Journal ArticleDOI
Correlation-Based Tracker-Level Fusion for Robust Visual Tracking
Madan Kumar Rapuru,Sumithra Kakanuru,Pallavi M. Venugopal,Deepak Mishra,Gorthi R. K. Sai Subrahmanyam +4 more
TLDR
A novel robust tracking algorithm is proposed by fusing the frame level detection strategy of tracking, learning, & detection with the systematic model update strategy of Kernelized Correlation Filter tracker, which takes advantages of both and outperforms them on their short ends by virtue of other.Abstract:
Although visual object tracking algorithms are capable of handling various challenging scenarios individually, none of them are robust enough to handle all the challenges simultaneously. For any online tracking by detection method, the key issue lies in detecting the target over the whole frame and updating systematically a target model based on the last detected appearance to avoid the drift phenomenon. This paper aims at proposing a novel robust tracking algorithm by fusing the frame level detection strategy of tracking, learning, & detection with the systematic model update strategy of Kernelized Correlation Filter tracker. The risk of drift is mitigated by the fact that the model updates are primarily driven by the detections that occur in the spatial neighborhood of the latest detections. The motivation behind the selection of trackers is their complementary nature in handling tracking challenges. The proposed algorithm efficiently combines the two state-of-the-art tracking algorithms based on conservative correspondence measure with strategic model updates, which takes advantages of both and outperforms them on their short ends by virtue of other. Extensive evaluation of the proposed method based on different metrics is carried out on the data sets ALOV300++, Visual Tracker Benchmark, and Visual Object Tracking. We demonstrated its performance in terms of robustness and success rate by comparing with state-of-the-art trackers.read more
Citations
More filters
Journal ArticleDOI
Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
TL;DR: This study concludes that Discriminative Correlation Filter (DCF) based trackers perform better than the others and reveals that inclusion of different types of regularizations over DCF often results in boosted tracking performance.
Patent
Tracking-learning-detection (TLD)-based video object tracking method
TL;DR: According to the method, the conventional TLD algorithm is improved to obtain a video object tracking algorithm which is more ideal than the T LD algorithm.
Journal ArticleDOI
Discriminative Fusion Correlation Learning for Visible and Infrared Tracking
TL;DR: The proposed discriminative filter selection model considers the surrounding background information in order to increase the discriminability of the template filters so as to improve model learning and achieves superior performances in challenging visible and infrared tracking tasks.
Posted Content
Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
TL;DR: This study concludes that Discriminative Correlation Filter (DCF) based trackers perform better than the others, and reveals that inclusion of different types of regularizations over DCF often results in boosted tracking performance.
Posted Content
Handcrafted and Deep Trackers: A Review of Recent Object Tracking Approaches.
TL;DR: This study concludes that Discriminative Correlation Filter (DCF) based trackers perform better than the others, and reveals that inclusion of different types of regularizations over DCF often results in boosted tracking performance.
References
More filters
Proceedings Article
Minimum error bounded efficient ℓ1 tracker with occlusion detection.
TL;DR: In this paper, the authors proposed a Bounded Particle Resampling (BPR)-L1 tracker, where the minimum error bound is calculated from a linear least squares equation, and serves as a guide for particle resampling in a particle filter framework.
Proceedings ArticleDOI
Average of Synthetic Exact Filters
TL;DR: A class of correlation filters called average of synthetic exact filters (ASEF), which is in marked contrast to prior methods such as synthetic discriminant functions (SDFs) which only specify a single output value per training image, is introduced.
Journal ArticleDOI
Robust Visual Tracking Using Local Sparse Appearance Model and K-Selection
TL;DR: This work has developed a robust tracking algorithm using a local sparse appearance model (SPT) and a locally constrained sparse representation, called K-Selection, which has demonstrated better performance than alternatives reported in the recent literature.
Patent
Tracking-learning-detection (TLD)-based video object tracking method
TL;DR: According to the method, the conventional TLD algorithm is improved to obtain a video object tracking algorithm which is more ideal than the T LD algorithm.
Book ChapterDOI
Color invariant SURF in discriminative object tracking
TL;DR: This paper proposes to use color invariant SURF features in the discriminative tracking framework, showing this set of invariant features has been shown to be of increased invariance and discrim inative power.