Is there something new in the 0.8.3 update for recognition when there is no motion? Until 0.8.2 Frigate was working fine when there was no movement, the bounding box showed detection all the time.
Now with 0.8.3 if the person doesn’t move, after 3 to five seconds the bounding box first turns blue und then disapperes (and the movement sensor goes to off). Did i miss a new config option or does anyone now how to enable the old behaviour?
Thanks Mike
This was purposely changed in 0.8.2 so that detection is not run for stationary objects. See the changelog: https://github.com/blakeblackshear/frigate/releases/tag/v0.8.2
The adverse effect of this change is that object count sensors in HA are not necessarily accurate anymore. Maybe a distinction could be made between objects that have had their detection stopped because they are stationary and objects that actually disappear from the frame?
Why would we want detection of stationary objects? If they moved again, they would be picked up as a new event anyway…
Thanks both. I tried the object mask but it still kept detecting the car over and again. I think motion is being triggered by shadows of the masked area and a lot of artifacts in the stream. I’m going to experiment with some different bitrates to see if that improves the artifacts/corruption.
I guess I’ll just turn off car detection for now, I don’t really need it that bad.
It’s ironic that Mike doesn’t want to stop detecting stationary objects and I do and neither of us are getting the results we want 
Hi all, I’m sure I’m doing something stupid but I can’t figure out what. Anyone have an idea why it doesn’t see my coral when I run with docker compose but it does see it when I run on the command line?
Here’s the log:
* Starting nginx nginx
...done.
Starting migrations
peewee_migrate INFO : Starting migrations
There is nothing to migrate
peewee_migrate INFO : There is nothing to migrate
frigate.mqtt INFO : MQTT connected
frigate.app INFO : Camera processor started for right: 37
frigate.app INFO : Camera processor started for left: 39
frigate.app INFO : Camera processor started for front: 40
frigate.app INFO : Camera processor started for back: 41
frigate.app INFO : Capture process started for right: 42
frigate.app INFO : Capture process started for left: 43
frigate.app INFO : Capture process started for front: 44
frigate.app INFO : Capture process started for back: 45
detector.coral INFO : Starting detection process: 35
frigate.edgetpu INFO : Attempting to load TPU as usb
Process detector:coral:
frigate.edgetpu INFO : No EdgeTPU detected.
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 152, in load_delegate
delegate = Delegate(library, options)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 111, in __init__
raise ValueError(capture.message)
ValueError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/opt/frigate/frigate/edgetpu.py", line 124, in run_detector
object_detector = LocalObjectDetector(tf_device=tf_device, num_threads=num_threads)
File "/opt/frigate/frigate/edgetpu.py", line 63, in __init__
edge_tpu_delegate = load_delegate('libedgetpu.so.1.0', device_config)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 154, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1.0
frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate...
frigate.app INFO : Stopping...
frigate.events INFO : Exiting event cleanup...
frigate.object_processing INFO : Exiting object processor...
frigate.record INFO : Exiting recording maintenance...
frigate.events INFO : Exiting event processor...
frigate.watchdog INFO : Exiting watchdog...
frigate.stats INFO : Exiting watchdog...
peewee.sqliteq INFO : writer received shutdown request, exiting.
root INFO : Waiting for detection process to exit gracefully...
frigate.video INFO : left: exiting subprocess
* Starting nginx nginx
...done.
Starting migrations
peewee_migrate INFO : Starting migrations
There is nothing to migrate
peewee_migrate INFO : There is nothing to migrate
frigate.mqtt INFO : MQTT connected
frigate.app INFO : Camera processor started for right: 35
frigate.app INFO : Camera processor started for left: 36
frigate.app INFO : Camera processor started for front: 37
frigate.app INFO : Camera processor started for back: 38
frigate.app INFO : Capture process started for right: 40
frigate.app INFO : Capture process started for left: 41
frigate.app INFO : Capture process started for front: 42
frigate.app INFO : Capture process started for back: 44
detector.coral INFO : Starting detection process: 33
Process detector:coral:
Traceback (most recent call last):
frigate.edgetpu INFO : Attempting to load TPU as usb
frigate.edgetpu INFO : No EdgeTPU detected.
