7 June 2017 Urban vehicle detection in high-resolution aerial images via superpixel segmentation and correlation-based sequential dictionary learning
Author Affiliations +
Abstract
Vehicle detection in high-resolution aerial images has received widespread interests when it comes to providing the required information for traffic management and urban planning. It is challenging due to the relatively small size of the vehicles and the complex background. Furthermore, it is particularly challenging if the higher detection efficiency is required. Therefore, an urban vehicle detection algorithm is proposed via improved entropy rate clustering (IERC) and correlation-based sequential dictionary learning (CSDL). First, to enhance the detection accuracy, IERC is designed to generate more regular superpixels. It aims to avoid the situation that one superpixel sometimes straddles multiple vehicles. The generated superpixels are then treated as the seeds for the training sample selection. Then, CSDL is constructed to achieve a fast sequential training and updating of the dictionary. In CSDL, only the atoms correlated with the sparse representation of the new training data are inferred. Finally, comprehensive analyses and comparisons on two data sets demonstrate that the proposed method generates satisfactory and competitive results.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Xunxun Zhang, Xunxun Zhang, Hongke Xu, Hongke Xu, Jianwu Fang, Jianwu Fang, Gang Sheng, Gang Sheng, } "Urban vehicle detection in high-resolution aerial images via superpixel segmentation and correlation-based sequential dictionary learning," Journal of Applied Remote Sensing 11(2), 026028 (7 June 2017). https://doi.org/10.1117/1.JRS.11.026028 . Submission: Received: 20 December 2016; Accepted: 17 April 2017
Received: 20 December 2016; Accepted: 17 April 2017; Published: 7 June 2017
JOURNAL ARTICLE
17 PAGES


SHARE
Back to Top