DeepAI AI Chat
Log In Sign Up

SoildNet: Soiling Degradation Detection in Autonomous Driving

by   Arindam Das, et al.

In the field of autonomous driving, camera sensors are extremely prone to soiling because they are located outside of the car and interact with environmental sources of soiling such as rain drops, snow, dust, sand, mud and so on. This can lead to either partial or complete vision degradation. Hence detecting such decay in vision is very important for safety and overall to preserve the functionality of the "autonomous" components in autonomous driving. The contribution of this work involves: 1) Designing a Deep Convolutional Neural Network (DCNN) based baseline network, 2) Exploiting several network remodelling techniques such as employing static and dynamic group convolution, channel reordering to compress the baseline architecture and make it suitable for low power embedded systems with nearly 1 TOPS, 3) Comparing various result metrics of all interim networks dedicated for soiling degradation detection at tile level of size 64 x 64 on input resolution 1280 x 768. The compressed network, is called SoildNet (Sand, snOw, raIn/dIrt, oiL, Dust/muD) that uses only 9.72 reduces the model size by more than 7 times with no loss in accuracy


page 1

page 2

page 7


CAAD: Computer Architecture for Autonomous Driving

We describe the computing tasks involved in autonomous driving, examine ...

Complex accident, clear responsibility

The problem of allocating accident responsibility for autonomous driving...

Safety Metrics for Semantic Segmentation in Autonomous Driving

Within the context of autonomous driving, safety-related metrics for dee...

ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

Autonomous driving has attracted remarkable attention from both industry...

Deep Learning Accelerator in Loop Reliability Evaluation for Autonomous Driving

The reliability of deep learning accelerators (DLAs) used in autonomous ...

Fast Recurrent Fully Convolutional Networks for Direct Perception in Autonomous Driving

Deep convolutional neural networks (CNNs) have been shown to perform ext...