frigate/
 ADD frigate frigate/
 COPY detect_objects.py .
+COPY benchmark.py .
 
 CMD ["python3.7", "-u", "detect_objects.py"]

README.md

@@ -1,14 +1,13 @@
 # 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 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
-- No motion detection (for now)
-- Object detection with Tensorflow runs in a separate thread
+Use of a [Google Coral USB Accelerator](https://coral.withgoogle.com/products/accelerator/) is optional, but highly recommended. On my Intel i7 processor, I can process 2-3 FPS with the CPU. The Coral can process 100+ FPS with very low CPU load.
+
+- Leverages multiprocessing heavily with an emphasis on realtime over processing every frame
+- Uses a very low overhead motion detection to determine where to run object detection
+- Object detection with Tensorflow runs in a separate process
 - Object info is published over MQTT for integration into HomeAssistant as a binary sensor
-- An endpoint is available to view an MJPEG stream for debugging
+- An endpoint is available to view an MJPEG stream for debugging, but should not be used continuously
 
 ![Diagram](diagram.png)
 
@@ -22,12 +21,16 @@ Build the container with
 docker build -t frigate .
 ```
 
-The `mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite` model is included and used by default. You can use your own model and labels by mounting files in the container at `/frozen_inference_graph.pb` and `/label_map.pbtext`. Models must be compatible with the Coral according to [this](https://coral.withgoogle.com/models/).
+Models for both CPU and EdgeTPU (Coral) are bundled in the image. You can use your own models with volume mounts:
+- CPU Model: `/cpu_model.tflite`
+- EdgeTPU Model: `/edgetpu_model.tflite`
+- Labels: `/labelmap.txt`
 
 Run the container with
-```
+```bash
 docker run --rm \
 --privileged \
+--shm-size=512m \ # should work for a 2-3 cameras
 -v /dev/bus/usb:/dev/bus/usb \
 -v <path_to_config_dir>:/config:ro \
 -v /etc/localtime:/etc/localtime:ro \
@@ -37,11 +40,12 @@ frigate:latest
 ```
 
 Example docker-compose:
-```
+```yaml
   frigate:
     container_name: frigate
     restart: unless-stopped
     privileged: true
+    shm_size: '1g' # should work for 5-7 cameras
     image: frigate:latest
     volumes:
       - /dev/bus/usb:/dev/bus/usb
@@ -57,6 +61,8 @@ A `config.yml` file must exist in the `config` directory. See example [here](con
 
 Access the mjpeg stream at `http://localhost:5000/<camera_name>` and the best snapshot for any object type with at `http://localhost:5000/<camera_name>/<object_name>/best.jpg`
 
+Debug info is available at `http://localhost:5000/debug/stats`
+
 ## Integration with HomeAssistant
 ```
 camera:
@@ -93,30 +99,34 @@ automation:
             photo:
               - url: http://<ip>:5000/<camera_name>/person/best.jpg
                 caption: A person was detected.
+
+sensor:
+  - platform: rest
+    name: Frigate Debug
+    resource: http://localhost:5000/debug/stats
+    scan_interval: 5
+    json_attributes:
+      - back
+      - coral
+    value_template: 'OK'  
+  - platform: template
+    sensors:
+      back_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["back"]["fps"] }}'
+        unit_of_measurement: 'FPS'
+      back_skipped_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["back"]["skipped_fps"] }}'
+        unit_of_measurement: 'FPS'
+      back_detection_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["back"]["detection_fps"] }}'
+        unit_of_measurement: 'FPS'
+      frigate_coral_fps: 
+        value_template: '{{ states.sensor.frigate_debug.attributes["coral"]["fps"] }}'
+        unit_of_measurement: 'FPS'
+      frigate_coral_inference:
+        value_template: '{{ states.sensor.frigate_debug.attributes["coral"]["inference_speed"] }}' 
+        unit_of_measurement: 'ms'
 ```
 
 ## Tips
 - 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
-- [x] Try running object detection in a thread rather than a process
-- [x] Implement min person size again
-- [x] Switch to a config file
-- [x] Handle multiple cameras in the same container
-- [ ] Attempt to figure out coral symlinking
-- [ ] Add object list to config with min scores for mqtt
-- [ ] Move mjpeg encoding to a separate process
-- [ ] Simplify motion detection (check entire image against mask, resize instead of gaussian blur)
-- [ ] See if motion detection is even worth running
-- [ ] Scan for people across entire image rather than specfic regions
-- [ ] Dynamically resize detection area and follow people
-- [ ] Add ability to turn detection on and off via MQTT
-- [ ] Output movie clips of people for notifications, etc.
-- [ ] Integrate with homeassistant push camera
-- [ ] Merge bounding boxes that span multiple regions
-- [ ] Implement mode to save labeled objects for training
-- [ ] Try and reduce CPU usage by simplifying the tensorflow model to just include the objects we care about
-- [ ] Look into GPU accelerated decoding of RTSP stream
-- [ ] Send video over a socket and use JSMPEG
-- [x] Look into neural compute stick

benchmark.py

@@ -1,20 +1,18 @@
 import statistics
 import numpy as np
-from edgetpu.detection.engine import DetectionEngine
+import time
+from frigate.edgetpu import ObjectDetector
 
