Road crack is one of the prominent problems that can frequently occur in highways and main roads. The manual road crack evaluation is laborious, time-consuming, inaccurate, and it has several implementation issues. Conversely, the computer vision-based solution is very challenging due to the complex ambient conditions, including illumination, shadow, dust, and crack shape. Most of the cracks exist as irregular edge patterns and are the most important features for detection purpose. Recent advances in deep learning adopt a convolutional neural network as the base model to detect and localize crack with a single RGB image. Yet, this approach has an inaccurate boundary for crack localization, resulting in thicker and blurry edges. To overcome this problem, the study proposes a novel and robust road crack detection based on deep learning which also considers the original edge of the image as the additional feature. The main contribution of this work is adapting the original image gradient with the coarse crack detection result and refining it to produce more precise crack boundaries. Extensive experimental results have shown that the proposed method outperforms the former state-of-the-art methods in terms of the detection accuracy.

Road crack inspection is an important process to maintain the quality of roads for safety issues. The manual road inspection is laborious and time consuming. Thus, an automatic road crack detection is essential to make the inspection process easier and faster. Normally, this crack detection is conducted in real-time with low power computational devices and limited memory. Consequently, many former approaches adopted the patch-based approach to reduce computation for single forward, where the input image is divided into several non-overlapping patches. The generated patches are processed by independent CNN models to capture the crack position. Yet, this approach can lead to disintegrating issues because each patch is processed independently when the CNN fails to detect some patches of the crack. In this study, the improved patch-based crack detector is proposed, and the global patch analyzer is adopted to handle the above issue by considering the relation of each patch processing. Moreover, the proposed model also involves more features such as multiple decoder design and automatic resource mapper to yield superior results than that of the state-of-the-art methods in terms of the speed and accuracy as examined by extensive experiments.

Recent advances in salient object detection adopting deep convolutional neural networks have achieved state-of-the-art performance. Salient object detection is task in computer vision to detect interesting objects. Most of the Convolutional Neural Network (CNN)-based methods produce plausible saliency outputs, yet with extra computational time. However in practical, the low computation algorithm is demanded. One approach to overcome this limitation is to resize the input into a smaller size to reduce the heavy computation in the backbone network. However, this process degrades the performance, and fails to capture the exact details of the saliency boundaries due to the downsampling process. A robust refinement strategy is needed to improve the final result where the refinement computation should be lower than that of the original prediction network. Consequently, a novel approach is proposed in this study using the original image gradient as a guide to detect and refine the saliency result. This approach lowers the computational cost by eliminating the huge computation in the backbone network, enabling flexibility for users in choosing a desired size with a more accurate boundary. The proposed method bridges the benefits of smaller computation and a clear result on the boundary. Extensive experiments have demonstrated that the proposed method is able to maintain the stability of the salient detection performance given a smaller input size with a desired output size and improvise the overall salient object detection result.