Open Access Open Access  Restricted Access Subscription or Fee Access

An Algorithm for Human Motion Detecting and Tracking

Yang Shun, Long Xian’ai, Peng Hao

Abstract


In this thesis, the system of intelligent monitoring pedestrian and tracking is designed. In order to improve speed and accuracy in detecting and tracking, an algorithm for human detecting and tracking is proposed. For pedestrian detection, the algorithm uses a kind of intelligent monitoring; for tracking use the Mean Shift and Cam Shift method. At first, extract the figure characters in the motion scene about model in mixed Gaussian background, then pedestrian detection based on HOG character; at last, track the result of detection based on Mean Shift and Cam Shift method. The algorithm is the key to change with the size of the target, and adaptively adjust the tracking frame to track. The experiment verified that by single pedestrians’ image, images sequence library and real-time video to test system, the system realized the people detection accuracy is higher than 100% under complicated background. It achieves a single pedestrian tracking in video and ensures pedestrian tracking box to cover objectives range greater than 95%.

Keywords


Gaussian mixture background model, pedestrian detection, HOG features, pedestrian tracking.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.