[1] [1] 1侯佳伟. 从七次全国人口普查看我国人口发展新特点及新趋势［J］. 学术论坛， 2021， 44（5）： 1-14. doi: 10.3969/j.issn.1004-4434.2021.05.001HOUJ W. Looking at the new characteristics and trends of China’s population development from the seven national censuses［J］. Academic Forum， 2021， 44（5）： 1-14. （in Chinese）. doi: 10.3969/j.issn.1004-4434.2021.05.001

[2] LUO C X, YANG X D, YUILLE A. Exploring Simple 3D Multi-Object Tracking for Autonomous Driving[C], 10468-10477(10).

[3] LIU C, TANG X, MA J J et al. Remote Sensing Images Feature Learning Based on Multi-Branch Networks[C], 2057-2060(2021).

[4] KE W, ZHANG T L, HUANG Z Y et al. Multiple Anchor Learning for Visual Object Detection[C], 10203-10212(13).

[5] LI S, YANG L X, HUANG J Q et al. Dynamic Anchor Feature Selection for Single-Shot Object Detection[C], 6608-6617(2019).

[6] GIRSHICK R, DONAHUE J, DARRELL T et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C], 580-587(23).

[7] REDMON J, DIVVALA S, GIRSHICK R et al. You Only Look Once： Unified， Real-Time Object Detection[C], 779-788(27).

[8] ROSZYK K, NOWICKI M R, SKRZYPCZYŃSKI P. Adopting the YOLOv4 architecture for low-latency multispectral pedestrian detection in autonomous driving[J]. Sensors, 22, 1082(2022).

[9] GAWANDE U, HAJARI K, GOLHAR Y. SIRA： Scale illumination rotation affine invariant mask R-CNN for pedestrian detection[J]. Applied Intelligence, 52, 10398-10416(2022).

[10] [10] 10李经宇， 杨静， 孔斌， 等. 基于注意力机制的多尺度车辆行人检测算法［J］. 光学 精密工程， 2021， 29（6）： 1448-1458. doi: 10.37188/OPE.20212906.1448LIJ Y， YANGJ， KONGB， et al. Multi-scale vehicle and pedestrian detection algorithm based on attention mechanism［J］. Opt. Precision Eng.， 2021， 29（6）： 1448-1458. （in Chinese）. doi: 10.37188/OPE.20212906.1448

[11] [11] 11马立， 巩笑天， 欧阳航空. Tiny YOLOV3目标检测改进［J］. 光学 精密工程， 2020， 28（4）： 988-995. doi: 10.3788/OPE.20202804.0988MAL， GONGX T， OUYANGH K. Improvement of Tiny YOLOV3 target detection［J］. Opt. Precision Eng.， 2020， 28（4）： 988-995. （in Chinese）. doi: 10.3788/OPE.20202804.0988

[12] JIN Z C, LIU B, CHU Q et al. SAFNet： A Semi-Anchor-Free Network with Enhanced Feature Pyramid for Object Detection[C], 9445-9457(2020).

[13] ZHU C C, HE Y H, SAVVIDES M. Feature Selective Anchor-Free Module for Single-Shot Object Detection[C], 840-849(15).

[14] ZHANG S F, CHI C, YAO Y Q et al. Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection[C], 9756-9765(13).

[15] LAW H, DENG J. CornerNet： detecting objects as paired keypoints[J]. International Journal of Computer Vision, 128, 642-656(2020).

[16] ZHOU X, WANG D, KRÄHENBÜHL P. Objects as points[J]. arXiv preprint(2019).

[17] DUAN K W, BAI S, XIE L X et al. Centernet： keypoint triplets for object detection[C], 6568-6577(2019).

[18] CAO Z W, YANG H H, XU W J et al. Multiscale anchor-free region proposal network for pedestrian detection[J]. Wireless Communications and Mobile Computing, 2021, 1-12(2021).

[19] DING Z F, GU Z C, SUN Y P et al. Cascaded cross-layer fusion network for pedestrian detection[J]. Mathematics, 10, 139(2022).

