浏览全部资源
扫码关注微信
新疆大学 电气工程学院,新疆维吾尔自治区 乌鲁木齐 830017
Received:30 May 2022,
Revised:08 July 2022,
Published:25 May 2023
移动端阅览
吕志轩,魏霞,黄德启.多分支无锚框网络密集行人检测算法[J].光学精密工程,2023,31(10):1532-1547.
LÜ Zhixuan,WEI Xia,HUANG Deqi.Dense pedestrian detection algorithm in multi-branch non-anchor frame network[J].Optics and Precision Engineering,2023,31(10):1532-1547.
吕志轩,魏霞,黄德启.多分支无锚框网络密集行人检测算法[J].光学精密工程,2023,31(10):1532-1547. DOI: 10.37188/OPE.20233110.1532.
LÜ Zhixuan,WEI Xia,HUANG Deqi.Dense pedestrian detection algorithm in multi-branch non-anchor frame network[J].Optics and Precision Engineering,2023,31(10):1532-1547. DOI: 10.37188/OPE.20233110.1532.
针对街道等多人流量场景图像中人员密集、姿态变化多、人体遮挡严重造成的行人检测漏检问题,提出一种多分支无锚框网络(MBAN)行人检测方法。首先,在检测模型主干网络后加入多分支网络结构用以检测行人的多个关键区域局部特征;然后,设计了关键区域之间的距离损失函数引导分支网络对行人的局部检测位置进行差异化学习,接下来为了提高分支网络对行人局部特征空间信息的理解能力,在Resnet50网络尾部加入四个上采样块构成沙漏结构(Hourglass);最后,设计了一种局部特征选择网络自适应抑制多分支输出的非最优值,消除预测时的冗余特征框。实验结果表明MBAN方法对多人流量场景行人检测的mAP值、F1值、Prec和Recall分别达到85.22%,0.87,80.07%和94.39%,证明该方法对密集人群检测能力较强,与其他行人检测算法相比有较高的召回率。
Considering the problem of missed pedestrian detection in dense pedestrian images, a multi-branch non-anchor frame network (MBAN) detection method is proposed to detect various posture changes and serious human occlusion in multi-person traffic scenes, such as streets. First, a multi-branch network structure is added after model backbone network detection to detect the local features of multiple key areas with pedestrians. Subsequently, the distance loss function between key areas is designed to guide the branch network to differentially learn the local detection position of pedestrians. Thereafter, four up-sampling blocks are added to the tail of the ResNet50 network to form an hourglass structure, thereby improving the branch network’s ability to understand the spatial information of local features of pedestrians. Finally, a local feature selection network is designed to adaptively suppress the non-optimal values of the multi-branch output and eliminate the redundant feature box in prediction. In the experimental results, the mAP, F1, Prec, and Recall values of the MBAN method for pedestrian detection in multi-person scenes reached 85.22%, 0.87, 80.07%, and 94.39%, respectively. Therefore, this method is effective in detecting pedestrians in dense crowds and has higher recall rate compared with other pedestrian detection algorithms.
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.1004-4434.2021.05.001 http://dx.doi.org/10.3969/j.issn.1004-4434.2021.05.001
HOU J 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 http://dx.doi.org/10.3969/j.issn.1004-4434.2021.05.001
LUO C X , YANG X D , YUILLE A . Exploring Simple 3D Multi-Object Tracking for Autonomous Driving [C]. 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . 10 - 17 , 2021, Montreal, QC, Canada. IEEE , 2022: 10468 - 10477 . doi: 10.1109/iccv48922.2021.01032 http://dx.doi.org/10.1109/iccv48922.2021.01032
LIU C , TANG X , MA J J , et al . Remote Sensing Images Feature Learning Based on Multi-Branch Networks [C]. IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium . 262,2020 , Waikoloa , HI, USA . IEEE , 2021 : 2057 - 2060 . doi: 10.1109/igarss39084.2020.9323967 http://dx.doi.org/10.1109/igarss39084.2020.9323967
KE W , ZHANG T L , HUANG Z Y , et al . Multiple Anchor Learning for Visual Object Detection [C]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . 13 - 19 , 2020, Seattle, WA, USA. IEEE , 2020: 10203 - 10212 . doi: 10.1109/cvpr42600.2020.01022 http://dx.doi.org/10.1109/cvpr42600.2020.01022
LI S , YANG L X , HUANG J Q , et al . Dynamic Anchor Feature Selection for Single-Shot Object Detection [C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27 - November 2 , 2019 , Seoul, Korea (South). IEEE , 2020 : 6608 - 6617 . doi: 10.1109/iccv.2019.00671 http://dx.doi.org/10.1109/iccv.2019.00671
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 . 23 - 28 , 2014, Columbus, OH, USA. IEEE , 2014: 580 - 587 . doi: 10.1109/cvpr.2014.81 http://dx.doi.org/10.1109/cvpr.2014.81
REDMON J , DIVVALA S , GIRSHICK R , et al . You Only Look Once: Unified, Real-Time Object Detection [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 27 - 30 , 2016, Las Vegas, NV, USA. IEEE , 2016: 779 - 788 . doi: 10.1109/cvpr.2016.91 http://dx.doi.org/10.1109/cvpr.2016.91
