[1]刘丛昊,王 军,谢 非,等.基于改进NanoDet的复杂运动场景多人体检测算法[J].南京师大学报(自然科学版),2024,(02):140-148.[doi:10.3969/j.issn.1001-4616.2024.02.016]
　Liu Conghao,Wang Jun,Xie Fei,et al.An Improved NanoDet-Based Multi-Human Detection Algorithm for Complex Motion Scenes[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(02):140-148.[doi:10.3969/j.issn.1001-4616.2024.02.016]
点击复制

基于改进NanoDet的复杂运动场景多人体检测算法()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2024年02期
页码:
140-148
栏目:
计算机科学与技术
出版日期:
2024-06-15

文章信息/Info

Title:
An Improved NanoDet-Based Multi-Human Detection Algorithm for Complex Motion Scenes
文章编号:
1001-4616(2024)02-0140-09
作者:
刘丛昊1; 王 军2; 谢 非1; 杨继全1; 马 磊2; 王 琼3
(1.南京师范大学 电气与自动化工程学院,江苏 南京 210023)
(2.南京三万物联网科技有限公司,江苏 南京 210000)
(3.南京师范大学 计算机与电子信息学院,江苏 南京 210023)
Author(s):
Liu Conghao1; Wang Jun2; Xie Fei1; Yang Jiquan1; Ma Lei2; Wang Qiong3
(1.School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210023,China)
(2.Nanjing Sanwan Internet of Things Technology Co.,Nanjing 210000,China)
(3.School of Computer and Electronic Information,Nanjing Normal University
关键词:
深度学习; 人体检测; 轻量化模型; 注意力机制
Keywords:
deep learning; human detection; lightweight model; attention mechanism
分类号:
TP391.41,TP18
DOI:
10.3969/j.issn.1001-4616.2024.02.016
文献标志码:
A
摘要:
在运动赛事场景下,运动员的行为识别、传球投篮动作次数统计以及AI解说等方面都离不开对运动员的人体检测,这使得复杂场景下对运动员的人体检测速度和精度上均有较高要求. 因此,本文提出一种基于NanoDet的复杂运动场景多人体检测算法. 首先,该算法使用更平滑的Mish函数作为主干网络的激活函数,改进ShuffleNetV2网络,构建主干网络,并引入CBAM注意力模块,采用轻量化路径汇集网络进行特征融合,提高检测准确性; 其次,使用无锚轻量化检测头GFLV2进行回归和分类,实现复杂运动场景下多人体目标检测; 最后,为了进一步验证提出算法的性能,将研究算法与目前主流的检测算法进行实验对比,实验结果表明,相较于其他算法如Yolov3-tiny、Yolov4-tiny等本文算法有着更高的检测精度,比同类型的轻量化检测模型Yolov4-tiny高14.87%,此外,单帧检测时间与Yolov4-tiny的10.67 ms相比减少了31.68%,由此可见,本文研究算法在保持检测速度的基础上,大幅提高了检测精度.
Abstract:
In sports event scenarios,athlete behaviour recognition,passing and shooting action count and AI commentary are inseparable from human body detection of athletes,which makes high requirements on the speed and accuracy of human body detection of athletes in complex scenarios. Therefore,this paper proposes a NanoDet-based multi-body detection algorithm for complex sports scenes. First,the algorithm uses a smoother Mish function as the activation function of the backbone network,improves the ShuffleNetV2 network,builds the backbone network,and introduces the CBAM attention module,and uses a lightweight path pooling network for feature fusion to improve detection accuracy; next,it uses the anchorless lightweight detection head GFLV2 for regression and classification to achieve multi-body target detection in complex motion scenes. Finally,in order to further verify the performance of the proposed algorithm,the research algorithm is experimentally compared with the current mainstream detection algorithms,the experimental results show that the algorithm in this paper has higher detection accuracy compared to other algorithms such as Yolov3-tiny and Yolov4-tiny,which is 14.87% higher than the same type of lightweight detection model Yolov4-tiny. In addition,the single-frame detection time is reduced by 31.68% compared to the 10.67ms of Yolov4-tiny,which shows that the investigated method substantially improves the detection accuracy while maintaining the detection speed improvement.

