Title :
Height measurements of moving people based on single camera
Author :
Jiang, Mingxin ; Mu, Fangshun ; Wang, Hongyu
Abstract :
This work presents a method for height measurements of moving objects based on rubust tracking. At first, we compute vanishing line of the ground plane and the vertical vanishing point using three vertical poles. Secondly, tracking of multiple people is performed by graph cuts. Then, the head feature points and the feet feature points are extracted in each frame of video sequences, and obtain height measurements of multiple objects according to the projective geometric constraint. Finally, the multiframe measurements are optimized using RANSAC algorithm. The experimental results demonstrate that our method is effective and also achieves real-time performance.
Keywords :
cameras; feature extraction; geometry; height measurement; image sequences; object tracking; RANSAC algorithm; feet feature point extraction; graph cut; ground plane vanishing line computation; head feature point extraction; height measurement; moving objects; multiframe measurement; multiple people tracking; projective geometric constraint; robust tracking; single camera; vertical pole; vertical vanishing point computation; video sequence frame; Bismuth; Computational modeling; Vectors; codebook; height measurements; projective geometric constraint; real-time performance;
Conference_Titel :
Awareness Science and Technology (iCAST), 2011 3rd International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4577-0887-9
DOI :
10.1109/ICAwST.2011.6163097
