Design Hints for Efficient Robotic Vision - Lessons Learned from a Robotic Platform

Interest in autonomous vehicles has steadily increased in recent years. A number of tasks, like lane tracking, semaphore detection and decoding, are key features for a self-driving robot. This paper presents a path detection and tracking algorithm using the Inverse Perspective Mapping and Hough Transform methods compounded with real-time vision techniques and a semaphore recognition system based on color segmentation. An evaluation of the proposed algorithm is performed and a comparison between the results using real-time techniques is also presented. The suggested architecture has been put to test on autonomous driving robot who competed in the Portuguese autonomous vehicle competition called “Festival Nacional de Robotica”. The overall process of the lane tracking algorithm, takes about 1.4 ms per image, almost 60 times faster than the first algorithm tested and a good accuracy, showing a translation error below 0.03 m and a rotation error below 5\(^\circ \). Regarding the real-time semaphore recognition, it takes about 0.35 ms to detect a semaphore and has achieved a perfect score in the laboratory tests performed.

[1]  Ning Chen A vision-guided autonomous vehicle: an alternative micromouse competition , 1997 .

[2]  António Fernando Ribeiro,et al.  Vision and distance integrated sensor (Kinect) for an autonomous robot , 2011 .

[3]  Sebastian Ramos,et al.  Vision-Based Offline-Online Perception Paradigm for Autonomous Driving , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[4]  Antonella Ferrara,et al.  Visual Interaction for Real-Time Navigation of Autonomous Mobile Robots , 2009, 2009 International Conference on CyberWorlds.

[5]  Li Deyi,et al.  Traffic light detection and recognition for autonomous vehicles , 2015 .

[6]  Kang-Hyun Jo,et al.  Traffic sign recognition system for autonomous vehicle using cascade SVM classifier , 2014, IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society.

[7]  Miguel Oliveira,et al.  Multimodal inverse perspective mapping , 2015, Inf. Fusion.

[8]  Fatin Zaklouta,et al.  Real-time traffic sign recognition in three stages , 2014, Robotics Auton. Syst..

[9]  Kwanghoon Sohn,et al.  Real-time illumination invariant lane detection for lane departure warning system , 2015, Expert Syst. Appl..

[10]  A. Hussain,et al.  Implementation of inverse perspective mapping algorithm for the development of an automatic lane tracking system , 2004, 2004 IEEE Region 10 Conference TENCON 2004..

[11]  Luis Magdalena,et al.  A Color Vision-Based Lane Tracking System for Autonomous Driving on Unmarked Roads , 2004, Auton. Robots.

[12]  Fawzi Nashashibi,et al.  Traffic light recognition using image processing compared to learning processes , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Mohamed Aly,et al.  Real time detection of lane markers in urban streets , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[14]  Gregory D. Hager,et al.  X Vision: A Portable Substrate for Real-Time Vision Applications , 1998, Comput. Vis. Image Underst..

[15]  Mohamed S. Kamel,et al.  Image Analysis and Recognition , 2014, Lecture Notes in Computer Science.