联合分布式摄像头的山岳型景区游客精准时空信息近场感知

doi:10.13474/j.cnki.11-2246.2025.0112

测绘通报 ›› 2025, Vol. 0 ›› Issue (1): 72-77.doi: 10.13474/j.cnki.11-2246.2025.0112

• 学术研究 • 上一篇

联合分布式摄像头的山岳型景区游客精准时空信息近场感知

施坤涛¹, 朱长明^1,2, 张新², 杨帆¹, 张琨¹, 高宏进³

1. 江苏师范大学地理测绘与城乡规划学院, 江苏徐州 221116;
2. 中国科学院空天信息创新研究院遥感科学国家重点实验室, 北京 100101;
3. 齐鲁空天信息研究院, 山东济南 250101

收稿日期:2024-04-15 发布日期:2025-02-09
通讯作者: 朱长明。E-mail:zhuchangming@jsnu.edu.cn
作者简介:施坤涛(1999—),男,硕士,主要研究方向为高分遥感、近场感知与计算机视觉等。E-mail:2020211467@jsnu.edu.cn
基金资助:
国家重点研发计划(2021YFB1407004;2023YFE0103800);江苏高校优势学科建设工程资助;江苏师范大学研究生科研与实践创新计划校级项目(2019XKT041)

Spatio-temporal perception of tourists in mountainous scenic areas using distributed camera networks proximal sensing

SHI Kuntao¹, ZHU Changming^1,2, ZHANG Xin², YANG Fan¹, ZHANG Kun¹, GAO Hongjin³

1. School of Geography, Geomatics and Planning, Jiangsu Normal University, Xuzhou 221116, China;
2. State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China;
3. Qilu Institute of Aerospace Information, Jinan 250101, China

Received:2024-04-15 Published:2025-02-09

摘要/Abstract

摘要： 山岳型景区游客信息实时感知是智慧景区建设的核心内容之一,本文充分利用山岳型景区分布式摄像头近场感知网的优势,提出了联合分布式摄像头的山岳型景区游客目标动态精准被动感知方法体系。首先,通过注意力模块(CBAM)和自适应空间特征融合(ASFF)技术改进YOLOX网络,完成复杂场景视频流的游客目标初步识别;进而,引入目标动态跟踪算法改善山岳景区游客动态目标遮挡问题,进一步提升模型检测精度和稳定性;在此基础上,通过检测目标的像素坐标空间到地理坐标空间的转化定位算法推导出游客的时间位置信息。结果表明,该方法能够很好地协助完成山岳型景区复杂场景下游客的近场被动感知与空间定位,游客动态目标被动感知总体识别精度达到90%以上,空间定位误差RMSE小于1.109 4,为山岳型景区无/弱卫星导航信号情况下区域游客目标的被动实时动态精准感知与安全管理提供了技术方案和信息支持。

关键词: 目标识别, 近场感知, 时空分布, 游客信息, 山岳景区

Abstract: Mountainous scenic areas rely on distributed camera networks for real-time visitor perception, a crucial aspect of intelligent scenic area development. This paper exploits these networks to propose a method for dynamic and precise passive perception of visitors in mountainous scenic areas through distributed cameras. By enhancing the YOLOX network with a convolutional block attention module (CBAM) and adaptive spatial feature fusion (ASFF) techniques, and incorporating a dynamic target tracking algorithm, this method achieves accurate detection and tracking of visitors' movements. Subsequently, a localization algorithm is utilized to derive real-time positional information of visitors. The results demonstrate the method's effectiveness in near-field passive perception and spatial positioning within mountainous scenic areas, achieving a detection precision over 90%, spatial positioning accuracy within 1 m, and a root mean square error (RMSE) of less than 1.109 4. This provides a technical solution and information support for the passive real-time dynamic precise perception and safety management of visitors in areas with weak or no satellite navigation signals.

Key words: object detection, near-field perception, spatio-temporal distribution, dynamic management, mountainous scenic areas

中图分类号:

P237

施坤涛, 朱长明, 张新, 杨帆, 张琨, 高宏进. 联合分布式摄像头的山岳型景区游客精准时空信息近场感知[J]. 测绘通报, 2025, 0(1): 72-77.

