Vision-based action recognition of construction workers using dense trajectories

Yang, Jun; Shi, Zhongke; Wu, Zhang

doi:10.1016/j.aei.2016.04.009

Cited by 123 publications

(61 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The TSNs with the new fusion strategy also outperforms the state‐of‐the‐art method in Yang et al. (), which used dense trajectories (Wang and Schmid, ; Wang et al., ) and produced the average accuracy of 0.59.…”

Section: Experiments and Results Analysismentioning

confidence: 87%

“…The 0.84 average accuracy is comparable with the average accuracies produced with the original method on the public data sets, namely 0.64 on HMDB-51 and 0.94 on UCF-101 . The TSNs with the new fusion strategy also outperforms the state-of-theart method in Yang et al (2016), which used dense trajectories (Wang and Schmid, 2011; and produced the average accuracy of 0.59.…”

Section: Rgb Imagesmentioning

confidence: 93%

“…However, considering the latest advances in deep action recognition (Wang et al., ), recognizing workers’ basic actions in far‐field surveillance videos is feasible. This study follows the convention of action recognition that short clips are used to record finite basic actions (Gong et al., ; Golparvar‐Fard et al., ; Yang et al., ). On the contrary, it is believed that precategorizing workers’ activities is difficult because of their varying durations and inscrutable transitions.…”

Section: Scope and Objectivementioning

confidence: 99%

“…The method uses spatiotemporal features and support vector machine (SVM) classifiers. Yang et al (2016) integrated dense trajectories (Wang and Schmid, 2011; with SVM classifiers to classify workers' actions and reported the best average accuracy of 0.59. The published research (Gong et al, 2011;Golparvar-Fard et al, 2013;Yang et al, 2014) only tackles segmented video clips, in which there are only single actions; none of these studies have investigated the relations among the actions.…”

Section: Action Recognitionmentioning

confidence: 99%

See 3 more Smart Citations

Capturing and Understanding Workers’ Activities in Far‐Field Surveillance Videos with Deep Action Recognition and Bayesian Nonparametric Learning

Luo

Yang

et al. 2018

Computer aided Civil Eng

View full text Add to dashboard Cite

Recording workers’ activities is an important, but burdensome, management task for site supervisors. The last decade has seen a growing trend toward vision‐based activity recognition. However, recognizing workers’ activities in far‐field surveillance videos is understudied. This study proposes a hierarchical statistical method for recognizing workers’ activities in far‐field surveillance videos. The method consists of two steps. First, a deep action recognition method was used to recognize workers’ actions, and a new fusion strategy was proposed to consider the characteristics of far‐field surveillance videos. The deep action recognition method with the new fusion strategy has achieved the comparable performance (0.84 average accuracy) on the far‐field surveillance data set in contrast to the original method on the public data sets. Second, a Bayesian nonparametric hidden semi‐Markov model was innovatively used to model and infer workers’ activities based on action sequences. The latent states of the fitted Bayesian model captured workers’ activities in terms of state duration distributions and state transition distributions, which are indispensable for understanding workers’ time allocation. It has been preliminarily illustrated that the activity information learned by the Bayesian model possesses the potential to implement objective work sampling, personal physical fatigue monitoring, trade‐level health risk assessment, and process‐based quality control. Also, the limitations of this study are discussed.

show abstract

Section: Experiments and Results Analysismentioning

confidence: 87%

Section: Rgb Imagesmentioning

confidence: 93%

Section: Scope and Objectivementioning

confidence: 99%

Section: Action Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Capturing and Understanding Workers’ Activities in Far‐Field Surveillance Videos with Deep Action Recognition and Bayesian Nonparametric Learning

Luo

Yang

et al. 2018

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…This method is invariant to execution rate of the activity and uses transported-square root vector fields (TSRVFs) of trajectories and standard Euclidean norm to achieve the computational efficiency. Another method for recognition of actions of construction workers using dense trajectories was proposed in [67]. In this method, different descriptors such as HOG, HOF, and motion boundary histogram (MBH) were used for the trajectories.…”

Section: Space-time-based Approachesmentioning

confidence: 99%

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

2017

View full text Add to dashboard Cite

Human activity recognition (HAR) is an important research area in the fields of human perception and computer vision due to its wide range of applications. These applications include: intelligent video surveillance, ambient assisted living, human computer interaction, human-robot interaction, entertainment, and intelligent driving. Recently, with the emergence and successful deployment of deep learning techniques for image classification, researchers have migrated from traditional handcrafting to deep learning techniques for HAR. However, handcrafted representation-based approaches are still widely used due to some bottlenecks such as computational complexity of deep learning techniques for activity recognition. However, approaches based on handcrafted representation are not able to handle complex scenarios due to their limitations and incapability; therefore, resorting to deep learning-based techniques is a natural option. This review paper presents a comprehensive survey of both handcrafted and learning-based action representations, offering comparison, analysis, and discussions on these approaches. In addition to this, the well-known public datasets available for experimentations and important applications of HAR are also presented to provide further insight into the field. This is the first review paper of its kind which presents all these aspects of HAR in a single review article with comprehensive coverage of each part. Finally, the paper is concluded with important discussions and research directions in the domain of HAR.

show abstract

Towards Industrial Assistance Systems: Experiences of Applying Multi-sensor Fusion in Harsh Environments

Haslgrübler

Gollan

Ferscha

2019

Physiological Computing Systems

View full text Add to dashboard Cite

Vision-based action recognition of construction workers using dense trajectories

Cited by 123 publications

References 24 publications

Capturing and Understanding Workers’ Activities in Far‐Field Surveillance Videos with Deep Action Recognition and Bayesian Nonparametric Learning

Capturing and Understanding Workers’ Activities in Far‐Field Surveillance Videos with Deep Action Recognition and Bayesian Nonparametric Learning

A Comprehensive Review on Handcrafted and Learning-Based Action Representation Approaches for Human Activity Recognition

Towards Industrial Assistance Systems: Experiences of Applying Multi-sensor Fusion in Harsh Environments

Contact Info

Product

Resources

About