Robust object tracking based on local region sparse appearance model

Han, Guang; Wang, Xingyue; Liu, Jixin; Sun, Ning; Wang, Cailing

doi:10.1016/j.neucom.2015.07.122

Cited by 24 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where 𝑤 and 𝑢 are patches numbers in the row and column orientation. The weighting rule for the small-scale patch group is similar to the equation (12). Ultimately, the final weighted pooled features should be integrated together to form likelihood of target candidate.…”

Section: A Appearance Modelmentioning

confidence: 99%

See 1 more Smart Citation

Patchwise object tracking via structural local sparse appearance model

Kashiyani¹,

Shokouhi²

2017

2017 7th International Conference on Computer and Knowledge Engineering (ICCKE)

View full text Add to dashboard Cite

In this paper, we propose a robust visual tracking method which exploits the relationships of targets in adjacent frames using patchwise joint sparse representation. Two sets of overlapping patches with different sizes are extracted from target candidates to construct two dictionaries with consideration of joint sparse representation. By applying this representation into structural sparse appearance model, we can take two-fold advantages. First, the correlation of target patches over time is considered. Second, using this local appearance model with different patch sizes takes into account local features of target thoroughly. Furthermore, the position of candidate patches and their occlusion levels are utilized simultaneously to obtain the final likelihood of target candidates. Evaluations on recent challenging benchmark show that our tracking method outperforms the state-of-the-art trackers.

show abstract

Section: A Appearance Modelmentioning

confidence: 99%

“…Then, the likelihood of candidate is computed by incorporating two dictionaries. In [12], Han et al utilize spatial information of target using dictionaries which are obtained by clustering local patches. To enhance the performance of tracker, occluded patches are eliminated using mask histogram.…”

Section: Introductionmentioning

confidence: 99%

Patchwise object tracking via structural local sparse appearance model

Kashiyani¹,

Shokouhi²

2017

2017 7th International Conference on Computer and Knowledge Engineering (ICCKE)

View full text Add to dashboard Cite

show abstract

“…Currently, sparse representation (SR) based tracking methods have gained substantial interest [14][15][16]. Its main idea is that, for current frame, object candidates are sparsely represented and that having the lowest reconstruction error is thought to be the real target [17][18][19]. Many works have shown the effectiveness of such methods, but there still exist two critical problems.…”

Section: Introductionmentioning

confidence: 99%

Multi-feature local sparse representation for infrared pedestrian tracking

2019

KSII TIIS

View full text Add to dashboard Cite

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

show abstract

“…for example, mutilation, turn and scaling [13]. These may bring about confuse or lose object amid tracking and lessen the precision of tracker [14]. Visual tracking is planned as an online twofold characterization issue and the objective appearance designs are overhauled adaptively utilizing the pictures tracked from the past casings [15].…”

Section: Introductionmentioning

confidence: 99%

Similar Object Detection and Tracking in H.264 Compressed Video Using Modified Local Self Similarity Descriptor and Particle Filtering

Kuppuswamy¹,

Panchanathan²

2017

IJIES

View full text Add to dashboard Cite

Abstract:Object tracking is a dynamic optimization process based on the temporal information related to the previous frames. Proposing a method with higher precision in complex environments is a challenge for researchers in the field of study. In this paper, we have proposed a novel framework for similar object tracking. In our proposed technique we are considering both PETS and Cricket video for input video sequence. The primary steps of suggested technique are preprocessing, background subtraction and segmentation, similar object detection and object tracking. In the preprocessing stage, the adaptive median filter is used to remove the noise from each frame. Next, the foreground and background images are separated and then segmentation of object is carried out by using morphological operation. For similar object detection, the recommended technique uses the modified local self-similarity descriptor and similar object tracking is done by a particle filter. The performance of the suggested technique is evaluated by means of precision, recall, F-measure, FPR, FNR, PWC, FAR, similarity, specificity, and accuracy. An experimental result shows that the proposed technique attains the maximum tracking efficiency for both videos when compared to the existing techniques.

show abstract

Robust object tracking based on local region sparse appearance model

Cited by 24 publications

References 41 publications

Patchwise object tracking via structural local sparse appearance model

Patchwise object tracking via structural local sparse appearance model

Multi-feature local sparse representation for infrared pedestrian tracking

Similar Object Detection and Tracking in H.264 Compressed Video Using Modified Local Self Similarity Descriptor and Particle Filtering

Contact Info

Product

Resources

About