SHI Kuntao, ZHU Changming, ZHANG Xin, YANG Fan, ZHANG Kun, GAO Hongjin. Spatio-temporal perception of tourists in mountainous scenic areas using distributed camera networks proximal sensing[J]. Bulletin of Surveying and Mapping, 2025, 0(1): 72-77.

参考文献

[1] SHEN H,LIN D,YANG X,et al.Vision-based multi-object tracking through UAV swarm[J].IEEE Geoscience and Remote Sensing Letters,2023,20:6008905.
[2] BHARATI P,PRAMANIK A.Deep learning techniques—R-CNN to mask R-CNN: a survey[C]//Proceedings of 2020 Computational Intelligence in Pattern Recognition.[S.l.]: Springer,2020:657-668.
[3] TERVEN J,CORDOVA-ESPARZA D M,Romero-González J A.A comprehensive review of YOLO architectures in computer vision:from YOLOv1 to YOLOv8 and YOLO-NAS[J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716.
[4] ZHENG D,DONG W,HU H,et al.Less is more:focus attention for efficient DETR[C]//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision.Paris:IEEE,2023:6674-6683.
[5] CIAPARRONE G,SÁNCHEZ F L,TABIK S,et al.Deep learning in video multi-object tracking:a survey[J].Neurocomputing,2020,381:61-88.
[6] PAL S K,PRAMANIK A,MAITI J,et al.Deep learning in multi-object detection and tracking:state of the art[J].Applied Intelligence,2021,51(21):6400-6429.
[7] REDMON J,FARHADI A.YOLOv3:an incremental improvement[EB/OL].2018-04-01[2024-03-02].https://arxiv.org/abs/1804.02767v1.
[8] 王玺坤,姜宏旭,林珂玉.基于改进型YOLO算法的遥感图像舰船检测[J].北京航空航天大学学报,2020,46(6):1184-1191.
[9] 马啸,邵利民,金鑫,等.改进的YOLO模型及其在舰船目标识别中的应用[J].电讯技术,2019,59(8):869-874.
[10] 吴杰,段锦,赫立群,等.DS-YOLO网络在遥感图像中的飞机检测算法研究[J].计算机工程与应用,2021,57(1):181-187.
[11] 郑志强,刘妍妍,潘长城,等.改进YOLO V3遥感图像飞机识别应用[J].电光与控制,2019,26(4):28-32.
[12] GE Z,LIU S T,WANG F,et al.YOLOX:exceeding YOLO series in 2021[EB/OL].[2024-03-02].https://arxiv.org/abs/2107.08430v2.
[13] BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[EB/OL].[2024-03-02].https://arxiv.org/abs/2004.10934v1.
[14] BATHIJA A,SHARMA G.Visual object detection and tracking using YOLO and SORT[J].International Journal of Engineering Research and Technology,2019,8(11):345-355.
[15] VEERAMANI B,RAYMOND J W,CHANDA P.DeepSort:deep convolutional networks for sorting haploid maize seeds[J].BMC Bioinformatics,2018,19(9):289.
[16] ZHANG J,ZHOU S P,WANG J J,et al.Frame-wise motion and appearance for real-time multiple object tracking[EB/OL].[2024-03-02].https://arxiv.org/abs/1905.02292v1.
[17] FISCHER T,HUANG T E,PANG J,et al.Qdtrack:quasi-dense similarity learning for appearance-only multiple object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(12):15380-15393.
[18] NIU Z,ZHONG G,YU H.A review on the attention mechanism of deep learning[J].Neurocomputing,2021,452:48-62.
[19] ZHANG Y,SUN P,JIANG Y,et al.Bytetrack:multi-object tracking by associating every detection box[C]//Proceedings of 2022 European Conference on Computer Vision.Cham:Springer Nature Switzerland,2022:1-21.
[20] SHAO S,ZHAO Z J,LI B X,et al.CrowdHuman:a benchmark for detecting human in a crowd[EB/OL].[2024-03-02].https://arxiv.org/abs/1805.00123v1.
[21] MILAN A,LEAL-TAIXE L,REID I,et al.MOT16:a benchmark for multi-object tracking[EB/OL].[2024-03-02].https://arxiv.org/abs/1603.00831v2.
[22] ZHANG S,BENENSON R,SCHIIELE B.Citypersons:a diverse dataset for pedestrian detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:3213-3221.
[23] ZHANG S,XIE Y,WAN J,et al.Widerperson:a diverse dataset for dense pedestrian detection in the wild[J].IEEE Transactions on Multimedia,2019,22(2):380-393.
[23] 韩世静,苗书锋,郝向阳,等.监控视频动态目标的空间定位方法[J].测绘通报,2022(8):87-92.

