Application of vision aided strapdown integrated navigation in lane vehicles

Abstract

The application of global navigation satellite system (GNSS) is extensive in lane applications with the development of science and technology. Vision aided strapdown integrated navigation is an effective aided-navigation method in the case of GNSS failure in lane vehicles, which plays an important role in realising high-precision navigation of lane navigation system. A vision-aided navigation system based on GNSS positioning is constructed using the electrical powered platform as the research object. The hardware platform of vision navigation system is presented and digital image processing is used to segment the collected lane image. The image pre-processing operation, including denoising filtering and greyscale processing, is carried out to complete the segmentation and get the effective navigation area. According to the effective area of navigation, a navigation datum line is extracted by the least squares linear fitting and Hough transform. According to the camera imaging model and the camera's internal and external parameters, the navigation datum line in the image coordinates is transformed into the world coordinates, and the heading angle is calculated. Kalman filter algorithm is used to fuse the navigation parameters of the vision navigation module and the GNSS positioning module, and the integrated navigation model is established.

Self-similarity single image super-resolution based on blur kernel estimation for texture reconstruction

“…Deep CNN have shown impressive improvement in image processing tasks especially in the super-resolution (SR) reconstruction field. High-resolution images provide enhanced reconstructed details of both scenes and objects, which are essential for applications in many other domains like image segmentation (Li et al, 2019;Chen et al, 2017;Wang et al, 2020a), small object detection (Bai et al, 2018), medical imaging (Greenspan, 2009), remote sensing (Lillesand et al, 2015), fingerprint identification (Alsmirat et al, 2019), and image retrieval (Wang et al, 2020b;Chen et al, 2020;Aghav-Palwe and Mishra, 2020).…”