Color Point Cloud Registration Algorithm Based on Hue

ICP is a well-known method for point cloud registration but it only uses geometric information to do this, which will result in bad results some similar structures. Adding color when registering improve the performance. However, of cloud, such as gray, varies differently under different lighting conditions. Using gray register can cause large errors and even wrong results. To solve this problem, we propose algorithm based on hue, has good robustness at We extract hue component according clouds make distribution tangent plane continuous. The error function consists two current transformation. optimize using Gauss–Newton method. If value less than preset threshold or maximum number iterations reached, transformation relationship required. use RGB-D Scenes V2 dataset evaluate our show that average recall algorithms 8.63% higher excellent algorithms, its RMSE 14.3% lower other compared algorithms.