联合分布式摄像头的山岳型景区游客精准时空信息近场感知

Spatio-temporal perception of tourists in mountainous scenic areas using distributed camera networks proximal sensing

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张学鹏, 曾铖, 勾鹏, 黄莹双. 云贵高原地区生态系统健康时空分布及其驱动因素影响[J]. 测绘通报, 2024, 0(8): 37-41.
[2]	王岩, 刘纪平, 赵阳阳, 徐婧. 基于GTWR模型的3km京津冀PM_2.5时空分布和影响因素分析[J]. 测绘通报, 2024, 0(6): 82-89.
[3]	郭紫祎, 张红娟, 赵智博, 李必军. 基于路侧激光雷达的车辆目标跟踪与定位[J]. 测绘通报, 2024, 0(12): 84-89.
[4]	王冬梅, 吴勇锋, 石一凡, 梁文广, 王轶虹, 潘思远. 利用Sentinel-2遥感影像分析水葫芦时空分布规律[J]. 测绘通报, 2023, 0(6): 44-49.
[5]	蔡军, 温日强, 江伟, 严娇, 卢丽娟. 传统村落航拍图像中民族建筑识别的DeepLabV3+改进算法[J]. 测绘通报, 2023, 0(4): 49-53.
[6]	徐海燕, 郭为人, 李德民, 郝君, 徐刚. 实景三维模型纹理的敏感目标自动识别与脱密方法[J]. 测绘通报, 2023, 0(12): 153-158.
[7]	王步云, 李宏伟, 赵姗. 融合点云与全景影像的路侧多目标识别[J]. 测绘通报, 2023, 0(10): 40-46.
[8]	王孟杰, 王艳军, 李少春, 林云浩, 滕菲, 蔡恒藩. 融合多源遥感数据的长株潭城市群碳排放时空差异分析[J]. 测绘通报, 2023, 0(1): 65-70.
[9]	杨映新, 洪武胜, 吴曼乔. 利用Sentinel-1影像监测土地回填导致的地表形变[J]. 测绘通报, 2021, 0(6): 67-70.
[10]	王维思, 马清霞, 张建辰, 李广佳. 2015—2019年冬季黄河流域中游大气污染物空间分布特征[J]. 测绘通报, 2021, 0(10): 39-47.
[11]	孙薇, 李胜, 江鹢, 柯水松, 夏安科. 深度学习方法应用于深圳市多调合一工作的思考[J]. 测绘通报, 2021, 0(1): 138-141.
[12]	黄泽纯, 刘子璞, 范心仪, 洪安东. 利用时空立方体挖掘小微地震时空演变模式[J]. 测绘通报, 2020, 0(9): 106-109.
[13]	余正, 黄加坡, 陈袁芳, 陈炳蓉, 徐刚, 王晶, 龙程. 温州市新型冠状病毒肺炎时空分布格局演化分析[J]. 测绘通报, 2020, 0(7): 45-49,87.
[14]	常明, 尹海权, 苏广利, 田晓, 徐玉健. 利用水准数据的天津市地面沉降时空特征分析[J]. 测绘通报, 2020, 0(7): 88-92.
[15]	吴益玲, 李成名, 戴昭鑫, 吴政. 城区空气质量指数时空分布特征及影响机制分析[J]. 测绘通报, 2020, 0(4): 81-86.