[1]齐鹏宇,王洪元,张继,等.基于改进FCOS的拥挤行人检测算法[J].智能系统学报,2021,16(4):811-818.[doi:10.11992/tis.202010012]
QI Pengyu,WANG Hongyuan,ZHANG Ji,et al.Crowded pedestrian detection algorithm based on improved FCOS[J].CAAI Transactions on Intelligent Systems,2021,16(4):811-818.[doi:10.11992/tis.202010012]
点击复制
QI Pengyu,WANG Hongyuan,ZHANG Ji,et al.Crowded pedestrian detection algorithm based on improved FCOS[J].CAAI Transactions on Intelligent Systems,2021,16(4):811-818.[doi:10.11992/tis.202010012]
基于改进FCOS的拥挤行人检测算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第4期
页码:
811-818
栏目:
吴文俊人工智能科学技术奖论坛
出版日期:
2021-07-05
- Title:
- Crowded pedestrian detection algorithm based on improved FCOS
- Keywords:
- pedestrian detection; multi-scale detection; fully convolutional one-stage object detection; crowded pedestrian scene; training strategy; small object detection; scale regression; pixel by pixel prediction
- 分类号:
- TP391.41
- 摘要:
- 针对大规模拥挤场景视频中行人目标小、行人遮挡和行人交叠而导致的检测困难等问题，本文将逐像素预测目标检测框架—全卷积单阶段目标检测FCOS（fully convolutional one-stage object detection）应用于行人检测，提出一种改进的主干网络用于提取行人特征，通过增加尺度回归实现目标行人的多尺度检测，同时减少其他特征层检测的目标数量，进而提升行人检测的能力。在拥挤行人场景数据集CrowdHuman和小目标行人数据集Caltech上的大量实验结果表明，和目前先进的方法相比，本文的方法对行人的检测精度有所提升，特别是对于小目标行人检测。与原始FCOS算法相比，在CrowdHuman上平均精度提升接近15%，丢失率降低接近33.0%；在Caltech上的平均精度提升2%。在复杂拥挤场景下的实际应用也证明本文方法的有效性。
- Abstract:
- In view of the detection difficulty resulting from small pedestrian objects, pedestrian occlusion, and pedestrian overlap in large-scale crowded scene videos, this study applies a pixel-by-pixel prediction object detection framework, i.e., fully convolutional one-stage object detection (FCOS), for pedestrian detection. An improved backbone network is proposed to extract pedestrian features, achieve multi-scale detection of object pedestrians by increasing scale regression, reduce the number of objects detected by other feature layers, and thereby improve the ability of pedestrian detection. Several experiments have been performed on the crowded pedestrian scene dataset CrowdHuman and the small object pedestrian dataset Caltech. The results show that compared with current advanced methods, the proposed algorithm makes some improvements in the pedestrian detection accuracy, especially for small object pedestrian detection. Compared with the original FCOS framework, the average precision on CrowdHuman is increased by nearly 15% and the miss rate is decreased by nearly 33.0%. The average precision on Caltech is increased by 2%. Moreover, the actual use in complex, crowded scenarios proves the effectiveness of this algorithm.
- 参考文献/References:
-
[1] NI Tongguang, DING Zongyuan, CHEN Fuhua, et al. Relative distance metric leaning based on clustering centralization and projection vectors learning for person re-identification[J]. IEEE access, 2018, 6: 11405-11411.
[2] WANG Hongyuan, DING Zongyuan, ZHANG Ji, et al. Person reidentification by semisupervised dictionary rectification learning with retraining module[J]. Journal of electronic imaging, 2018, 27(4): 043043.
[3] 戴臣超, 王洪元, 倪彤光, 等. 基于深度卷积生成对抗网络和拓展近邻重排序的行人重识别[J]. 计算机研究与发展, 2019, 56(8): 1632-1641
DAI Chenchao, WANG Hongyuan, NI Tongguang, et al. Person re-identification based on deep convolutional generative adversarial network and expanded neighbor reranking[J]. Journal of computer research and development, 2019, 56(8): 1632-1641
[4] JIAO Licheng, ZHANG Fan, LIU Fang, et al. A survey of deep learning-based object detection[J]. IEEE access, 2019, 7: 128837-128868.
[5] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.
[6] DAI Jifeng, LI Yi, HE Kaiming, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Barcelona, Spain, 2016: 379-387.
[7] HE Kaiming, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 2961-2969.
[8] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 2980-2988.
[9] CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 6154-6162.
[10] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 7263-7271.
[11] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 21-37.
[12] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 9627-9636.
