一种基于机器学习算法的单目里程计研究  

A Study on Monocular Mileage based on Machine Learning Algorithm

作　　者：顾海艳[1] 陈颖洁[2] 丁尧[2] GU Hai-yan;CHEN Ying-jie;DING Yao(Nanjing University Jinling College,Nanjing,Jiangsu 210089,China;Jiangsu Police Institute,Nanjing,Jiangsu 210000,China)

机构地区：[1]江苏警官学院,江苏南京210000 [2]南京大学金陵学院,江苏南京210089

出　　处：《教育教学论坛》2016年第43期257-259,共3页Education And Teaching Forum

摘　　要：视觉里程计(VO)通过轨迹推算,累加运动矢量,得出当前位置的相对定位方法,单目里程计仅使用单个相机作为图像获取载体,使获得信息的要求更低,且能较精确地识别和定位特征点,实时性好,成本也少很多,因此具有更广的应用前景。本课题采用SURF算法来同时检测和匹配特征点,使用一种基于机器学习算法(SVM)自适应卡尔曼滤波器,减缓原本卡尔曼滤波器中会出现的精度低和发散状况,起到优化单目里程计的系统准确度。Visual odometry (VO) through the trajectory calculation,cumulative motion vector,the relative positioning method of current position. Monocular odometer using only a single camera as image acquisition carrier,make information requirements lower,and can identify and locate the feature point accurately,real-time,cost much less,so it has more wide prospect of application. This paper uses SURF algorithm to simultaneously detect and match feature points,using a machine learning algorithm based on adaptive Calman filter (SVM),slow down will appear originally Calman filter in low precision and divergence,to systemoptimization of monocular odometric accuracy.

关 键 词：单目 视觉里程计 SURF算法 卡尔曼滤波 

分 类 号：G642.0[文化科学—高等教育学]