Histogram of Oriented Principal Components for Cross-View Action Recognition

Rahmani, Hossein; Mahmood, Arif; Huynh, Du Q.; Mian, Ajmal

doi:10.1109/tpami.2016.2533389

Cited by 179 publications

(197 citation statements)

References 57 publications

Supporting

Mentioning

196

Contrasting

Order By: Relevance

“…To perform experiments, we obtained off-the-shelf codes for HON4D [11], HOPC [13], LARP-SO [19], HPM+TM [14], IndRNN [27] and ST-GCN [26] from the respective authors' websites. For SCK+DCK [23], HDG [12], P-LSTM [18] and Clips+CNN+MTLN [21], we used our own Matlab implementations given that codes for these methods are not publicly available.…”

Section: Experimental Settingmentioning

confidence: 99%

“…This dataset has high between-class similarity and contains frequent self-occlusions. UWA3D Multiview Activity II [13] contains 30 actions performed by 9 people in a cluttered environment. In this dataset, the Kinect camera was moved to different positions to capture the actions from 4 different views (see Fig.…”

Section: A Benchmark Datasetsmentioning

confidence: 99%

“…This allows action recognition researchers to focus their effort more on getting robust feature descriptors to describe the actions rather than on low level segmentation. Numerous representative methods for 3D action analysis using depth videos include [9][10][11][12][13][14]. These methods employ advanced machine learning techniques for which good results have been reported.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

Wang

Huynh

Koniusz

2020

IEEE Trans. on Image Process.

216

View full text Add to dashboard Cite

Video-based human action recognition is currently one of the most active research areas in computer vision. Various research studies indicate that the performance of action recognition is highly dependent on the type of features being extracted and how the actions are represented. Since the release of the Kinect camera, a large number of Kinect-based human action recognition techniques have been proposed in the literature. However, there still does not exist a thorough comparison of these Kinect-based techniques under the grouping of feature types, such as handcrafted versus deep learning features and depthbased versus skeleton-based features. In this paper, we analyze and compare ten recent Kinect-based algorithms for both crosssubject action recognition and cross-view action recognition using six benchmark datasets. In addition, we have implemented and improved some of these techniques and included their variants in the comparison. Our experiments show that the majority of methods perform better on cross-subject action recognition than cross-view action recognition, that skeleton-based features are more robust for cross-view recognition than depth-based features, and that deep learning features are suitable for large datasets.

show abstract

Section: Experimental Settingmentioning

confidence: 99%

Section: A Benchmark Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

Wang

Huynh

Koniusz

2020

IEEE Trans. on Image Process.

216

View full text Add to dashboard Cite

show abstract

“…At the same time, AUC values of the ROC curves help to understand and compare the ROC curves in a clearer way when they cross each other or nearly close to each other. [32] 12fps 16fps HOPC [20] 0.04fps 0.5fps HPM+TM [18] 22fps 25fps Ours 36fps 28 fps…”

Section: Ntu Rgb-d Human Activity Datasetmentioning

confidence: 99%

View-Invariant Deep Architecture for Human Action Recognition Using Two-Stream Motion and Shape Temporal Dynamics

Dhiman

Vishwakarma

2020

IEEE Trans. on Image Process.

130

View full text Add to dashboard Cite

Human action Recognition for unknown views is a challenging task. We propose a view-invariant deep human action recognition framework, which is a novel integration of two important action cues: motion and shape temporal dynamics (STD). The motion stream encapsulates the motion content of action as RGB Dynamic Images (RGB-DIs) which are processed by the fine-tuned InceptionV3 model. The STD stream learns longterm view-invariant shape dynamics of action using human pose model (HPM) based view-invariant features mined from structural similarity index matrix (SSIM) based key depth human pose frames. To predict the score of the test sample, three types of late fusion (maximum, average and product) techniques are applied on individual stream scores. To validate the performance of the proposed novel framework the experiments are performed using both cross subject and cross-view validation schemes on three publically available benchmarks-NUCLA multi-view dataset, UWA3D-II Activity dataset and NTU RGB-D Activity dataset. Our algorithm outperforms with existing state-of-the-arts significantly that is reported in terms of accuracy, receiver operating characteristic (ROC) curve and area under the curve (AUC).

show abstract

“…Although this method is not robust to the changing of viewing angle and human's body scale, it has recognized 90 percent of actions and the error was halved compared to 2D methods. Rahmani et al [34] used Histogram of Oriented Principal Components (HOPC) descriptor on point clouds for cross-view action recognition.…”

Section: Introductionmentioning

confidence: 99%

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

2018

View full text Add to dashboard Cite

Abstract-Human action recognition has been one of the most active fields of research in computer vision over the last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of data. Development of depth sensors has made it feasible to track positions of human body joints over time. This paper proposes a novel method for action recognition which uses temporal 3D skeletal Kinect data. This method introduces the definition of body states and then every action is modeled as a sequence of these states. The learning stage uses Fisher Linear Discriminant Analysis (LDA) to construct discriminant feature space for discriminating the body states. Moreover, this paper suggests the use of the Mahalonobis distance as an appropriate distance metric for the classification of the states of involuntary actions. Hidden Markov Model (HMM) is then used to model the temporal transition between the body states in each action. According to the results, this method significantly outperforms other popular methods, with recognition (recall) rate of 88.64% for eight different actions and up to 96.18% for classifying the class of all fall actions versus normal actions.Index Terms-Human action recognition, involuntary action recognition, Fisher, linear discriminant analysis (LDA), kinect, 3D skeleton data, hidden markov model (HMM).

show abstract

Histogram of Oriented Principal Components for Cross-View Action Recognition

Cited by 179 publications

References 57 publications

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

View-Invariant Deep Architecture for Human Action Recognition Using Two-Stream Motion and Shape Temporal Dynamics

Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

Contact Info

Product

Resources

About