ROSZYK K , NOWICKI M R , SKRZYPCZYŃSKI P . Adopting the YOLOv4 architecture for low-latency multispectral pedestrian detection in autonomous driving [J]. Sensors , 2022 , 22 ( 3 ): 1082 . doi: 10.3390/s22031082 http://dx.doi.org/10.3390/s22031082
GAWANDE U , HAJARI K , GOLHAR Y . SIRA: Scale illumination rotation affine invariant mask R-CNN for pedestrian detection [J]. Applied Intelligence , 2022 , 52 ( 9 ): 10398 - 10416 . doi: 10.1007/s10489-021-03073-z http://dx.doi.org/10.1007/s10489-021-03073-z
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.20212906.1448 http://dx.doi.org/10.37188/OPE.20212906.1448
LI J Y , YANG J , KONG B , 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 http://dx.doi.org/10.37188/OPE.20212906.1448
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.20202804.0988 http://dx.doi.org/10.3788/OPE.20202804.0988
MA L , GONG X T , OUYANG H K . Improvement of Tiny YOLOV3 target detection [J]. Opt. Precision Eng. , 2020 , 28 ( 4 ): 988 - 995 . (in Chinese) . doi: 10.3788/OPE.20202804.0988 http://dx.doi.org/10.3788/OPE.20202804.0988
JIN Z C , LIU B , CHU Q , et al . SAFNet: A Semi-Anchor-Free Network with Enhanced Feature Pyramid for Object Detection [C]. IEEE Transactions on Image Processing.7 , 2020 , IEEE , 2020: 9445 - 9457 . doi: 10.1109/tip.2020.3028196 http://dx.doi.org/10.1109/tip.2020.3028196
ZHU C C , HE Y H , SAVVIDES M . Feature Selective Anchor-Free Module for Single-Shot Object Detection [C]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . 15 - 20 , 2019, Long Beach, CA, USA. IEEE , 2020: 840 - 849 . doi: 10.1109/cvpr.2019.00093 http://dx.doi.org/10.1109/cvpr.2019.00093
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]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . 13 - 19 , 2020, Seattle, WA, USA. IEEE , 2020: 9756 - 9765 . doi: 10.1109/cvpr42600.2020.00978 http://dx.doi.org/10.1109/cvpr42600.2020.00978
LAW H , DENG J . CornerNet: detecting objects as paired keypoints [J]. International Journal of Computer Vision , 2020 , 128 ( 3 ): 642 - 656 . doi: 10.1007/s11263-019-01204-1 http://dx.doi.org/10.1007/s11263-019-01204-1
ZHOU X , WANG D , KRÄHENBÜHL P . Objects as points [J]. arXiv preprint arXiv: 1904.07850 , 2019 .
DUAN K W , BAI S , XIE L X , et al . Centernet: keypoint triplets for object detection [C]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27 - November 2 , 2019 , Seoul, Korea (South). IEEE , 2020 : 6568 - 6577 . doi: 10.1109/iccv.2019.00667 http://dx.doi.org/10.1109/iccv.2019.00667
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 , 2021 : 1 - 12 . doi: 10.1155/2021/5590895 http://dx.doi.org/10.1155/2021/5590895
DING Z F , GU Z C , SUN Y P , et al . Cascaded cross-layer fusion network for pedestrian detection [J]. Mathematics , 2022 , 10 ( 1 ): 139 . doi: 10.3390/math10010139 http://dx.doi.org/10.3390/math10010139
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.2020.0124 http://dx.doi.org/10.13195/j.kzyjc.2020.0124
ZOU Y Q , XIAO ZH H , TANG X 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 http://dx.doi.org/10.13195/j.kzyjc.2020.0124
HE K M , ZHANG X Y , REN S Q , et al . Deep Residual Learning for Image Recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 27 - 30 , 2016, Las Vegas, NV, USA. IEEE , 2016: 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
CHU S W , SONG Y , ZOUO J J , et al . Human Pose Estimation Using Deep Convolutional Densenet Hourglass Network with Intermediate Points Voting [C]. 2019 IEEE International Conference on Image Processing (ICIP) . 22 - 25 , 2019, Taipei, China. IEEE , 2019: 594 - 598 . doi: 10.1109/icip.2019.8803789 http://dx.doi.org/10.1109/icip.2019.8803789
WENG X , YAN Y , DONG G S , et al . Deep multi-branch aggregation network for real-time semantic segmentation in street scenes [C]. IEEE Transactions on Intelligent Transportation Systems.16 , 2022 , IEEE , 2022: 17224 - 17240 . doi: 10.1109/tits.2022.3150350 http://dx.doi.org/10.1109/tits.2022.3150350
CHEN Z F , QIN X , YANG C , et al . Composite localization for human pose estimation [J]. arXiv preprint arXiv: 2105.07245 , 2021 .
