This paper presents a new vehicle's shape representation, which can describe its shape features. An algorithm called transformation-ring-projection (TRP), which is usually used in the recognition of characters in a binary image, is now applied to obtain multiple one-dimension patterns of vehicle shape. Firstly, in order to acquire high classification accuracy of vehicle types, we apply transformations-semi-ring-projection (TSRP) at eight central points which are distributed on the minimum ring of the vehicle region-of-interest (ROI) to traffic images and can obtain eight one-dimension patterns. Secondly, we calculate the fractal signatures in discrete wavelet transformation (DWT) domain of four one-dimension patterns. Thirdly, applying the MFC algorithm to process this kind of shape feature vector data set and generating several clusters. Finally, vehicles can be classified by shape feature matching system. Experiments results demonstrate the effectiveness and robustness of the proposed vehicle classification scheme.
Automated detection of road damage (ADRD) is a challenging topic in road maintenance. It focuses on automatically detecting road damage and assessing severity by deep learning. Because of the sparse distribution of characteristic pixels, it is more challenging than object detection. Although some public datasets provide a database for the development of ADRD, their amounts of data and the standard of classification cannot meet network training and feature learning. With the aim of solving this problem, this work publishes a new road damage dataset named CNRDD, which is labeled according to the latest evaluation standard for highway technical conditions in China (JTG5210-2018). The dataset is collected by professional onboard cameras and is manually labeled in eight categories with three different degrees (mild, moderate and severe), which can effectively help promote research of automated detection of road damage. At the same time, a novel baseline with attention fusion and normalization is proposed to evaluate and analyze the published dataset. It explicitly leverages edge detection cues to guide attention for salient regions and suppresses the weights of non-salient features by attention normalization, which can alleviate the interference of sparse pixel distribution on damage detection. Experimental results demonstrate that the proposed baseline significantly outperforms most existing methods on the existing RDD2020 dataset and the newly released CNRDD dataset. Further, the CNRDD dataset is proved more robust, as its high damage density and professional classification are more conducive to promote the development of ADRD.
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.