In recent years, deep learning-based detection methods have been applied to pavement crack detection. In practical applications, surface cracks are divided into inner and edge regions for pavements with rough surfaces and complex environments. This creates difficulties in the image detection task. This paper is inspired by the U-Net semantic segmentation network and holistically nested edge detection network. A side-output part is added to the U-Net decoder that performs edge extraction and deep supervision. A network model combining two tasks that can output the semantic segmentation results of the crack image and the edge detection results of different scales is proposed. The model can be used for other tasks that need both semantic segmentation and edge detection. Finally, the segmentation and edge images are fused using different methods to improve the crack detection accuracy. The experimental results show that mean intersection over union reaches 69.32 on our dataset and 61.05 on another pavement dataset group that did not participate in training. Our model is better than other detection methods based on deep learning. The proposed method can increase the MIoU value by up to 5.55 and increase the MPA value by up to 10.41 when compared to previous semantic segmentation models.
This paper presents an innovative complete observable initial alignment method for strapdown inertial navigation system. This method negates the need for multi-position rotation or a complex rotating mechanism. First, the coupling relationship between the error state variables is analytically derived. Based on the equivalence relationship between the acceleration output and the angular rate output and error state variables, an improved extended-measurement equation is then established. The feasibility of the scheme that accelerates the convergence speed is theoretically demonstrated, and the observability of the proposed method is qualitatively and quantitatively analyzed in comparisons with established methods (piece-wise constant system, singular value decomposition, and error covariance matrix analysis). The results confirm that the improved measurement model enhances the observability of state variables to different extent and can achieve complete observability of the system. The proposed method not only can provide the fast and accurate estimation of the alignment error, but also can predict the gyro bias online. More specifically, the equivalent horizontal accelerometer output certainly accelerated the convergence of the horizontal alignment error, and introducing the equivalent gyroscope output improved the convergence speed of the heading alignment error. It is a potential candidate for speeding up the convergence of the stationary initial alignment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.