Abstract
A remote sensing video satellite multiple object detection and tracking method based on road masking, Gaussian mixture model (GMM), and data association is proposed. This method first extracts the road network from the remote sensing video based on deep learning. In the detection stage, the background subtraction algorithm is used based on the GMM to obtain the detection results of the moving targets on the road. In the tracking stage, the data association of the same target detection result in adjacent frames is realized based on the neighborhood search algorithm, so as to obtain the continuous tracking trajectory of each target. The experiments about multiobject detection and tracking are conducted on data measure by real remote sensing satellites, and the results verified the feasibility of the proposed method.
Highlights
At present, with the rapid development of aerospace technology and the gradual deepening of remote sensing applications, the demand for high-resolution satellite remote sensing applications has gradually shifted from static reconnaissance to real-time dynamic monitoring
A series of video satellites have been deployed in recent years. e video satellite can obtain the submeter resolution color dynamic video through the staring imaging mode and obtain continuous video image data of the area of interest, which is suitable for regional dynamic change monitoring, such as situation changes, dynamic target reconnaissance and surveillance, and attack effect evaluation [1,2,3,4]
This paper focuses on video satellites, an emerging aerospace remote sensing technology, and performs fully automatic, high-precision, and high-speed information extraction of dynamic remote sensing videos acquired by video satellites in the “gaze” imaging mode
Summary
With the rapid development of aerospace technology and the gradual deepening of remote sensing applications, the demand for high-resolution satellite remote sensing applications has gradually shifted from static reconnaissance to real-time dynamic monitoring. Erefore, improving the intelligent processing level of the remote sensing video satellite multiobject detection and tracking algorithm can greatly reduce the degree of manual participation in the information extraction process, which could bring important promotion significance to the development aerospace information industry and social and economic progress. In this context, this paper focuses on video satellites, an emerging aerospace remote sensing technology, and performs fully automatic, high-precision, and high-speed information extraction of dynamic remote sensing videos acquired by video satellites in the “gaze” imaging mode. Aiming at the needs of satellite video moving target detection and tracking, this paper proposes a background subtraction method based on a hybrid Gaussian background model combined with a road mask. It has high accuracy and rich information in areas with large terrain undulations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
