search

asmirnou / watsor

Object detection for video surveillance
MIT License
252 stars 32 forks source link

Car detection #10

Closed jasonmadigan closed 4 years ago

jasonmadigan commented 4 years ago

First of all, this is great. Had been waiting on frigate to get GPU support for a while now, but seems to be languishing, and I believe you'd contributed it. The docs for this are significantly better, so I've been looking at switching. I have a pretty good working setup with deepstack currently, but would like some of watsor's functionality (in particular, good Home Assistant integration).

I've got some cameras setup, and all seems to be working well. person detection works very well, with low-latency, but for some reason I don't seem to be able to trigger a match for car or truck with stationary or moving vehicles. My config is pretty sparse:

...
# Detect the following labels of the object detection model.
# Optional, can be overwritten per camera.
detect:
  - person:
      confidence: 60
  - car:
  - truck:

# List of cameras and their configurations.
cameras:
  - pumphouse:
      width: 640
      height: 480
      input: rtsp://foo:bar@192.168.1.150:554/Streaming/Channels/2/
...

Any pointers?

jasonmadigan commented 4 years ago

Think I got this sorted, I had to drop the area way down low to something like area: 0.1 before I could see cars which were pretty prominent in frame. Am pointing watsor at a 640x480 substream - thought the default, 10%, would fine. But I guess not.

asmirnou commented 4 years ago

Right, when an object isn't detected, first thought should be about it's filtered out. I doubled checked the math is correct, but let me know, if you see a mistake there.