Simultaneous detection of obstacles in the near field of the mobile robot is extremely urgent and complex task. In general, environment around robot is very complicated due to differences in change of lighting conditions and viewing angles. These problems lead to decrease accuracy of obstacles recognition. They can change quickly. However, obstacles must occupy a certain region in space. In this paper, we propose algorithms for obstacle detection with algorithm "3D-point cloud". Algorithm contains some main steps: Creation 3D-point cloud, transformation «2D- Point Cloud», obtaining results. Obstacles are detected based on their specific areas. 3D-point cloud are obtained from the depth data. Using 3D-point clouds allows satisfying requirements for obstacle detection in real time. The experimental results show the effectiveness of proposed approach using in vision system of a mobile robot platform

Keywords: 3D-point cloud, 2D point cloud, obstacle, mobile robot, image recognition, depth image, Kinect, downsampling algorithm, clustering algorithm, k-mean clustering, Density-Based Spatial Clustering of Applications with Noise