A novel approach of multi-stage tracking for precise localization of target in video sequences. (15th July 2017)
- Record Type:
- Journal Article
- Title:
- A novel approach of multi-stage tracking for precise localization of target in video sequences. (15th July 2017)
- Main Title:
- A novel approach of multi-stage tracking for precise localization of target in video sequences
- Authors:
- Walia, Gurjit Singh
Raza, Saim
Gupta, Anjana
Asthana, Rajesh
Singh, Kuldeep - Abstract:
- Highlights: Proposed multi-stage tracker improves accuracy and reduces time complexity. Spatio-temporal model can handle various challenges of dynamic environments. Adaptive multicue fusion model effectively combines appearance models. Quick adaptation due to incorporation of context sensitive reliability. Robust and real time implementation. Abstract: Visual tracking methods are mostly based on single stage state estimation that limitedly caters to precise localization of target under dynamic environment such as occlusion, object deformation, rotation, scaling and cluttered background. In order to address these issues, we introduce a novel multi-stage coarse-to-fine tracking framework with quick adaptation to environment dynamics. The key idea of our work is to propose two-stage estimation of object state and to develop an adaptive fusion model. Coarse estimation of object state is achieved using optical flow and multiple fragments are generated around this approximation. Precise localization of object is obtained through evaluation of these fragments using three complementary cues. Adaptation of proposed tracker to dynamic environment changes is quick due to incorporation of context sensitive cue reliability, which encompass its direct application for development of expert system for video surveillance. In addition, proposed framework caters to object rotation and scaling through a random walk state model and rotation invariant features. The proposed tracker is evaluatedHighlights: Proposed multi-stage tracker improves accuracy and reduces time complexity. Spatio-temporal model can handle various challenges of dynamic environments. Adaptive multicue fusion model effectively combines appearance models. Quick adaptation due to incorporation of context sensitive reliability. Robust and real time implementation. Abstract: Visual tracking methods are mostly based on single stage state estimation that limitedly caters to precise localization of target under dynamic environment such as occlusion, object deformation, rotation, scaling and cluttered background. In order to address these issues, we introduce a novel multi-stage coarse-to-fine tracking framework with quick adaptation to environment dynamics. The key idea of our work is to propose two-stage estimation of object state and to develop an adaptive fusion model. Coarse estimation of object state is achieved using optical flow and multiple fragments are generated around this approximation. Precise localization of object is obtained through evaluation of these fragments using three complementary cues. Adaptation of proposed tracker to dynamic environment changes is quick due to incorporation of context sensitive cue reliability, which encompass its direct application for development of expert system for video surveillance. In addition, proposed framework caters to object rotation and scaling through a random walk state model and rotation invariant features. The proposed tracker is evaluated over eight- benchmarked color video sequences and competitive results are obtained. As an average of the outcomes, we achieved mean center location error (in pixels) of 6.791 and F-measure of 0.78. Results demonstrate that proposed tracker not only outperforms various state-of-the-art trackers but also effectively caters to various dynamic environments. … (more)
- Is Part Of:
- Expert systems with applications. Volume 78(2017)
- Journal:
- Expert systems with applications
- Issue:
- Volume 78(2017)
- Issue Display:
- Volume 78, Issue 2017 (2017)
- Year:
- 2017
- Volume:
- 78
- Issue:
- 2017
- Issue Sort Value:
- 2017-0078-2017-0000
- Page Start:
- 208
- Page End:
- 224
- Publication Date:
- 2017-07-15
- Subjects:
- Multicue -- Data fusion -- Object tracking -- Cue reliability
Expert systems (Computer science) -- Periodicals
Systèmes experts (Informatique) -- Périodiques
Electronic journals
006.33 - Journal URLs:
- http://www.sciencedirect.com/science/journal/09574174 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.eswa.2017.02.007 ↗
- Languages:
- English
- ISSNs:
- 0957-4174
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3842.004220
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 2757.xml