Dual attention-based deep learning for construction equipment activity recognition considering transition activities and imbalanced dataset

Shen, Yuying; Wang, Jixin; Feng, Chenlong; Wang, Qi

doi:10.1016/j.autcon.2024.105300

Cited by 2 publications

(2 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite their benefits, vision-based methods encounter significant challenges. These include obstructions by adverse weather conditions (e.g., fog, dust, rain, and snow), unfavorable lighting conditions (e.g., luminous flux, illuminance, beam angle, and color temperature), and occlusions by construction equipment, which can significantly impair activity recognition [20,21]. For example, poor lighting and occlusions have been identified as factors that may lead to inaccurate activity detection and classification [22].…”

Section: Vision-based Methods For Recognizing Equipment Activitymentioning

confidence: 99%

“…For example, in a study that applied IMU and GPS signals data to the fractional random forest (FRF) technique, the same learning method was applied to actual excavators and a one-twelfth scale model, but the experiment showed a difference in accuracy, with 84.1% for the actual excavator and 72.9% for the model excavator [14]. Thus, the accuracy of subsequent activity recognition in the kinematic method is significantly affected by the sensor's location, tag number, and positioning details of the construction equipment structure [20].…”

Section: Sensor-based Methods For Recognizing Equipment Activitymentioning

confidence: 99%

See 1 more Smart Citation

Time of Flight Distance Sensor–Based Construction Equipment Activity Detection Method

Park,

2024

Applied Sciences

View full text Add to dashboard Cite

In this study, we delve into a novel approach by employing a sensor-based pattern recognition model to address the automation of construction equipment activity analysis. The model integrates time of flight (ToF) sensors with deep convolutional neural networks (DCNNs) to accurately classify the operational activities of construction equipment, focusing on piston movements. The research utilized a one-twelfth-scale excavator model, processing the displacement ratios of its pistons into a unified dataset for analysis. Methodologically, the study outlines the setup of the sensor modules and their integration with a controller, emphasizing the precision in capturing equipment dynamics. The DCNN model, characterized by its four-layered convolutional blocks, was meticulously tuned within the MATLAB environment, demonstrating the model’s learning capabilities through hyperparameter optimization. An analysis of 2070 samples representing six distinct excavator activities yielded an impressive average precision of 95.51% and a recall of 95.31%, with an overall model accuracy of 95.19%. When compared against other vision-based and accelerometer-based methods, the proposed model showcases enhanced performance and reliability under controlled experimental conditions. This substantiates its potential for practical application in real-world construction scenarios, marking a significant advancement in the field of construction equipment monitoring.

show abstract

Section: Vision-based Methods For Recognizing Equipment Activitymentioning

confidence: 99%

Section: Sensor-based Methods For Recognizing Equipment Activitymentioning

confidence: 99%