Soft Mask Correlation Filter for Visual Object Tracking

Huo, Yang; Wang, Yuehuan; Yan, Xiaoyun; Dai, Kaiheng

doi:10.1109/icip.2018.8451607

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huo et al. [ 39 ] proposed a soft mask correlation filter, which exploits a soft mask to pay attention to the target patch and crop the area around the target by applying a mask value of zero. Compared with [ 36 ], the background-suppressed module in our work obtains the sample directly in the current frame without padding zeros in the target area.…”

Section: Related Workmentioning

confidence: 99%

“…However, in BSCF, the target appearance model and background sample need to be updated separately. Compared with [ 37 , 38 , 39 ], our method does not choose the way that removes the background information in [ 37 ], sets the pixels of the background away from the target to zero and crops the target area for training model in [ 38 , 39 ]. By contrast, we apply low and high weights on the area of the target and background with the proposed matrix for learning the filter.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Response-Consistent and Background-Suppressed Correlation Filters for Real-Time UAV Tracking

Zhang

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

With the advantages of discriminative correlation filter (DCF) in tracking accuracy and computational efficiency, the DCF-based methods have been widely used in the field of unmanned aerial vehicles (UAV) for target tracking. However, UAV tracking inevitably encounters various challenging scenarios, such as background clutter, similar target, partial/full occlusion, fast motion, etc. These challenges generally lead to multi-peak interferences in the response map that cause the target drift or even loss. To tackle this problem, a response-consistent and background-suppressed correlation filter is proposed for UAV tracking. First, a response-consistent module is developed, in which two response maps are generated by the filter and the features extracted from adjacent frames. Then, these two responses are kept to be consistent with the response from the previous frame. By utilizing the l2-norm constraint for consistency, this module not only can avoid sudden changes of the target response caused by background interferences but also enables the learned filter to preserve the discriminative ability of the previous filter. Second, a novel background-suppressed module is proposed, which makes the learned filter to be more aware of background information by using an attention mask matrix. With the introduction of this module into the DCF framework, the proposed method can further suppress the response interferences of distractors in the background. Finally, extensive comparative experiments have been conducted on three challenging UAV benchmarks, including UAV123@10fps, DTB70 and UAVDT. Experimental results have proved that our tracker has better tracking performance compared with 22 other state-of-the-art trackers. Moreover, our proposed tracker can run at ∼36 FPS on a single CPU for real-time UAV tracking.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Learning Response-Consistent and Background-Suppressed Correlation Filters for Real-Time UAV Tracking

Zhang

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This tracker performs poorly at background clutters. Huo et al (2018): They propose a soft mask correlation filter (SMCF) to deal with the boundary effects to perform better at background clutters. The soft mask describes the spatial reliability of the target and enables the correlation filter to pay more attention to the center part of the target.…”

Section: Introductionmentioning

confidence: 99%

An experimental study on visual tracking based on deep learning

PVN

2021

IJIUS

View full text Add to dashboard Cite

PurposeIn the community of visual tracking or object tracking, discriminatively learned correlation filter (DCF) has gained more importance. When it comes to speed, DCF gives the best performance. The main objective of this study is to anticipate the object visually. For tracking the object visually, the authors proposed a new model based on the convolutional regression technique. Features like HOG & Harris are used for the process of feature extraction. The proposed method will give the best results when compared to other existing methods.Design/methodology/approachThis paper introduces the concept and research status of tracks; later the authors focus on the representative applications of deep learning in visual tracking.FindingsBetter tracking algorithms are not mentioned in the existing method.Research limitations/implicationsVisual tracking is the ability to control eye movements using the oculomotor system (vision and eye muscles working together). Visual tracking plays an important role when it comes to identifying an object and matching it with the database images. In visual tracking, deep learning has achieved great success.Practical implicationsThe authors implement the multiple tracking methods, for better tracking purpose.Originality/valueThe main theme of this paper is to review the state-of-the-art tracking methods depending on deep learning. First, we introduce the visual tracking that is carried out manually, and secondly, we studied different existing methods of visual tracking based on deep learning. For every paper, we explained the analysis and drawbacks of that tracking method. This paper introduces the concept and research status of tracks, later we focus on the representative applications of deep learning in visual tracking.

show abstract

Detection of safety wearable’s of the industry workers using deep neural network

Balaji

Srinivasan

2023

Materials Today: Proceedings

View full text Add to dashboard Cite

Soft Mask Correlation Filter for Visual Object Tracking

Cited by 4 publications

References 15 publications

Learning Response-Consistent and Background-Suppressed Correlation Filters for Real-Time UAV Tracking

Learning Response-Consistent and Background-Suppressed Correlation Filters for Real-Time UAV Tracking

An experimental study on visual tracking based on deep learning

Detection of safety wearable’s of the industry workers using deep neural network

Contact Info

Product

Resources

About