A comprehensive survey of the R-CNN family for object detection

Oussama Hmidani, El Mehdi Ismaili Alaoui

202273 citationsDOI

Abstract

Object detection using deep learning, one of the most challenging problems in computer vision, seeks to locate instances of objects from a large number of predefined categories in natural images. Given this period of rapid evolution, the main contribution of this paper is to provide a comprehensive survey of the region-based convolutional neural network (R-CNN) family (R-CNN, Fast R-CNN, and Faster R-CNN). In comparison to the R-CNN and Fast R-CNN, simulation results show that the faster R-CNN improves not only accuracy but also detection speed. For robust object detection, it has been found that the Faster R-CNN is particularly suited for this purpose. We conclude with several open issues and challenges that are keys to the design of future work.

Topics & Concepts

Convolutional neural networkComputer scienceArtificial intelligenceObject detectionObject (grammar)Deep learningCellular neural networkPattern recognition (psychology)Cognitive neuroscience of visual object recognitionComputer visionArtificial neural networkAdvanced Neural Network ApplicationsAdversarial Robustness in Machine LearningIndustrial Vision Systems and Defect Detection