Traffic Sign Recognition for Computer Vision Project-Based Learning

2013 ◽  
Vol 56 (3) ◽  
pp. 364-371 ◽  
Author(s):  
David Geronimo ◽  
Joan Serrat ◽  
Antonio M. Lopez ◽  
Ramon Baldrich
Keyword(s):  
Computer Vision ◽  
Project Based Learning ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition

scholarly journals Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2684 ◽  
Author(s):  
Obed Tettey Nartey ◽  
Guowu Yang ◽  
Sarpong Kwadwo Asare ◽  
Jinzhao Wu ◽  
Lady Nadia Frempong
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Supervised Learning ◽  
Machine Learning Algorithms ◽  
Unbalanced Data ◽  
Traffic Sign Recognition ◽  
Training Set ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Weakly Supervised

Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms. Although both computer vision and machine learning techniques have constantly been improved to solve this problem, the sudden rise in the number of unlabeled traffic signs has become even more challenging. Large data collation and labeling are tedious and expensive tasks that demand much time, expert knowledge, and fiscal resources to satisfy the hunger of deep neural networks. Aside from that, the problem of having unbalanced data also poses a greater challenge to computer vision and machine learning algorithms to achieve better performance. These problems raise the need to develop algorithms that can fully exploit a large amount of unlabeled data, use a small amount of labeled samples, and be robust to data imbalance to build an efficient and high-quality classifier. In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data. The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection algorithm to generate and select pseudo-labeled samples. The method improves the performance by: (1) normalizing the class-wise confidence levels to prevent the model from ignoring hard-to-learn samples, thereby solving the imbalanced data problem; (2) jointly learning a model and optimizing pseudo-labels generated on unlabeled data; and (3) enlarging the training set to satisfy the hunger of deep learning models. Extensive evaluations on two public traffic sign recognition datasets demonstrate the effectiveness of the proposed technique and provide a potential solution for practical applications.

scholarly journals Automated Traffic Sign Recognition System using Computer Vision

2019 ◽  
Vol 9 (1) ◽  
pp. 1157-1160
Keyword(s):  
Computer Vision ◽  
Intelligent System ◽  
Input Image ◽  
Assistance System ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Internet Connectivity ◽  
Sign Recognition ◽  
Driving Assistance ◽  
Driving Assistance System

There are many existing companies who are developing cars on the autonomous driving technology. With the help of GPS and internet connectivity they create a dynamic map which helps the cars to navigate. This technology is still new and undergoing rigorous changes. There are many shortcomings to this existing technology. They are capable of navigating through those areas which are accounted for and surveyed but when the car enters in any unchartered terrain or there is any internet connectivity issues, the updation in the map is not possible, which leaves the car to navigate on its own. This can cause many troubles like you can get late or maybe lost. So to overcome these problems we need such an intelligent system with the help of camera feeds can monitor and identify the traffic signals dynamically. Traffic sign recognition is based on Advanced Driving Assistance System (ADAS) which is used by vehicles to recognise various traffic signs ahead. The system takes continuous video input from the dashboard camera or the camera mounted on the bonnet of the car. The underlying algorithm extracts the features of the input image and matches them with an existing library of traffic sign. The output is fed to the driving assistance system and it in turn drives the car accordingly. This intelligent system uses computer vision. This device will take camera feeds and upgrade the ADA system instantaneously. The algorithm has been implemented using Python language.

Sign in / Sign up

Export Citation Format

Share Document