Image classification system based on deep learning applied to the recognition of traffic signs for intelligent robotic vehicle navigation purposes

Bruno, Diego Renan; Osório, Fernando Santos

doi:10.1109/sbr-lars-r.2017.8215287

Cited by 26 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the system presented in this paper, the 2D images representing the traffic sign are sent to a classifier based on a Deep Learning model, adopting a DCNN (Deep Convolutional Neural Network / ConvNet) network implemented using TensorFlow [14].…”

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

“…We used the free software library for machine learning TensorFlow [14]. The CNN networks have been successfully applied to image recognition of different classes, from manuscript digits (MNIST) to images of objects / animals (ImageNet Large Scale Visual Recognition Challenge (ILSVRC)), and is now being used in many real world applications.…”

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

“…The CNN networks have been successfully applied to image recognition of different classes, from manuscript digits (MNIST) to images of objects / animals (ImageNet Large Scale Visual Recognition Challenge (ILSVRC)), and is now being used in many real world applications. TensorFlow was developed for machine learning and research in Deep ANNs [14].…”

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

“…Through transfer learning we inserted 21 new classes of traffic signs into the network. We do not modify the structure, so we take advantage of all filters and convolutions [14].…”

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

See 3 more Smart Citations

Computer Vision System with 2D and 3D Data Fusion for Detection of Possible Auxiliaries Routes in Stretches of Interdicted Roads

Bruno¹,

Nunes²,

Amaro³

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

In this paper we present an intelligent system to help autonomous vehicles in real cities and with local traffic rules. A 2D and 3D visual attention system is proposed, capable of detecting the use of signs and aids in cases of major roadblock (road under work, with a traffic accident, etc.). For this to be possible, we analyze the cones and traffic signs that usually alert a driver about this type of problem. The main objective is to provide support for autonomous vehicles to be able to find an auxiliary route that is not previously mapped. For this we use a Grid Point Cloud Map. Using the ORB-SLAM visual odometry system we can correctly fit each stereo frame point cloud in the pose where the images were collected. With the concatenation of point clouds generated by the stereo camera, every grid block can draw the main characteristics of its region and an auxiliary route can be mapped. In this type of situation the vision system must work in real time. The results are promising and very satisfactory, we obtained an accuracy of 98.4% in the 2D classification task and 83% accuracy in the single frame 3D detection task.

show abstract

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

“…Through transfer learning we inserted 21 new classes of traffic signs into the network. We do not modify the structure, so we take advantage of all filters and convolutions [14].…”

Section: Deep Learning Cnn To Classify the Type Of Traffic Signmentioning

confidence: 99%

See 2 more Smart Citations

Computer Vision System with 2D and 3D Data Fusion for Detection of Possible Auxiliaries Routes in Stretches of Interdicted Roads

Bruno¹,

Nunes²,

Amaro³

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…notório ressaltar que os trabalhos de aprendizado profundo, como as redes neurais profundas (DNN) e DQN, marcam uma nova era da IA, apresentando excelentes resultados em diversos domínios da robótica, jogos(MNIH et al, 2015;LILLICRAP et al, 2015;JUSTESEN et al, 2017), visão computacional (BRUNO;OSORIO, 2017), entre outros. No problema do HFO, o DQN pode ser uma interessante estratégia e pode permitir uma significativa melhora nos resultados.…”

unclassified

Sistema de raciocínio baseado em casos qualitativos: um estudo no domínio do futebol de robôs humanoides

Homem¹

View full text Add to dashboard Cite

Automated TSR Using DNN Approach for Intelligent Vehicles

Sanyal

Biswal

Mohapatra

et al. 2022

The New Advanced Society

View full text Add to dashboard Cite

Image classification system based on deep learning applied to the recognition of traffic signs for intelligent robotic vehicle navigation purposes

Cited by 26 publications

References 10 publications

Computer Vision System with 2D and 3D Data Fusion for Detection of Possible Auxiliaries Routes in Stretches of Interdicted Roads

Computer Vision System with 2D and 3D Data Fusion for Detection of Possible Auxiliaries Routes in Stretches of Interdicted Roads

Sistema de raciocínio baseado em casos qualitativos: um estudo no domínio do futebol de robôs humanoides

Automated TSR Using DNN Approach for Intelligent Vehicles

Contact Info

Product

Resources

About