Open Access
A homography-based multiple-camera person-tracking algorithm
Matthew R obert Turk
- 01 Jan 2008
TL;DR: Testing shows that the algorithm solves the consistent labelling problem and requires few edge events as part of the learning process, and the homography-based matcher was shown to completely overcome partial and full target occlusions in one of a pair of cameras.
read more
Abstract: It is easy to install multiple inexpensive video surveillance cameras around an area. However, multiple-camera tracking is still a developing field. Surveillance products that can be produced with multiple video cameras include camera cueing, wide-area traffic analysis, tracking in the presence of occlusions, and tracking with in-scene entrances. All of these products require solving the consistent labelling problem. This means giving the same meta-target tracking label to all projections of a realworld target in the various cameras. This thesis covers the implementation and testing of a multiple-camera peopletracking algorithm. First, a shape-matching single-camera tracking algorithm was partially re-implemented so that it worked on test videos. The outputs of the single-camera trackers are the inputs of the multiple-camera tracker. The algorithm finds the feet feature of each target: a pixel corresponding to a point on a ground plane directly below the target. Field of view lines are found and used to create initial meta-target associations. Meta-targets then drop a series of markers as they move, and from these a homography is calculated. The homographybased tracker then refines the list of meta-targets and creates new meta-targets as required. Testing shows that the algorithm solves the consistent labelling problem and requires few edge events as part of the learning process. The homography-based matcher was shown to completely overcome partial and full target occlusions in one of a pair of cameras.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multiple camera-based codebooks for object detection under sudden illumination change
T. Malathi,Manas Kamal Bhuyan +1 more
- 03 Apr 2013
TL;DR: Experimental results show that the proposed foreground segmentation method gives better performance compared to the single camera-based counterparts and other conventional approaches, and is also robust to shadows.
4
•Dissertation
Exploiting Inertial Planes for Multi-sensor 3D Data Registration
Hadi Ali Akbarpour
- 22 Nov 2012
TL;DR: Tese de doutoramento em Engenharia Eletrotecnica e de Computadores, no ramo de especializacao em Automacao e Robotica, apresentada a Faculdade de Ciencias e Engenhartia da Universidade de Coimbra as discussed by the authors
2
Foreground object detection under camouflage using multiple camera-based codebooks
T. Malathi,Manas Kamal Bhuyan +1 more
- 01 Dec 2013
TL;DR: This paper presents a multiple camera-based object detection method under camouflage i.e., when the background color is almost similar to the foreground color, which is quite robust to camouflage.
References
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Multiple View Geometry in Computer Vision.
Bernhard P. Wrobel
- 01 Jan 2001
TL;DR: This book is referred to read because it is an inspiring book to give you more chance to get experiences and also thoughts and it will show the best book collections and completed collections.
14.2K
Object tracking: A survey
TL;DR: The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends to discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
Kernel-based object tracking
TL;DR: A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed, which employs a metric derived from the Bhattacharyya coefficient as similarity measure, and uses the mean shift procedure to perform the optimization.
Detecting moving objects, ghosts, and shadows in video streams
TL;DR: A general-purpose method is proposed that combines statistical assumptions with the object-level knowledge of moving objects, apparent objects (ghosts), and shadows acquired in the processing of the previous frames to improve object segmentation and background update.