Effects of Video Filters for Learning an Action Recognition Model for Construction Machinery from Simulated Training Data

Sim, Jinhyeok; Kasahara, Jun Younes Louhi; Chikushi, Shota; Nagatani, Keiji; Chiba, Takumi; Chayama, Kazuhiro; Yamashita, Atsushi; Asama, Hajime

doi:10.1109/ieeeconf49454.2021.9382735

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, this study offers valuable information about research themes published on the topic of deep learning and its implementation in the construction industry through cluster analysis and critical review. Despite the contributions offered, the (Bang et al 2019, Chen et al 2020, Guo et al 2020, Slaton et al 2020, Xuehui et al 2021, Zhou et al 2021b, Lin et al 2021, Sim et al 2021 (Olanrewaju et al 2020, Kamal et al 2020, Liu et al 2020, Scarpiniti et al 2021)…”

Section: Discussionmentioning

confidence: 99%

Scientometric analysis and critical review on the application of deep learning in the construction industry

et al. 2023

View full text Add to dashboard Cite

Deep learning in construction industry has attracted increasing attention among researchers. In this article, scientometric analysis and critical review are performed to analyze the state-of-the-art literature on the application of deep learning in construction. This research used the science mapping method to quantitatively and systematically analyze 423 related bibliographic records retrieved from the Scopus database, and further, a critical review is performed on collected themes. The results of the critical review indicate that deep convolution neural networks, you only look once, residual neural networks and fast region-based convolution neural networks have been the most widely used methods in the construction industry. The most commonly addressed problems in the construction industry using deep learning methods includes classification of construction equipment, worker's safety helmet detection and ergonomics analysis. This paper provides an in-depth understanding of the existing literature along with the challenges and future direction of deep learning in the construction industry.

show abstract

Section: Discussionmentioning

confidence: 99%

Scientometric analysis and critical review on the application of deep learning in the construction industry

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Machine learning methods designed to process videos use different features. In some applications, consistency is not necessary, and the method should only extract spatial features; however, in some applications-for example, in human action recognition (HAR)frame continuity is critical [3]. Among the research that tries to optimize a video as an input of machine learning systems, Ref.…”

Section: Introductionmentioning

confidence: 99%

Best Frame Selection to Enhance Training Step Efficiency in Video-Based Human Action Recognition

et al. 2022

View full text Add to dashboard Cite

In recent years, with the growth of digital media and modern imaging equipment, the use of video processing algorithms and semantic film and image management has expanded. The usage of different video datasets in training artificial intelligence algorithms is also rapidly expanding in various fields. Due to the high volume of information in a video, its processing is still expensive for most hardware systems, mainly in terms of its required runtime and memory. Hence, the optimal selection of keyframes to minimize redundant information in video processing systems has become noteworthy in facilitating this problem. Eliminating some frames can simultaneously reduce the required computational load, hardware cost, memory and processing time of intelligent video-based systems. Based on the aforementioned reasons, this research proposes a method for selecting keyframes and adaptive cropping input video for human action recognition (HAR) systems. The proposed method combines edge detection, simple difference, adaptive thresholding and 1D and 2D average filter algorithms in a hierarchical method. Some HAR methods are trained with videos processed by the proposed method to assess its efficiency. The results demonstrate that the application of the proposed method increases the accuracy of the HAR system by up to 3% compared to random image selection and cropping methods. Additionally, for most cases, the proposed method reduces the training time of the used machine learning algorithm.

show abstract

Action Recognition of Excavator with Data Augmentation of Simulator-Generated Training Data

Kasahara¹,

Sim²,

KOMATSU³

et al. 2022

Journal of the Japan Society for Precision Engineering

View full text Add to dashboard Cite

Effects of Video Filters for Learning an Action Recognition Model for Construction Machinery from Simulated Training Data

Cited by 3 publications

References 13 publications

Scientometric analysis and critical review on the application of deep learning in the construction industry

Scientometric analysis and critical review on the application of deep learning in the construction industry

Best Frame Selection to Enhance Training Step Efficiency in Video-Based Human Action Recognition

Action Recognition of Excavator with Data Augmentation of Simulator-Generated Training Data

Contact Info

Product

Resources

About