参考文献/References:

[1]EINFALT M,LIENHART R. Decoupling video and human motion:towards practical event detection in athlete recordings[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Virtual,2020:892-893.
[2]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. Columbus,Ohio,USA,2014:580-587.
[3]REN S,HE K,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.
[4]REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:Unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,USA,2016:779-788.
[5]LIU W,ANGUELOV D,ERHAN D,et al. Ssd:Single shot multibox detector[C]//European Conference on Computer Vision. Springer,Cham,Amsterdam,Netherlands,2016:21-37.
[6]TIAN Z,SHEN C,CHEN H,et al. Fcos:Fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul,Korea(South),2019:9627-9636.
[7]TAN M,PANG R,LE Q V. Efficientdet:Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Virtual,2020:10781-10790.
[8]YANG Z,LI Z,JIANG X,et al. Focal and global knowledge distillation for detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans,LA,USA,2022:4643-4652.
[9]GAO Z,WANG L,HAN B,et al. AdaMixer:A Fast-Converging Query-Based Object Detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans,LA,USA,2022:5364-5373.
[10]HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las,Vegas,USA,2016:770-778.
[11]SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J/OL]. arXiv Preprint arXiv:1409.1556,2014.
[12]SZEGEDY C,IOFFE S,VANHOUCKE V,et al. Inception-v4,inception-resnet and the impact of residual connections on learning[C]//Thirty-first AAAI Conference on Artificial Intelligence. San Francisco,USA,2017:4278-4284.
[13]LIN T Y,DOLL?R P,GIRSHICK R,et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. San,Juan,USA,2017:2117-2125.
[14]LIU S,QI L,QIN H,et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018:8759-8768.
[15]ZHANG S,CHI C,YAO Y,et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:9759-9768.
[16]ZHANG X,ZHOU X,LIN M,et al. Shufflenet:An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018:6848-6856.
[17]WOO S,PARK J,LEE J Y,et al. Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV). Munich,Germany,2018:3-19.
[18]LI X,WANG W,WU L,et al. Generalized focal loss:Learning qualified and distributed bounding boxes for dense object detection[J]. Advances in neural information processing systems,2020,33:21002-21012.
[19]HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA,2018:7132-7141.
[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 the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach,USA,2019:658-666.
[21]刘方坚,李媛. 基于视觉显著性的 SAR 遥感图像 NanoDet 舰船检测方法[J]. 雷达学报,2021,10(6):885-894.

相似文献/References:

