Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking
As one of the core contents of intelligent monitoring, target tracking is the basis for video content analysis and processing. In visual tracking, due to occlusion, illumination changes, and pose and scale variation, handling such large appearance changes of the target object and the background over...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-11-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/7/11/1059 |
id |
doaj-331202a8b0ea4e9f8195d6f89d487b98 |
---|---|
record_format |
Article |
spelling |
doaj-331202a8b0ea4e9f8195d6f89d487b982020-11-25T01:48:11ZengMDPI AGMathematics2227-73902019-11-01711105910.3390/math7111059math7111059Combining Spatio-Temporal Context and Kalman Filtering for Visual TrackingHaoran Yang0Juanjuan Wang1Yi Miao2Yulu Yang3Zengshun Zhao4Zhigang Wang5Qian Sun6Dapeng Oliver Wu7College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaKey Laboratory of Computer Vision and System, Ministry of Education, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaDepartment of Electrical& Computer Engineering, University of Florida, Gainesville, FL 32611, USAAs one of the core contents of intelligent monitoring, target tracking is the basis for video content analysis and processing. In visual tracking, due to occlusion, illumination changes, and pose and scale variation, handling such large appearance changes of the target object and the background over time remains the main challenge for robust target tracking. In this paper, we present a new robust algorithm (STC-KF) based on the spatio-temporal context and Kalman filtering. Our approach introduces a novel formulation to address the context information, which adopts the entire local information around the target, thereby preventing the remaining important context information related to the target from being lost by only using the rare key point information. The state of the object in the tracking process can be determined by the Euclidean distance of the image intensity in two consecutive frames. Then, the prediction value of the Kalman filter can be updated as the Kalman observation to the object position and marked on the next frame. The performance of the proposed STC-KF algorithm is evaluated and compared with the original STC algorithm. The experimental results using benchmark sequences imply that the proposed method outperforms the original STC algorithm under the conditions of heavy occlusion and large appearance changes.https://www.mdpi.com/2227-7390/7/11/1059spatio-temporal context algorithmkalman filterobject detectiontarget tracking |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Haoran Yang Juanjuan Wang Yi Miao Yulu Yang Zengshun Zhao Zhigang Wang Qian Sun Dapeng Oliver Wu |
spellingShingle |
Haoran Yang Juanjuan Wang Yi Miao Yulu Yang Zengshun Zhao Zhigang Wang Qian Sun Dapeng Oliver Wu Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking Mathematics spatio-temporal context algorithm kalman filter object detection target tracking |
author_facet |
Haoran Yang Juanjuan Wang Yi Miao Yulu Yang Zengshun Zhao Zhigang Wang Qian Sun Dapeng Oliver Wu |
author_sort |
Haoran Yang |
title |
Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking |
title_short |
Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking |
title_full |
Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking |
title_fullStr |
Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking |
title_full_unstemmed |
Combining Spatio-Temporal Context and Kalman Filtering for Visual Tracking |
title_sort |
combining spatio-temporal context and kalman filtering for visual tracking |
publisher |
MDPI AG |
series |
Mathematics |
issn |
2227-7390 |
publishDate |
2019-11-01 |
description |
As one of the core contents of intelligent monitoring, target tracking is the basis for video content analysis and processing. In visual tracking, due to occlusion, illumination changes, and pose and scale variation, handling such large appearance changes of the target object and the background over time remains the main challenge for robust target tracking. In this paper, we present a new robust algorithm (STC-KF) based on the spatio-temporal context and Kalman filtering. Our approach introduces a novel formulation to address the context information, which adopts the entire local information around the target, thereby preventing the remaining important context information related to the target from being lost by only using the rare key point information. The state of the object in the tracking process can be determined by the Euclidean distance of the image intensity in two consecutive frames. Then, the prediction value of the Kalman filter can be updated as the Kalman observation to the object position and marked on the next frame. The performance of the proposed STC-KF algorithm is evaluated and compared with the original STC algorithm. The experimental results using benchmark sequences imply that the proposed method outperforms the original STC algorithm under the conditions of heavy occlusion and large appearance changes. |
topic |
spatio-temporal context algorithm kalman filter object detection target tracking |
url |
https://www.mdpi.com/2227-7390/7/11/1059 |
work_keys_str_mv |
AT haoranyang combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT juanjuanwang combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT yimiao combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT yuluyang combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT zengshunzhao combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT zhigangwang combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT qiansun combiningspatiotemporalcontextandkalmanfilteringforvisualtracking AT dapengoliverwu combiningspatiotemporalcontextandkalmanfilteringforvisualtracking |
_version_ |
1725012347699855360 |