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 152, in load_delegate
delegate = Delegate(library, options)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 111, in __init__
raise ValueError(capture.message)
ValueError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/opt/frigate/frigate/edgetpu.py", line 124, in run_detector
object_detector = LocalObjectDetector(tf_device=tf_device, num_threads=num_threads)
File "/opt/frigate/frigate/edgetpu.py", line 63, in __init__
edge_tpu_delegate = load_delegate('libedgetpu.so.1.0', device_config)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 154, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1.0
frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate...
frigate.app INFO : Stopping...
frigate.object_processing INFO : Exiting object processor...
frigate.record INFO : Exiting recording maintenance...
frigate.events INFO : Exiting event processor...
frigate.events INFO : Exiting event cleanup...
frigate.watchdog INFO : Exiting watchdog...
frigate.stats INFO : Exiting watchdog...
peewee.sqliteq INFO : writer received shutdown request, exiting.
root INFO : Waiting for detection process to exit gracefully...
watchdog.left INFO : Terminating the existing ffmpeg process...
* Starting nginx nginx
...done.
Starting migrations
peewee_migrate INFO : Starting migrations
There is nothing to migrate
peewee_migrate INFO : There is nothing to migrate
frigate.mqtt INFO : MQTT connected
frigate.app INFO : Camera processor started for right: 36
frigate.app INFO : Camera processor started for left: 38
frigate.app INFO : Camera processor started for front: 40
frigate.app INFO : Camera processor started for back: 41
frigate.app INFO : Capture process started for right: 42
frigate.app INFO : Capture process started for left: 44
frigate.app INFO : Capture process started for front: 48
frigate.app INFO : Capture process started for back: 50
detector.coral INFO : Starting detection process: 34
Process detector:coral:
frigate.edgetpu INFO : Attempting to load TPU as usb
frigate.edgetpu INFO : No EdgeTPU detected.
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 152, in load_delegate
delegate = Delegate(library, options)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 111, in __init__
raise ValueError(capture.message)
ValueError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/opt/frigate/frigate/edgetpu.py", line 124, in run_detector
object_detector = LocalObjectDetector(tf_device=tf_device, num_threads=num_threads)
File "/opt/frigate/frigate/edgetpu.py", line 63, in __init__
edge_tpu_delegate = load_delegate('libedgetpu.so.1.0', device_config)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 154, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1.0
frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate...
frigate.app INFO : Stopping...
frigate.record INFO : Exiting recording maintenance...
frigate.object_processing INFO : Exiting object processor...
frigate.events INFO : Exiting event processor...
frigate.events INFO : Exiting event cleanup...
frigate.watchdog INFO : Exiting watchdog...
frigate.stats INFO : Exiting watchdog...
peewee.sqliteq INFO : writer received shutdown request, exiting.
root INFO : Waiting for detection process to exit gracefully...
