Papers by Keyword: Stereoscopic Vision

Abstract: A clamping robot serving for several NC machines can recognize the best fit in manny blank parts. Forthermore, the shape information acquisition and pose measurment can be achieved by its computer vision system. The key question is that the clamping robot automatively choices the best fit part by statistical result of geometric dimension of all parts. The best fit part is the one that its length and its diameter are mostly proximate to the processing requirement. This choice method can save staff, reduce working allowance, and lessen finished cost. According to the shape information and position information, the robot can confirm the grab order, grab angle and finger joint distance. Firstly, the part image is smoothing by noise reduction technology, secondly, the feature points are extracted. The feature points present the information of the location of the mass center, the dip angle and diameter. Finally, the clamping robot can grab the most fit bar part by means of rotational motion, rectilinear motion, and finger open-close movement when the shape information and location information of the bar part have been confirmed.

Abstract: The paper introduces a kind of detection method of face pose based on stereoscopic vision technology, approximately divides head’s deflexion into three plane rotations. By calculating the deflexion angle of three directions, you can determine the face’s pose. This method obtains face images by the left and right video channels, first analyses the similarity of double channels’ images to obtain three-dimensional information of face features’ key points. Then calculates three deflexion angles according to these information, therefore can correspondingly adjust and deform the original image to get standard frontal face image, and provides correction image for the latter face recognition. By this method the impact of pose change to face recognition can be reduced obviously in the earlier stage, so the system’s overall recognition accuracy rate is enhanced effectively.

Abstract: Gas shield Tungsten Arc Welding (GTAW) is an important process method in material processing. Welding quality is vital for the product quality. It is an important way to improve the quality of product by raising the personal capability and handling technique of the welder. In this investigation, because of the deficiency in classic welding training scheme, some new technology were introduced into classic welding training field to improve the efficiency of welding training and reduce training cost. A computer simulation system that can be used to train primary welders was developed combined with three-dimensional stereoscopic vision and API interface of OpenGL, virtual reality is the kernel technology. In this system, welders were trained not in the real operating environment but in the virtual environment where has experience personally effect that simulated by computer. There is unnecessary with welding material and welding energy in virtual environment simulated by computer. It has highly automatic and intelligent and lower required to welding teachers. It is healthy to welder because that intensive arc and harmful dust are disappeared in virtual environment. It is a lower cost and high efficiency method by use of virtual training system to training new welder.

Abstract: With the continuous development and popularity of optical sensor and computer vision, machining process monitoring based on CCD camera has attracted more and more attention in recent years. Aiming at detecting the shape of cutting chip forming in cylindrical turning, a special matching algorithm is presented in this paper. As a reliable measuring method of chip shape parameter doesn’t exist, this algorithm can hardly be verified in a precise manner, however comparison between experimental results and the original images shows that this matching algorithm is effective. A double-CCD stereoscopic vision monitoring system employing this algorithm can be used to estimate the wearing and breakage of tool, and provide significant instruction for the design of tool groove for its capability of in-process measuring chip shape.