Spatial location method of dynamic targets in surveillance videos

doi:10.13474/j.cnki.11-2246.2022.0237

Abstract

Abstract: Aiming at the problem of dynamic targets' location in surveillance videos, this paper studies the mapping relationship among surveillance cameras, target pixel coordinates and geographical scenes on the premise of considering the camera distortion, and proposes the spatial location methods based on the digital surface model (DSM) and the plane constraint. Firstly, the camera calibration is completed and the imaging model of the camera is determined. Secondly, the pixel coordinates of the targets after distortion correction are extracted, and the 3D geographic coordinates of the targets are calculated by the two spatial location methods. Finally, the positioning accuracy is evaluated, and the application characteristics of the two spatial location methods are analyzed. The methods proposed in this paper parse the target data located by pixel coordinates into the spatial geographic information located by 3D coordinates, which provides a unified geographic reference framework for multi-camera target tracking.

Key words: surveillance video, dynamic target, 3D geographic information, spatial localization, digital surface model

CLC Number:

HAN Shijing, MIAO Shufeng, HAO Xiangyang, CHEN Runze. Spatial location method of dynamic targets in surveillance videos[J]. Bulletin of Surveying and Mapping, 2022, 0(8): 87-92.

References

[1] ELHARROUSS O,ALMAADEED N,AL-MAADEED S. A review of video surveillancesystems[J].Journal of Visual Communication and Image Representation,2021,77: 103116.
[2] GHONIEM N A,HESHAM S,FARES S,et al.Intelligent surveillance systems for smart cities: a systematic literature review[M]//Smart Systems: Innovations in Computing.Singapore: Springer Singapore,2021: 135-147.
[3] MILOSAVLJEVIĆ A,RAN AČU1 IĆ D,DIMITRIJEVIĆ A,et al.Integration of GIS and video surveillance[J].International Journal of Geographical Information Science,2016,30(10): 2089-2107.
[4] ZHENG Jin,ZHANG Dongni,ZHANG Zhi,et al.An integrated system of video surveillance and GIS[J].IOP Conference Series: Earth and Environmental Science,2018,170:022088.
[5] 刘垒.基于地理约束场景的动态目标检测及行为识别方法研究[D].桂林: 桂林理工大学,2020.
[6] 韩世静,苗书锋,郝向阳,等.监控视频与地理信息融合技术发展综述[J].测绘通报,2022(5): 1-6.
[7] HAN Shijing,DONG Xiaorui,HAO Xiangyang,et al.Extracting objects' spatial-temporal information based on surveillance videos and the digital surface model[J].ISPRS International Journal of Geo-Information,2022,11(2):103.
[8] MILOSAVLJEVIĆ A,RAN AČU1 IĆ D,DIMITRIJEVIĆ A,et al.A method for estimating surveillance video georeferences[J].ISPRS International Journal of Geo-Information,2017,6(7):211.
[9] 徐汝东,刘进.可量测视频目标动态轨迹生成及GIS应用[J].武汉大学学报(信息科学版),2016,41(6):818-824.
[10] XIE Yujia,WANG Meizhen,LIU Xuejun,et al.Integration of GIS and moving objects in surveillance video[J].ISPRS International Journal of Geo-Information,2017,6(4):94.
[11] XIE Yujia,WANG Meizhen,LIU Xuejun,et al.Integration of multi-camera video moving objects and GIS[J].ISPRS International Journal of Geo-Information,2019,8(12):561.
[12] 张旭,郝向阳,李建胜,等.监控视频中动态目标与地理空间信息的融合与可视化方法[J].测绘学报,2019,48(11):1415-1423.
[13] 李景文,韦晶闪,姜建武,等.多视角监控视频中动态目标的时空信息提取方法[J].测绘学报,2022,51(3):388-400.
[14] MILOSAVLJEVIĆ A,DIMITRIJEVIĆ A,RAN AČU1 IĆ D.GIS-augmented video surveillance[J].International Journal of Geographical Information Science,2010,24(9):1415-1433.
[15] 张兴国.地理场景协同的多摄像机目标跟踪研究[D].南京:南京师范大学,2014.
[16] 唐丽玉,王熠中,陈崇成,等.视频图像中监控目标的空间定位方法[J].福州大学学报(自然科学版),2014,42(1):55-61.
[17] HARTLEY R,ZISSERMAN A.Multiple view geometry incomputer vision[M].2nd ed.Cambridge,UK:Cambridge University Press,2003.
[18] ZHANG Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[19] LEPETIT V,MORENO-NOGUER F,FUA P.EPnP:an accurate O(n) solution to the PnP problem[J].International Journal of Computer Vision,2009,81(2):155.
[20] PENATE-SANCHEZ A,ANDRADE-CETTO J,MORENO-NOGUER F.Exhaustive linearization for robust camera pose and focal length estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(10):2387-2400.