frigate.video INFO : back: exiting subprocess
Fatal Python error: Bus error
Thread 0x00007faddde62700 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 302 in wait
File "/usr/lib/python3.8/multiprocessing/queues.py", line 227 in _feed
File "/usr/lib/python3.Fatal Python error: 8Bus error
Thread 0x00007faddde62700 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 302 in wait
File "/usr/lib/python3.8/multiprocessing/queues.py", line 227 in _feed
File "/usr/lib/python3.8/threading.py", line 870 in run
File "/usr/lib/python3.8/threading/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Current thread 0x00007fadde663700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 117 in capture_frames
File "/opt/frigate/frigate/video.py", line 231 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007faddee64700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 205 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadcc994700 (most recent call first):
File "/opt/frigate/friga.py", line 870 in run
File "/usr/tle/log.py", line 71 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadeb057740 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 1027 in _wait_for_tstate_lock
File "/usr/lib/python3.8/threading.py", line 1011 in join
File "/opt/frigate/frigate/video.py", line 245 in capture_camera
File "/usr/lib/python3.8/multiprocessing/process.py", line 108 in run
File "/usr/lib/python3.8/multiprocessing/process.py", line 315 in _bootstrap
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 75 in _launch
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 19 in __init__
File "/usr/lib/python3.8/multiprocessing/context.py", line 277 in _Popen
File "/usr/lib/python3.8/multiprocessing/context.py", line 224 in _Popen
File "/usr/lib/python3.8/multiprocessing/process.py", line 121 in start
File "/opt/frigate/frigate/app.py", line 182 in start_camera_capture_processes
File "/opt/frigate/frigate/app.py", line 228 in start
File "/opt/frigate/frigate/__main__.py", line 15 in <module>
File "/usr/lib/python3.8/runpy.py", line 87 in _run_code
File "/usr/lib/python3.8/runpy.py", line 194 in _run_module_as_main
ib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Current thread 0x00007fadde663700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 117 in capture_frames
File "/opt/frigate/frigate/video.py", line 231 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007faddee64700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 205 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadcc994700 (most recent call first):
File "/opt/frigate/frigate/log.py", line 71 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadeb057740 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 1027 in _wait_for_tstate_lock
File "/usr/lib/python3.8/threading.py", line 1011 in join
File "/opt/frigate/frigate/video.py", line 245 in capture_camera
File "/usr/lib/python3.8/multiprocessing/process.py", line 108 in run
File "/usr/lib/python3.8/multiprocessing/process.py", line 315 in _bootstrap
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 75 in _launch
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 19 in __init__
File "/usr/lib/python3.8/multiprocessing/context.py", line 277 in _Popen
File "/usr/lib/python3.8/multiprocessing/context.py", line 224 in _Popen
File "/usr/lib/python3.8/multiprocessing/process.py", line 121 in start
File "/opt/frigate/frigate/app.py", line 182 in start_camera_capture_processes
File "/opt/frigate/frigate/app.py", line 228 in start
File "/opt/frigate/frigate/__main__.py", line 15 in <module>
File "Fatal Python error: Bus error
Thread 0x00007faddde62700 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 302 in wait
File "/usr/lib/python3.8/multiprocessing/queues.py", line 227 in _feed
File "/usr/lib/python3.8/threading.py", line 870 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Current thread 0x00007fadde663700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 117 in capture_frames
File "/opt/frigate/frigate/video.py", line 231 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007faddee64700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 205 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadcc994700 (most recent call first):
File "/opt/frigate/frigate/log.py", line 71 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadeb057740 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 1027 in _wait_for_tstate_lock
File "/usr/lib/python3.8/threading.py", line 1011 in join
File "/opt/frigate/frigate/video.py", line 245 in capture_camera
File "/usr/lib/python3.8/multiprocessing/process.py", line 108 in run
File "/usr/lib/python3.8/multiprocessing/process.py", line 315 in _bootstrap
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 75 in _launch
