Autonomous Selective Parts-Based Tracking

Journal Article · Thu Jan 23 00:00:00 EST 2020 · IEEE Transactions on Image Processing

DOI:https://doi.org/10.1109/tip.2020.2967580· OSTI ID:1799122

Cornacchia, Maria ^[1]; Velipasalar, Senem ^[2]

---

1. Syracuse Univ., NY (United States); Syracuse Univ., NY (United States)
2. Syracuse Univ., NY (United States)

Object tracking from videos is still a challenging task due to various changes throughout a video sequence including occlusions, motion blur, scale and other deformation changes. In this paper, we propose a selective parts-based approach, using correlation filters, that makes choices based on a consensus of the parts and global tracking. Moreover, we further enhance our parts-based approach by introducing a segmentation-assisted parts initialization. In addition, we present a genetic algorithm-based method to autonomously select various parameters of the tracking algorithm, as opposed to the common practice of manually tuning those parameters. In contrast to existing part-based methods, the proposed method does not dilute accurate tracking by averaging results over multiple parts at every frame. Instead, we take a selective approach based on the relative weight of the responses across parts. Moreover, we only make location corrections when a part diverges, and rely on these location corrections to maintain an accurate appearance model. In the case of occlusions, which are among the main reasons for using a parts-based approach, our proposed approach consistently achieves the best performance. It is due to the ability to handle occlusion and not dilute decisions with incorrect parts, that our proposed approach enables state-of-the-art performance. The approach we propose was evaluated on videos from three different challenging benchmark datasets. Our approach has resulted in better overall precision and success rates for three different base tracking approaches.

• Research Organization: Syracuse Univ., NY (United States)
• Sponsoring Organization: USDOE Advanced Research Projects Agency - Energy (ARPA-E)
• Grant/Contract Number: AR0000940
• OSTI ID: 1799122
• Journal Information: IEEE Transactions on Image Processing, Journal Name: IEEE Transactions on Image Processing Vol. 29; ISSN 1057-7149
• Publisher: IEEE
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
Correlation
Correlation filters
Genetic algorithm
Genetic algorithms
Neural networks
Parts-based
Target tracking
Tracking
Training
Video
Videos