Advances in human action recognition: an updated survey

Abu-Bakar, S. A. R.

doi:10.1049/iet-ipr.2019.0350

Cited by 30 publications

(17 citation statements)

References 84 publications

(238 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To handle actions different temporal lengths and generate fixed-length outputs, the original flatten layer is replaced by an SPP layer. Moreover, due to the small size of the DJMM, some of the strides of the Conv-2D and pooling layers are reset to (1,1) [Color figure can be viewed at wileyonlinelibrary.com] Figure 8A-C show the accuracy curves and loss curves on Florence-3D, HanYue-3D and UT-3D based on four different sample strategies. Figure 8D presents the test accuracies that correspond to the trained CNN models.…”

Section: Multi-scale Action Recognitionmentioning

confidence: 99%

“…Human action recognition (HAR) has a wide range of industrial applications, such as video retrieval, video summarization, virtual reality, and human-computer interaction. 1,2 In recent years, with the help of deep learning technology, the accuracy of HAR has improved. However, in practice, human behaviour videos are typically long and complex and contain several different actions.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, temporal action localization (TAL), with the aim of identifying the start key frame (SKF) and the end key frame (EKF) of each action in a long and complicated video, is becoming a new challenging task in HAR and has attracted increasing attention from researchers. 3 In general, TAL should answer two questions: (1) when do the actions occur and finish? and (2) what categories do the actions belong to?…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

Yao

Yang

Huang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

The aim of temporal action localization (TAL) is to determine the start and end frames of an action in a video. In recent years, TAL has attracted considerable attention because of its increasing applications in video understanding and retrieval. However, precisely estimating the duration of an action in the temporal dimension is still a challenging problem. In this paper, we propose an effective one‐stage TAL method based on a self‐defined motion data structure, called a dense joint motion matrix (DJMM), and a novel temporal detection strategy. Our method provides three main contributions. First, compared with mainstream motion images, DJMMs can preserve more pre‐processed motion features and provides more precise detail representations. Furthermore, DJMMs perfectly solve the temporal information loss problem caused by motion trajectory overlaps within a certain time period. Second, a spatial pyramid pooling (SPP) layer, which is widely used in the object detection and tracking fields, is innovatively incorporated into the proposed method for multi‐scale feature learning. Moreover, the SPP layer enables the backbone convolutional neural network (CNN) to receive DJMMs of any size in the temporal dimension. Third, a large‐scale‐first temporal detection strategy inspired by a well‐developed Chinese text segmentation algorithm is proposed to address long‐duration videos. Our method is evaluated on two benchmark data sets and one self‐collected data set: Florence‐3D, UTKinect‐Action3D and HanYue‐3D. The experimental results show that our method achieves competitive action recognition accuracy and high TAL precision, and its time efficiency and few‐shot learning capabilities enable it to be utilized for real‐time surveillance.

show abstract

Section: Multi-scale Action Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

Yao

Yang

Huang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…However, cameras may also capture video streams, continuously, which should be processed in real time for the identification of events of interest. Although this last scenario can be more effective, real time video processing may be very costly [30,31], being prohibitive when many EDUs have to be deployed over an area under some budget constraints. Actually, we believe that the processing of image snapshots and scalar sensed data under the same frequency is the best approach for practical events detection in smart cities, especially for low values of f s (u) .…”

Section: Visual Data Processingmentioning

confidence: 99%

On the Use of Cameras for the Detection of Critical Events in Sensors-Based Emergency Alerting Systems

Costa

Vasques

Portugal

et al. 2020

JSAN

View full text Add to dashboard Cite

The adoption of emergency alerting systems can bring countless benefits when managing urban areas, industrial plants, farms, roads and virtually any area that is subject to the occurrence of critical events, supporting in rescue operations and reducing their negative impacts. For such systems, a promising approach is to exploit scalar sensors to detect events of interest, allowing for the distributed monitoring of different variables. However, the use of cameras as visual sensors can enhance the detection of critical events, which can be employed along with scalar sensors for a more comprehensive perception of the environment. Although the particularities of visual sensing may be challenging in some scenarios, the combination of scalar and visual sensors for the early detection of emergency situations can be valuable for many scenarios, such as smart cities and industry 4.0, bringing promising results. Therefore, in this article, we extend a sensors-based emergency detection and alerting system to also exploit visual monitoring when identifying critical events. Implementation and experimental details are provided to reinforce the use of cameras as a relevant sensor unit, bringing promising results for emergencies management.

show abstract

“…With the rapid development of digital image processing technology and intelligent hardware manufacturing technology, human action recognition has wide application prospects in intelligent video monitoring [1][2][3][4], natural human computer interaction [5,6], smart home products [7][8][9], and virtual reality [10]. e popularity of human action recognition has led to several survey articles that have appeared in refs [11][12][13][14][15]. ese articles discuss various features and classifiers that have been used for human action recognition.…”

Section: Introductionmentioning

confidence: 99%

Using a Multilearner to Fuse Multimodal Features for Human Action Recognition

Tang

Wang

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The representation and selection of action features directly affect the recognition effect of human action recognition methods. Single feature is often affected by human appearance, environment, camera settings, and other factors. Aiming at the problem that the existing multimodal feature fusion methods cannot effectively measure the contribution of different features, this paper proposed a human action recognition method based on RGB-D image features, which makes full use of the multimodal information provided by RGB-D sensors to extract effective human action features. In this paper, three kinds of human action features with different modal information are proposed: RGB-HOG feature based on RGB image information, which has good geometric scale invariance; D-STIP feature based on depth image, which maintains the dynamic characteristics of human motion and has local invariance; and S-JRPF feature-based skeleton information, which has good ability to describe motion space structure. At the same time, multiple K-nearest neighbor classifiers with better generalization ability are used to integrate decision-making classification. The experimental results show that the algorithm achieves ideal recognition results on the public G3D and CAD60 datasets.

show abstract

Advances in human action recognition: an updated survey

Cited by 30 publications

References 84 publications

Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

Multi‐scale feature learning and temporal probing strategy for one‐stage temporal action localization

On the Use of Cameras for the Detection of Critical Events in Sensors-Based Emergency Alerting Systems

Using a Multilearner to Fuse Multimodal Features for Human Action Recognition

Contact Info

Product

Resources

About