Skip to content
Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
images
False-FalsePositives.pdf Initial commit Jan 15, 2019
README.md Update README.me Jul 24, 2019
generate_dataset.py Update README.me Jul 24, 2019

README.md

Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images

Lucas Tabelini Torres, Thiago M. Paixão, Rodrigo F. Berriel, Alberto F. De Souza, Claudine Badue, Nicu Sebe and Thiago Oliveira-Santos

Paper accepted at IJCNN 2019 Conference. A preprint version can be accessed here. Overview

Abstract

Deep learning has been successfully applied to several problems related to autonomous driving. Often, these solutions rely on large networks that require databases of real image samples of the problem (i.e., real world) for proper training. The acquisition of such real-world data sets is not always possible in the autonomous driving context, and sometimes their annotation is not feasible (e.g., takes too long or is too expensive). Moreover, in many tasks, there is an intrinsic data imbalance that most learning-based methods struggle to cope with. It turns out that traffic sign detection is a problem in which these three issues are seen altogether. In this work, we propose a novel database generation method that requires only (i) arbitrary natural images, i.e., requires no real image from the domain of interest, and (ii) templates of the traffic signs, i.e., templates synthetically created to illustrate the appearance of the category of a traffic sign. The effortlessly generated training database is shown to be effective for the training of a deep detector (such as Faster R-CNN) on German traffic signs, achieving 95.66% of mAP on average. In addition, the proposed method is able to detect traffic signs with an average precision, recall and F1-score of about 94%, 91% and 93%, respectively. The experiments surprisingly show that detectors can be trained with simple data generation methods and without problem domain data for the background, which is in the opposite direction of the common sense for deep learning.

Source-code

Faster R-CNN

The Faster R-CNN implementation used in this paper is publicly available here.

Data set generation

New data sets can be generated with the script generate_dataset.py. As described in the paper, background images and templates are necessary.

Pre-trained models

Every model trained is available here. Each model directory follows the following pattern: {experiment}_cycle{id}_binary_train
Where experiment can be "germany", "germany_singleimage", or "coco_gtsd", for the upper bound, lower bound and proposed method experiments, respectively. The id is the run number of the experiment (10 runs for each).

Data sets

GTSDB

The German Traffic Sign Detection Benchmark (GTSDB) data set is available here.

Data sets generated by the proposed method

An example (which was used in the paper) of a data set generated by the proposed method is available here.

Qualitative results

Video1

False False-Positives

The impact of removal of False False-Positives on the metrics and its cases can be seen in the file False-FalsePositives.pdf.

BibTeX


@article{tabelini2019ijcnn,
	Title		= {{Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images}},
	Author		= {Lucas Tabelini Torres and Thiago M. Paixão and Rodrigo F. Berriel and Alberto F. De Souza and Claudine Badue and Nicu Sebe and Thiago Oliveira-Santos},
	Journal 	= {arXiv preprint arXiv:1907.09679},
	Year 		= {2019}
}
You can’t perform that action at this time.