Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving release_sb6pmvj6nvd2zdkv32wddxxyb4

by Alexander Frickenstein and Manoj Rohit Vemparala and Jakob Mayr and Naveen Shankar Nagaraja and Christian Unger and Federico Tombari and Walter Stechele

Released as a article .

2020  

Abstract

Driveable area detection is a key component for various applications in the field of autonomous driving (AD), such as ground-plane detection, obstacle detection and maneuver planning. Additionally, bulky and over-parameterized networks can be easily forgone and replaced with smaller networks for faster inference on embedded systems. The driveable area detection, posed as a two class segmentation task, can be efficiently modeled with slim binary networks. This paper proposes a novel binarized driveable area detection network (binary DAD-Net), which uses only binary weights and activations in the encoder, the bottleneck, and the decoder part. The latent space of the bottleneck is efficiently increased (x32 -> x16 downsampling) through binary dilated convolutions, learning more complex features. Along with automatically generated training data, the binary DAD-Net outperforms state-of-the-art semantic segmentation networks on public datasets. In comparison to a full-precision model, our approach has a x14.3 reduced compute complexity on an FPGA and it requires only 0.9MB memory resources. Therefore, commodity SIMD-based AD-hardware is capable of accelerating the binary DAD-Net.
In text/plain format

Archived Files and Locations

application/pdf  3.8 MB
file_tqaw65zbnvgineswjnhyurd2jy
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-06-15
Version   v1
Language   en ?
arXiv  2006.08178v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: afbf6399-b145-485e-96b9-d6846a8f661d
API URL: JSON