Parametric Tracking Across Multiple Cameras with Spatial Estimation. Issue 2 (17th February 2023)

• Record Type: Journal Article
• Authors: Sebastian, Patrick; Vooi Voon, Yap; Comley, Richard
• Is Part Of: IETE journal of research. Volume 69:Issue 2(2023)
• Page Start: 839
• Page End: 853
• Publication Date: 2023-02-17
• Subjects: Blob -- Multiple cameras -- Parametric tracking -- Surveillance -- Tracking -- Video; Electronics -- Periodicals; Telecommunication -- Periodicals; Electronics; Telecommunication; Periodicals; 621.38
• DOI: 10.1080/03772063.2020.1844065
• Languages: English
• ISSNs: 0377-2063

Abstract

Abstract : This paper presents a method of tracking a target based on the combination of parameters between colour blobs. Apart from tracking targets based on parameters between colour regions, the blob parameters can be used as a means for estimating the spatial location of the target relative to the location of the cameras. The blobs are obtained by segmenting the overall target into multiple colour regions. The colour regions are segmented using the EM method. After segmentation into different regions on different colour layers, parameters can be generated between colour regions of interest. In this instance, the colour regions of interest are the top and bottom colour regions. Parameters between colour regions of interest were the vector magnitude, vector angle and the value difference between colour regions. These parameters are used for tracking the target of interest across an array of cameras which in this instance are three cameras. The summarized results of tracking targets across three cameras have shown that parameters between colour regions have the capability to track targets across cameras. In addition to tracking targets across multiple cameras, the work presented in this paper also shows the capability of estimating spatial information based on tracking of targets as it moves across different camera view fields. The spatial information that can be estimated from an array of cameras with non-overlapping view fields is distance estimation of the target from camera and distance estimation between cameras.