Yazhe Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yazhe Hu has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Tomonari Furukawa
Department of Mechanical Engineering, University of Virginia, Charlottesville, VA 22903, USA
2 shared publications
Latest Publications
- Open Access
Degenerate Near-Planar 3D Reconstruction from Two Overlapped Images for Road Defects Detection
This paper presents a technique to reconstruct a three-dimensional (3D) road surface from two overlapped images for road defects detection using a downward-facing camera. Since some road defects, such as potholes, are characterized by 3D geometry, the proposed technique reconstructs road surfaces from the overlapped images prior to defect detection. The uniqueness of the proposed technique lies in the use of near-planar characteristics of road surfaces‘ in the 3D reconstruction process, which solves the degenerate road surface reconstruction problem. The reconstructed road surfaces thus result from the richer information. Therefore, the proposed technique detects road surface defects based on the accuracy-enhanced 3D reconstruction. Parametric studies were first performed in a simulated environment to analyze the 3D reconstruction error affected by different variables and show that the reconstruction errors caused by the camera’s image noise, orientation, and vertical movement are so small that they do not affect the road defects detection. Detailed accuracy analysis then shows that the mean and standard deviation of the errors are less than mm and 1 mm through real road surface images. Finally, on-road tests demonstrate the effectiveness of the proposed technique in identifying road defects while having over 94% in precision, accuracy, and recall rate.Open AccessDegenerate Near-Planar 3D Reconstruction from Two Overlapped Images for Road Defects Detection
This paper presents a technique to reconstruct a three-dimensional (3D) road surface from two overlapped images for road defects detection using a downward-facing camera. Since some road defects, such as potholes, are characterized by 3D geometry, the proposed technique reconstructs road surfaces from the overlapped images prior to defect detection. The uniqueness of the proposed technique lies in the use of near-planar characteristics of road surfaces‘ in the 3D reconstruction process, which solves the degenerate road surface reconstruction problem. The reconstructed road surfaces thus result from the richer information. Therefore, the proposed technique detects road surface defects based on the accuracy-enhanced 3D reconstruction. Parametric studies were first performed in a simulated environment to analyze the 3D reconstruction error affected by different variables and show that the reconstruction errors caused by the camera’s image noise, orientation, and vertical movement are so small that they do not affect the road defects detection. Detailed accuracy analysis then shows that the mean and standard deviation of the errors are less than mm and 1 mm through real road surface images. Finally, on-road tests demonstrate the effectiveness of the proposed technique in identifying road defects while having over 94% in precision, accuracy, and recall rate. - Open Access
- 1 January 2018
- Published by Society of Automotive Engineers of Japan, Inc. in International Journal of Automotive Engineering
- Vol. 9 (4) , 323-331
Automatic Detection and Evaluation of 3D Pavement Defects Using 2D and 3D Information at the High Speed
This paper presents a technique of automatic 3D pavement defects detection using both the two-dimensional (2D) and three-dimensional (3D) information from the images captured at high speed. Scaled 3D points reconstructed from Structure from Motion algorithm are first used to detect the defect regions based on the 3D information. A mismatched points rejection method then eliminates incorrectly matched points and reconstructs a final 3D road surface. The proposed technique uses both 3D and 2D information for the defects detection where the characteristics of defect regions in 2D images together with the 3D information from the 3D reconstruction detect the defect region. The capability of the proposed technique was first investigated through parameters studies. Quantitative analyses have shown the accuracy, precision, and recall rate of the proposed technique are all above 90%. The result demonstrates the potential of the proposed technique for the automatic detection of 3D pavement defects.
- 1 January 2018
- Published by Society of Automotive Engineers of Japan, Inc. in International Journal of Automotive Engineering
- Vol. 9 (4) , 323-331
Open AccessAutomatic Detection and Evaluation of 3D Pavement Defects Using 2D and 3D Information at the High Speed
This paper presents a technique of automatic 3D pavement defects detection using both the two-dimensional (2D) and three-dimensional (3D) information from the images captured at high speed. Scaled 3D points reconstructed from Structure from Motion algorithm are first used to detect the defect regions based on the 3D information. A mismatched points rejection method then eliminates incorrectly matched points and reconstructs a final 3D road surface. The proposed technique uses both 3D and 2D information for the defects detection where the characteristics of defect regions in 2D images together with the 3D information from the 3D reconstruction detect the defect region. The capability of the proposed technique was first investigated through parameters studies. Quantitative analyses have shown the accuracy, precision, and recall rate of the proposed technique are all above 90%. The result demonstrates the potential of the proposed technique for the automatic detection of 3D pavement defects.