Human Action Recognition Using Salient Opponent-Based Motion Features

Shabani, Amir-Hossein; Zelek, John; Clausi, David A.

doi:10.1109/crv.2010.54

Cited by 12 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other tasks like object recognition, tracking, and detection can also be refined by incorporating visual attention information [16,25,22]. Most of the state-of-the-art methods have exploited the contrast and the uniqueness properties in either local or global context to extract saliency regions [14,2,6,20,32].…”

Section: Introductionmentioning

confidence: 99%

Monte Carlo Sampling based Salient Region Detection

Zhang

Jin

et al. 2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

In this paper, a simple and e↵ective method is proposed for salient region detection. Based on the observation that salient regions tend to be compact, connected and surrounded, our original idea is to exploit these three kinds of prior knowledge. However, concepts of spatial structure (such as connectivity and surroundedness) only have definite meanings in binary images. Thus, a Monte Carlo Sampling based Saliency model is proposed. Our model has two main advantages over other methods. Firstly, the result of each sampling process is a binary map which can greatly simplify the combination with prior knowledge of spatial structure. Secondly, our method is naturally parallelized because every sampling process is independent with each other, which makes our method very e cient. Experimental results on two datasets show that, compared with eleven state-of-theart methods, our approach has a competitive performance and also runs very fast.

show abstract

Section: Introductionmentioning

confidence: 99%

Monte Carlo Sampling based Salient Region Detection

Zhang

Jin

et al. 2014

Proceedings of International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

show abstract

“…In their filtering framework, the motion-energy map is extracted from motion patterns captured from lateral viewing conditions. This approach has been improved further by Shabani et al (2010) utilising for human's action modelling. In this paper, a new template feature, i.e., GSI, has been introduced that is based on the improved Adelson's motion energy model.…”

Section: Introductionmentioning

confidence: 99%

GSI: efficient spatio-temporal template for human gait recognition

Ghaeminia

Shokouhi

2018

IJBM

View full text Add to dashboard Cite

Human gait recognition is a challenging task in computer vision community. In order to represent the gait, the most common feature is a gait template. Many efficient templates have been developed recently, however, the effectiveness of the proposed motion models is still under investigation. A novel template feature, named gait salient image (GSI) is introduced in this paper. The main contribution of the proposed GSI is encoding the motion energy of gait into a single template. This idea is being conceptualised by applying appropriate spatio-temporal filter for extracting motion features and averaging it over a gait period. To show how GSI-based feature is being efficient, the proposed template is classified using PCA+LDA. Extensive experiments on popular gait databases reveal an improvement over the available methods in terms of efficiency and accuracy. The value of recognition rate is 58.44% for Rank1 and 76.60% for Rank5 based on the USF database.

show abstract

“…To obtain a contrast polarity insensitive response, the energy of the filters R = (G k u 0 ) 2 + (G k h u 0 ) 2 is utilized. The local maxima in the motion energy map localizes the salient features [5,27] (Fig. 1(a)).…”

Section: Salient Feature Detectionmentioning

confidence: 99%

“…For action classification, we incorporated the same bag-of-words (BOW) setting utilized in [5,27,32]. Salient features are clustered based on their 3DSIFT descriptors [26] into visual words using K-means algorithm with random seed initialization.…”

Section: Action Classification Testmentioning

confidence: 99%

“…This filtering is utilized for a biologically-inspired filtering by Jhuang et al [14]. Shabani et al [27] showed the promising performance of using this filtering in extraction of opponent-based motion features and robust local motion event detection in [29] We model the scale-space filtering of a 2D+t video signal using circuit theory [10,12,22], but considering the time causality. For our development, a graphical network of connected pixels in video is constructed.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Improved Spatio-temporal Salient Feature Detection for Action Recognition

Shabani¹,

Clausi²,

Zelek³

2011

Procedings of the British Machine Vision Conference 2011

Self Cite

View full text Add to dashboard Cite

Spatio-temporal salient features can localize the local motion events and are used to represent video sequences for many computer vision tasks such as action recognition. The robust detection of these features under geometric variations such as affine transformation and view/scale changes is however an open problem. Existing methods use the same filter for both time and space and hence, perform an isotropic temporal filtering. A novel anisotropic temporal filter for better spatio-temporal feature detection is developed. The effect of symmetry and causality of the video filtering is investigated. Based on the positive results of precision and reproducibility tests, we propose the use of temporally asymmetric filtering for robust motion feature detection and action recognition.

show abstract

Human Action Recognition Using Salient Opponent-Based Motion Features

Cited by 12 publications

References 20 publications

Monte Carlo Sampling based Salient Region Detection

Monte Carlo Sampling based Salient Region Detection

GSI: efficient spatio-temporal template for human gait recognition

Improved Spatio-temporal Salient Feature Detection for Action Recognition

Contact Info

Product

Resources

About