[1]郑德鹏,杜吉祥,翟传敏.基于深度学习MPCANet的年龄估计[J].南京师大学报(自然科学版),2017,40(01):20.[doi:10.3969/j.issn.1001-4616.2017.01.004]
　Zheng Depeng,Du Jixiang,Zhai Chuanmin.Age Estimation Based on Deep Learning MPCANet[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(02):20.[doi:10.3969/j.issn.1001-4616.2017.01.004]
[2]朱 繁,王洪元,张 继.基于深度学习的行人重识别研究综述[J].南京师大学报(自然科学版),2018,41(04):93.[doi:10.3969/j.issn.1001-4616.2018.04.015]
　Zhu Fan,Wang Hongyuan,Zhang Ji.A Survey of Person Re-identification Based on Deep Learning[J].Journal of Nanjing Normal University(Natural Science Edition),2018,41(02):93.[doi:10.3969/j.issn.1001-4616.2018.04.015]
[3]孙茹君,张鲁飞.基于动态指导的深度学习模型稀疏化执行方法[J].南京师大学报(自然科学版),2019,42(03):11.[doi:10.3969/j.issn.1001-4616.2019.03.002]
　Sun Rujun,Zhang Lufei.Dynamic Sparse Method for Deep Learning Execution[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(02):11.[doi:10.3969/j.issn.1001-4616.2019.03.002]
[4]赵文芳,林润生,唐 伟,等.基于深度学习的PM2.5短期预测模型[J].南京师大学报(自然科学版),2019,42(03):32.[doi:10.3969/j.issn.1001-4616.2019.03.005]
　Zhao Wenfang,Lin Runsheng,Tang Wei,et al.Forecasting Model of Short-Term PM2.5 ConcentrationBased on Deep Learning[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(02):32.[doi:10.3969/j.issn.1001-4616.2019.03.005]
[5]张新峰,闫昆鹏,赵 珣.基于双向LSTM的手写文字识别技术研究[J].南京师大学报(自然科学版),2019,42(03):58.[doi:10.3969/j.issn.1001-4616.2019.03.008]
　Zhang Xinfeng,Yan Kunpeng,Zhao Xun.Handwriting Chinese Text Recognition Using BiLSTM Network[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(02):58.[doi:10.3969/j.issn.1001-4616.2019.03.008]
[6]贾玉福,胡胜红,刘文平,等.使用条件生成对抗网络的自然图像增强方法[J].南京师大学报(自然科学版),2019,42(03):88.[doi:10.3969/j.issn.1001-4616.2019.03.012]
　Jia Yufu,Hu Shenghong,Liu Wenping,et al.Wild Image Enhancement with Conditional Generative Adversarial Network[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(02):88.[doi:10.3969/j.issn.1001-4616.2019.03.012]
[7]汤 凯,何 庆,赵 群,等.基于改进的深度残差网络的图像识别[J].南京师大学报(自然科学版),2019,42(03):115.[doi:10.3969/j.issn.1001-4616.2019.03.015]
　Tang Kai,He Qing,Zhao Qun,et al.Image Recognition Based on Improved Deep Neural Network[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(02):115.[doi:10.3969/j.issn.1001-4616.2019.03.015]
[8]汪 晨,张辉辉,乐继旺,等.基于深度学习和遥感影像的松材线虫病疫松树目标检测[J].南京师大学报(自然科学版),2021,44(03):84.[doi:10.3969/j.issn.1001-4616.2021.03.013]
　Wang Chen,Zhang Huihui,Le Jiwang,et al.Object Detection to the Pine Trees Affected by Pine Wilt Diseasein Remote Sensing Images Using Deep Learning[J].Journal of Nanjing Normal University(Natural Science Edition),2021,44(02):84.[doi:10.3969/j.issn.1001-4616.2021.03.013]
[9]韩 悦,张永寿,郭依廷,等.乳腺癌腋窝淋巴结超声图像分割算法研究[J].南京师大学报(自然科学版),2021,44(04):122.[doi:10.3969/j.issn.1001-4616.2021.04.016]
　Han Yue,Zhang Yongshou,Guo Yiting,et al.Research on Ultrasound Image Segmentation Algorithm forAxillary Lymph Node with Breast Cancer[J].Journal of Nanjing Normal University(Natural Science Edition),2021,44(02):122.[doi:10.3969/j.issn.1001-4616.2021.04.016]
[10]闫靖昆,黄毓贤,秦伟森,等.棉田复杂背景下棉花黄萎病病斑分割算法研究[J].南京师大学报(自然科学版),2021,44(04):127.[doi:10.3969/j.issn.1001-4616.2021.04.017]
　Yan Jingkun,Huang Yuxian,Qin Weisen,et al.Study on Segmentation Algorithm of Cotton Verticillium WiltDisease Spot in Cotton Field Under Complex Background[J].Journal of Nanjing Normal University(Natural Science Edition),2021,44(02):127.[doi:10.3969/j.issn.1001-4616.2021.04.017]

备注/Memo

备注/Memo:
收稿日期:2022-11-04.
基金项目:国家自然科学基金项目(41974033)、江苏省科技成果转化项目(BA2020004)、江苏省省级工业和信息产业转型升级专项资金项目(JITC-2000AX0676-71)、江苏省研究生科研与实践创新计划项目.
通讯作者:谢非,博士,副教授,研究方向:机器视觉与深度学习. E-mail:xiefei@njnu.edu.cn
更新日期/Last Update: 2024-06-15