Mastering OpenCV 4 with Python

Deep learning for object detection

Object detection is a hot topic in deep learning that is suited for identifying and locating multiple relevant objects in a single image. To benchmark object detection algorithms, three databases are commonly used. The first one is the PASCAL Visual Object Classification (PASCAL VOC) dataset (http://host.robots.ox.ac.uk/pascal/VOC/), which consists of 20 categories and 10,000 images for training and validation, containing bounding boxes with objects. ImageNet has released an object detection dataset since 2013, and it is composed of around 500,000 images for training only and 200 categories. Finally, Common Objects in Context (COCO) (http://cocodataset.org/) is a large-scale object detection, segmentation, ...