OBJECT DETECTION: YOLO VS FASTER R-CNN
Fiza Joiya, . Ghani Bdulghan, L Tan, T Huangfu, L Wu, W Chen, J Redmon, S Divvala, R Farhadi, S Ren, K He, R Girshick, J Sun, J Du
Abstract
Object detection is one of the unique abilities of computer vision that locates objects within an image or video. The field of Artificial Intelligence is built on Object detection techniques. Object Detection typically leverages machine learning and deep learning to produce meaningful and accurate results. It basically consists of classification and localization. In recent years there has been an advancement in the state-of-the-art algorithms used for real-time object detection. The objective of this research paper is to compare the state-of-the-art algorithms i.e. you only look once (YOLO) and faster region convolutional neural network (Faster R-CNN). These algorithms are representations of deep neural networks i.e. neural networks with many hidden layers. Both these algorithms are compared to check which one is better, although they both stand-out for their own uniqueness, this paper researches on the area that shows which of the either are more efficient to use even though they have the same core i.e. CNN (Convolutional Neural Networks).