Instructing people for training gestural interactive systems

Fothergill, Simon; Mentis, Helena M.; Kohli, Pushmeet; Nowozin, Sebastian

doi:10.1145/2207676.2208303

Cited by 325 publications

(313 citation statements)

References 12 publications

Supporting

Mentioning

307

Contrasting

Unclassified

Order By: Relevance

“…We have chosen a random forest classifier as our base classifier, as they are fast and efficient for training, and more importantly, for testing, making them well-suited for real-time applications. Random forests have been shown to work well for action and gesture recognition in the past, either through a voting framework [20] or by direct classification [6].…”

Section: Base Classifiermentioning

confidence: 99%

“…A number of gesture recognition methods have been proposed in the literature [15,6,13], including some which operate on the human pose estimated from the Kinect [15,6]. Most of these methods follow a standard classification paradigm.…”

Section: Introductionmentioning

confidence: 99%

“…which may or may not generalize to his or her gestures. Gestures, however, like handwriting and speech, are inherently unique to an individual [6]. For instance, people in western societies usually perform a "Greet" gesture by shaking hands, while people from eastern societies, such as Japan, greet by bowing, or in the case of India, by performing "Namaste" 1 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Gesture Recognition Portfolios for Personalization

Yao

Gool

Kohli

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Human gestures, similar to speech and handwriting, are often unique to the individual. Training a generic classifier applicable to everyone can be very difficult and as such, it has become a standard to use personalized classifiers in speech and handwriting recognition. In this paper, we address the problem of personalization in the context of gesture recognition, and propose a novel and extremely efficient way of doing personalization. Unlike conventional personalization methods which learn a single classifier that later gets adapted, our approach learns a set (portfolio) of classifiers during training, one of which is selected for each test subject based on the personalization data. We formulate classifier personalization as a selection problem and propose several algorithms to compute the set of candidate classifiers. Our experiments show that such an approach is much more efficient than adapting the classifier parameters but can still achieve comparable or better results.

show abstract

Section: Base Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gesture Recognition Portfolios for Personalization

Yao

Gool

Kohli

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Microsoft Research Cambridge created MSRC-12 Gesture dataset [26] in 2012, which includes relevant gestures and their corresponding semantic labels for evaluating gesture recognition and detection systems. This dataset consists of 594 sequences of human skeletal body part gestures, which are totally 719,359 frames with a duration over 6 hours and 40 min at a sample rate of 30H z.…”

Section: Microsoft Research Cambridge-12 Kinect Gesture Datasetmentioning

confidence: 99%

RGB-D datasets using microsoft kinect or similar sensors: a survey

Cai

Han

Liu

et al. 2016

Multimed Tools Appl

130

View full text Add to dashboard Cite

RGB-D data has turned out to be a very useful representation of an indoor scene for solving fundamental computer vision problems. It takes the advantages of the color image that provides appearance information of an object and also the depth image that is immune to the variations in color, illumination, rotation angle and scale. With the invention of the low-cost Microsoft Kinect sensor, which was initially used for gaming and later became a popular device for computer vision, high quality RGB-D data can be acquired easily. In recent years, more and more RGB-D image/video datasets dedicated to various applications have become available, which are of great importance to benchmark the stateof-the-art. In this paper, we systematically survey popular RGB-D datasets for different applications including object recognition, scene classification, hand gesture recognition, 3D-simultaneous localization and mapping, and pose estimation. We provide the insights into the characteristics of each important dataset, and compare the popularity and the difficulty of those datasets. Overall, the main goal of this survey is to give a comprehensive description about the available RGB-D datasets and thus to guide researchers in the selection of suitable datasets for evaluating their algorithms.

show abstract

“…Inference is performed using a Bayes filter to iteratively update a probability distribution over the model classes. Fothergill et al (2012) employ joint angles, joint angle velocities and xyz-velocities of joints as feature vector at each frame. Then gesture recognition is carried out using random forests.…”

Section: Human Action Recognition With Rgb-d Devicesmentioning

confidence: 99%

Evolutionary joint selection to improve human action recognition with RGB-D devices

Chaaraoui

Padilla-López

Climent-Pérez

et al. 2014

Expert Systems with Applications

138

View full text Add to dashboard Cite

Interest in RGB-D devices is increasing due to their low price and the wide range of possible applications that come along. These devices provide a marker-less body pose estimation by means of skeletal data consisting of 3D positions of body joints. These can be further used for pose, gesture or action recognition. In this work, an evolutionary algorithm is used to determine the optimal subset of skeleton joints, taking into account the topological structure of the skeleton, in order to improve the final success rate. The proposed method has been validated using a state-of-the-art RGB action recognition approach, and applying it to the MSR-Action3D dataset. Results show that the proposed algorithm is able to significantly improve the initial recognition rate and to yield similar or better success rates than the state-of-the-art methods.

show abstract

Instructing people for training gestural interactive systems

Cited by 325 publications

References 12 publications

Gesture Recognition Portfolios for Personalization

Gesture Recognition Portfolios for Personalization

RGB-D datasets using microsoft kinect or similar sensors: a survey

Evolutionary joint selection to improve human action recognition with RGB-D devices

Contact Info

Product

Resources

About