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

06/15/2020
by   Alexander Frickenstein, et al.
19

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

research
02/24/2020

Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images

Semantic segmentation has made striking progress due to the success of d...
research
07/20/2023

TwinLiteNet: An Efficient and Lightweight Model for Driveable Area and Lane Segmentation in Self-Driving Cars

Semantic segmentation is a common task in autonomous driving to understa...
research
10/10/2022

Edge Device Deployment of Multi-Tasking Network for Self-Driving Operations

A safe and robust autonomous driving system relies on accurate perceptio...
research
12/19/2022

Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task

Robustness of different pattern recognition methods is one of the key ch...
research
08/24/2022

YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception

Over the last decade, multi-tasking learning approaches have achieved pr...
research
09/05/2023

AutonomROS: A ReconROS-based Autonomonous Driving Unit

Autonomous driving has become an important research area in recent years...
research
09/30/2019

XNOR-Net++: Improved Binary Neural Networks

This paper proposes an improved training algorithm for binary neural net...

Please sign up or login with your details

Forgot password? Click here to reset