Since you do not have dual NIC going, that means ALL traffic is going through your router. And then the issue is compounded by not using the substreams...
Wifi routers are problematic for surveillance cameras because they are always streaming and passing data. And the data demands go up with motion and then you lose signal. A lost packet and it has to resend. It can bring the whole network down if trying to send cameras through a wifi router. At the very least it can slow down your system.
Unlike Netflix and other streaming services that buffer a movie, these cameras do not buffer up part of the video, so drop outs are frequent. You would be amazed how much streaming services buffer - don't believe me, start watching something and unplug your router and watch how much longer you can watch NetFlix before it freezes - mine goes 45 seconds. Now do the same with a wifi camera and it is fairly instantaneous (within the latency of the stream itself)...
The same issue applies even with the hard-wired cameras trying to send all this non-buffer video stream through a router. Most consumer grade wifi routers are not designed to pass the constant video stream data of cameras, and since they do not buffer, you get these issues. The consumer routers are just not designed for this kind of traffic even a GB speed router.
Regarding your cancelled event above, keep in mind that the "Analyze with Deepstack" under "Testing & Tuning" will
ALWAYS perform better than live as it is after the fact and should not be used as an analysis tool to try to figure out why it didn't see a car or person. It should only be used to see what DeepStack can find in that clip, like "hmm I wonder if DeepStack can find a toothbrush" and then walk around with a toothbrush and have it identify it. I can run this on a camera not using Deepstack and it will show EVERYTHING that Deepstack has in its objects to find that it sees in the clip.
Your image above tells you absolutely nothing other than that DeepStack can identify it is a person IF you have your settings correct...
You need to use the .DAT file analysis that shows how DeepStack responded and behaved live. You have to select it under AI for the camera to check the Deepstack analysis option. Only then can you start to figure out why it missed these events. It is an error in your settings or setup.
So if you are not using the "Save Deepstack Analysis details", check that box so that you can then use the .DAT file to actually see why BI is missing it. Otherwise all you are doing is chasing and looking at the wrong data to try to figure that part out.
But as
@icpilot said, the first step is and should be to figure out why YOUR system isn't sending all of the ONVIF triggers. If it is missing doing that, then it will cause other problems down the line in the processing for that camera.