pith. sign in

arxiv: 1811.05894 · v1 · pith:VOGIYHCNnew · submitted 2018-11-14 · 💻 cs.CV

Development of Real-time ADAS Object Detector for Deployment on CPU

classification 💻 cs.CV
keywords objectdetectiondeploymentdevelopmentmodelnetworkproblemsachieves
0
0 comments X
read the original abstract

In this work, we outline the set of problems, which any Object Detection CNN faces when its development comes to the deployment stage and propose methods to deal with such difficulties. We show that these practices allow one to get Object Detection network, which can recognize two classes: vehicles and pedestrians and achieves more than 60 frames per second inference speed on Core$^{TM}$ i5-6500 CPU. The proposed model is built on top of the popular Single Shot MultiBox Object Detection framework but with substantial improvements, which were inspired by the discovered problems. The network has just 1.96 GMAC complexity and less than 7 MB model size. It is publicly available as a part of Intel$\circledR$ OpenVINO$^{TM}$ Toolkit.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.