Atomic Action Features: A New Feature for Action Recognition

2012 ◽  
pp. 291-300 ◽  
Author(s):  
Qiang Zhou ◽  
Gang Wang
Keyword(s):  
Action Recognition ◽  
Atomic Action ◽  
New Feature

scholarly journals NPU RGB+D Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players

2021 ◽  
Vol 11 (10) ◽  
pp. 4426
Author(s):  
Chunyan Ma ◽  
Ji Fan ◽  
Jinghao Yao ◽  
Tao Zhang
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Short Term Memory ◽  
Evaluation Criteria ◽  
Image Data ◽  
Basketball Player ◽  
Basketball Players ◽  
Convolutional Network ◽  
Atomic Actions ◽  
New Feature

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

scholarly journals CGA: a new feature selection model for visual human action recognition

2020 ◽  
Author(s):  
Ritam Guha ◽  
Ali Hussain Khan ◽  
Pawan Kumar Singh ◽  
Ram Sarkar ◽  
Debotosh Bhattacharjee
Keyword(s):  
Feature Selection ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Selection Model ◽  
New Feature

Feature Extraction and Representation for Distributed Multi-View Human Action Recognition

2013 ◽  
Vol 3 (2) ◽  
pp. 145-154 ◽  
Author(s):  
Jiajia Luo ◽  
Wei Wang ◽  
Hairong Qi
Keyword(s):  
Action Recognition ◽  
Approximation Error ◽  
Human Action Recognition ◽  
Human Action ◽  
Base Station ◽  
Feature Representation ◽  
Superior Performance ◽  
Feature Descriptor ◽  
Testing Stage ◽  
New Feature

Multi-view human action recognition has gained a lot of attention in recent years for its superior performance as compared to single view recognition. In this paper, we propose a new framework for the real-time realization of human action recognition in distributed camera networks (DCNs). We first present a new feature descriptor (Mltp-hist) that is tolerant to illumination change, robust in homogeneous region and computationally efficient. Taking advantage of the proposed Mltp-hist, the noninformative 3-D patches generated from the background can be further removed automatically that effectively highlights the foreground patches. Next, a new feature representation method based on sparse coding is presented to generate the histogram representation of local videos to be transmitted to the base station for classification. Due to the sparse representation of extracted features, the approximation error is reduced. Finally, at the base station, a probability model is produced to fuse the information from various views and a class label is assigned accordingly. Compared to the existing algorithms, the proposed framework has three advantages while having less requirements on memory and bandwidth consumption: 1) no preprocessing is required; 2) communication among cameras is unnecessary; and 3) positions and orientations of cameras do not need to be fixed. We further evaluate the proposed framework on the most popular multi-view action dataset IXMAS. Experimental results indicate that our proposed framework repeatedly achieves state-of-the-art results when various numbers of views are tested. In addition, our approach is tolerant to the various combination of views and benefit from introducing more views at the testing stage. Especially, our results are still satisfactory even when large misalignment exists between the training and testing samples.

Fusing appearance and motion information for action recognition on depth sequences

2021 ◽  
pp. 1-13
Author(s):  
Cong Pei ◽  
Feng Jiang ◽  
Mao Li
Keyword(s):  
Action Recognition ◽  
Feature Representation ◽  
Depth Cameras ◽  
Feature Descriptors ◽  
Single Feature ◽  
Benchmark Datasets ◽  
Depth Sequences ◽  
Cost Efficient ◽  
New Feature ◽  
Representation Scheme

With the advent of cost-efficient depth cameras, many effective feature descriptors have been proposed for action recognition from depth sequences. However, most of them are based on single feature and thus unable to extract the action information comprehensively, e.g., some kinds of feature descriptors can represent the area where the motion occurs while they lack the ability of describing the order in which the action is performed. In this paper, a new feature representation scheme combining different feature descriptors is proposed to capture various aspects of action cues simultaneously. First of all, a depth sequence is divided into a series of sub-sequences using motion energy based spatial-temporal pyramid. For each sub-sequence, on the one hand, the depth motion maps (DMMs) based completed local binary pattern (CLBP) descriptors are calculated through a patch-based strategy. On the other hand, each sub-sequence is partitioned into spatial grids and the polynormals descriptors are obtained for each of the grid sequences. Then, the sparse representation vectors of the DMMs based CLBP and the polynormals are calculated separately. After pooling, the ultimate representation vector of the sample is generated as the input of the classifier. Finally, two different fusion strategies are applied to conduct fusion. Through extensive experiments on two benchmark datasets, the performance of the proposed method is proved better than that of each single feature based recognition method.

