Last year, we did a Test on IP Camera Latency that generated a lot of interest.
Over the weekend, we spotted a new Axis whitepaper on latency.
Here are some of the key points / metrics in the paper:
- "The time it takes for this process in the camera is under 50 ms... Roughly speaking, each frame takes a time gap of 1 / 30s exposure. It then requires a millisecond (ms) to scale and encode the image. The encoded image is then chopped up and packaged for the network. Finally, an image is outputted onto the network every 33 ms."
- "The receiving buffer in the client is the part that affects the latency the most, even up to several seconds. With a big buffer the chance of jerky video stream is reduced; video will be able to play evenly. However, that comes with a cost of added latency."
- "The display device’s refresh frequency also plays an important role. For TV the refresh rate could be up to 1 sec. For computer monitor frames the refresh rate is around 14-15 ms, whereas special gaming monitors have a refresh rate of 4-5 ms."
- Axis made a few general points about decoding time / latency but no specific quantified claims.
- TCP vs UDP: Axis says TCP takes longer to transport than UDP but does not quantify. We suspect relative to other delays induced (camera processing, display, etc.), this is not significant.
Axis recommends testing latency just like we did in our test report. Here is one of the videos from our test that shows how it is done: