Abstract
AbstractArtificial Neural Networks can be considered to be one of the greatest inventions because the way they are making the machines intelligent is phenomenal. One of the biggest accomplishments of ANNs is in the field of computer vision as they have given computers the ability to see and distinguish between different types of objects. Although Convolutional Neural Networks, are able to successfully learn robust and high-level feature representations of images, Object Detection still remains one of the most complex domains and highly evolving domains. Every year, scientists come up with a new algorithm that tries to outperform previous ones. Advancement in GPU technology and deep learning has allowed researchers to create models for processing complex images. This paper discusses the difference between the popular object detection models including Fast-RCNN, Faster-RCNN, YOLO, and SSD and compared them on the basis of their performance in detecting objects belonging to the PASCAL VOC 2007 dataset. KeywordsObject detectionRCNNYOLOSSD
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
