View-independent human action recognition with Volume Motion Template on single stereo camera

Roh, Myung-Cheol; Shin, Ho-Keun; Lee, Seong–Whan

doi:10.1016/j.patrec.2009.11.017

Cited by 79 publications

(37 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using stereo, the existing methods typically try to make the algorithm insensitive to a camera viewpoint [11]. Similarly [12] uses a special room and a multi-camera setup to construct viewpoint invariant action representation, and [13] incorporate temporal information to the multi-view setup.…”

Section: Introductionmentioning

confidence: 99%

Action Recognition Robust to Background Clutter by Using Stereo Vision

Sanchez-Riera¹,

Čech²,

Horaud³

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

View full text Add to dashboard Cite

Abstract. An action recognition algorithm which works with binocular videos is presented. The proposed method uses standard bag-of-words approach, where each action clip is represented as a histogram of visual words. However, instead of using classical monocular HoG/HoF features, we construct features from the scene-flow computed by a matching algorithm on the sequence of stereo images. The resulting algorithm has a comparable or slightly better recognition accuracy than standard monocular solution in controlled setup with a single actor present in the scene. However, we show its significantly improved performance in case of strong background clutter due to other people freely moving behind the actor.

show abstract

Section: Introductionmentioning

confidence: 99%

Action Recognition Robust to Background Clutter by Using Stereo Vision

Sanchez-Riera¹,

Čech²,

Horaud³

2012

Computer Vision – ECCV 2012. Workshops and Demonstrations

View full text Add to dashboard Cite

show abstract

“…Figure 9 shows disparity maps for an action sequence, with 100 levels obtained between the tip of hand (last image) and background. The quality of results demonstrate that our setup can be used in applications such as autonomous navigation in robots [36], scene understanding [5] and action recognition [33]. For robotic applications, our system can be more effective than using multiple cameras due to limited space and resources on a mobile platform.…”

Section: More Resultsmentioning

confidence: 97%

“…Here we describe the use of the system for 3D reconstruction which has wide ranging applications in 3D immersive technology [32], face and expression recognition [1,2], action recognition [33], archeology [34]. Many of the above applications demand portability without sacrificing the quality of the reconstruction.…”

Section: D Reconstructionmentioning

confidence: 99%

Single Camera Stereo System Using Prism and Mirrors

Somanath

Rohith

Kambhamettu

2010

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Stereo and 3D reconstruction are used by many applications such as object modeling, facial expression studies and human motion analysis. But synchronizing multiple high frame rate cameras require special hardware or sophisticated software solutions. In this paper, we propose a single camera stereo system by using a setup made of prism and mirrors. Our setup is cost effective, portable and can be calibrated similar to two camera stereo to obtain high quality 3D reconstruction. We demonstrate the application of the proposed system in dynamic 3D face expression capture, depth super-resolution in stereo video and general depth estimation.

show abstract

“…This work was extended in [33] where MHI and two appearance-based features namely foreground image and histogram of oriented gradients (HOG) were combined for action representation, followed by simulated annealing multiple instance learning support vector machine (SMILE-SVM) for action classification. The method proposed in [34] also extended the [32] from 2D to 3D space for view-independent human action recognition using a volume motion template. The experimental results using these techniques are presented in Table 1.…”

Section: Space-time-based Approachesmentioning

confidence: 99%

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

2017

View full text Add to dashboard Cite

Human activity recognition (HAR) is an important research area in the fields of human perception and computer vision due to its wide range of applications. These applications include: intelligent video surveillance, ambient assisted living, human computer interaction, human-robot interaction, entertainment, and intelligent driving. Recently, with the emergence and successful deployment of deep learning techniques for image classification, researchers have migrated from traditional handcrafting to deep learning techniques for HAR. However, handcrafted representation-based approaches are still widely used due to some bottlenecks such as computational complexity of deep learning techniques for activity recognition. However, approaches based on handcrafted representation are not able to handle complex scenarios due to their limitations and incapability; therefore, resorting to deep learning-based techniques is a natural option. This review paper presents a comprehensive survey of both handcrafted and learning-based action representations, offering comparison, analysis, and discussions on these approaches. In addition to this, the well-known public datasets available for experimentations and important applications of HAR are also presented to provide further insight into the field. This is the first review paper of its kind which presents all these aspects of HAR in a single review article with comprehensive coverage of each part. Finally, the paper is concluded with important discussions and research directions in the domain of HAR.

show abstract

View-independent human action recognition with Volume Motion Template on single stereo camera

Cited by 79 publications

References 17 publications

Action Recognition Robust to Background Clutter by Using Stereo Vision

Action Recognition Robust to Background Clutter by Using Stereo Vision

Single Camera Stereo System Using Prism and Mirrors

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

Contact Info

Product

Resources

About