Two-level superpixel and feedback based visual object tracking

Wang, Jun; Liu, Weibin; Xing, Weiwei; Zhang, Shunli

doi:10.1016/j.neucom.2017.06.031

Cited by 8 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the model drift problem, another paper [18] proposed an optimized tracking framework. There are also some papers [19]- [20] combined traditional algorithms with algorithms based on Correlation Filter. They have achieved good tracking results obviously.…”

Section: Related Workmentioning

confidence: 99%

A robust Correlation Filter based tracker with rich representation and a relocation component

2019

KSII TIIS

View full text Add to dashboard Cite

Correlation Filter was recently demonstrated to have good characteristics in the field of video object tracking. The advantages of Correlation Filter based trackers are reflected in the high accuracy and robustness it provides while maintaining a high speed. However, there are still some necessary improvements that should be made. First, most trackers cannot handle multi-scale problems. To solve this problem, our algorithm combines position estimation with scale estimation. The difference from the traditional method in regard to the scale estimation is that, the proposed method can track the scale of the object more quickly and effective. Additionally, in the feature extraction module, the feature representation of traditional algorithms is relatively simple, and furthermore, the tracking performance is easily affected in complex scenarios. In this paper, we design a novel and powerful feature that can significantly improve the tracking performance. Finally, traditional trackers often suffer from model drift, which is caused by occlusion and other complex scenarios. We introduce a relocation component to detect object at other locations such as the secondary peak of the response map. It partly alleviates the model drift problem.

show abstract

Section: Related Workmentioning

confidence: 99%

A robust Correlation Filter based tracker with rich representation and a relocation component

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…A superpixel based representation got much a ention by computer vision community for object recognition [17], human detection [120], activity recognition [163], and image segmentation [2]. Numerous tracking algorithms have been developed using superpixels [75,95,154,155,167].…”

Section: Superpixel Basedmentioning

confidence: 99%

“…Optical ow is used for the temporal smoothness to impose short-term target appearance, while appearance tness servers as long-term appearance model to enforce objectness. Wang et al [154] presented a Bayesian tracking method at coarse-level and ne-level superpixel appearance model. e coarse-level appearance model computes few superpixels such that there is only one superpixel in the target bounding box, and a con dence measure de nes whether that superpixel corresponds to background/target.…”

Section: Superpixel Basedmentioning

confidence: 99%

Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends

Fiaz¹,

Mahmood²,

Javed³

et al. 2018

Preprint

View full text Add to dashboard Cite

In recent years visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year. It is because tracking has wide applications in various real world problems such as humancomputer interaction, autonomous vehicles, robotics, surveillance and security just to name a few. In the current study, we review latest trends and advances in the tracking area and evaluate the robustness of di erent trackers based on the feature extraction methods. e rst part of this work comprises a comprehensive survey of the recently proposed trackers. We broadly categorize trackers into Correlation Filter based Trackers (CFTs) and Non-CFTs. Each category is further classi ed into various types based on the architecture and the tracking mechanism. In the second part, we experimentally evaluated 24 recent trackers for robustness, and compared handcra ed and deep feature based trackers. We observe that trackers using deep features performed be er, though in some cases a fusion of both increased performance signi cantly. In order to overcome the drawbacks of the existing benchmarks, a new benchmark Object Tracking and Temple Color (OTTC) has also been proposed and used in the evaluation of di erent algorithms. We analyze the performance of trackers over eleven di erent challenges in OTTC, and three other benchmarks. Our study concludes that Discriminative Correlation Filter (DCF) based trackers perform be er than the others. Our study also reveals that inclusion of di erent types of regularizations over DCF o en results in boosted tracking performance. Finally, we sum up our study by pointing out some insights and indicating future trends in visual object tracking eld.

show abstract

“…As the term "superpixel" suggests, it meets the goal of representing an image by perceptually meaningful entitieswhich heavily reduces the number of pixels. This is why superpixels can significantly improve the efficiency of segmentation in practice and become a key preprocessing step for advanced tasks such as video segmentation [2], target tracking [3], object recognition [4], super-resolution [5] and depth estimation [6].…”

Section: Introductionmentioning

confidence: 99%

A Two-Stage Gradient Ascent-Based Superpixel Framework for Adaptive Segmentation

Guo

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Superpixel segmentation usually over-segments an image into fragments to extract regional features, thus linking up advanced computer vision tasks. In this work, a novel coarse-to-fine gradient ascent framework is proposed for superpixel-based color image adaptive segmentation. In the first stage, a speeded-up Simple Linear Iterative Clustering (sSLIC) method is adopted to generate uniform superpixels efficiently, which assumes that homogeneous regions preserve high consistence during clustering, consequently, much redundant computation for updating can be avoided. Then a simple criterion is introduced to evaluate the uniformity in each superpixel region, once a superpixel region is under-segmented, an adaptive marker-controlled watershed algorithm processes a finer subdivision. Experimental results show that the framework achieves better performance on detail-rich regions than previous superpixel approaches with satisfactory efficiency.

show abstract

Two-level superpixel and feedback based visual object tracking

Cited by 8 publications

References 26 publications

A robust Correlation Filter based tracker with rich representation and a relocation component

A robust Correlation Filter based tracker with rich representation and a relocation component

Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends

A Two-Stage Gradient Ascent-Based Superpixel Framework for Adaptive Segmentation

Contact Info

Product

Resources

About