详情

原文传递 Automated Inventory and Analysis of Highway Assets. Phase II.

题名：	Automated Inventory and Analysis of Highway Assets. Phase II.
作者：	wang, k. c. p. gong, w. hou, z.
关键词：	human observation, automated system, sign detection, sign classification, neural network, support vector machine, statistical learning method
摘要：	Road sign plays an important role in highway system management by providing drivers and road users guidance, warning and other driving related information. Proper sign maintenance and inventory is therefore necessary. Sign inventory system is an essential tool for infrastructure management and maintenance. Currently, sign inventory is mostly conducted by human observation of the digital images of roadway scenes. Automated system would substantially improve the processing speed and accuracy of two key processing tasks, sign detection and sign classification, since the human observation of the large amount of images is tedious, error-prone and time-consuming. The research in this final report emphasizes on the study of the classification. Classification is to categorize signs into proper classes, which is important and also more difficult for automation in the automated sign inventory system. The most frequently used technique in previous research for classification is neural network. However, neural network has the local minimum problem. In addition, neural network lacks explainable inner theoretical rule which brings difficulty to fine tune the performance of the model. This research presents a method for sign classification which combines feature extraction, Support Vector Machine (SVM), and multi-class classification. SVM is a statistical learning method based on Vapnik-Chervonenkis (VC) dimension and structural minimum principle. It is supposed to overcome the aforementioned two drawbacks of neural network method. The feature extraction is accomplished by Principal Component Analysis (PCA) which reduces the dimension of the image as well as keeping the most important features. Preliminary experimental result presented in the report demonstrates that the SVM method has potential to solve the road sign classification problem. / NOTE: Technical rept. (Final). 1 Jul 06-15 Aug 07. / Supplementary Notes: See also report PB2007-107300. Sponsored by Department of Transportation, Washington, DC. University Transportation Centers Program. / Availability Note: Product reproduced from digital image. Order this product from NTIS by: phone at 1-800-553-NTIS (U.S. customers); (703)605-6000 (other countries); fax at (703)605-6900; and email at orders@ntis.gov. NTIS is located at 5285 Port Royal Road, Springfield, VA, 22161, USA.
总页数：	u0819；18p
报告类型：	科技报告