Point clouds are a widely used format for representing 3D objects and scenes. With the aim of enhancing the streamlined transfer and storage of such data, extensive attention has been directed towards point cloud comp...
详细信息
ISBN:
(纸本)9798350374223;9798350374216
Point clouds are a widely used format for representing 3D objects and scenes. With the aim of enhancing the streamlined transfer and storage of such data, extensive attention has been directed towards point cloud compression (PCC). This has led to a significant research emphasis on advancing PCC methods. Audio Video coding Standard workgroup (AVS) of China have launched a PCC project, which employs the octree representation to compress the geometry information of point cloud data. This paper aims to improve the coding efficiency of AVS PCC. Specifically, the neighbouring occupancy information is used in various ways to construct efficient context driving geometry entropy coding. To reduce the memory footprint in context construction, a context reduction mechanism is proposed utilizing the historical coding information. Moreover, an adaptive context switching method is proposed to fit the diversity of point cloud distribution. Experimental results show that the proposed octree coding method achieves coding gains over 3.0% and 8.0% for lossless and lossy coding conditions, respectively without runtime increase. Due to the superiority of the proposed method, it has been recently adopted as the geometry coding method in AVS PCC.
Aiming at the high workload, low precision, strong stress of the traditional manual measurement to obtain the sheep growth parameters, a novel measurement technology was proposed. The specimen of the Sunite sheep abou...
详细信息
ISBN:
(纸本)9783030061784
Aiming at the high workload, low precision, strong stress of the traditional manual measurement to obtain the sheep growth parameters, a novel measurement technology was proposed. The specimen of the Sunite sheep about 2–3 years old were chosen for study. By reverse engineering technology, point cloud data of sheep was captured by the 3D laser scanner. Because of noise point cloud data, the improved algorithm of k-nearest neighbor was used to process the data. To improve the subsequent processing time and efficiency,octree coding was employed to reduce data, which can get evenly distribution of point cloud data and retain sheep features. Then, 3D surface model of sheep body was reconstructed using Delaunay triangulation. Some parameters were extracted, including sheep body length, body height, hip height, hip width and chest width. Compared actual parameters values with computing values of two ways, by Geomagic platform and the proposed algorithms on the Matlab,average relative errors of two ways were 1.23% and 1.01%, respectively. So results of the proposed algorithm were with small error range. Using the point clouds can reconstruct sheep surface for computing body size without stress.
暂无评论