Multi-Fusion Sensors for Action Recognition based on Discriminative Motion Cues and Random Forest

2021 ◽  
Author(s):  
Sadaf Hafeez ◽  
Ahmad Jalal ◽  
Shaharyar Kamal
Keyword(s):  
Random Forest ◽  
Action Recognition ◽  
Motion Cues

Human Action Recognition Based on Local Image Contour and Random Forest

2014 ◽  
Vol 34 (10) ◽  
pp. 1015006
Author(s):  
蔡加欣 Cai Jiaxin ◽  
冯国灿 Feng Guocan ◽  
汤鑫 Tang Xin ◽  
罗志宏 Luo Zhihong
Keyword(s):  
Random Forest ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Image Contour ◽  
Local Image

Action recognition based on on-line random forest voting

2016 ◽  
Vol 24 (8) ◽  
pp. 2010-2017 ◽  
Author(s):  
王世刚 WANG Shi-gang ◽  
鲁奉军 LU Feng-jun ◽  
赵文婷 ZHAO Wen-ting ◽  
赵晓琳 ZHAO Xiao-lin ◽  
卢 洋 LU Yang
Keyword(s):  
Random Forest ◽  
Action Recognition ◽  
On Line

scholarly journals Learning a Mid-Level Representation for Multiview Action Recognition

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Cuiwei Liu ◽  
Zhaokui Li ◽  
Xiangbin Shi ◽  
Chong Du
Keyword(s):  
Random Forest ◽  
Action Recognition ◽  
Random Forests ◽  
Random Forest Classifier ◽  
Multiple Views ◽  
Human Actions ◽  
Single View ◽  
Learning Framework ◽  
Camera View ◽  
Action Category

Recognizing human actions in videos is an active topic with broad commercial potentials. Most of the existing action recognition methods are supposed to have the same camera view during both training and testing. And thus performances of these single-view approaches may be severely influenced by the camera movement and variation of viewpoints. In this paper, we address the above problem by utilizing videos simultaneously recorded from multiple views. To this end, we propose a learning framework based on multitask random forest to exploit a discriminative mid-level representation for videos from multiple cameras. In the first step, subvolumes of continuous human-centered figures are extracted from original videos. In the next step, spatiotemporal cuboids sampled from these subvolumes are characterized by multiple low-level descriptors. Then a set of multitask random forests are built upon multiview cuboids sampled at adjacent positions and construct an integrated mid-level representation for multiview subvolumes of one action. Finally, a random forest classifier is employed to predict the action category in terms of the learned representation. Experiments conducted on the multiview IXMAS action dataset illustrate that the proposed method can effectively recognize human actions depicted in multiview videos.

Integrating Complementary Appearance, Posture and Motion Cues for RGB-D Action Recognition

2018 ◽  
Vol 27 (08) ◽  
pp. 1850030 ◽  
Author(s):  
Wanjun Chen ◽  
Erhu Zhang ◽  
Yan Zhang
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Geometric Feature ◽  
Integration Scheme ◽  
Shape Information ◽  
Visual Appearance ◽  
Motion Cues ◽  
Novel Approach ◽  
Depth Feature

This work presents a novel approach to multimodal human action recognition by jointly using visual RGB and depth (including skeleton joint positions) data captured from depth camera. For the depth feature extraction, Local Surface Geometric Feature (LSGF) is adopted to capture the geometric appearance and postures cues. Simultaneously, the improved dense trajectory feature (IDT) is extracted from RGB modality to jointly characterize the motion, visual appearance and trajectory shape information. These features from different modalities are complementary to each other. Then a two-stage integration scheme is proposed, which incorporates the probability weights of each classifier for action recognition. The proposed approach is evaluated on four publicly available human action databases: NJUST RGB-D Action, MSR-ActionPairs, MSR-DailyAct3D, and UTD-MHAD. Experimental results demonstrate that the proposed approach outperforms or is comparable to the state-of-the-art methods.

scholarly journals Exploiting better motion cues for better action recognition

2021 ◽  
Author(s):  
Jawad Khan
Keyword(s):  
Action Recognition ◽  
Space Time ◽  
Motion Cues ◽  
Large Margin ◽  
Additional Information ◽  
Recognition Algorithms ◽  
Video Description ◽  
Shear Characteristics

Several recent studies on action recognition have emphasised the significance of including motioncharacteristics clearly in the video description. This work shows that properly partitioning visualmotion into dominant and residual motions enhances action recognition algorithms greatly, both interms of extracting space-time trajectories and computing descriptors. Then, using differentialmotion scalar variables, divergence, curl, and shear characteristics, we create a new motiondescriptor, the DCS descriptor. It adds to the results by capturing additional information on localmotion patterns. Finally, adopting the recently proposed VLAD coding technique in image retrievalimproves action recognition significantly. On three difficult datasets, namely Hollywood 2,HMDB51, and Olympic Sports, our three additions are complementary and lead to beat all reportedresults by a large margin.

Sign in / Sign up

Export Citation Format

Share Document