I have an aerial image containing planes like this:
I want to detect planes in the image (find bounding boxes around planes). For this user draws a bounding box on one of the planes and the algorithm finds rest of the planes. I think approaches like "Training-free, generic object detection using locally adaptive regression kernels" can be used for this purpose. But i could not find any paper using recent advances in computer vision. Is there any deep learning (CNN) based method to achieve this? / Are DNNs suitable for this kind of problems?
I used search queries including Template/patch matching, single query based object detection but got no results.
Can someone recommend papers using dl to detect same class of objects in an image given single instance of the object from the image?