An Improved Crack Identification Method for Asphalt Concrete Pavement

Article Computer Science, Artificial Intelligence

Classification of pavement crack types based on square bounding box diagonal matching method

Guofeng Qin et al.

Summary: With the increase in traffic volume, the task of inspection and maintenance of road pavements has become increasingly arduous. This paper proposes a crack classification method based on diagonal matching of square bounding boxes, providing quantitative criteria for refining the intrinsic relationship of complex types of crack areas. Experimental results demonstrate that the proposed method performs better in the classification of pavement crack types.

NEURAL COMPUTING & APPLICATIONS (2022)

Add to Collection

Article Energy & Fuels

Fractal Characterization of Multimodal, Multiscale Images of Shale Rock Fracture Networks

Bolivia Vega et al.

Summary: In this study, an array of fractured shale rock samples and analogs were collected to improve the numerical representation of fracture networks. The analysis of multimodal and multiscale images revealed that the origin of the fracture networks plays a crucial role in the resulting fracture systems and their scaling. The evaluation of rock analogs using descriptive tools demonstrated their faithfulness in depicting maturation-induced fracture networks.

ENERGIES (2022)

Add to Collection

Article Engineering, Civil

A Crack Detection Algorithm for Concrete Pavement Based on Attention Mechanism and Multi-Features Fusion

Zhong Qu et al.

Summary: The study proposes a novel crack detection algorithm for concrete pavement based on attention mechanism and multi-features fusion, which uses techniques such as encoder-decoder structure, cascade and parallel mode dilated convolutions to effectively handle different types of cracks in various pavement backgrounds.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Automation & Control Systems

A New Watershed Algorithm for Pothole Image Segmentation

Tutuk Indriyani et al.

Summary: This study successfully determined the surface area of potholed roads using a new watershed algorithm, achieving a high accuracy of 95.34%. The proposed algorithm effectively reduced the effects of excessive segmentation and outperformed existing watershed segmentation methods.

STUDIES IN INFORMATICS AND CONTROL (2021)

Add to Collection

Article Engineering, Civil

Crack grid detection and calculation based on convolutional neural network

Liyang Xiao et al.

Summary: In this paper, crack grid detection based on convolutional neural network is developed, achieving high accuracy crack detection through image denoising and grid segmentation. The 30 x 30 grids perform the best, automatic detection avoids fracture phenomenon, and ensures the integrity of cracks.

CANADIAN JOURNAL OF CIVIL ENGINEERING (2021)

Add to Collection

Article Automation & Control Systems

Topographically Guided UAV for Identifying Tension Cracks Using Image-Based Analytics in Open-Pit Mines

Garrett Winkelmaier et al.

Summary: Aerial imaging integrated with visual analytics provides a novel approach for routine monitoring of tension cracks in an open-pit mine to ensure mine safety. The research aimed to automate report generation for the mine controller by using drone flights to capture high-resolution images for delineating tension cracks. Deep learning models like ENet showed promising performance in accurately detecting tension cracks with an Aggregated Jaccard Index and F1-Score of 0.51 and 0.79, using a leave-one-out cross-validation method.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2021)

Add to Collection

Article Construction & Building Technology