Unified framework for human activity recognition: An approach using spatial edge distribution and ℜ-transform

Vishwakarma, Dinesh Kumar; Kapoor, Rajiv; Dhiman, Ashish

doi:10.1016/j.aeue.2015.12.016

Cited by 27 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section experiments are performed extensively to evaluate the proposed method using three popular benchmark action recognition datasets viz., Weizmann, KTH and UCF50 [5,46,57]. These datasets are designed to test general purpose action recognition systems academically.…”

Section: Resultsmentioning

confidence: 99%

Human action recognition using distance transform and entropy based features

Ramya

Rajeswari

2020

Multimed Tools Appl

View full text Add to dashboard Cite

Human action recognition based on silhouette images has wide applications in computer vision, human computer interaction and intelligent surveillance. It is a challenging task due to the complex actions in nature. In this paper, a human action recognition method is proposed which is based on the distance transform and entropy features of human silhouettes. In the first stage, background subtraction is performed by applying correlation coefficient based frame difference technique to extract silhouette images. In the second stage, distance transform based features and entropy features are extracted from the silhouette images. The distance transform based features and entropy features provide the shape and local variation information. These features are given as input to neural networks to recognize various human actions. The proposed method is tested on three different datasets viz., Weizmann, KTH and UCF50. The proposed method obtains an accuracy of 92.5%, 91.4% and 80% for Weizmann, KTH and UCF50 datasets respectively. The experimental results show that the proposed method for human action recognition is comparable to other state-of-the-art human action recognition methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Human action recognition using distance transform and entropy based features

Ramya

Rajeswari

2020

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Liu et al (2008) recognize human activities using multiple features. Feature fusion for visual tracking and face recognition is extensively used by different authors (Kong et al, 2013;Ma et al, 2015;Vishwakarma et al, 2016aVishwakarma et al, , 2016bVishwakarma & Singh, ) at different times. However, the same ideologies can also be extended to the activity recognition domain.…”

Section: Related Methodsmentioning

confidence: 99%

A sparse coded composite descriptor for human activity recognition

et al. 2021

View full text Add to dashboard Cite

This paper proposes a novel algorithm for computing discriminative descriptors named as a sparse coded composite descriptor (SCCD) for robust human activity recognition. The proposed method blends the state-of-the-art handcrafted features and the discriminative nature of the sparse representation of visual information. The human activity is firstly modelled using any handcrafted feature, and then the sparse codes computed on a discriminative sparse dictionary of these features are embedded to provide discrimination in the feature set. Finally, a support vector machine (SVM) is trained using the proposed SCCDs to perform classification of different human activities. A new feature named as differential motion descriptor (DMD) is also proposed to extract the motion as well as spatial information from an activity video. The simulation results reveal that in comparison with the handcrafted feature, the corresponding SCCD improves the recognition accuracy significantly. The proposed method is compared with state-of-the-art methods on KTH, Ballet, UCF50, and HMDB51 datasets and the proposed methodology of composite features outperforms these methods in terms of recognition accuracy.

show abstract

“…To better illustrate the behaviors of MTA, we visualize the temporal adaptive weights α tp in different layers (1,4,7,10) for two action classes ('sit down' and 'jump up') of NTU-RGB+D dataset. According to Fig.…”

Section: B Motion-driven Adaptationmentioning

confidence: 99%

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

Huang

Dou

Lin

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Graph convolutional networks (GCN) have attracted increasing interest in action recognition in recent years. GCN models human skeleton sequences as spatio-temporal graphs. Also, attention mechanisms are often jointly used with GCNs to highlight important frames or body joints in a sequence. However, attention modules learn parameters offline and are fixed, so may not adapt well to various action samples. In this paper, we propose a simple but effective motion-driven spatial and temporal adaptation strategy to dynamically strengthen the features of important frames and joints for skeleton-based action recognition. The rationale is that the joints and frames with dramatic motions are generally more informative and discriminative. We decouple and combine the spatial and temporal refinements by using a two-branch structure, in which the joint and frame-wise feature refinements perform in parallel. Such a structure can also lead to learn more complementary feature representations. Moreover, we propose to use the fully connected graph convolution to learn the long-range spatial dependencies. Besides, we investigate two high-resolution skeleton graphs by creating virtual joints, aiming to improve the representation of skeleton features. By combining the above proposals, we develop a novel motion-driven spatial and temporal adaptive high-resolution GCN. Experimental results demonstrate that the proposed model achieves state-of-the-art (SOTA) results on the challenging large-scale Kinetics-Skeleton and UAV-Human datasets, and it is on par with the SOTA methods on the two NTU-RGB+D 60&120 datasets. Additionally, our motiondriven adaptation method shows encouraging performance when compared with the attention mechanisms.

show abstract

Unified framework for human activity recognition: An approach using spatial edge distribution and ℜ-transform

Cited by 27 publications

References 33 publications

Human action recognition using distance transform and entropy based features

Human action recognition using distance transform and entropy based features

A sparse coded composite descriptor for human activity recognition

Motion-Driven Spatial and Temporal Adaptive High-Resolution Graph Convolutional Networks for Skeleton-Based Action Recognition

Contact Info

Product

Resources

About