No abstract

An on-line non-contact method for measuring the wear of a form grinding wheel is presented. A CCD (charge coupled device) camera with a selected optical lens and a frame grabber was used to capture the image of a grinding wheel. The analogue signals of the image were transformed into corresponding digital grey level values. Using the binarisation technique, the images of background and the grinding wheel were segmented. Thus the grinding wheel edge was identified. The 'mapping function method' is used to transform an image pixel coordinate to a space coordinate. An auto-focus technology is also developed. The statistics of pixels are used as the focusing index. The signal was sent through an 8255 control card to drive a d.c. motor, and then to control the lens focusing movement to acquire the focal plane. The images before and after the grinding process were captured. The position deviation of the grinding wheel edge was analysed. Then, the grinding wheel wear was evaluated. The wear detection accuracy is about 1m.

With the unprecedented success of deep learning in computer vision tasks, many cloud-based visual analysis applications are powered by deep learning models. However, the deep learning models are also characterized with high computational complexity and are task-specific, which may hinder the large-scale implementation of the conventional data communication paradigms. To enable a better balance among bandwidth usage, computational load and the generalization capability for cloud-end servers, we propose to compress and transmit intermediate deep learning features instead of visual signals and ultimately utilized features. The proposed strategy also provides a promising way for the standardization of deep feature coding. As the first attempt to this problem, we present a lossy compression framework and evaluation metrics for intermediate deep feature compression. Comprehensive experimental results show the effectiveness of our proposed methods and the feasibility of the proposed data transmission strategy. It is worth mentioning that the proposed compression framework and evaluation metrics have been adopted into the ongoing AVS (Audio Video Coding Standard Workgroup) -Visual Feature Coding Standard.

3D sensing and content capture have made significant progress in recent years and the MPEG standardization organization is launching a new project on immersive media with point cloud compression (PCC) as one key corner stone. In this work, we introduce a new binary tree based point cloud content partition and explore the graph signal processing tools, especially the graph transform with optimized Laplacian sparsity, to achieve better energy compaction and compression efficiency. The resulting rate-distortion operating points are convex-hull optimized over the existing Lagrangian solutions. Simulation results with the latest high quality point cloud content captured from the MPEG PCC demonstrated the transform efficiency and rate-distortion (R-D) optimal potential of the proposed solutions.