HMM-based human motion recognition with optical flow data

Gehrig, Dirk; Kuehne, Hilde; Woerner, Annika; Schultz, Tanja

doi:10.1109/ichr.2009.5379546

Cited by 27 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, activity recognition still is in its infancy due to the many challenges involved: large variety of activities, limited observability, complex human motions and interactions, large intra-class variability vs. small inter-class variability, etc. Many approaches have been researched ranging from low level image and video features [6,15,38], over semantic human pose detection [33], to temporal activity models [12,22,32].…”

Section: Introductionmentioning

confidence: 99%

A database for fine grained activity detection of cooking activities

Rohrbach

Amin

Andriluka

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

461

436

View full text Add to dashboard Cite

While activity recognition is a current focus of research the challenging problem of fine-grained activity recognition is largely overlooked. We thus propose a novel database of 65 cooking activities, continuously recorded in a realistic setting. Activities are distinguished by fine-grained body motions that have low inter-class variability and high intraclass variability due to diverse subjects and ingredients. We benchmark two approaches on our dataset, one based on articulated pose tracks and the second using holistic video features. While the holistic approach outperforms the posebased approach, our evaluation suggests that fine-grained activities are more difficult to detect and the body model can help in those cases. Providing high-resolution videos as well as an intermediate pose representation we hope to foster research in fine-grained activity recognition.

show abstract

Section: Introductionmentioning

confidence: 99%

A database for fine grained activity detection of cooking activities

Rohrbach

Amin

Andriluka

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

461

436

View full text Add to dashboard Cite

show abstract

“…As per the Siebel and Maybank [15] proposal human-tracker with the detection of head movement is alike to the method taken in our system. Tao [19,20] and Ivan Laptev and Tony Lindeberg [21] proposes to track multiple-people using algorithmic approach where they have used some sophisticated filtering techniques. This scheme has addressed human-shape-model [13].…”

Section: Related Workmentioning

confidence: 99%

Tracking Humans Based on Interest Point over Span-Space in Multifarious Situations

Hossain¹,

Sanyal²

2016

IJSEIA

View full text Add to dashboard Cite

show abstract

“…Dalal et al in [2] use Histogram of oriented gradients as a feature set for human detection. Gehrig et al in [3] demonstrates the use of optical flow motion gradient histograms. Yilmaz and Shah in [4] build 3D volumes to describe actions by exploiting people contourpoint tracking .…”

Section: Introductionmentioning

confidence: 98%

Use of Kinect in a Multicamera setup for action recognition applications

Kayal¹,

Samarabandu²

2014

2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE)

View full text Add to dashboard Cite

Conventional human action recognition methods use a single light camera to extract all the necessary information needed to perform the recognition. However, the use of a single light camera poses limitations which can not be addressed without a hardware change. In this paper, we propose a novel hardware setup to help solve many of said limitations without changing the available human action algorithms. The setup uses the depth information from the Microsoft Kinect camera for the Xbox 360 gaming console, and a secondary light camera in a stereo camera configuration. In the paper we explain how the configuration is setup, and how it is used to extract the skeletal data from the Kinect camera and project this skeletal data onto the secondary camera's image. The results of the extraction are tested for accuracy, and potential applications are discussed.

show abstract

HMM-based human motion recognition with optical flow data

Cited by 27 publications

References 11 publications

A database for fine grained activity detection of cooking activities

A database for fine grained activity detection of cooking activities

Tracking Humans Based on Interest Point over Span-Space in Multifarious Situations

Use of Kinect in a Multicamera setup for action recognition applications

Contact Info

Product

Resources

About