To meet the low cost and real-time requirements of logistics sorting, a systematic method was proposed to extract complete stereo information of typical objects by using multiple stereo cameras. Combining the cameras with an arm and other hardware, a validation and experiment platform was constructed to test the performance of this method. Two Microsoft Kinect cameras were used to measure the locations of objects in horizontal plane with accuracy of 3 millimeters. The stereo features and models of objects were calculated from the complete stereo information at processing rate of about 1 second per frame. Utilizing these features, the arm continuously picked 100 objects without failure. The experimental results demonstrate that the proposed method can extract the stereo features of objects with various sizes and shapes in real-time without off-line training, and based on which the arm can operate on objects with high accuracy.