On May 13, 2016, at 1:55 AM, Calin Crisan couk unfortunately I'm afraid that's the best you can get with motionEyeOS. I really want to be able to use MotionEyeOS for this, but it won't recognize the Foscams for some reason. I intend to offload the camera data from the Pi to a USB attached hard drive. So would it not be a good idea to use a RPi 3 as a hub for 3x Foscam IP cameras? They are capable of 720p video. Would be great if something like this could be integrated into motioneyeos. Maybe I will pick it up again and put some prototype on github. Unfortunately, I did not have a lot of time to continue with the project as I finished my PhD last year. So it is definitely possible to use the raspberry pi for motion detection at high resolutions (without having only 2 or 3 fps). I don't remember the exact numbers, but by bypassing the encoding of the video the raspberry pi 3 could easily handle at least two Full HD cameras 25 fps. The major advantage is that this approach is super fast. Second, my approach was only able to handle h264 streams (which was not a problem for me as my camera was a h264 stream). First, no information can be added to the video, as only the incoming stream is stored (e.g., no frame can be drawn around a detected moving object). There are two main disadvantages with my approach. By doing this, the encoding (4.) could be skipped completely. As soon as a motion was detected in step 3, I multiplexed the frames from the ring buffer to an mp4 video.
Instead of encoding the video, I stored the incoming h264 frames in a ring buffer (2. Last year, I started prototyping my own motion detection software. The computationally expensive part is the encoding of the video, which in my opinion is completely unnecessary. If motion is detected, encode raw images to video stream (raw images -> h264).Decode video stream (h264 to raw images).Demultiplex incoming camera stream (e.g., mp4 to h264).Typical motion detection software works like this: I think the general problem is not that the raspberry is too slow, but the way videos are handled is extremly inefficient.
0 kommentar(er)
