1
$\begingroup$

Suppose you want to detect objects and also track objects and people. Is it better to train a model using a single fisheye camera or using multiple cameras that mimic the view of the fisheye camera?

Also, what can be done to remove objects that are washed out? Like for very small objects, how do you make them more visible? Would multicamera tracking be better in this scenario?

$\endgroup$
1
$\begingroup$

Fisheye camera is always worst. Both convolutional networks object detectors and feature-based object detectors rely on the "isometry" of planar image - lack of strong distortions. Multiple camera have added benefit of several independent sources of information - ensembling. If each camera processed by separate network that may help in verification of objects by voting. With very small objects no simple methods would help. Multiple camera may help a little if all camera output processed together (stacked) as single network input, but don't hold much hope - detecting few pixel objects is very difficult, if possible at all.

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.