Deep learning–based autonomous concrete crack evaluation through hybrid image scanning

TLDR

Hybrid vision‑infrared thermography images improve crack detectability and reduce false alarms, yet expert‑dependent crack identification remains cumbersome and unreliable, making automated decision‑making increasingly desirable for large concrete structures. The study proposes an autonomous concrete crack detection method that uses deep learning on hybrid vision‑infrared images. The method scans large concrete structures with an unmanned vehicle equipped with a vision camera, infrared camera, and continuous‑wave line laser, then applies transfer‑learning of GoogLeNet on hybrid images to automatically identify and visualize cracks, as validated on a lab‑scale specimen with varying crack sizes. Experiments show that macro‑ and microcracks are automatically visualized with minimal false alarms.

Abstract

This article proposes a deep learning–based autonomous concrete crack detection technique using hybrid images. The hybrid images combining vision and infrared thermography images are able to improve crack detectability while minimizing false alarms. In particular, large-scale concrete-made infrastructures such as bridge and dam can be effectively inspected by spatially scanning the unmanned vehicle–mounted hybrid imaging system including a vision camera, an infrared camera, and a continuous-wave line laser. However, the expert-dependent decision-making for crack identification which has been widely used in industrial fields is often cumbersome, time-consuming, and unreliable. As a target concrete structure gets larger, automated decision-making becomes more desirable from the practical point of view. The proposed technique is able to achieve automated crack identification and visualization by transfer learning of a well-trained deep convolutional neural network, that is, GoogLeNet, while retaining the advantages of the hybrid images. The proposed technique is experimentally validated using a lab-scale concrete specimen with cracks of various sizes. The test results reveal that macro- and microcracks are automatically visualized while minimizing false alarms.