[13] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 4438-4446.
[14] LIU Fayao, SHEN Chunhua, LIN Guosheng, et al. Learning depth from single monocular images using deep convolutional neural fields[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 38(10): 2024-2039.
[15] CHEN Yu, SHEN Chunhua, WEI Xiushen, et al. Adversarial PoseNet: a structure-aware convolutional network for human pose estimation[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 1212-1221.
[16] BOOMINATHAN L, KRUTHIVENTI S S S, BABU R V. CrowdNet: a deep convolutional network for dense crowd counting[C]//Proceedings of the 24th ACM International Conference on Multimedia. Amsterdam, The Netherlands, 2016: 640-644.
[17] YU Jiahui, JIANG Yuning, WANG Zhangyang, et al. UnitBox: an advanced object detection network[C]//Proceedings of the 24th ACM International Conference on Multimedia. Amsterdam, The Netherlands, 2016: 516-520.
[18] HUANG Lichao, YANG Yi, DENG Yafeng, et al. DenseBox: unifying landmark localization with end to end object detection[EB/OL]. (2015?09-19)[2021?05-07] https://arxiv.org/abs/1509.04874.
[19] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 2117-2125.
[20] REZATOFIGHI H, TSOI N, GWAK J Y, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 658-666.
[21] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770-778.
[22] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 4700-4708.
[23] LEE Y, HWANG J W, LEE S, et al. An energy and GPU-computation efficient backbone network for real-time object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Long Beach, USA, 2019: 752-760.
[24] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 7132-7141.
[25] SHAO Shuai, ZHAO Zijian, LI Boxun, et al. CrowdHuman: a benchmark for detecting human in a crowd[EB/OL]. (2018?04-30)[2021?05-07] https://arxiv.org/pdf/1805.00123.pdf.
[26] LIU Songtao, HUANG Di, WANG Yunhong. Adaptive NMS: refining pedestrian detection in a crowd[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 6459-6468.
[27] GOYAL P, DOLLáR P, GIRSHICK R, et al. Accurate, large minibatch SGD: training ImageNet in 1 hour[EB/OL]. (2018?04-30)[2021?05-07] https://arxiv.org/pdf/1706.02677.pdf.
- 相似文献/References:
-
[1]伍鹏瑛,张建明,彭建,等.多层卷积特征的真实场景下行人检测研究[J].智能系统学报,2019,14(2):306.[doi:10.11992/tis.201710019]
WU Pengying,ZHANG Jianming,PENG Jian,et al.Research on pedestrian detection based on multi-layer convolution feature in real scene[J].CAAI Transactions on Intelligent Systems,2019,14():306.[doi:10.11992/tis.201710019]
[2]陈丽,马楠,逄桂林,等.多视角数据融合的特征平衡YOLOv3行人检测研究[J].智能系统学报,2021,16(1):57.[doi:10.11992/tis.202010003]
CHEN Li,MA Nan,PANG Guilin,et al.Research on multi-view data fusion and balanced YOLOv3 for pedestrian detection[J].CAAI Transactions on Intelligent Systems,2021,16():57.[doi:10.11992/tis.202010003]
[3]杨玉婷,苗夺谦.基于多粒度匹配的行人搜索算法[J].智能系统学报,2022,17(2):420.[doi:10.11992/tis.202105038]
YANG Yuting,MIAO Duoqian.Person search algorithm based on multi-granularity matching[J].CAAI Transactions on Intelligent Systems,2022,17():420.[doi:10.11992/tis.202105038]
[4]毕晓君,孙梓玮,刘进.高层火灾智能报警及逃生指导系统[J].智能系统学报,2022,17(4):814.[doi:10.11992/tis.202110018]
BI Xiaojun,SUN Ziwei,LIU Jin.Intelligent fire alarm and escape guidance systems for highrise buildings[J].CAAI Transactions on Intelligent Systems,2022,17():814.[doi:10.11992/tis.202110018]
备注/Memo
收稿日期:2020-10-14。
基金项目:国家自然科学基金项目 (61976028，61572085，61806026，61502058)；江苏省自然科学基金项目 (BK20180956)
作者简介:齐鹏宇，硕士研究生，主要研究方向为计算机视觉和行人检测;王洪元，教授，博士，主要研究方向为人工智能和模式识别。承担国家自然科学基金项目、省市科技研究基金项目等多项课题研究，发表学术论文百余篇;张继，讲师，主要研究方向为计算机视觉和行人检测
通讯作者:王洪元.E-mail:hywang@cczu.edu.cn
更新日期/Last Update:
1900-01-01