This paper describes a system which locates and grasps doughnut shaped parts from a pile.The system uses photometric stereo and binocular stereo as vision input tools. 本論文之主要研究目標是建立移動(dòng)式機器人雙眼視覺(jué)系統，使機器人具有三維空間的距離感測能力。
Based on characters of human vision, deblurring and contrast enhancement methods are presented for true color images. 研究了受到煙霧惡化的近景彩色圖像的處理原理和方法，探索真彩色圖像基于人眼視覺(jué)特征的消模糊和對比度增強方法。
Experiment results showed that hypercomplex SVD method is much better than traditional methods and it is more consistent with human vision judgment. 實(shí)驗結果證明該法評估結果優(yōu)于傳統彩色圖像質(zhì)量評估法的評估結果，與人眼視覺(jué)評估結果更相符。
An approach based on disparity space to a binocular visual odometry system is presented. 提出了一種基于視差空間的雙目視覺(jué)里程計算法。
