基于YOLOv3 改进的行人检测

小陆 马(安徽工业大学，中国)
石林 洪(安徽工业大学，中国)

摘要

针对目前行人检测 anchor 尺寸不匹配和特征尺度不连续的会影响检测精度的问题，提出基于 YOLOv3 改进的行人检测算法。论文使用 Guided anchoring 指导生成 anchors，融入自适应空间特征融合。在路口行人数据集上的测试结果表明，改进后的YOLOv3 行人检测算法 mAP 达到了 95.56%，提高了检测精度。

关键词

YOLOv3；指导锚；自适应空间特征融合；行人检测

参考

Girshick R. Fast r-cnn[C]. Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of the IEEE conference on computer vision and pattern recognition.2014: 580-587.

Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector [C]. European conference on computer vision. Springer,Cham, 2016: 21-37.

Redmon J, Divvala S, Girshick R, et al. You only look once[C].Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

Redmon J, Farhadi A. YOLO9000: better, faster, stronger [J]. arXiv preprint, 2017.

Redmon J, Farhadi A. YOLOv3: An incremental improvement [J]. arXiv:1804.02767, 2018.

Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu,and Yurong Chen. Ron: Reverse connection with objectness prior networks for object detection. In CVPR, 2017.

Songtao Liu Beihang University liusongtao Di Huang Beihang University Yunhong Wang Beihang University Learning Spatial Fusion for Single-Shot Object Detection [J]. arXiv:1911.09516v2.

Research Kilian Q. Weinberger Cornell University CondenseNet: An Efficient DenseNet using Learned Group Convolutions[J].arXiv:1711.09224v2.

Lin Tsungyi, Dollár Piotr, Girshick Ross, et al. Feature pyramid networks for object detection[C]IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2017: 936 － 944.

Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun.Faster r-cnn:Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems, 2015.

Jifeng Dai, Yi Li, Kaiming He, and Jian Sun. R-FCN: Object detection via region-based fully convolutional networks.[J] In

Advances in Neural Information Processing Systems, 2016.

Jiahui Yu, Yuning Jiang, Zhangyang Wang, Zhimin Cao, and Thomas Huang. Unitbox: An advanced object detection network. In ACMM, 2016.

Chenchen Zhu, Yihui He, and Marios Savvides. Feature selective anchor-free module for single-shot object detection. In CVPR,2019.

A 戴 思 达，’ 准 确 率 (Accuracy), 精 确 率 (Precision), 召 回 率(Recall) 和 F1-Measure’ 2016, (accessed 22 July 2016).

L. Perez and J. Wang,The effectiveness of data augmentation in image classification using deep learning,2017, arXiv:1712.04621.

DOI: http://dx.doi.org/10.26549/gcjsygl.v4i3.3662