Human Motion Classification Based on Global Representation and Conditional Model

Zhang, Hao; Liu, Zhijing; Zhao, Huijing; Wei, Qing

doi:10.4304/jcp.6.10.2060-2067

Cited by 4 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gait energy image (GEI) [15] is a spatio-temporal method which is proposed to characterize human walking properties for individual recognition by gait. Global representation and conditional model are employed for human motion recognition [16].…”

Section: Pedestrian Classificationmentioning

confidence: 99%

Pedestrian Classification Based on Full-SVM Decision Tree

Xue¹,

Liu²,

Xiong³

2015

IJMUE

Self Cite

View full text Add to dashboard Cite

Visual analysis has potential to be used for recognition, and it is one of the hottest but most difficult subjects in computer vision. In order to identify pedestrian movement in an Intelligent Security Monitoring System, the video activity in the prospect is represented by a series of spatio-temporal interest points. Since human posture has the characteristics of uncertainty and illegibility, the clustering centers of each class are computed by fuzzy clustering techniques. We presented a pedestrian classification method based on improved support vector machines in order to solve non-rigid objects that are difficult to identify in intelligent monitoring systems. The Support Vector Machine technology and the decision tree have combined into one multi-class classifier so as to solve multi-class classification problems. Then a full-SVM (Support Vector Machine) decision tree is constructed based on the conventional decision tree. At last, the method is evaluated on the KTH action dataset and receives a comparatively high correct recognition rate.

show abstract

Section: Pedestrian Classificationmentioning

confidence: 99%

Pedestrian Classification Based on Full-SVM Decision Tree

Xue¹,

Liu²,

Xiong³

2015

IJMUE

Self Cite

View full text Add to dashboard Cite

show abstract

“…By generalized Huffman transformation [10], several means are presented to extract contour, such as active contour models [11], artificial neural network [12], Coupled Hidden Markov Models [13] and Linear-chain Conditional Random Fields [14]. According to these, we presented and implemented an algorithm for accurate contour, and this is helpful for vision measurement.…”

Section: Introductionmentioning

confidence: 99%

Extraction of Bubble Contour in Single Width

Zhang

Yang

et al. 2013

2013 Fifth International Conference on Measuring Technology and Mechatronics Automation

View full text Add to dashboard Cite

We presented an algorithm to obtain exact bubble contour. For classic algorithms commonly extracting contour with multi-pixels in width, it is difficult in obtaining accurate values of bubble contour to evaluate its physical properties. For complete bubble contour, candidate regions and vectors are integrated. Calculating and comparing the angles of adjoining vectors, we get point set of bubble contour and describe it with single-pixel line. Subsequently, we go on performing the algorithm of complete contour to get accurate contour. This algorithm solves the problem that any point locates on bubble contour accurately. It takes the advantages in image processing of bubble silhouette.

show abstract

“…Gait energy image (GEI) [19] is a spatio-temporal method which is proposed to characterize human walking properties for individual recognition by gait. Global representation and conditional model are employed for human motion recognition [20].…”

Section: Introductionmentioning

confidence: 99%

Pedestrian Classification Based on Improved Support Vector Machines

Xue

Liu

2013

2013 5th International Conference on Intelligent Networking and Collaborative Systems

Self Cite

View full text Add to dashboard Cite

We presented a pedestrian classification method based on improved support vector machine in order to solve non-rigid objects are difficult to identify in intelligent monitoring system. The video activity in the prospect is represented by a series of spatio-temporal interest point. Since human posture has the characteristics of uncertainty and illegibility, the clustering centers of each class are computed by fuzzy clustering technique. Then a full-SVM decision tree is constructed based on conventional decision tree. At last, the method is evaluated on the Weizmann action dataset and received comparative high correct recognition rate.

show abstract

Human Motion Classification Based on Global Representation and Conditional Model

Cited by 4 publications

References 29 publications

Pedestrian Classification Based on Full-SVM Decision Tree

Pedestrian Classification Based on Full-SVM Decision Tree

Extraction of Bubble Contour in Single Width

Pedestrian Classification Based on Improved Support Vector Machines

Contact Info

Product

Resources

About