Development of Real-time ADAS Object Detector for Deployment on CPU
This work addresses real-time object detection for ADAS deployment on CPUs, representing an incremental improvement over existing methods.
The paper tackles the challenge of deploying object detection CNNs in real-time on CPU hardware, achieving over 60 FPS on a Core i5-6500 CPU for detecting vehicles and pedestrians with a model of 1.96 GMAC complexity and under 7 MB size.
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.