-# Path to frozen detection graph. This is the actual model that is used for the object detection.
-PATH_TO_CKPT = '/frozen_inference_graph.pb'
-
-# Load the edgetpu engine and labels
-engine = DetectionEngine(PATH_TO_CKPT)
+object_detector = ObjectDetector()
 
 frame = np.zeros((300,300,3), np.uint8)
-flattened_frame = np.expand_dims(frame, axis=0).flatten()
+input_frame = np.expand_dims(frame, axis=0)
 
 detection_times = []
 
-for x in range(0, 1000):
-    objects = engine.detect_with_input_tensor(flattened_frame, threshold=0.1, top_k=3)
-    detection_times.append(engine.get_inference_time())
+for x in range(0, 100):
+    start = time.monotonic()
+    object_detector.detect_raw(input_frame)
+    detection_times.append(time.monotonic()-start)
 
-print("Average inference time: " + str(statistics.mean(detection_times)))
+print(f"Average inference time: {statistics.mean(detection_times)*1000:.2f}ms")

config/config.example.yml

@@ -39,8 +39,6 @@ mqtt:
 #     - -use_wallclock_as_timestamps
 #     - '1'
 #   output_args:
-#     - -vf
-#     - mpdecimate
 #     - -f
 #     - rawvideo
 #     - -pix_fmt
@@ -89,12 +87,15 @@ cameras:
     # width: 720
 
     ################
-    ## Optional mask. Must be the same dimensions as your video feed.
+    ## Optional mask. Must be the same aspect ratio 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.
+    ## 
+    ## Masked areas are also ignored for motion detection.
     ################
     # mask: back-mask.bmp
 
@@ -106,13 +107,14 @@ cameras:
     take_frame: 1
 
     ################
-    # The number of seconds frigate will allow a camera to go without sending a frame before
-    # assuming the ffmpeg process has a problem and restarting.
+    # The expected framerate for the camera. Frigate will try and ensure it maintains this framerate
+    # by dropping frames as necessary. Setting this lower than the actual framerate will allow frigate
+    # to process every frame at the expense of realtime processing.
     ################
-    # watchdog_timeout: 300
+    fps: 5
 
     ################
-    # Configuration for the snapshot sent over mqtt
+    # Configuration for the snapshots in the debug view and mqtt
     ################
     snapshots:
       show_timestamp: True
@@ -128,21 +130,3 @@ cameras:
           min_area: 5000
           max_area: 100000
           threshold: 0.5
-    
-    ################
-    # 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)
-    # 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
-      - size: 400
-        x_offset: 350
-        y_offset: 250
-      - size: 400
-        x_offset: 750
-        y_offset: 250

frigate/video.py

@@ -350,38 +350,3 @@ def track_camera(name, config, ffmpeg_global_config, global_objects_config, dete
         plasma_client.put(frame, plasma.ObjectID(object_id))
         # add to the queue
         detected_objects_queue.put((name, frame_time, object_tracker.tracked_objects))
-
-        # if (frames >= 700 and frames <= 1635) or (frames >= 2500):
-        # if (frames >= 300 and frames <= 600):
-        # if (frames >= 0):
-            # row1 = cv2.hconcat([gray, cv2.convertScaleAbs(avg_frame)])
-            # row2 = cv2.hconcat([frameDelta, thresh])
-            # cv2.imwrite(f"/lab/debug/output/{frames}.jpg", cv2.vconcat([row1, row2]))
-            # # cv2.imwrite(f"/lab/debug/output/resized-frame-{frames}.jpg", resized_frame)
-            # for region in motion_regions:
-            #     cv2.rectangle(frame, (region[0], region[1]), (region[2], region[3]), (255,128,0), 2)
-            # for region in object_regions:
-            #     cv2.rectangle(frame, (region[0], region[1]), (region[2], region[3]), (0,128,255), 2)
-            # for region in merged_regions:
-            #     cv2.rectangle(frame, (region[0], region[1]), (region[2], region[3]), (0,255,0), 2)
-            # for box in motion_boxes:
-            #     cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (255,0,0), 2)
-            # for detection in detections:
-            #     box = detection[2]
-            #     draw_box_with_label(frame, box[0], box[1], box[2], box[3], detection[0], f"{detection[1]*100}%")
-            # for obj in object_tracker.tracked_objects.values():
-            #     box = obj['box']
-            #     draw_box_with_label(frame, box[0], box[1], box[2], box[3], obj['label'], obj['id'], thickness=1, color=(0,0,255), position='bl')
-            # cv2.putText(frame, str(total_detections), (10, 10), cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.5, color=(0, 0, 0), thickness=2)
-            # cv2.putText(frame, str(frame_detections), (10, 30), cv2.FONT_HERSHEY_SIMPLEX, fontScale=0.5, color=(0, 0, 0), thickness=2)
-            # cv2.imwrite(f"/lab/debug/output/frame-{frames}.jpg", frame)
-            # break
-
-    # start a thread to publish object scores
-    # mqtt_publisher = MqttObjectPublisher(self.mqtt_client, self.mqtt_topic_prefix, self)
-    # mqtt_publisher.start()
-
-    # create a watchdog thread for capture process
-    # self.watchdog = CameraWatchdog(self)
-
-