Monocular vision system for distance measurement based on feature points
Autor: | 张志胜 Zhang Zhi-sheng, 韩延祥 Han Yan-xiang, 戴敏 Dai Min |
---|---|
Rok vydání: | 2011 |
Předmět: |
Monocular
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials Feature (computer vision) Approximation error Pinhole (optics) Point (geometry) Computer vision Artificial intelligence business Monocular vision Feature detection (computer vision) |
Zdroj: | Optics and Precision Engineering. 19:1082-1087 |
ISSN: | 1004-924X |
DOI: | 10.3788/ope.20111905.1082 |
Popis: | To alleviate the effect of matching of corresponding feature points and extraction error of single feature point,a method by using a single camera as monocular measurement is presented based on image processing.Firstly,this paper sets up the mapping relationship between image point and target point,and establishes pinhole imaging model.Secondly,it describes the mapping relationship between object area and image area of object by using image analysis,and establishes the model of distance measurement in optical direction.Then,the principle of distance measurement between optical center and feature point is proposed after image processing and feature point extracting are carried out.At last,the paper starts out verification experiments and analyzes the cause that error increases with further distance.After analyzing the data of experiment,the conclusion that error is related with the optical axis deviation is made.Sequentially,with the maximum relative error 1.68% of revised data,there is a remarkable improvement which proves the feasibility and the effectiveness of the proposed principle. |
Databáze: | OpenAIRE |
Externí odkaz: |