scholarly journals Composite Feature Vector Assisted Human Action Recognition through Supervised Learning

2020 ◽  
Vol 8 (6) ◽  
pp. 1556-1566
Keyword(s):  
Feature Extraction ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Research Direction ◽  
Human Action ◽  
Support Vector ◽  
Complex Wavelet Transform ◽  
Simulation Experiments ◽  
Composite Feature ◽  
New Feature

Human Action Recognition is a key research direction and also a trending topic in several fields like machine learning, computer vision and other fields. The main objective of this research is to recognize the human action in image of video. However, the existing approaches have many limitations like low recognition accuracy and non-robustness. Hence, this paper focused to develop a novel and robust Human Action Recognition framework. In this framework, we proposed a new feature extraction technique based on the Gabor Transform and Dual Tree Complex Wavelet Transform. These two feature extraction techniques helps in the extraction of perfect discriminative features by which the actions present in the image or video are correctly recognized. Later, the proposed framework accomplished the Support Vector Machine algorithm as a classifier. Simulation experiments are conducted over two standard datasets such as KTH and Weizmann. Experimental results reveal that the proposed framework achieves better performance compared to state-of-art recognition methods.

scholarly journals Efficient Sparse Representation based Action Recognition in video

2019 ◽  
Vol 9 (2) ◽  
pp. 728-732
Keyword(s):  
Sparse Representation ◽  
Action Recognition ◽  
Real Life ◽  
Human Action Recognition ◽  
Human Action ◽  
Feature Representation ◽  
Svm Classifier ◽  
Interest Points ◽  
Frame Sequence ◽  
New Feature

Human Action Recognition (HAR) is an interesting and helpful topic in various real-life applications such as surveillance based security system, computer vision and robotics. The selected features and feature representation methods, classification algorithms decides the accuracy of the HAR systems. A new feature called, Skeletonized STIP (Spatio Temporal Interest Points) is identified and used in this work. The skeletonization on the action video’s foreground frames are performed and the new feature is generated as STIP values of the skeleton frame sequence. Then the feature set is used for initial dictionary construction in sparse coding. The data for action recognition is huge, since the feature set is represented using the sparse representation. To refine the sparse representation the max pooling method is used and the action recognition is performed using SVM classifier. The proposed approach outperforms on the benchmark datasets.

Dielectronic Recombination in the Average-Atom Model

1988 ◽  
Vol 102 ◽  
pp. 215
Author(s):  
R.M. More ◽  
G.B. Zimmerman ◽  
Z. Zinamon
Keyword(s):  
Detailed Balance ◽  
Systematic Errors ◽  
Dielectronic Recombination ◽  
Rate Equations ◽  
Strong Correlations ◽  
Dense Plasmas ◽  
Atom Model ◽  
New Feature ◽  
Average Atom Model ◽  
Attachment Process

Autoionization and dielectronic attachment are usually omitted from rate equations for the non–LTE average–atom model, causing systematic errors in predicted ionization states and electronic populations for atoms in hot dense plasmas produced by laser irradiation of solid targets. We formulate a method by which dielectronic recombination can be included in average–atom calculations without conflict with the principle of detailed balance. The essential new feature in this extended average atom model is a treatment of strong correlations of electron populations induced by the dielectronic attachment process.

Kindler's Syndrome with Recurrent Neutropenia: Report of Two Cases from Saudi Arabia

2020 ◽  
Author(s):  
Yousef Binamer ◽  
Muzamil A. Chisti
Keyword(s):  
Autosomal Recessive ◽  
Common Mechanism ◽  
Sequencing Analysis ◽  
Loss Of Function ◽  
Skin Atrophy ◽  
Whole Exome ◽  
Infancy And Childhood ◽  
Genetics And Genomics ◽  
New Feature ◽  
Generation Sequencing

AbstractKindler syndrome (KS) is a rare photosensitivity disorder with autosomal recessive mode of inheritance. It is characterized by acral blistering in infancy and childhood, progressive poikiloderma, skin atrophy, abnormal photosensitivity, and gingival fragility. Besides these major features, many minor presentations have also been reported in the literature. We are reporting two cases with atypical features of the syndrome and a new feature of recurrent neutropenia. Whole exome sequencing analysis was done using next-generation sequencing which detected a homozygous loss-of-function (LOF) variant of FERMT1 in both patients. The variant is classified as a pathogenic variant as per the American College of Medical Genetics and Genomics guidelines. Homozygous LOF variants of FERMT1 are a common mechanism of KS and as such confirm the diagnosis of KS in our patients even though the presentation was atypical.

Sign in / Sign up

Export Citation Format

Share Document