Multicamera Video Stitching for Multiple Human Tracking | IGI Global Scientific Publishing
Welcome to the InfoSci Platform
Reference Hub1
Multicamera Video Stitching for Multiple Human Tracking

Multicamera Video Stitching for Multiple Human Tracking

S. Vasuhi, A. Samydurai, Vijayakumar M.
Copyright: © 2021 |Volume: 11 |Issue: 1 |Pages: 22
ISSN: 2155-6997|EISSN: 2155-6989|EISBN13: 9781799862024|DOI: 10.4018/IJCVIP.2021010102
Cite Article Cite Article

MLA

Vasuhi, S., et al. "Multicamera Video Stitching for Multiple Human Tracking." IJCVIP vol.11, no.1 2021: pp.17-38. https://doi.org/10.4018/IJCVIP.2021010102

APA

Vasuhi, S., Samydurai, A., & Vijayakumar M. (2021). Multicamera Video Stitching for Multiple Human Tracking. International Journal of Computer Vision and Image Processing (IJCVIP), 11(1), 17-38. https://doi.org/10.4018/IJCVIP.2021010102

Chicago

Vasuhi, S., A. Samydurai, and Vijayakumar M. "Multicamera Video Stitching for Multiple Human Tracking," International Journal of Computer Vision and Image Processing (IJCVIP) 11, no.1: 17-38. https://doi.org/10.4018/IJCVIP.2021010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this paper, a novel approach is proposed to track humans for video surveillance using multiple cameras and video stitching techniques. SIFT key points are extracted from all camera inputs. Using k-d tree algorithm, all the key points are matched and random sample consensus (RANSAC) is used to identify the match correspondence among all the matched points. Homography matrix is calculated using four matched robust feature correspondences, the images are warped with respect to the other images, and the human tracking is performed on the stitched image. To identify the human in the stitched video, background modeling is performed using fuzzy inference system and perform foreground extraction. After foreground extraction, the blobs are constructed around each detected human and centroid point is calculated for each blob. Finally, tracking of multiple humans is done by Kalman filter (KF) with Hungarian algorithm.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global Scientific Publishing bookstore.