半导体光电, 2020, 41 (1): 1, 网络出版: 2020-04-13
基于深度学习的目标检测技术的研究综述
Research Progresses of Target Detection Technology Based on Deep Learning
摘要
深度学习已经成为机器视觉领域应用最为广泛的技术方法, 基于深度学习的目标检测技术是当前的一项热门研究课题。文章首先对国内外目标检测技术的最新研究进展进行了梳理, 并分析和总结了传统目标检测方法的优缺点; 然后详细介绍了几种基于深度学习的目标检测技术及其优缺点; 最后讨论了现阶段深度学习存在的问题和未来的发展方向。
Abstract
Deep learning has become the most widely used technical method in the field of computer vision. Target detection technology based on deep learning is a hot research topic. In this paper, the latest research progress of target detection technology at home and abroad are reviewed, then the advantages and disadvantages of traditional target detection methods are analyzed and summarized. Then, several target detection techniques based on deep learning and their merits and demerits are introduced. Finally, the existing problems of deep learning and the development trends are discussed.
罗元, 王薄宇, 陈旭. 基于深度学习的目标检测技术的研究综述[J]. 半导体光电, 2020, 41(1): 1. LUO Yuan, WANG Boyu, CHEN Xu. Research Progresses of Target Detection Technology Based on Deep Learning[J]. Semiconductor Optoelectronics, 2020, 41(1): 1.