Probability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D

Hernández-Vela, Antonio; Bautista, Miguel Ángel; Perez-Sala, Xavier; Ponce-López, Víctor; Escalera, Sérgio; Baró, Xavier; Pujol, Oriol; Ángulo, Cecilio

doi:10.1016/j.patrec.2013.09.009

Cited by 48 publications

(28 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we propose a genetic program to learn weighting schemes by combining a set of primitives. One should note that there are efforts for improving the bag of visual words in several directions, most notably, great advances have been obtained for incorporating spatial information [6], [4], [5], [17], [18]. The term-weighting schemes developed in this work can also be applied with the previous extensions.…”

Section: The Bag Of Visual Words Representationmentioning

confidence: 99%

Improving bag of visual words representations with genetic programming

Martinez-Carraza

Escalera

Ponce-López

et al. 2015

2015 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

The bag of visual words is a well established repre sentation in diverse computer vision problems. Ta king inspiration from the fields of text mining and retrieval, this representation has proved to be very effective in a large number of domains.In most cases, a standard term-frequency weighting scheme is considered for representing images and videos in computer vision. This is somewhat surprising, as there are many alternative ways of generating bag of words representations within the text processing community. This paper explores the use of alternative weighting schemes for landmark tasks in computer vision: image categorization and gesture recognition. We study the suitability of using well-known supervised and unsupervised weighting schemes for such tasks. More importantly, we devise a genetic program that learns new ways of representing images and videos under the bag of visual words representation. The proposed method learns to combine term-weighting primitives trying to maximize the classification performance. Experimental results are reported in standard image and video data sets showing the effectiveness of the proposed evolutionary algorithm.

show abstract

Section: The Bag Of Visual Words Representationmentioning

confidence: 99%

Improving bag of visual words representations with genetic programming

Martinez-Carraza

Escalera

Ponce-López

et al. 2015

2015 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hernandez-Vela et al [10,11] used the Harris 3D detector to detect keypoints

S_{R G B}

in the RGB volumes and keypoints

S_{D}

in the depth volumes. Then, the HOG, HOF and HOG/HOF feature descriptors for

S_{R G B}

and the VFHCRH descriptors for

S_{D}

are calculated to represent gestures.…”

Section: Related Workmentioning

confidence: 99%

“…The single or combined application of 3D SMoSIFT, HOG, HOF and MBH feature descriptors achieves excellent performance in one-shot learning gesture recognition, which has been demonstrated by some state-of-the-art approaches [1,9,10,11,35,36,37], and is also widely used for human activity recognition [15,30,38]. In this paper, 3D SMoSIFT, HOG, HOF and MBH feature descriptors are concatenated to represent gestures.…”

Section: Feature Descriptormentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition

Lin

Ruan

et al. 2016

Sensors

View full text Add to dashboard Cite

Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation.

show abstract

“…1). The sensitivity analysis of the micro-patterns is carried out as follows: Recognize (match) a p micro-pattern in a new sequence (s) implies extracting an s sub-sequence from s, which is of the same length as p, and calculate the Levenshtein distance (L) [11,12] between p and s. If L is less than the threshold α, there is therefore an occurrence with a positive result. This is repeated for all the s that form part of s. We defined the matching threshold (α) as in [13] (In this case, it is related to football strategies).…”

Section: Loitering Behavior Identification Based On Sequential Micro-mentioning

confidence: 99%

Identification of Loitering Human Behaviour in Video Surveillance Environments

Martínez‐Tomás

Tapia

et al. 2015

Artificial Computation in Biology and Medicine

View full text Add to dashboard Cite

Abstract. Loitering is a common behaviour of the elderly people. We goal is develop an artificial intelligence system that automatically detects loitering behaviour in video surveillance environments. The first step to identify this behaviour was used a Generalized Sequential Patterns that detects sequential micro-patterns in the input loitering video sequences. The test phase determines the appropriate percentage of inclusion of this set of micro-patterns in a new input sequence, namely those that are considered to form part of the profile, and then be identified as loitering. The system is dynamic; it obtains micro-patterns on a repetitive basis. During the execution time, the system takes into account the human operator and updates the performance values of loitering in shopping mall. The profile obtained is consistent with what has been documented by experts in this field and is sufficient to focus the attention of the human operator on the surveillance monitor.

show abstract

Probability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D

Abstract: We present a methodology to address the problem of human gesture seg-

Cited by 48 publications

References 18 publications

Improving bag of visual words representations with genetic programming

Improving bag of visual words representations with genetic programming

Adaptive Local Spatiotemporal Features from RGB-D Data for One-Shot Learning Gesture Recognition

Identification of Loitering Human Behaviour in Video Surveillance Environments

Contact Info

Product

Resources

About