Experiments with teaching of recognition methods for road signs with the use of synthetic data

Chigorin, Alexander; Konushin, Anton

doi:10.7463/0813.0603378

Cited by 1 publication

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2019. № 2 (8) ISSN 2524-2296 (online) configured between two 14 × 14 and 10 × 10 cards with a 5 × 5 weight matrix. In the conglomerate it will be the number of elements of the matrix of weights, that is, 25 parameters, in the perceptron, this will be the number of all the links between the cards, that is, 19600 parameters.…”

Section: Methodsmentioning

confidence: 99%

“…No. 2 (8) image convolution passages and pushing densities, the system is rebuilt from a specific high-resolution pixel network to more abstract feature cards. As a rule, each subsequent layer increases the number of channels and decreases the dimension of the image in each channel.…”

Section: Methodsmentioning

confidence: 99%

“…In order to take into account these features, it is necessary to have a significant amount of video captured in different conditions. An alternative can be the use of synthetic data obtained by generating different noise and transformations [8].…”

Section: Analysis Of Publications and Problem Statementmentioning

confidence: 99%

“…No. 2 (8) 132 necessary, it will be possible to integrate the data thus prepared with the results into the navigator base.…”

Section: Description Of the Existing Process Of Recognizing The Road ...mentioning

confidence: 99%

“…No. 2 (8) -when the shape is recognized, the set of possible variants of the character types will also be reduced;…”

Section: Fig 4 Diagram Of the Activity Of The Technology Of Recogniti...mentioning

confidence: 99%

See 4 more Smart Citations

Information Technology for Recognition of Road Signs Using a Neural Network

Yashina

Artiukh²,

Рan

et al. 2019

Innovative Technologies and Scientific Solutions for Industries

View full text Add to dashboard Cite

The subject of the study is the methods and tools for automation of recognition of road signs at the level of software implementation. Detection of road signs is associated with the processing of a significant amount of video data in real time, which requires significant computing power. Therefore, the purpose of the work is to automate the process of recognition of road signs for filling the databases of navigators, which will allow operatively provide drivers with up-to-date information on established road signs. The following tasks are solved: analysis of methods and software for image recognition; development of the search algorithm for characters in the video frame; implementation of the definition of the contour of the sign; realization of a convolutional neural network for recognition of a sign; testing of applied information technology work. Methods are used: convolutional neural networks; Viola-Jones's method for recognizing objects in an image, the Bousting method as a way to accelerate the recognition process with a large amount of information. Results: Different approaches to the identification of symbols on images, various software tools for object recognition, image transformation for optimal fragment are considered. An algorithm for detecting and recognizing the sign is developed. Using the Viola-Jones method, a fast way to calculate the values of attributes using the integral representation of an image is implemented. The recognition process takes place by constructing a convolutional neural network. Features of the layers of the roller network are considered. Schematically illustrated script recognition. The process of interaction of the system with different data sources is represented by a diagram of precedents. The main result is the creation of information technology for the automated recognition of road signs. The algorithm of its work is presented in the form of a sequence diagram. Conclusions. Using the applied application information technology, recognition of road signs is made with an average probability of 88%, which allows automating the process of filling the database of navigators to a large extent, to increase the reliability and productivity of the given process.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Analysis Of Publications and Problem Statementmentioning

confidence: 99%

“…No. 2 (8) 132 necessary, it will be possible to integrate the data thus prepared with the results into the navigator base.…”

Section: Description Of the Existing Process Of Recognizing The Road ...mentioning

confidence: 99%

“…No. 2 (8) -when the shape is recognized, the set of possible variants of the character types will also be reduced;…”

Section: Fig 4 Diagram Of the Activity Of The Technology Of Recogniti...mentioning

confidence: 99%

See 3 more Smart Citations

Information Technology for Recognition of Road Signs Using a Neural Network

Yashina

Artiukh²,

Рan

et al. 2019

Innovative Technologies and Scientific Solutions for Industries

View full text Add to dashboard Cite

show abstract

Experiments with teaching of recognition methods for road signs with the use of synthetic data

Cited by 1 publication

References 9 publications

Information Technology for Recognition of Road Signs Using a Neural Network

Information Technology for Recognition of Road Signs Using a Neural Network

Contact Info

Product

Resources

About