针对地下车库场景中SLAM定位不准的问题,文章提出一种基于视觉和雷达信息融合的SLAM算法,将三维ICP算法IMLS-ICP(Implicit Moving Least Square-Iterative Closest Point)进行二维化,并融入入PL-ICP(Point to Line-Iterative Closest Po...针对地下车库场景中SLAM定位不准的问题,文章提出一种基于视觉和雷达信息融合的SLAM算法,将三维ICP算法IMLS-ICP(Implicit Moving Least Square-Iterative Closest Point)进行二维化,并融入入PL-ICP(Point to Line-Iterative Closest Point)和N-ICP(Normal-Iterative Closest Point)的内容,使得IMLS-ICP更加适合于二维环境,获得更好的点云匹配效果。然后,从图像中提取ORB(Oriented FAST and Rotated BRIEF)特征点进行特征匹配,并针对于地下车库场景亮度不稳定的特点,对图像进行了直方图均衡化滤波处理,并用BRIEF(Binary Robust Independent Elementary Feature)描述子进行约束,使得ORB特征点的提取与匹配更具精确性和鲁棒性,并对得到的结果进行了局部的BA(Bundle Adjustment)优化。应用加权最小二乘法进行位姿融合。通过实验对位姿进行了分析,与主流2DSLAM算法进行对比,验证文章算法的有效性。展开更多
A novel filter for image restoration is proposed in this paper. The filter estimates histogram of original image via input image. It gets a membership function through the histogram, and the membership function contai...A novel filter for image restoration is proposed in this paper. The filter estimates histogram of original image via input image. It gets a membership function through the histogram, and the membership function contains a lot of information of original image. Then a weighted fuzzy mean filter is established based on this membership function; meanwhile, the filter adaptively adopts different filter scale according to the character divergence of image region and intensity of impulsive noise. Experimental result shows that new filter gives superior performance to conventional filters and currently used fuzzy filter.展开更多
基金the National Natural Science Foundation of China(No.69972041)
文摘A novel filter for image restoration is proposed in this paper. The filter estimates histogram of original image via input image. It gets a membership function through the histogram, and the membership function contains a lot of information of original image. Then a weighted fuzzy mean filter is established based on this membership function; meanwhile, the filter adaptively adopts different filter scale according to the character divergence of image region and intensity of impulsive noise. Experimental result shows that new filter gives superior performance to conventional filters and currently used fuzzy filter.