Real Time Vision System for Obstacle Detection and Localization on FPGA

详细信息    查看全文

• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9163
• 期：1
• 页码：80-90
• 全文大小：2,465 KB
• 参考文献：1.Bendaoudi, H., Khouas, A., Cherki, B.: FPGA design of a real-time obstacle detection system using stereovision. In: 24th International Conference on Microelectronics (ICM), 2012, pp. 1-. IEEE (2012)
  2.Bertozzi, M., Broggi, A., Fascioli, A.: Stereo inverse perspective mapping: theory and applications. Image Vis. Comput. 16(8), 585-90 (1998)View Article
  3.Botero, D., Piat, J., Chalimbaud, P., Devy, M.: FPGA implementation of mono and stereo inverse perspective mapping for obstacle detection. In: Design and Architectures for Signal and Image Processing (DASIP), pp. 1-. IEEE (2012)
  4.Bresengham, J.: Algorithm for computer control of a digital plotter. IBM Syst. 4(1), 25-0 (1965)View Article
  5.Cesar, C., Mendes, T., Osorio, F.S., Wolf, D.F.: An efficient obstacle detection approach for organized point clouds. In: Intelligent Vehicles Symposium, pp. 1203-208. IEEE (2013)
  6.Ha, J., Sattigeri, R.: Vision-based obstacle avoidance based on monocular slam and image segmentation for UAVs. In: Infotech@Aerospace 2012, pp. 1-. AIAA (2012)
  7.Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, UK (2004)MATH View Article
  8.He, C.Y., Hongand, C.T., Lo, R.C.: An improved obstacle detection using optical flow adjusting based on inverse perspective mapping for the vehicle safety. In: International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS), 2012, pp. 85-9. IEEE (2012)
  9.Mallot, H.A., Blthoff, H.H., Little, J.J., Bohrer, S.: Inverse perspective mapping simplifies optical flow computation and obstacle detection. Biol. Cybern. 64(3), 177-85 (1991)MATH View Article
  10.Otsu, N.: Threshold selection method from gray-level histogram. IEEE Trans.Syst. SMC-(1), 62-6 (1979)MathSciNet
  11.Yankun, Z., Chuyang, H., Norman, W.: A single camera based rear obstacle detection system. In: Intelligent Vehicles Symposium, pp. 485-90. IEEE (2011)
  
• 作者单位：Ali Alhamwi (17)
  Bertrand Vandeportaele (17) (18)
  Jonathan Piat (17) (18)
  
  17. LAAS-CNRS, 7 Avenue du Colonel Roche, 31077, Toulouse Cedex 4, France
  18. University of Toulouse, 31077, Toulouse Cedex 4, France
  
• 丛书名：Computer Vision Systems
• ISBN：978-3-319-20904-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Obstacle detection is a mandatory function for a robot navigating in an indoor environment especially when interaction with humans is done in a cluttered environment. Commonly used vision-based solutions like SLAM (Simultaneous Localization and Mapping) or optical flow tend to be computation intensive and require powerful computation resources to meet low speed real-time constraints. Solutions using LIDAR (Light Detection And Ranging) sensors are more robust but not cost effective. This paper presents a real-time hardware architecture for vision-based obstacle detection and localization based on IPM (Inverse Perspective Mapping) for obstacle detection, and Otsu’s method plus Bresenham’s algorithm for obstacle segmentation and localization under the hypothesis of a flat ground. The proposed architecture combines cost effectiveness, high frame-rate with low latency, low power consumption and without any prior knowledge of the scene compared to existing implementations.