Hybrid Machine Learning for Automated Road Safety Inspection of Auckland Harbour Bridge

被引:0
作者
Rathee, Munish [1 ]
Bacic, Boris [1 ]
Doborjeh, Maryam [1 ,2 ]
机构
[1] Auckland Univ Technol, Sch Engn Comp & Math Sci, Auckland 1010, New Zealand
[2] Auckland Univ Technol, Knowledge Engn & Discovery Res Innovat, Auckland 1010, New Zealand
关键词
anomaly detection; structural damage detection; traffic safety; computer vision; machine learning; deep learning; transfer learning; ARDAD; ALGORITHMS;
D O I
10.3390/electronics13153030
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Auckland Harbour Bridge (AHB) utilises a movable concrete barrier (MCB) to regulate the uneven bidirectional flow of daily traffic. In addition to the risk of human error during regular visual inspections, staff members inspecting the MCB work in diverse weather and light conditions, exerting themselves in ergonomically unhealthy inspection postures with the added weight of protection gear to mitigate risks, e.g., flying debris. To augment visual inspections of an MCB using computer vision technology, this study introduces a hybrid deep learning solution that combines kernel manipulation with custom transfer learning strategies. The video data recordings were captured in diverse light and weather conditions (under the safety supervision of industry experts) involving a high-speed (120 fps) camera system attached to an MCB transfer vehicle. Before identifying a safety hazard, e.g., the unsafe position of a pin connecting two 750 kg concrete segments of the MCB, a multi-stage preprocessing of the spatiotemporal region of interest (ROI) involves a rolling window before identifying the video frames containing diagnostic information. This study utilises the ResNet-50 architecture, enhanced with 3D convolutions, within the STENet framework to capture and analyse spatiotemporal data, facilitating real-time surveillance of the Auckland Harbour Bridge (AHB). Considering the sparse nature of safety anomalies, the initial peer-reviewed binary classification results (82.6%) for safe and unsafe (intervention-required) scenarios were improved to 93.6% by incorporating synthetic data, expert feedback, and retraining the model. This adaptation allowed for the optimised detection of false positives and false negatives. In the future, we aim to extend anomaly detection methods to various infrastructure inspections, enhancing urban resilience, transport efficiency and safety.
引用
收藏
页数:29
相关论文
共 64 条
[1]  
Agrawal S., 2021, P 2021 4 INT C EL CO, P1
[2]  
[Anonymous], 2024, Wikipedia Barrier Transfer Machine
[3]   Anomaly Detection in Connected and Autonomous Vehicles: A Survey, Analysis, and Research Challenges [J].
Baccari, Sihem ;
Hadded, Mohamed ;
Ghazzai, Hakim ;
Touati, Haifa ;
Elhadef, Mourad .
IEEE ACCESS, 2024, 12 :19250-19276
[4]   Automating Inspection of Moveable Lane Barrier for Auckland Harbour Bridge Traffic Safety [J].
Bacic, Boris ;
Rathee, Munish ;
Pears, Russel .
NEURAL INFORMATION PROCESSING, ICONIP 2020, PT I, 2020, 12532 :150-161
[5]   Surface defect detection methods for industrial products with imbalanced samples: A review of progress in the 2020s [J].
Bai, Dongxu ;
Li, Gongfa ;
Jiang, Du ;
Yun, Juntong ;
Tao, Bo ;
Jiang, Guozhang ;
Sun, Ying ;
Ju, Zhaojie .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 130
[6]  
Bharambe U., 2023, Computational Intelligence in Image and Video Processing, P317
[7]   Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences [J].
Butt, Umair Muneer ;
Ullah, Hadiqa Aman ;
Letchmunan, Sukumar ;
Tariq, Iqra ;
Hassan, Fadratul Hafinaz ;
Koh, Tieng Wei .
CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 74 (03) :5017-5033
[8]   Traffic Foreground Detection at Complex Urban Intersections Using a Novel Background Dictionary Learning Model [J].
Cao, Qianxia ;
Wang, Zhengwu ;
Long, Kejun .
JOURNAL OF ADVANCED TRANSPORTATION, 2021, 2021
[9]  
Carlson M., 2005, EDUC STUD MATH, V58, P45, DOI DOI 10.1007/S10649-005-0808-X
[10]  
Chaurasiya R.K., 2023, P 2023 7 INT C COMP, P1