Abstract:
Highway and main road cracks are common. Manual road crack evaluation is tedious, inaccurate, and difficult to implement. The complex ambient conditions—illumination, shadow, dust, and crack shape—make the computer vision-based solution difficult. Most cracks have irregular edge patterns, making them the most detectable. Recent deep learning advances use a convolutional neural network to detect and localize cracks in a single RGB image. However, its crack localization boundary is inaccurate, resulting in thicker and blurrier edges. The study proposes a deep learning-based road crack detection method that uses the image’s original edge. This work improves crack boundaries by adapting the image gradient to the coarse crack detection result. The proposed method outperforms state-of-the-art methods in detection accuracy, according to extensive experiments.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
