Object detection and tracking under Complex environment using deep learning‐based LPM
Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a co...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-03-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5129 |
| _version_ | 1797684244251672576 |
|---|---|
| author | Yundong Li Xueyan Zhang Hongguang Li Qichen Zhou Xianbin Cao Zhifeng Xiao |
| author_facet | Yundong Li Xueyan Zhang Hongguang Li Qichen Zhou Xianbin Cao Zhifeng Xiao |
| author_sort | Yundong Li |
| collection | DOAJ |
| description | Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)‐based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy. |
| first_indexed | 2024-03-12T00:27:50Z |
| format | Article |
| id | doaj.art-0bd3caf3d19c46d8a0d758d13e5be8eb |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:27:50Z |
| publishDate | 2019-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-0bd3caf3d19c46d8a0d758d13e5be8eb2023-09-15T10:31:50ZengWileyIET Computer Vision1751-96321751-96402019-03-0113215716410.1049/iet-cvi.2018.5129Object detection and tracking under Complex environment using deep learning‐based LPMYundong Li0Xueyan Zhang1Hongguang Li2Qichen Zhou3Xianbin Cao4Zhifeng Xiao5School of Electronic and Information EngineeringNorth China University of TechnologyBeijingPeople's Republic of ChinaSchool of Electronic and Information EngineeringNorth China University of TechnologyBeijingPeople's Republic of ChinaUnmanned Systems Research Institute, Beihang UniversityBeijingPeople's Republic of ChinaSchool of Electronic and Information EngineeringNorth China University of TechnologyBeijingPeople's Republic of ChinaSchool of Electronic and Information EngineeringBeihang UniversityBeijingPeople's Republic of ChinaState Key Laboratory of Information Engineering in SurveyingWuhan UniversityWuhanPeople's Republic of ChinaObject detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand‐crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)‐based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.https://doi.org/10.1049/iet-cvi.2018.5129histograms of oriented gradientscolour histogramsstacked denoising autoencodersMS tracking algorithmLPM-based mean shift algorithmlocal probability model |
| spellingShingle | Yundong Li Xueyan Zhang Hongguang Li Qichen Zhou Xianbin Cao Zhifeng Xiao Object detection and tracking under Complex environment using deep learning‐based LPM IET Computer Vision histograms of oriented gradients colour histograms stacked denoising autoencoders MS tracking algorithm LPM-based mean shift algorithm local probability model |
| title | Object detection and tracking under Complex environment using deep learning‐based LPM |
| title_full | Object detection and tracking under Complex environment using deep learning‐based LPM |
| title_fullStr | Object detection and tracking under Complex environment using deep learning‐based LPM |
| title_full_unstemmed | Object detection and tracking under Complex environment using deep learning‐based LPM |
| title_short | Object detection and tracking under Complex environment using deep learning‐based LPM |
| title_sort | object detection and tracking under complex environment using deep learning based lpm |
| topic | histograms of oriented gradients colour histograms stacked denoising autoencoders MS tracking algorithm LPM-based mean shift algorithm local probability model |
| url | https://doi.org/10.1049/iet-cvi.2018.5129 |
| work_keys_str_mv | AT yundongli objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm AT xueyanzhang objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm AT hongguangli objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm AT qichenzhou objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm AT xianbincao objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm AT zhifengxiao objectdetectionandtrackingundercomplexenvironmentusingdeeplearningbasedlpm |