A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="http://engine.scichina.com/doi/pdf/4D92A2CD84EC4CB1BDB8A64B16514E13">the original URL</a>. The file type is <code>application/pdf</code>.
<i title="Springer Science and Business Media LLC">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikvx2lmj7rew7jpw4lygqgjpby" style="color: black;">Science China Information Sciences</a>
3D point cloud data, which are produced by various 3D sensors such as LIDAR and stereo cameras, have been widely deployed by industry leaders such as Google, Uber, Tesla, and Mobileye, for mobile robotic applications such as autonomous driving and humanoid robots. Point cloud data, which are composed of reliable depth information, can provide accurate location and shape characteristics for scene understanding, such as object recognition and semantic segmentation. However, deep neural networks<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11432-019-9932-3">doi:10.1007/s11432-019-9932-3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/py7ttpbxunfuxfyprv2g2bpkse">fatcat:py7ttpbxunfuxfyprv2g2bpkse</a> </span>
more »... NNs), which directly consume point cloud data, are particularly computation-intensive because they have to not only perform multiplication-and-accumulation (MAC) operations but also search neighbors from the irregular 3D point cloud data. Such a task goes beyond the capabilities of general-purpose processors in realtime to figure out the solution as the scales of both point cloud data and DNNs increase from application to application. We present the first accelerator architecture that dynamically configures the hardware onthe-fly to match the computation of both neighbor point search and MAC computation for point-based DNNs. To facilitate the process of neighbor point search and reduce the computation costs, a grid-based algorithm is introduced to search neighbor points from a local region of grids. Evaluation results based on the scene recognition and segmentation tasks show that the proposed design harvests 16.4× higher performance and saves 99.95% of energy than an NVIDIA Tesla K40 GPU baseline in point cloud scene understanding applications. Keywords deep neural network acceleration, point cloud data, neighbor point search, mobile robotics, hardware architecture Citation Liu B S, Chen X M, Han Y H, et al. Accelerating DNN-based 3D point cloud processing for mobile computing. Sci China Inf Sci, 2019, 62(11): 212102, https://doi.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200510084804/http://engine.scichina.com/doi/pdf/4D92A2CD84EC4CB1BDB8A64B16514E13" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ef/3c/ef3c7017939a8fa813056c391604183b5473af99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11432-019-9932-3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>