05-05-2011, 03:42 PM
Technique of Measuring Leading Vehicle Distance Based on Digital Image
Processing Theory
Abstract
Based on the digital image processing theory, a newmethod of measuring the leading vehicle distance wasproposed. The input image using the method of edgeenhancement and morphological transformation wasestablished, so the edges of objects were enhanced to identify.The target vehicle was identified and calibrated in the imageby using the method of the obstacle detection by segmentationand decision tree. The relationship between coordinates valuein image space and the data of the real space plane wasestablished by applying the ray angles. Thus, throughaccessing to image pixel coordinates of the vehicle, the vehicle'sactual position in the plane can be calculated. At last, theleading vehicle distance based on the calculating model ofinverse perspective mapping was measured. By using softwareVC++, an experiment program was made. The experimentresults prove that the method of measuring the leading vehicledistance is simple and effective. It can meet the requirement ofintelligent vehicle technologies. It is an more available andmore advanced method to calculate the leading vehicledistance.
Keywords-Active Safety; Leading Vehicle Distance; DigitalImage Processing; Obstacle Detection; Monocular Ranging
I. INTRODUCTION
Advanced Vehicle Control System (AVCS) is animportant component of the Intelligent TransportationSystem. By measuring the leading vehicle distance, it canprovide effective vehicle driving information for theprevention of traffic accident, thereby enhancing trafficsafety level. Based on domestic and international VisionRanging technology and digital image processing theoryresearch, this paper proposes a new method of measuring theleading vehicle distance based on the digital imageprocessing theory, and obtains the leading vehicle distancedata through the image pre-processing, obstacle detectionand ranging model calculation and other steps. This methodis a passive ranging method, and not transmits the signal tothe outside environment, furthermore, also has easy to updatealgorithm, equipment light etc. [1].
II. IMAGE PRE-PROCESSING METHOD OF CHOICE
Image pre-processing can improve image quality andreduce image noise and lay the foundation for obstacledetection. Required to select an appropriate way in digitalimage processing method to conduct a comprehensive preprocessingto image, this paper selects edge enhancementand method of morphological opening and closing to smoothdetails and to enhance the edges of objects so as to identify.
A. Edge Enhancement
Because image edge depicts the contour, enhancing theimage edges has important implications for the objectrecognition. Image enhancement is divided into two maincategories: Space domain method and frequency domainmethod. Study the use of space-domain processing methods,as much as possible to shorten the processing. In the pixelmatrix size of M rows, N columns of the image, the templateR with m rows, n columns carried space domain linearfiltering is given by the following formula:is the template coefficient and mn z is the imagepixels under template.Using Laplace second-order differential image edgeenhancement, the corresponding algorithm is as follows:g( x, y) f ( x, y) −∇f 2 (2)Where f ( x , y ) is the image before handling;g ( x , y ) is the image after Laplace enhancement; anddefine Laplace transform operator ∇f 2 as:Using Laplace transformation the image is much clearerthan before, with edge part enhancement and backgroundkeynote maintenance.
B. Operation of Morphological Opening and Closing
While after space domain enhancement, someinterference factors in the image possibly impact ObstacleDetection. This paper focuses on image noise reduction bythe operation of the mathematical morphological openingand closing.With the features of mathematical morphology operation,processing the image captured by grey scale open and close,the effects of image noise removal is the best[2]
Download full report
http://doi.ieeecomputersociety10.1109/ICICTA.2010.153