A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and powerful programmatic image processing application.
Hi,
I am looking to take a video split it into frames.
Then for each frame, use an object detection model like https://github.com/facebookresearch/detectron2.
The resulting inferences can also be used for things like tracking, auto cropping or stabilization.
For example.
Using the resulting inference I want to crop the original frame so that only the detected bounding box (or some threshold around it) remains. Then combine the cropped images into separate videos for each detected entity.
Hi, I am looking to take a video split it into frames. Then for each frame, use an object detection model like https://github.com/facebookresearch/detectron2. The resulting inferences can also be used for things like tracking, auto cropping or stabilization.
For example. Using the resulting inference I want to crop the original frame so that only the detected bounding box (or some threshold around it) remains. Then combine the cropped images into separate videos for each detected entity.
Is this supported by chaiNNer?