Read more
AN DEEP LEARNING BASED SHADOW REMOVAL AND PAVEMENT CRACK DETECTION
Here the challenging task is Automatic pavement crack detection for maintaining the pavement stability by removing shadow which is having same intensity as cracks, which interfere with the crack detection performance. Till to the present, there still lacks efficient algorithm models and training datasets to deal with the interference brought by the shadows. Methodology involves three steps first pre-processing steps improves quality of the image. Second step involves detection of both shadows and removal of shadows whereas classification of cracks is done by using deep learning approach. The system uses intensity values for precision and supports multiple image formats. Advanced filtering eliminates noise. Binarizing and filling holes improves crack detection by using canny edge detection. To isolate important features, insignificant blobs are removed and cracks are identified by using feature extraction network. Based on this mechanism, we propose a data augmentation method based on the difference in brightness values, which can adapt to brightness changes caused by seasonal and weather changes. Finally, we introduced a residual feature augmentation algorithm to detect small cracks that can predict sudden disasters, and the algorithm improves the performance of the model overall. Finally, we introduced a and deep learning method for classification of cracks that can predict sudden disasters, and the algorithm improves overall performance. The proposed system uses shadow-crack dataset for training and testing. The system detects cracks at 94% with least MSE. The testing and training accuracy of the proposed model out performs the other state of art methods.
off/-10%
