Options
2013
Conference Paper
Titel
Utilizing temporal information in UAV surveillance videos for distant moving object recognition
Abstract
Image sequences contain more information than single images due to the temporal context. There are many potential benefits for the automatic analysis of especially distant moving objects in surveillance videos such as temporal noise reduction, track-before-detect, estimating motion information of the camera itself and objects in the scene, or acquiring different appearances of an object for classification. In this report, example approaches are presented for utilizing the temporal information to make the detection, segmentation, and classification of such objects more robust. Using real surveillance datasets, various algorithms for independent motion detection and moving object segmentation are presented and evaluated. Some ideas for considering temporal information for object classification are discussed in a conceptual manner.