Anti‐occlusion particle filter object‐tracking method based on feature fusion

Huan, Ruohong; Bao, Sheng-Lin; Wang, Chu; Pan, Yun

doi:10.1049/iet-ipr.2017.1068

Cited by 12 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu [4] proposed particle filter tracking with HOG feature model to detect occlusion and predict the location after occlusion. Huan [5] proposed a sub-blocks based appearance model with the texture feature and discrete object area from background region. Elafi [6] proposed a chromatic co-occurrence matrix to rebuild the RGB appearance model with particles in patches in the occlusion handling.…”

Section: Introductionmentioning

confidence: 99%

Position reset and hybrid feature based particle filter tracking for large-size and long-term full occlusion

CAO

CHENG

LIU

et al. 2023

Third International Conference on Computer Vision and Information Technology (CVIT 2022)

View full text Add to dashboard Cite

Object tracking plays an important role in the computer vision field and has many applications such as video surveillance and vehicle navigation. But the occlusion problem is one of the most challenging problems in the applications. Although there are many approaches in the object tracking field that focus on dealing with occlusion scenes, the occlusion with large size barriers and long occlusion time still cannot be solved. To handle the problems, this paper proposes a reliable tracking method based on particle filter focus on long-term full occlusion with large size barriers. In this paper the large size is defined as pixel width from 350 to 600 in fixed resolution images. and the long term is defined as occlusion frame number from 180 to 600. First, this paper proposed a particle position reset module to replace the resampling process during the occlusion periods to solve the problem of losing the target after occlusion. In addition, a hybrid feature based likelihood model is proposed for the occlusion happening and ending judgments. Experiments on the extreme occlusion situation sequences demonstrate the reliability and accuracy of the proposed work on these challenging scenes. The algorithm finally implements the average 92% success rate at the tested sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Position reset and hybrid feature based particle filter tracking for large-size and long-term full occlusion

CAO

CHENG

LIU

et al. 2023

Third International Conference on Computer Vision and Information Technology (CVIT 2022)

View full text Add to dashboard Cite

show abstract

“…It has been observed that particle filter in feature space provides a clear understanding and effective analysis of the target object in a scene. Hence, feature based particle filter algorithms [7][8][9] are preferred to other algorithms. Further, it has been reported in the literature that single feature based object models in particle filters such as color feature based particle filters [22][23][24], edge feature based particle filter [25], motion feature based particle filter [26][27][28], appearance feature based particle filter [29,30], entropy feature based particle filter [31,32] could handle one or two typical issues of the scene during tracking and have achieved good tracking accuracy in initial frames.…”

Section: Introductionmentioning

confidence: 99%

“…Based on different issues of the scene complexity, different methods of tracking have been proposed in literature such as feature-based tracking [7][8][9][10], model-based tracking [11][12][13][14][15][16][17], region-based tracking [18], and deformable template-based tracking [19][20][21]. It has been observed that particle filter in feature space provides a clear understanding and effective analysis of the target object in a scene.…”

Section: Introductionmentioning

confidence: 99%

Particle Filter Based Video Object Tracking Scheme With Target Remodeling and Reinitialization and its Hardware Implementation Using Raspberry Pi

Panda

Nanda

Pradhan

2023

Preprint

View full text Add to dashboard Cite

Video object tracking in real-world scenarios is one of the challenging problems of computer vision. The issue is compounded in the presence of varying illumination conditions, dynamic entities of the background, and bad weather conditions. In this research, a particle filter based new video object tracking scheme is developed with the proposed notions of target remodeling and reinitialization. During the tracking phase, the target is remodeled in each frame to take care of the changing scene dynamics over frames. The target is remodeled by fused feature distributions chosen from the created bank of fused feature distributions having discriminating potential to differentiate the target and the background in a given frame. The fused feature bank is created by fusing two features from the set consisting of Color, LBP, and HOG features. The features are fused probabilistically where the weights are determined based on the discriminating ability of a given feature. In order to achieve high tracking accuracy, the deviation of the tracker is evaluated ineach frame using the notion of time motion history and reinitialization of the tracker position takes place when the deviation is above a preselected threshold. Besides, the proposed algorithm has been implemented successfully on a Raspberry Pi based hardware setup and thus becomes a potential candidate for real time implementation. The proposed scheme is successfully tested on videos from DAVIS 2016, LASIESTA, and CDnet 2014 databases and the tracking accuracy is found to be higher than those of the existing algorithms.

show abstract

“…The occlusion mentioned in this article means a short-term occlusion caused by motion. Some traditional methods (Huan et al, 2018;Radmard et al, 2018;Ren and Hao, 2012;Tang and Zhang, 2011) simplify the target into some feature points to establish its motion law. This type of method can be adapted to scenes with no occlusion or less occlusion.…”

Section: Introductionmentioning

confidence: 99%

Predictive visual control network for occlusion solution in human-following robot

Zou

2021

View full text Add to dashboard Cite

Purpose The purpose of this paper is to propose a new video prediction-based methodology to solve the manufactural occlusion problem, which causes the loss of input images and uncertain controller parameters for the robot visual servo control. Design/methodology/approach This paper has put forward a method that can simultaneously generate images and controller parameter increments. Then, this paper also introduced target segmentation and designed a new comprehensive loss. Finally, this paper combines offline training to generate images and online training to generate controller parameter increments. Findings The data set experiments to prove that this method is better than the other four methods, and it can better restore the occluded situation of the human body in six manufactural scenarios. The simulation experiment proves that it can simultaneously generate image and controller parameter variations to improve the position accuracy of tracking under occlusions in manufacture. Originality/value The proposed method can effectively solve the occlusion problem in visual servo control.

show abstract

Anti‐occlusion particle filter object‐tracking method based on feature fusion

Cited by 12 publications

References 18 publications

Position reset and hybrid feature based particle filter tracking for large-size and long-term full occlusion

Position reset and hybrid feature based particle filter tracking for large-size and long-term full occlusion

Particle Filter Based Video Object Tracking Scheme With Target Remodeling and Reinitialization and its Hardware Implementation Using Raspberry Pi

Predictive visual control network for occlusion solution in human-following robot

Contact Info

Product

Resources

About