Accelerating real-time embedded scene labeling with convolutional networks
- 7 June 2015
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
Today there is a clear trend towards deploying advanced computer vision (CV) systems in a growing number of application scenarios with strong real-time and power constraints. Brain-inspired algorithms capable of achieving record-breaking results combined with embedded vision systems are the best candidate for the future of CV and video systems due to their flexibility and high accuracy in the area of image understanding. In this paper, we present an optimized convolutional network implementation suitable for real-time scene labeling on embedded platforms. We show that our algorithm can achieve up to 96GOp/s, running on the Nvidia Tegra K1 embedded SoC. We present experimental results, compare them to the state-of-the-art, and demonstrate that for scene labeling our approach achieves a 1.5x improvement in throughput when compared to a modern desktop CPU at a power budget of only 11 W.Keywords
Funding Information
- armasuisse Science & Technology
This publication has 14 references indexed in Scilit:
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- An efficient implementation of deep convolutional neural networks on a mobile coprocessorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- A 240 G-ops/s Mobile Coprocessor for Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Distributed Embedded Smart CamerasPublished by Springer Science and Business Media LLC ,2014
- Learning Hierarchical Features for Scene LabelingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- NeuFlow: A runtime reconfigurable dataflow processor for visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Internet inter-domain trafficPublished by Association for Computing Machinery (ACM) ,2010
- Efficiently selecting regions for scene understandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Stacked Hierarchical LabelingLecture Notes in Computer Science, 2010
- Decomposing a scene into geometric and semantically consistent regionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009