Title | ||
---|---|---|
Convolutional Neural Network On Neural Compute Stick For Voxelized Point-Clouds Classification |
Abstract | ||
---|---|---|
2D Convolutional Neural Networks (CNNs) have enjoyed a surge in popularity over the last few years, mainly because they outperform traditional algorithms/methods in a myriad of computer vision (and other fields) tasks. On the other hand, the problem becomes more complex when dealing with 3D volumes. Lack of readily available training data, memory and computational requirements are just some of the factors hindering the progress of 3D CNNs. We propose a synthetic 3D voxelized point-clouds generation method containing object and scene in this paper. Furthermore, an efficient 3D volumetric representation called VOLA is applied. VOLA (Volumetric Accelerator) is a sexaquaternary (power-of-four subdivision) tree based representation which aims to save significant memory for volumetric data. After training the model, it was deployed onto Movidius Neural Compute Stick which is a USB, containing a low-power processing unit as well as dedicated CNN hardware blocks. The trained model on NCS takes only 90 frames per second to perform inference on each 3D volume, with an average power consumption of 1.2W. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 10TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI) | Point-clouds, Convolutional Neural Networks, Embedded Systems |
Field | DocType | Citations |
Computer vision,Pattern recognition,Convolutional neural network,Inference,Computer science,Subdivision,Frame rate,Artificial intelligence,Solid modeling,Point cloud,Cognitive neuroscience of visual object recognition,USB | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaofan Xu | 1 | 5 | 2.14 |
joao amaro | 2 | 10 | 2.30 |
Sam Caulfield | 3 | 0 | 1.01 |
Andrew Forembski | 4 | 0 | 0.34 |
Gabriel Falcão | 5 | 0 | 1.01 |
David Moloney | 6 | 12 | 7.69 |