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 19 in __init__
File "/usr/lib/python3.8/multiprocessing/context.py", line 277 in _Popen
File "/usr/lib/python3.8/multiprocessing/context.py", line 224 in _Popen
File "/usr/lib/python3.8/multiprocessing/process.py", line 121 in start
File "/opt/frigate/frigate/app.py", line 182 in start_camera_capture_processes
File "/opt/frigate/frigate/app.py", line 228 in start
File "/opt/frigate/frigate/__main__.py", line 15 in <module>
File "/usr/lib/python3.8/runpy.py", line 87 in _run_code
File "/usr/lib/python3.8/runpy.py", line 194 in _run_module_as_main
/usr/lib/python3.8/runpy.py", line 87 in _run_code
File "/usr/lib/python3.8/runpy.py", line 194 in _run_module_as_main
Fatal Python error: Bus error
Thread 0x00007faddde62700 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 302 in wait
File "/usr/lib/python3.8/multiprocessing/queues.py", line 227 in _feed
File "/usr/lib/python3.8/threading.py", line 870 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Current thread 0x00007fadde663700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 117 in capture_frames
File "/opt/frigate/frigate/video.py", line 231 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007faddee64700 (most recent call first):
File "/opt/frigate/frigate/video.py", line 205 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadcc994700 (most recent call first):
File "/opt/frigate/frigate/log.py", line 71 in run
File "/usr/lib/python3.8/threading.py", line 932 in _bootstrap_inner
File "/usr/lib/python3.8/threading.py", line 890 in _bootstrap
Thread 0x00007fadeb057740 (most recent call first):
File "/usr/lib/python3.8/threading.py", line 1027 in _wait_for_tstate_lock
File "/usr/lib/python3.8/threading.py", line 1011 in join
File "/opt/frigate/frigate/video.py", line 245 in capture_camera
File "/usr/lib/python3.8/multiprocessing/process.py", line 108 in run
File "/usr/lib/python3.8/multiprocessing/process.py", line 315 in _bootstrap
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 75 in _launch
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 19 in __init__
File "/usr/lib/python3.8/multiprocessing/context.py", line 277 in _Popen
File "/usr/lib/python3.8/multiprocessing/context.py", line 224 in _Popen
File "/usr/lib/python3.8/multiprocessing/process.py", line 121 in start
File "/opt/frigate/frigate/app.py", line 182 in start_camera_capture_processes
File "/opt/frigate/frigate/app.py", line 228 in start
File "/opt/frigate/frigate/__main__.py", line 15 in <module>
File "/usr/lib/python3.8/runpy.py", line 87 in _run_code
File "/usr/lib/python3.8/runpy.py", line 194 in _run_module_as_main
* Starting nginx nginx
...done.
Starting migrations
peewee_migrate INFO : Starting migrations
There is nothing to migrate
peewee_migrate INFO : There is nothing to migrate
frigate.mqtt INFO : MQTT connected
frigate.app INFO : Camera processor started for right: 35
frigate.app INFO : Camera processor started for left: 37
frigate.app INFO : Camera processor started for front: 38
frigate.app INFO : Camera processor started for back: 40
frigate.app INFO : Capture process started for right: 41
frigate.app INFO : Capture process started for left: 43
frigate.app INFO : Capture process started for front: 44
frigate.app INFO : Capture process started for back: 45
detector.coral INFO : Starting detection process: 33
Process detector:coral:
frigate.edgetpu INFO : Attempting to load TPU as usb
frigate.edgetpu INFO : No EdgeTPU detected.
Traceback (most recent call last):
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 152, in load_delegate
delegate = Delegate(library, options)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 111, in __init__
raise ValueError(capture.message)
ValueError
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/opt/frigate/frigate/edgetpu.py", line 124, in run_detector
object_detector = LocalObjectDetector(tf_device=tf_device, num_threads=num_threads)
File "/opt/frigate/frigate/edgetpu.py", line 63, in __init__
edge_tpu_delegate = load_delegate('libedgetpu.so.1.0', device_config)
File "/usr/local/lib/python3.8/dist-packages/tflite_runtime/interpreter.py", line 154, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1.0
frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate...
frigate.app INFO : Stopping...
frigate.object_processing INFO : Exiting object processor...
frigate.record INFO : Exiting recording maintenance...
frigate.events INFO : Exiting event processor...
frigate.events INFO : Exiting event cleanup...
frigate.watchdog INFO : Exiting watchdog...
frigate.stats INFO : Exiting watchdog...
peewee.sqliteq INFO : writer received shutdown request, exiting.
root INFO : Waiting for detection process to exit gracefully...
