Region-based Cycle-Consistent Data Augmentation for Object Detection

Roads constitute a major part of the lives of everybody. Heavy use, for instance by cars and especially trucks, and even soil movement lead to visible damages. While major roads are regularly inspected, smaller roads often lack attention. It is therefore of great interest to have camera-based system...

Full description

Saved in:

Bibliographic Details
Published in:	2018 IEEE International Conference on Big Data (Big Data) pp. 5205 - 5211
Main Authors:	Kluger, Florian, Reinders, Christoph, Raetz, Kevin, Schelske, Philipp, Wandt, Bastian, Ackermann, Hanno, Rosenhahn, Bodo
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-12-2018
Subjects:	Big Data Feature extraction Labeling Object detection Proposals Roads Training data
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Roads constitute a major part of the lives of everybody. Heavy use, for instance by cars and especially trucks, and even soil movement lead to visible damages. While major roads are regularly inspected, smaller roads often lack attention. It is therefore of great interest to have camera-based systems which can automatically detect and even classify damages.This report presents a system developed by the authors as part of the Road Damage Detection and Classification Challenge at the 2018 IEEE Big Data Cup [1]. Further contributions made here are techniques to augment the small set of training data. As a major contribution we also propose refinements to the dataset and evaluation metric to improve the challenge.
DOI:	10.1109/BigData.2018.8622318