Automatic Top-View Transformation and Image Stitching of In-Vehicle Smartphone Camera for Road Crack Evaluation

Geda, Jose Maria G.; Xue, Kai; Nagayama, Tomonori

doi:10.1007/978-3-030-93236-7_47

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLOv5 is an algorithm that estimates the class and position of objects in images with high speed and accuracy. In this study, the weighting parameters used were pre-trained in the previous study [27] using 65861 images taken by an in-vehicle camera. The labels were speed bump, manhole, road lane blur, linear crack, alligator crack, pothole, patch, construction crack, crack sealing, and also included 6332 expansion joint images.…”

Section: Expansion Joint Detection By Smartphone Camera and Object De...mentioning

confidence: 99%

Automatic Damage Detection of Bridge Finger-Type Expansion Joints Based on Video Object Detection and Sound Recorded on Vehicle

Imai¹,

Su²,

Mizutani³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Bridge finger type expansion joints are widely used because of their durability. However, they are susceptible to damage from fatigue and corrosion, and making the development of efficient damage detection methods crucial for preventing serious accidents. This study proposes a framework for automatic damage detection by simply driving in a vehicle, consisting of two steps: (1) detection of expansion joints by applying object detection to smartphone video, and (2) calculation of damage scores by passing sound recorded by an on-vehicle microphone. YOLOv5 object detection successfully detected 99.8% of expansion joints in the first step. Regarding the second step, experiments were conducted using one intact and four specimens modeling incremental damage. Finally, the damage score was proposed to quantify the sound of contact between among damaged structural members. After applying the proposed method to expansion joints that are in service, those identified as needing urgent replacement (Urgent Replacement Needed or U.R.N specimens) scored in the top 0.1% of the distribution of scores, indicating low false positives.</p>

show abstract

Section: Expansion Joint Detection By Smartphone Camera and Object De...mentioning

confidence: 99%

Automatic Damage Detection of Bridge Finger-Type Expansion Joints Based on Video Object Detection and Sound Recorded on Vehicle

Imai¹,

Su²,

Mizutani³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Apart from using RANSAC during the computation of homography matrices, scholars have proposed different feature-matching strategies. For instance, Geda et al [15] used the Accelerated-KAZE (AKAZE) featuredetection algorithm combined with the k-nearest neighbor algorithm and Lowe's ratio test [16] to stitch pavement images, while Wang et al [17] combined the uniformed ORB algorithm with the KD tree and k-nearest neighbor algorithms for feature-point matching, and similarly employed RANSAC to enhance the matching accuracy. These methods, which combine feature matching with different matching strategies and utilize RANSAC for stitching, have shown promising results in crack image stitching.…”

Section: Introductionmentioning

confidence: 99%

A Large-Crack Image-Stitching Method with Cracks as the Regions of Interest

Kao,

Lin,

Wang

et al. 2024

Infrastructures

View full text Add to dashboard Cite

While crack detection is crucial for maintaining concrete structures, existing methods often overlook the analysis of large cracks that span multiple images. Such analyses typically rely on image stitching to create a complete image of a crack. Current stitching methods are not only computationally demanding but also require manual adjustments; thus, a fast and reliable solution is still lacking. To address these challenges, we introduce a stitching method that leverages the advantages of crack image-segmentation models. This method first utilizes the Mask R-CNN model for the identification of crack regions as regions of interest (ROIs) within images. These regions are then used to calculate keypoints of the scale-invariant feature transform (SIFT), and descriptors for these keypoints are computed with the original images for image matching and stitching. Compared with traditional methods, our approach significantly reduces the computational time; by 98.6% in comparison to the Brute Force (BF) matcher, and by 58.7% with respect to the Fast Library for Approximate Nearest Neighbors (FLANN) matcher. Our stitching results on images with different degrees of overlap or changes in shooting posture show superior structural similarity index (SSIM) values, demonstrating excellent detail-matching performance. Moreover, the ability to measure complete crack images is indicated by the relative error of 7%, which is significantly better than that of traditional methods.

show abstract

Automatic Top-View Transformation and Image Stitching of In-Vehicle Smartphone Camera for Road Crack Evaluation

Cited by 2 publications

References 9 publications

Automatic Damage Detection of Bridge Finger-Type Expansion Joints Based on Video Object Detection and Sound Recorded on Vehicle

Automatic Damage Detection of Bridge Finger-Type Expansion Joints Based on Video Object Detection and Sound Recorded on Vehicle

A Large-Crack Image-Stitching Method with Cracks as the Regions of Interest

Contact Info

Product

Resources

About