Abstract: A 3D object detection and recognition method is proposed in this paper. The method achieves pose estimations of multiple object instances in 3D scenes with some occlusions and clutter. First, the normal vector of point is estimated by computing the distance between the neighboring points and the feature one within the local spherical support domain. The longer the distance is, the smaller the weight is. Next, we encode the 3D descriptor called color signatures of histogram of orientations(C-SHOT) based on improved normal vector. Then we match 3D feature correspondences between scenes and models to prove the existence of the objects being sought on 3D hough voting space. Finally, we reject wrong feature correspondences and get rough transformation using random sample consensus(RANSAC). Once reliable feature correspondences have been selected, a final transformation matrix based on levenberg marquardt iterative closest point(LM-ICP), can be performed to further refine pose estimations. A thorough experimental evaluations is carried on CVLab 3D datasets and real lab 3D datasets for object recognition. Experimental results demonstrate the recognition accuracy and robust performance of the proposed method.