SHAPE SEARCHING IN REAL WORLD IMAGES : A CNN-BASED APPROACH

This paper reports on work that focuses on the correct identification of road traffic signs in images taken by a car mounted camera. The basic technique used in this kind of situation is to compare each portion of an image with a set of known models. The approach taken in the work is to implement this comparison with cellular neural networks, making it possible to efficiently use a massively parallel architecture. In order to reduce the response time of the system, the approach also includes data reduction techniques. The results of several tests, in different conditions, are reported in the paper. The system correctly detects a test shape in almost all the experiments performed. The paper also contains a detailed description of the system architecture and of the processing steps.

• Supplemental Notes:
  • Publication Date: 1996 Published By: IEEE Service Center, Piscataway NJ
• Corporate Authors:

  Universita di Parma Dipartimento di ingegneria dell informazione

  ,    
• Authors:
  • Adorni, G
• Conference:
  • IEEE International Workshop on Cellular Neural Networks and their Applications (4th : 1996 : Seville, Spain). Proceedings ... CNNA-96
• Publication Date: 1996

Language

• English

Media Info

• Pagination: p. 213-218

Subject/Index Terms

• TRT Terms: Computer vision; Neural networks; Parallel processing; Traffic signs
• Subject Areas: Operations and Traffic Management;

Filing Info

• Accession Number: 00775133
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 1999 12:00AM