Robust Automatic Traffic Signs Recognition Using Fast Polygonal Approximation of Digital Curves and Neural Network

Salhi, Abderrahim; Minaoui, Brahim; Fakir, Mohamed

doi:10.14569/specialissue.2014.040201

Cited by 6 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the amount of data processed by the classifier, we apply a simple smoothing on the blobs, by using the Gaussian filter, the use histogram projection (HP) technic [2] for each color channel, for both vertical and horizontal.…”

Section: A Histogram Projection (Hp)mentioning

confidence: 99%

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Salhi¹,

Minaoui²,

Fakir³

et al. 2017

ijacsa

View full text Add to dashboard Cite

Section: A Histogram Projection (Hp)mentioning

confidence: 99%

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Salhi¹,

Minaoui²,

Fakir³

et al. 2017

ijacsa

View full text Add to dashboard Cite

“…In [5], the authors used image patch of the detected road sign as the sign descriptor to recognise its type using a support vector machine (SVM) classifier. The authors in [6] employed feed‐forward artificial neural networks to implement a scale‐invariant sign classifier, which recognises the detected road sign using a resized version of the detected sign image patch. In [7], Jin et al implemented a robust traffic sign classifier to accomplish both feature extracting and classifying tasks without feature description processing based on convolutional neural networks (CNN).…”

Section: Introductionmentioning

confidence: 99%

“…The road sign was then detected by segmenting the Hue component as it shows more robustness against variations in light and weather conditions. Recently, Salhi et al [6] proposed an automatic traffic recognition system, which also detects red and blue road signs in HSV colour space. The shape of the detected signs was then determined using polygonal approximated contour information.…”

Section: Introductionmentioning

confidence: 99%

Real‐time embedded implementation of robust speed‐limit sign recognition using a novel centroid‐to‐contour description method

Tsai

Liao

Hsu

2017

IET Computer Vision

View full text Add to dashboard Cite

Traffic sign recognition is a very important function in automatic driving assistance systems (ADAS). This study addresses the design and implementation of a vision-based ADAS based on an image-based speed-limit sign (SLS) recognition algorithm, which can automatically detect and recognise SLS on the road in real-time. To improve the recognition rate of SLS having different orientations and scales in the image, this study also presents a new sign content description algorithm, which describes the detected road sign using centroid-to-contour (CtC) distances of the extracted sign content. The proposed CtC descriptor is robust to translation, rotation and scale changes of the SLS in the image. This advantage improves the recognition accuracy of a support vector machine classifier trained using a large database of traffic signs. The proposed SLS recognition method had been implemented on two different embedded platforms, each of them equipped with an ARM-based Quad-Core CPU running Android 4.4 operating system. Experimental results validate that the proposed method not only provides a high recognition rate, but also achieves real-time performance up to 30 frames per second for processing 1280 × 720 video streams running on a commercial ARM-based smartphone.

show abstract

“…It is possible to fi nd a substantial amount of articles that deals with a road sign detection (see Loraskul et al (2007) or Salhi et al (2014)). The described methods vary from pixel correlation calculations to neural networks.…”

Section: Introductionmentioning

confidence: 99%

Assistance System for Traffic Signs Inventory

Žídek¹,

Koubek²,

Procházka³

et al. 2015

Acta Univ. Agric. Silvic. Mendelianae Brun.

View full text Add to dashboard Cite

We can see arising trend in the automotive industry in last years -autonomous cars that are driven just by on-board computers. The traffi c signs tracking system must deal with real conditions with data that are frequently obtained in poor light conditions, fog, heavy rain or are otherwise disturbed. Completely same problem is solved by mapping companies that are producing geospatial data for diff erent information systems, navigations, etc. They are frequently using cars equipped with a wide range of measuring instruments including panoramic cameras. These measurements are frequently done during early morning hours when the traffi c conditions are acceptable. However, in this time, the sun position is usually not optimal for the photography. Most of the traffi c signs and other street objects are heavily underexposed. Hence, it is diffi cult to fi nd an automatic approach that can identify them reliably. In this article, we focus on methods designed to deal with the described conditions. An overview of the state-of-the-art methods is outlined. Further, where it is possible, we outline an implementation of the described methods using well-known Open Computer Vision library. Finally, emphasis is placed on the methods that can deal with low light conditions, fog or other situations that complicate the detection process.

show abstract

Robust Automatic Traffic Signs Recognition Using Fast Polygonal Approximation of Digital Curves and Neural Network

Cited by 6 publications

References 5 publications

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Real‐time embedded implementation of robust speed‐limit sign recognition using a novel centroid‐to‐contour description method

Assistance System for Traffic Signs Inventory

Contact Info

Product

Resources

About