frigate.video INFO : back: exiting subprocess
Fatal Python error: Bus error
here’s my docker compose which gives me the above log
version: '3.9'
services:
frigate:
container_name: frigate
privileged: true
restart: unless-stopped
image: blakeblackshear/frigate:0.8.3-amd64
devices:
- /dev/bus/usb:/dev/bus/usb
- /dev/dri/renderD128
volumes:
- /etc/localtime:/etc/localtime:ro
- ${ROOT}/config:/config:ro
- ${ROOT}/storage:/storage
- ${VIDEO}/clips:/media/frigate/clips
- ${VIDEO}/recordings:/media/frigate/recordings
- type: tmpfs
target: /tmp/cache
tmpfs:
size: 1000000000
ports:
- '4000:5000'
- '1935:1935'
environment:
- FRIGATE_MQTT_PASSWORD=${MQTT_PASSWORD}
- FRIGATE_RTSP_PASSWORD=${RTSP_PASSWORD}
- FRIGATE_RTSP_PASSWORD_RIGHT=${FRIGATE_RTSP_PASSWORD_RIGHT}
- FRIGATE_RTSP_PASSWORD_LEFT=${FRIGATE_RTSP_PASSWORD_LEFT}
- FRIGATE_RTSP_PASSWORD_FRONT=${FRIGATE_RTSP_PASSWORD_FRONT}
- FRIGATE_RTSP_PASSWORD_BACK=${FRIGATE_RTSP_PASSWORD_BACK}
whereas the following command works fine:
docker run --rm --name frigate_command --privileged --shm-size=1g --mount type=tmpfs,target=/tmp/cache,tmpfs-size=1000000000 -v /dev/bus/usb:/dev/bus/usb -v /volume1/docker/frigate/config:/config:ro -v /etc/localtime:/etc/localtime:ro -v /volume1/docker/frigate/storage:/storage -v /volume1/video/frigate/clips:/media/frigate/clips -v /volume1/video/frigate/recordings:/media/frigate/recordings -p 4000:5000 -p 1935:1935 -e FRIGATE_MQTT_PASSWORD='PW' -e FRIGATE_RTSP_PASSWORD='PW' -e FRIGATE_RTSP_PASSWORD_RIGHT='PW' -e FRIGATE_RTSP_PASSWORD_LEFT='PW' -e FRIGATE_RTSP_PASSWORD_FRONT='PW' -e FRIGATE_RTSP_PASSWORD_BACK='PW'blakeblackshear/frigate:0.8.3-amd64 &
That doesn’t sound right. If you covered up your car entirely with an object mask and set it to the object of car, then you should not be getting the car detected at all in the mask. Are you sure its the car being detected? Enable snapshots and turn on bounding boxes in the config so you can see what exactly Frigate is locking on to if you haven’t done that already.
Post your config. That is the file that tells Frigate to use the Coral device. You need something like this in it if using the M.2 PCI-e Coral device like I have:
detectors:
coral_pci:
type: edgetpu
device: pci
I had issues with something very similar and blake told me to make sure the bottom center of the bounding box was inside the mask. So I made the mask larger than I thought it needed to and I haven’t had a vehicle parked in that location show up since.
@ hawkeye217
Thank you for the explanation. A distinction would be a solution for my problem, can you give me a hint how to do this?
@biggen1684
I am using Frigate for presence detection in 2 rooms. I have PIR sensors, but when there is not much movement they do not trigger. Thats why i have a cam in the room and use frigate to detect if a person is in the room. Even when there is no movement (eg sitting in front of the pc and reading a text without moving much) it should detect somebody is there. With the new update the lights turn off after a certain time because no movement and thereforce no person ist detectet (even a person is still in the room).
Any other hint how to solve this problem?
Thanks Mike
To get longer history of recordings I have an idea to move recordins folder from HA host to the NFS mount of Synology NAS, where I have large storage. Technically there’s no problem to mount whole recordings folder, but may be it’s a better for stability to keep live files in the root of recordings folder in local HA. With current setup I don’t see any way to separate those files from folder mount. Threre is what I mean:
artlov@akoxcy:~$ ls -lh frigate/recordings/
drwxr-xr-x 7 root root 4.0K Feb 23 00:02 2021-02
-rw-r--r-- 1 root root 38M Feb 23 09:54 hik1-20210223095339.mp4
-rw-r--r-- 1 root root 34M Feb 23 09:54 hik2-20210223095339.mp4
Or am I worrying unnecessarily?
