计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (8): 93-98.doi: 10.11896/jsjkx.220600258

• 计算机图形学&多媒体 • 上一篇    下一篇

一种面向航空图像的自适应目标计数模型

魏畅, 关佶红, 张毅超, 李文根   

  1. 同济大学电子与信息工程学院 上海 201800
  • 收稿日期:2022-06-18 修回日期:2022-11-14 出版日期:2023-08-15 发布日期:2023-08-02
  • 通讯作者: 关佶红(jhguan@tongji.edu.cn)
  • 作者简介:(593355341@qq.com)
  • 基金资助:
    国家自然科学基金联合基金(U1936205)

Adaptive Object Counting Model for Aerial Imagery

WEI Chang, GUAN Jihong, ZHANG Yichao, LI Wengen   

  1. School of Electronic and Information Engineering,Tongji University,Shanghai 201800,China
  • Received:2022-06-18 Revised:2022-11-14 Online:2023-08-15 Published:2023-08-02
  • About author:WEI Chang,born in 1999,master,is a student member of China Computer Federation.His main research interests include target counting,spatiotemporal data management and analysis.
    GUAN Jihong,professor,doctoral supervisor,is a member of China Computer Federation.Her main research interests include artificial intelligence,spatio-temporal data management and analysis,network modeling,game and colla-boration,application-oriented big data analysis and application services.
  • Supported by:
    Joint Funds of the National Natural Science Foundation of China(U1936205).

PDF (PC)

531

摘要： 目标计数旨在获取给定图像中包含的车辆、建筑物、人物等特定种类目标的数量,对城市规划、应急响应、国家安全等具有重要意义。当前目标计数任务主要依赖于低空摄像头所拍摄的图像,存在目标易被遮挡和计数空间范围小等突出问题。高清航空遥感图像的广泛使用使大范围目标计数成为可能。然而,面向航空图像的目标计数任务存在目标尺度差异大、分布密集、方向不确定等挑战,现有基于低空图像的目标检测计数模型和回归计数模型均无法适用于航空图像的目标计数。针对该问题,提出了一种面向航空图像的自适应目标计数模型。首先,利用几何自适应高斯卷积方法解决目标尺度变化问题;然后,利用基于结构相似性的图片损失判断方法解决目标密集区域计数稳定性较差的问题。实验结果表明,所提模型相较于基准模型取得了更好的目标计数精度。

关键词: 目标计数, 航空图像, 回归计数, 高斯卷积, 结构相似性

Abstract: Object counting aims to obtain the number of specific types of objects such as vehicles,buildings,people contained in a given image,which is of great significance to urban planning,emergency response,national security,etc.The current object coun-ting task mainly relies on the images taken by low-altitude cameras,and there are obvious problems such as the object being easily occluded and the small counting space range.Widespread use of high-definition aerial remote sensing imagery makes it possible to count objects in large areas.However,the object counting task for aerial images has challenges such as large differences in object scales,dense distribution,and uncertain orientation.Existing object detection counting models and regression counting models based on low-altitude images are not suitable for object counting in aerial images.To solve this problem,this paper proposes an adaptive object counting model for aerial images.Firstly,the geometric adaptive Gaussian convolution method is used to solve the problem of object scale variation.Then,the image loss judgment method based on structural similarity is used to solve the pro-blem of poor counting stability of object dense regions.Experimental analysis shows that the proposed model can achieve better object count accuracy than the benchmark model.

Key words: Object counting, Aerial imagery, Regression counting, Gaussian convolution, Structural similarity

中图分类号: 

  • TP391
[1]ZHANG Y,ZHOU D,CHEN S,et al.Single-image crowdcounting via multi-column convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:589-597.
[2]WANG Y,ZOU Y.Fast visual object counting via example-based density estimation[C]//2016 IEEE International Confe-rence on Image Processing(ICIP).IEEE,2016:3653-3657.
[3]FRENCH G,FISHER M,MACKIEWICZ M,et al.Convolu-tional neural networks for counting fish in fisheries surveillance video[C]//Workshop on Machine Vision of Animals and their Behaviour.BMVA Press,2015:7.1-7.10.
[4]DOLLAR P,WOJEK C,SCHIELE B,et al.Pedestrian detec-tion:a benchmark[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:304-311.
[5]UIJLINGS J R,VAN D S K E A,GEVERS T,et al.Selective search for object recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[6]LAZEBNIK S,SCHMID C,PONCE J.Beyond Bags of Fea-tures:Spatial Pyramid Matching for Recognizing Natural Scene Categories[C]//Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Paris:IEEE,2006:2169-2178.
[7]YU Y,ZHANG J,HUANG Y,et al.Object detection by context and boosted HOG-LBP[C]//ECCV Workshop on PASCAL VOC.2010.
[8]GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.Santiago:IEEE,2015:1440-1448.
[9]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:TowardsReal-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[10]HE K,GKIOXARI G,DOLLR P,et al.Mask R-CNN[C]//Pro-ceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Venice:IEEE,2017:2961-2969.
[11]REDMON J,FARHADI A.YOLO9000:Better,Faster,Stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:7263-7271.
[12]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single ShotMulti Box Detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37.
[13]XIE E,DING J,WANG W,et al.Detco:Unsupervised contrastive learning for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:8392-8401.
[14]XU M,ZHANG Z,HU H,et al.End-to-end semi-supervised object detection with soft teacher[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:3060-3069.
[15]DAI X,CHEN Y,YANG J,et al.Dynamic detr:End-to-end object detection with dynamic attention[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:2988-2997.
[16]DAI X,CHEN Y,XIAO B,et al.Dynamic head:Unifying object detection heads with attentions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:7373-7382.
[17]WANG C,ZHANG H,YANG L,et al.Deep people counting in extremely dense crowds[C]//Proceedings of the 23rd ACM International Conference on Multimedia.New York:ACM,2015:1299-1302.
[18]ZHANG C,LI H S,WANG X G,et al.Cross-scene crowdcounting via deep convolutional neural networks [C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2015:833-841.
[19]LIANG D,CHEN X,XU W,et al.TransCrowd:weakly-supervised crowd counting with transformers[J].Science China Information Sciences,2022,65(6):1-14.
[20]SUN G,LIU Y,PROBST T,et al.Boosting crowd counting with transformers[J].arXiv:2105.10926,2021.
[21]GAO G,LIU Q,WANG Y.Counting dense objects in remotesensing images[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics,Speech and Signal Processing(IC-ASSP).IEEE,2020:4137-4141.
[22]DING G,CUI M,YANG D,et al.Object Counting for Remote-
Sensing Images via Adaptive Density Map-Assisted Learning[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-11.
[23]LIU Z,LIN Y,CAO Y,et al.Swin transformer:Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:10012-10022.
[24]CAO X,WANG Z,ZHAO Y,et al.Scale aggregation network for accurate and efficient crowd counting[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:734-750.
[25]MUNDHENK T N,KONJEVOD G,SAKLA W A,et al.Alarge contextual dataset for classification,detection and counting of cars with deep learning[C]//European Conference on Computer Vision.Cham:Springer,2016:785-800.
[26]HSIEH M R,LIN Y L,HSU W H.Drone-based object counting by spatially regularized regional proposal network[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:4145-4153.
[27]XIA G S,BAI X,DING J,et al.DOTA:A large-scale dataset for object detection in aerial images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3974-3983.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发