Computer-Aided Civil and Infrastructure Engineering · 2020 · 149 citations · 54 references
ComputingComputer ScienceConstruction ManagementComputer VisionConstruction EngineeringMachine LearningConstruction AutomationDeep LearningObject DetectionObject RecognitionPattern RecognitionComputer Vision For ConstructionDeep Learning In ConstructionDeep Learning-based DetectionDeploymentMachine Learning In ConstructionSafety MonitoringSafety Monitoring SystemsSystem Selection
The study presents a practical deep‑learning framework for detecting construction vehicles, emphasizing the often‑neglected deployment phase. The framework was built through data preparation, improved SSD‑MobileNet training and validation, model optimization, embedded system selection, economic analysis, and field implementation, with several devices compared. The approach achieved consistently above 90 % mean average precision, demonstrating superior real‑time performance and validating its practicality for safety monitoring, productivity assessment, and managerial decision‑making.
Abstract This paper aims at providing researchers and engineering professionals from the first step of solution development to the last step of solution deployment with a practical and comprehensive deep‐learning‐based solution for detecting construction vehicles. This paper places particular focus on the often‐ignored last step of deployment. Our first phase of solution development involved data preparation, model selection, model training, and model validation. Given the necessarily small‐scale nature of construction vehicle image datasets, we propose as detection model an improved version of the single shot detector MobileNet, which is suitable for embedded devices. Our study's second phase comprised model optimization, application‐specific embedded system selection, economic analysis, and field implementation. Several embedded devices were proposed and compared. Results including a consistent above 90% mean average precision confirm the superior real‐time performance of our proposed solutions. Finally, the practical field implementation of our proposed solutions was investigated. This study validates the practicality of deep‐learning‐based object detection solutions for construction scenarios. Moreover, the detailed information provided by the current study can be employed for several purposes such as safety monitoring, productivity assessments, and managerial decision making.
54
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations