Abstract: Computer Vision is an important field that has been revolutionised by the emergence of Deep Learning and Neural Networks. Object Detection is an important subclass of Object Detection that involves image classification and object localization. There are 2 major classes of object detection algorithms - one stage detectors and multi-stage detectors. Multi-stage detectors like Region-based Convolutional Neural Networks (R-CNN), Fast R-CNN and Faster-RCNN first make region proposals and then make separate predictions for each of these regions. Single stage detectors like YOLO (You Only Look Once) require only one single pass through the convolutional network and predict the bounding boxes in one go. Single shot detectors like YOLO perform better when speed is the most important factor, even more so than accuracy. YOLO has applications in real-time systems like autonomous driving, crowd management, etc. The algorithm developed performs object counting in addition to object detection.
Keywords: YOLO, Object Detection, Object Counting, Convolutional Neural Networks.
|
DOI:
10.17148/IJARCCE.2022.11790