Sorry, I think you’ve misunderstood. The motion mask I set, as well as the object mask now, covers the black area to the top of the car which is the street. That area I’m not interested in. I was interested in the drive area where the grey car is parked, and indeed the grey car. I wanted notifications when it moved only. However, it seems I was getting notifications that it was detected every time something triggered motion (I think).
I thought you had covered the car with the object mask as well.
Is there any reason you need to detect a car in the driveway? Why not just detect person? The car can’t drive itself so if someone drives in/out of the driveway, you would detect them as a person object anyway as they enter/exit the vehicle.
Hmm… Perhaps you can play with the the global motion settings or object filters to make Frigate more sensitive so it can pick up on the smaller movements of people sitting at a desk.
Another option would be to run the detect stream at a higher resolution. That way you would pick up on smaller movements (e.g. face scratching, head movement, etc…).
You can always downgrade to the last previous working version until you get it sorted out too.
I’ve re-enabled car detection this morning and had a look at some of the snapshots. I have a few with corruption artefacts so I think this is causing motion to be detected. So I removed all the cameras except this one and my false positives have disappeared. Apart from when another object is detected like a person, then it triggers car again.
It would be nice if we had some way of avoiding this re-detection if the object hasn’t moved. That would also make the object count sensor relevant again.
My other issue is why I’m getting artefacts with all cameras enabled. Am I pushing the RPi4 gigabit ethernet bandwidth to it’s limits? The CPU is sitting around 60%.
These are the streams I have:
1 x Reolink RLC-520:
Detect: 640x480, 7fps, Max bitrate 256kbps (5 fps in frigate)
clips: 2048x1536 30fps 6144kbps max bitrate.
Video Codec: H264 - MPEG-4 AVC (part 10) (h264)
Audio Codec: MPEG AAC Audio (mp4a) 32khz
3 x TPLINK Tapo C200 all working at 1920x1080 5fps in frigate.
Detect: 640x360 15fps
Clips: 1920x1080 15fps
Codec: H264 - MPEG-4 AVC (part 10) (h264)
Audio Codec: PCM ALAW (alaw) Mono 8khz
2 x Neos (wyze clone) running dafang firmware:
clips/detect: 1280x720 15fps 1000kbps (5fps in frigate).
Video Codec: H264 - MPEG-4 AVC (part 10) (h264)
Audio: none
The RPi and the Reolink which I’m having problems with are hard wired to the same gigabit switch and my router is gigabit too.
Yes, that did occur to me. Primarily I wanted to detect the car so I knew who’s car was on there. For example if I’m driving home and need to unload something and my partner gets back before me I could get a notification and ask them to move it onto the street. Of course I could just get a bigger drive or ask them myself… But isn’t that what home automation is for? So we can ignore our SO 
Also I thought it might help with coming home automations as a trigger to check our location as this can be a bit slow to update with the companion app. I’m not even sure if this is possible to force an update to the app from HA but hey.
And lastly as a failsafe in case we left the hand brake off or the person detection failed.
In any case, why ask why, it should be why not? 
Try adding cameras one by one and test for a day with one camera at a time. If no artifacts with no single cameras, add two cameras, run for a day and see how it looks. Repeat with 3 etc… I run Frigate on a dedicated NUC so I can’t speak for how a RPi will handle multiple cameras.
It may be worth a feature request. PIR seems to be a constant problem people are trying to solve and the one that seems to be the most capable is something like this. I’ve seen recent posts in the various HA communities where people solve this problem with tools similar to frigate.
I say this since it worked like you desired until just recently. There are valid use cases for both ways.
I wonder if just dumb old motion detection via another program would be more appropriate for that since you can easily set it for extreme sensitivity.
is anyone else getting a log file filling up with errors since the last update ?
[homeassistant.components.rest.sensor] REST result could not be parsed as JSON
Getting literally hundreds and hundreds of these and not sure where they started
The change log for version 0.8 says to replace your rest sensors with the new integration. I assume it must have broke the rest sensor functionality somehow.