Improved GMM‐based method for target detection. Issue 1 (1st January 2020)

• Record Type: Journal Article
• Authors: Zhao, Juan; Xie, Guihui; Li, Dongming; Song, Mailing
• Is Part Of: IET networks. Volume 9:Issue 1(2020)
• Page Start: 7
• Page End: 11
• Publication Date: 2020-01-01
• Subjects: principal component analysis -- object detection -- feature extraction -- Gaussian processes -- image colour analysis; mean difference -- pixel features -- red HSV colour models -- green HSV colour models -- blue HSV colour models -- similar‐coloured components -- similar‐coloured background -- target areas -- detection‐accuracy improvement -- improved GMM‐based method -- target detection -- Gaussian mixture model -- large‐scale misdetection -- static case -- improved GMM method -- principal component analysis -- high‐dimensional space -- colour channels -- foreground areas; Computer network architectures -- Periodicals; Computer network protocols -- Periodicals; Information networks -- Periodicals; Telecommunication systems -- Periodicals; 004.605
• DOI: 10.1049/iet-net.2019.0038
• Languages: English
• ISSNs: 2047-4954

Abstract

Abstract : The Gaussian mixture model (GMM) is prone to large‐scale misdetection in the static case where the background and foreground have similar colours. This study presents an improved GMM method to solve this problem. First, the principal component analysis is used to transform the high‐dimensional space into the low‐dimensional one with three colour channels, which aims to reduce runtime. Then, the images are processed by GMM to obtain the foreground areas. At the same time, the mean and difference of pixel features in red, green and blue and hue, saturation and value (HSV) colour models are calculated to analyse the similar‐coloured components. The areas with similar colours are classified in this process, and thus the foreground is separated from similar‐coloured background. Then, all of the extracted areas are targets. The experimental results show that the presented method identified the target areas with high accuracy and high efficiency. Compared with conventional GMM, the presented method obtained the detection‐accuracy improvement by about 6% on average.