Object detection is a Computer Vision task which requires to find the locations of all objects in a given image and classify the objects.
Deep Neural Networks (DNNs) for object detection are in continuous development and change rapidly, with several different approaches for constructing DNNs that are suitable for the task.
In this project we will first examine several approaches to DNNs for object detection and then build a system that combines several approaches to one large and highly accurate system. How to combine the approaches and build the entire system is an open problem for us to think together. In addition, there is a lot of room creativity and new ideas which can be implemented in the project.
In this project we examine several approaches to DNNs (YOLO, MRCNN, RESNET50) for object detection and then build a system that combines several approaches to one large and highly accurate system.