Distance measurement for self-driving cars using stereo camera

Self-driving cars reduce human error and can accomplish various missions to help people in different fields.They have become one of the main interests in automotive research and development, both in the industry and academia. However, many challenges are encountered in dealing with distance measurement and cost, both in equipment and technique.The use of stereo camera to measure the distance of an object is convenient and popular for obstacle avoidance and navigation of autonomous vehicles.The calculation of distance considers angular distance, distance between cameras, and the pixel of the image.This study proposes a method that measures object distance based on trigonometry, that is, facing the self-driving car using image processing and stereo vision with high accuracy, low cost, and computational speed.The method achieves a high distance measuring accuracy of up to 20 m. It can be implemented in real time computing systems and can determine the safe driving distance between obstacles.

[1]  Valentin Obac Roda,et al.  Real-time disparity map extraction in a dual head stereo vision system , 2007 .

[2]  Noah J. Goodall,et al.  Ethical Decision Making during Automated Vehicle Crashes , 2014, ArXiv.

[3]  Klaus-Dieter Kuhnert,et al.  Fusion of Stereo-Camera and PMD-Camera Data for Real-Time Suited Precise 3D Environment Reconstruction , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  I. Brilakis,et al.  Multistep Explicit Stereo Camera Calibration Approach to Improve Euclidean Accuracy of Large-Scale 3D Reconstruction , 2016 .

[5]  Hermann Winner,et al.  „Automated Driving in Real Traffic: from Current Technical Approaches towards Architectural Perspectives“ , 2014 .

[6]  Torsten Sattler,et al.  Obstacle detection for self-driving cars using only monocular cameras and wheel odometry , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Constantin Ilas,et al.  Electronic sensing technologies for autonomous ground vehicles: A review , 2013, 2013 8TH INTERNATIONAL SYMPOSIUM ON ADVANCED TOPICS IN ELECTRICAL ENGINEERING (ATEE).

[8]  Jun Wang,et al.  A model based path planning algorithm for self-driving cars in dynamic environment , 2015, 2015 Chinese Automation Congress (CAC).

[9]  J. Mrovlje,et al.  Distance measuring based on stereoscopic pictures , 2008 .

[10]  Jan-Michael Frahm,et al.  Detailed Real-Time Urban 3D Reconstruction from Video , 2007, International Journal of Computer Vision.

[11]  Hans Walcher,et al.  Position Sensing: Angle and Distance Measurement for Engineers , 1994 .

[12]  Yücel Altunbasak,et al.  Misalignment correction for depth estimation using stereoscopic 3-D cameras , 2012, 2012 IEEE 14th International Workshop on Multimedia Signal Processing (MMSP).

[13]  Marc Pollefeys,et al.  Motion Estimation for Self-Driving Cars with a Generalized Camera , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  M. A. Mahammed,et al.  Object Distance Measurement by Stereo VISION , 2013 .

[15]  Ta-Chung Wang,et al.  An Improvement Stereo Vision Images Processing for Object Distance Measurement , 2015 .

[16]  Meysar Zeinali,et al.  A Real-Time Object Distance Measurement using a Monocular Camera , 2013 .

[17]  Naveen Appiah,et al.  Obstacle detection using stereo vision for self-driving cars , 2015 .

[18]  Don Ray Murray,et al.  Using Real-Time Stereo Vision for Mobile Robot Navigation , 2000, Auton. Robots.