[20] [20] 20邹逸群， 肖志红， 唐夏菲， 等. Anchor-free的尺度自适应行人检测算法［J］. 控制与决策， 2021， 36（2）： 295-302. doi: 10.13195/j.kzyjc.2020.0124ZOUY Q， XIAOZH H， TANGX F， et al. Anchor-free scale adaptive pedestrian detection algorithm［J］. Control and Decision， 2021， 36（2）： 295-302. （in Chinese）. doi: 10.13195/j.kzyjc.2020.0124

[21] HE K M, ZHANG X Y, REN S Q et al. Deep Residual Learning for Image Recognition[C], 770-778(27).

[22] CHU S W, SONG Y, ZOUO J J et al. Human Pose Estimation Using Deep Convolutional Densenet Hourglass Network with Intermediate Points Voting[C], 594-598(22).

[23] WENG X, YAN Y, DONG G S et al. Deep multi-branch aggregation network for real-time semantic segmentation in street scenes[C], 17224-17240(2022).

[24] CHEN Z F, QIN X, YANG C et al. Composite localization for human pose estimation[J]. arXiv preprint(2021).

[25] DU C J, YU H, YU L. A scale-sensitive heatmap representation for multi-person pose estimation[J]. IET Image Processing, 16, 1194-1207(2022).

[26] WU H, CAO Y, WEI H P et al. Face recognition based on haar like and euclidean distance[J]. Journal of Physics： Conference Series, 1813(2021).

[27] CHOI SBIN, LEE S S, PARK J et al. Standard greedy non maximum suppression optimization for efficient and high speed inference[C], 1-4(1).

[28] ZHANG S F, XIE Y L, WAN J et al. WiderPerson： a diverse dataset for dense pedestrian detection in the wild[J]. IEEE Transactions on Multimedia, 22, 380-393(2020).

[29] SHAO S, ZHAO Z, LI B et al. Crowdhuman： A benchmark for detecting human in a crowd[J]. arXiv preprint(2018).

[30] TIAN Z, SHEN C H, CHEN H et al. FCOS： A Simple and Strong Anchor-Free Object Detector[C], 1922-1933(2020).

[31] [31] 31王宸， 张秀峰， 刘超， 等. 改进YOLOv3的轮毂焊缝缺陷检测［J］. 光学 精密工程， 2021， 29（8）： 1942-1954. doi: 10.37188/OPE.20212908.1942WANGCH， ZHANGX F， LIUCH， et al. Detection method of wheel hub weld defects based on the improved YOLOv3［J］. Opt. Precision Eng.， 2021， 29（8）： 1942-1954. （in Chinese）. doi: 10.37188/OPE.20212908.1942

[32] KANG H J. Real-time Object Detection on 640x480 Image with VGG16 SSD[C], 419-422(9).

[33] WANG Y M, JIA K B, LIU P Y. Impolite pedestrian detection by using enhanced YOLOv3-tiny[J]. Journal on Artificial Intelligence, 2, 113-124(2020).

[34] [34] 34陈一潇， 阿里甫·库尔班， 林文龙， 等. 面向拥挤行人检测的CA-YOLOv5［J］. 计算机工程与应用， 2022， 58（9）： 238-245. doi: 10.3778/j.issn.1002-8331.2201-0058CHENY X， ALIFUK， LINW L， et al. CA-YOLOv5 for crowded pedestrian detection［J］. Computer Engineering and Applications， 2022， 58（9）： 238-245. （in Chinese）. doi: 10.3778/j.issn.1002-8331.2201-0058

[35] REDMON J, FARHADI A. YOLO9000： Better， Faster， Stronger[C], 6517-6525(21).

[36] CAO J, PANG Y, ANWER R M et al. PSTR： End-To-End One-Step Person Search with Transformers[C], 9458-9467(2022).

[37] YU R, DU D, LALONDE R et al. Cascade Transformers for End-to-End Person Search[C], 2022, 7267-7276.