摘 要：目标检测是计算机视觉领域内的热点研究课题，在医疗、监控及航空等领域都有广泛应用。先对目标检测技术的背景进行了介绍，然后从基于锚框的两阶段目标检测算法、基于锚框的单阶段目标检测算法、基于 Anchor Free 的目标检测算法三个阶段分别进行介绍，同时还介绍了主流的数据集以及主要的性能评价指标。最后叙述了当前目标检测领域存在的挑战，展望了目标检测技术在未来的发展方向。
关键词：深度学习；目标检测；卷积神经网络；计算机视觉
DOI:10.19850/j.cnki.2096-4706.2022.011.020
中图分类号：TP391.4 文献标识码：A 文章编号：2096-4706（2022）11-0076-06
A Review of Object Detection Study Based on Deep Learning
GU Yongli, ZONG Xinxin
(School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China)
Abstract: Object detection is a hot research topic in the field of computer vision, and it is widely used in medical, monitoring and aviation and other fields. Firstly, this paper introduces the background of object detection technology, and then, the three stages of two stage object detection algorithm based on Anchor frame, the single stage object detection algorithm based on anchor frame and the object detection algorithm based on Anchor Free are introduced respectively. Meanwhile, it also introduces mainstream datasets and main performance evaluation indicators. Finally, the current challenges in the field of object detection are presented, and the object detection technology development direction in future is prospected.
Keywords: deep learning; object detection; convolutional neural network; computer vision
参考文献：
[1] GIRSHICK R，DONAHUE J，DARRELL T，et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation [C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus：IEEE，2014：580-587.
[2] HE K M，ZHANG X Y，REN S Q，et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence，2015，37（9）：1904-1916.
[3] GIRSHICK R. Fast R-CNN [C]//2015 IEEE International Conference on Computer Vision.Santiago：IEEE，2015：1440-1448.
[4] REN S Q，HE K M，GIRSHICK R，et al. Faster R-CNN：Towards Real-Time Object Detection with Region Proposal Networks [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence，2017，39（6）：1137-1149.
[5] REDMON J，DIVVALA S，GIRSHICK R，et al. You Only Look Once：Unified, Real-Time Object Detection [C].IEEE Conference on Computer Vision and Pattern Recognition. USA：IEEE，2016：779-778.
[6] REDMON J，FARHADI A. YOLO9000：Better，Faster， Stronger [EB/OL].[2022-03-23].https://arxiv.org/pdf/1612.08242.pdf.
[7] REDMON J，FARHADI A. YOLOV3：An Incremental Improvement [EB/OL].[2022-03-23].https://arxiv.org/pdf/1804.02767.pdf. [8] LIU W，ANGUELOV D，ERHAN D，et al. SSD：Single Shot MultiBox Detector [J/OL].arXiv：1512.02325 [cs.CV].[2022-03-23]. https://arxiv.org/abs/1512.02325.2016：21-37.
[9] LAW H，DENG J. CornerNet：Detecting Objects as Paired Keypoints [EB/OL].[2022-03-23].https://www.doc88.com/p-3032522764056.html.
[10] DUAN K W，BAI S，XIE L X，et al. CenterNet： Keypoint Triplets for Object Detection[J/OL].[2022-03-23].https://blog. csdn.net/qq_41007606/article/details/89536530.
[11] EVERINGHAM M，GOOL L V，WILLIAMS C K L，et al. The Pascal Visual Object Classes （VOC） Challenge [J].International Journal of Computer Vision，2010，88：303-338.
[12] SHETTY S. Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset [EB/OL]. [2022-03-23].https://arxiv.org/ftp/arxiv/papers/1607/1607.03785.pdf.
[13] LIN T Y，MAIRE M，BELONGIE S，et al. Microsoft COCO： Common Objects in Context [EB/OL].[2022-03-23].https://arxiv.org/pdf/1405.0312.pdf.
作者简介：谷永立（2001—），男，汉族，安徽马鞍山人，本科在读，研究方向：图像处理、目标检测等；宗欣欣（1974—），女，汉族，安徽淮南人，讲师，硕士，研究方向：人工智能、嵌入式系统等。