DU C J , YU H , YU L . A scale-sensitive heatmap representation for multi-person pose estimation [J]. IET Image Processing , 2022 , 16 ( 4 ): 1194 - 1207 . doi: 10.1049/ipr2.12404 http://dx.doi.org/10.1049/ipr2.12404
WU H , CAO Y , WEI H P , et al . Face recognition based on haar like and euclidean distance [J]. Journal of Physics: Conference Series , 2021 , 1813 ( 1 ): 012036 . doi: 10.1088/1742-6596/1813/1/012036 http://dx.doi.org/10.1088/1742-6596/1813/1/012036
CHOI SBIN , LEE S S , PARK J , et al . Standard greedy non maximum suppression optimization for efficient and high speed inference [C]. 2021 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) . 1 - 3 , 2021, Gangwon, Korea, Republic of. IEEE , 2021: 1 - 4 . doi: 10.1109/icce-asia53811.2021.9641977 http://dx.doi.org/10.1109/icce-asia53811.2021.9641977
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 , 2020 , 22 ( 2 ): 380 - 393 . doi: 10.1109/tmm.2019.2929005 http://dx.doi.org/10.1109/tmm.2019.2929005
SHAO S , ZHAO Z , LI B , et al . Crowdhuman: A benchmark for detecting human in a crowd [J]. arXiv preprint arXiv: 1805.00123 , 2018 .
TIAN Z , SHEN C H , CHEN H , et al . FCOS: A Simple and Strong Anchor-Free Object Detector [C]. IEEE Transactions on Pattern Analysis and Machine Intelligence . 19,2020 , IEEE , 2020 : 1922 - 1933 . doi: 10.1109/tpami.2020.3032166 http://dx.doi.org/10.1109/tpami.2020.3032166
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.20212908.1942 http://dx.doi.org/10.37188/OPE.20212908.1942
WANG CH , ZHANG X F , LIU CH , 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 http://dx.doi.org/10.37188/OPE.20212908.1942
KANG H J . Real-time Object Detection on 640x480 Image with VGG16 SSD [C]. 2019 International Conference on Field-Programmable Technology (ICFPT) . 9 - 13 , 2019, Tianjin, China. IEEE , 2020: 419 - 422 . doi: 10.1109/icfpt47387.2019.00082 http://dx.doi.org/10.1109/icfpt47387.2019.00082
WANG Y M , JIA K B , LIU P Y . Impolite pedestrian detection by using enhanced YOLOv3-tiny [J]. Journal on Artificial Intelligence , 2020 , 2 ( 3 ): 113 - 124 . doi: 10.32604/jai.2020.010137 http://dx.doi.org/10.32604/jai.2020.010137
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.1002-8331.2201-0058 http://dx.doi.org/10.3778/j.issn.1002-8331.2201-0058
CHEN Y X , ALIFU K , LIN W 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 http://dx.doi.org/10.3778/j.issn.1002-8331.2201-0058
REDMON J , FARHADI A . YOLO9000: Better, Faster, Stronger [C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . 21 - 26 , 2017, Honolulu, HI, USA. IEEE , 2017: 6517 - 6525 . doi: 10.1109/cvpr.2017.690 http://dx.doi.org/10.1109/cvpr.2017.690
CAO J , PANG Y , ANWER R M , et al . PSTR: End-To-End One-Step Person Search with Transformers [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 2022 : 9458 - 9467 . doi: 10.1109/cvpr52688.2022.00924 http://dx.doi.org/10.1109/cvpr52688.2022.00924
YU R , DU D , LALONDE R , et al . Cascade Transformers for End-to-End Person Search [C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022 : 7267 - 7276 . doi: 10.1109/cvpr52688.2022.00712 http://dx.doi.org/10.1109/cvpr52688.2022.00712
0
Views
49
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution