Extracting Refined Low-Rank Features of Robust PCA for Human Action Recognition

Huang, Sijun; Ye, Junyong; Wang, Tongqing; Jiang, Li; Wu, Xuegang; Li, Yang

doi:10.1007/s13369-015-1635-8

Cited by 19 publications

(13 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lower α increases the complexity of background, thus we set α = 1 10 max(m, n + 1), according to the robust principal component analysis (RPCA) method [35] in this paper.…”

Section: Estimation Of the Moving Target Matrix Tmentioning

confidence: 99%

“…Fortunately, low-rank and sparse representation is an effective tool that is employed in many applications of computer vision, such as fore-and background separation [26][27][28][29][30][31][32], fabric defect inspection [33], face recognition [34], act recognition [35], and so on. Its basic principle is that the foreground occupies a small number of pixels and that the background images are linearly related in consecutive frames, meaning that the fore-and background patches can be treated as a low-rank matrix and a sparse matrix, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Wan

Qian

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Infrared moving target tracking plays a fundamental role in many burgeoning research areas of Smart City. Challenges in developing a suitable tracker for infrared images are particularly caused by pose variation, occlusion, and noise. In order to overcome these adverse interferences, a total variation regularization term-based low-rank and sparse matrix representation (TV-LRSMR) model is designed in order to exploit a robust infrared moving target tracker in this paper. First of all, the observation matrix that is derived from the infrared sequence is decomposed into a low-rank target matrix and a sparse occlusion matrix. For the purpose of preventing the noise pixel from being separated into the occlusion term, a total variation regularization term is proposed to further constrain the occlusion matrix. Then an alternating algorithm combing principal component analysis and accelerated proximal gradient methods is employed to separately optimize the two matrices. For long-term tracking, the presented algorithm is implemented using a Bayesien state inference under the particle filtering framework along with a dynamic model update mechanism. Both qualitative and quantitative experiments that were examined on real infrared video sequences verify that our algorithm outperforms other state-of-the-art methods in terms of precision rate and success rate.

show abstract

“…A lower α increases the complexity of background, thus we set α = 1 10 max(m, n + 1), according to the robust principal component analysis (RPCA) method [35] in this paper.…”

Section: Estimation Of the Moving Target Matrix Tmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Wan

Qian

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Afterwards, we extract the low-rank features of all subsequences. Then, each low-rank feature will be represented as a feature vector by accumulated edge distribution histogram (AEDH) descriptor [3]. The AEDH is specifically designed to describe the low-rank feature, which counts the edge distribution of low-rank image transformed from low-rank feature.…”

Section: Concatenated Low-rank Featuresmentioning

confidence: 99%

“…However, many traditional methods usually depend on accurate actor segmentation, body tracking or interest point detection. The low-rank feature proposed in our previous work [3] can well avoids these intermediate steps. Assuming that there is an action sequence, we first reshape each frame into a column vector.…”

Section: Introductionmentioning

confidence: 99%

“…The obtained lowrank feature can well capture the motion information and remove action background. However the manner of extracting low-rank feature in the work [3] neglects the temporal information among the action sequence. To overcame this shortcoming, we split an entire action sequence into multiple overlapping subsequences, and concatenate the low-rank features of all subsequences according to their time order.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning a Similarity Constrained Discriminative Kernel Dictionary from Concatenated Low-Rank Features for Action Recognition

Huang

Wang

et al. 2016

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYTraditional low-rank feature lose the temporal information among action sequence. To obtain the temporal information, we split an action video into multiple action subsequences and concatenate all the low-rank features of subsequences according to their time order. Then we recognize actions by learning a novel dictionary model from concatenated low-rank features. However, traditional dictionary learning models usually neglect the similarity among the coding coefficients and have bad performance in dealing with non-linearly separable data. To overcome these shortcomings, we present a novel similarity constrained discriminative kernel dictionary learning for action recognition. The effectiveness of the proposed method is verified on three benchmarks, and the experimental results show the promising results of our method for action recognition.

show abstract

Silhouette-Based Human Action Recognition by Embedding HOG and PCA Features

Jahagirdar

Nagmode²

2018

Intelligent Computing and Information and Communication

View full text Add to dashboard Cite

Extracting Refined Low-Rank Features of Robust PCA for Human Action Recognition

Cited by 19 publications

References 46 publications

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Total Variation Regularization Term-Based Low-Rank and Sparse Matrix Representation Model for Infrared Moving Target Tracking

Learning a Similarity Constrained Discriminative Kernel Dictionary from Concatenated Low-Rank Features for Action Recognition

Silhouette-Based Human Action Recognition by Embedding HOG and PCA Features

Contact Info

Product

Resources

About