Data debiased traffic sign recognition using MSERs and CNN

Jang, Cheolyong; Kim, Hyoungrae; Park, Eunsoo; Kim, Hakil

doi:10.1109/elinfocom.2016.7562938

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [14,15] followed a similar approach as that used in [12], with an RBchannel-normalized image as the input for the MSER segmentation algorithm. Since blue and red are the two dominant background colors of traffic signs, Kurnianggoro et al [15] tried to leave only the maximum value of those color channels (5).…”

Section: Related Workmentioning

confidence: 99%

An Improved Image Enhancement Method for Traffic Sign Detection

Sütő

2022

Electronics

View full text Add to dashboard Cite

Traffic sign detection (TRD) is an essential component of advanced driver-assistance systems and an important part of autonomous vehicles, where the goal is to localize image regions that contain traffic signs. Over the last decade, the amount of research on traffic sign detection and recognition has significantly increased. Although TRD is a built-in feature in modern cars and several methods have been proposed, it is a challenging problem due to the high computational demand, the large number of traffic signs, complex traffic scenes, and occlusions. In addition, it is not clear how can we perform real-time traffic sign detection in embedded systems. In this paper, we focus on image enhancement, which is the first step of many object detection methods. We propose an improved probability-model-based image enhancement method for traffic sign detection. To demonstrate the efficiency of the proposed method, we compared it with other widely used image enhancement approaches in traffic sign detection. The experimental results show that our method increases the performance of object detection. In combination with the Selective Search object proposal algorithm, the average detection accuracies were 98.64% and 99.1% on the GTSDB and Swedish Traffic Signs datasets. In addition, its relatively low computational cost allows for its usage in embedded systems.

show abstract

Section: Related Workmentioning

confidence: 99%

An Improved Image Enhancement Method for Traffic Sign Detection

Sütő

2022

Electronics

View full text Add to dashboard Cite

show abstract

“…The SPCNN code was programmed on MATLAB, and compared with IDSIA DNN [12], IDSIA MCDNN [12], and Multi-Scale CNN [4]. The detection results were evaluated by three metrics: Accuracy, mean Area under Curve (mAUC), and mean Average Precision (mAP).…”

Section: Traffic Sign Recognitionmentioning

confidence: 99%

“…Traffic signal recognition is a critical function of the intelligent vehicle system (IVS). Since the 1990s, many machine learning (ML) algorithms have been applied to realize traffic signal recognition of the IVS, namely, principal component analysis (PCA) [1], random forest (RF) [2], support vector machine (SVM) [3], convolutional neural network (CNN) [4][5][6], and sparse representation [7]. These ML algorithms can recognize traffic signals accurately.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Traffic Signal Recognition Algorithm Based on Self-paced Learning and Deep Learning

Wang¹,

Shen²,

Xue³

et al. 2020

ISI

View full text Add to dashboard Cite

Traffic signal recognition is a critical function of the intelligent vehicle system (IVS). Many algorithms can achieve a high accuracy in traffic signal recognition. But these algorithms have poor generalization ability, and their recognition rates vary greatly with datasets. These defects hinder their application in unmanned driving. To solve the problem, this paper introduces self-paced learning (SPL) to the image recognition of traffic signs. Based on complexity, the SPL automatically classifies samples into multiple sets. If machine learning (ML) algorithm is trained by the sample sets in ascending order of complexity, a universal computing model will be obtained, and the ML algorithm will have a better generalization ability. Here, the support vector machine (SVM) is adopted as the classifier for traffic sign detection, and the convolutional neural network (CNN) is employed as the classifier for traffic sign recognition. Then, the two classifiers were trained by the SPL on two public datasets: German Traffic Sign Detection Benchmark (GTSDB) and German Traffic Sign Recognition Benchmark (GTSRB). The model obtained through the training was tested on Belgium Traffic Sign Detection Benchmark (BTSDB) and KITTI datasets. The results show that the obtained computing model achieved similar accuracy on the training sets and test sets. Hence, the SPL can indeed enhance the generalization ability of ML algorithms, and promote the application of CNN, SVM, and other ML algorithms in unmanned driving.

show abstract