I’m a student currently trying to create a DL model that is able to identify a fox in an image. The initial plan was to have a robot detect a fox and chase it. As a starting point, i’d want to just have a DL model that actually is able to identify a fox!

The biggest problem at the moment is gathering training data, does anyone have any advice where or how I can get many pictures of foxes to use for training? Would using videos and splitting it down into frames work? I initially wanted to use night vision footage as the device would work at night, is there any way to convert normal pictures to nightvision?

Any advice would be appreciated, thanks 🙂