Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images (2019-07-01T00:00:00.000000Z)

TL;DR

A novel database generation method that requires only arbitrary natural images, which is able to detect traffic signs with an average precision, recall, and F1-score of about 94%, 91% and 93%, respectively, and the experiments surprisingly show that detectors can be trained with simple data generation methods and without problem domain data for the background.

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.

Authors

References30 items

Self-Driving Cars: A Survey

Few-Shot Object Detection via Feature Reweighting

Evaluation of deep neural networks for traffic sign detection systems

Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery

SPARC: Self-Paced Network Representation for Few-Shot Rare Category Characterization

Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition

Handling Pedestrians in Crosswalks Using Deep Neural Networks in the IARA Autonomous Car

Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision

Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection

LSTD: A Low-Shot Transfer Detector for Object Detection

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach

Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification

A deep learning approach to traffic lights: Detection, tracking, and classification

Traffic-Sign Detection and Classification in the Wild

Learning Deep Representation for Imbalanced Classification

Self Paced Deep Learning for Weakly Supervised Object Detection

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Microsoft COCO: Common Objects in Context

Detection of traffic signs in real-world images: The German traffic sign detection benchmark

TL;DR

Abstract

Authors

References30 items

Self-Driving Cars: A Survey

Few-Shot Object Detection via Feature Reweighting

Evaluation of deep neural networks for traffic sign detection systems

Conditional Transfer with Dense Residual Attention: Synthesizing traffic signs from street-view imagery

SPARC: Self-Paced Network Representation for Few-Shot Rare Category Characterization

Heading Direction Estimation Using Deep Learning with Automatic Large-scale Data Acquisition

Handling Pedestrians in Crosswalks Using Deep Neural Networks in the IARA Autonomous Car

Generative One-Shot Learning (GOL): A Semi-Parametric Approach to One-Shot Learning in Autonomous Vision

Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection

LSTD: A Low-Shot Transfer Detector for Object Detection

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach

Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification

A deep learning approach to traffic lights: Detection, tracking, and classification

Traffic-Sign Detection and Classification in the Wild

Learning Deep Representation for Imbalanced Classification

Self Paced Deep Learning for Weakly Supervised Object Detection

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Microsoft COCO: Common Objects in Context

Detection of traffic signs in real-world images: The German traffic sign detection benchmark

ImageNet classification with deep convolutional neural networks

Real-Time Speed Sign Detection Using the Radial Symmetry Detector

Road-Sign Detection and Recognition Based on Support Vector Machines

Learning From Imbalanced Data

Visual Object Tagging Tool

Learning to Model the Tail

A review on automatic detection and recognition of traffic sign

The Pascal Visual Object Classes Challenge 2006 ( VOC 2006 ) Results

“Scalabel,”

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names