scholarly journals Transfer Learning Based Traffic Sign Recognition Using Inception-v3 Model

2018 ◽  
Vol 47 (3) ◽  
pp. 242-250 ◽  
Author(s):  
Chunmian Lin ◽  
Lin Li ◽  
Wenting Luo ◽  
Kelvin C. P. Wang ◽  
Jiangang Guo
Keyword(s):  
Transfer Learning ◽  
Recognition Performance ◽  
Processing Technique ◽  
Learning Rate ◽  
Training Data ◽  
Fine Tuning ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition ◽  
High Level

Traffic sign recognition is critical for advanced driver assistant system and road infrastructure survey. Traditional traffic sign recognition algorithms can't efficiently recognize traffic signs due to its limitation, yet deep learning-based technique requires huge amount of training data before its use, which is time consuming and labor intensive. In this study, transfer learning-based method is introduced for traffic sign recognition and classification, which significantly reduces the amount of training data and alleviates computation expense using Inception-v3 model. In our experiment, Belgium Traffic Sign Database is chosen and augmented by data pre-processing technique. Subsequently the layer-wise features extracted using different convolution and pooling operations are compared and analyzed. Finally transfer learning-based model is repetitively retrained several times with fine-tuning parameters at different learning rate, and excellent reliability and repeatability are observed based on statistical analysis. The results show that transfer learning model can achieve a high-level recognition performance in traffic sign recognition, which is up to 99.18 % of recognition accuracy at 0.05 learning rate (average accuracy of 99.09 %). This study would be beneficial in other traffic infrastructure recognition such as road lane marking and roadside protection facilities, and so on.

scholarly journals Yolo V4 for advanced Traffic Sign Recognition with synthetic training data generated by various GAN

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
Christine Dewi ◽  
Rung-Ching Chen ◽  
Yan-Ting Liu ◽  
Xiaoyi Jiang ◽  
Kristoko Dwi Hartomo
Keyword(s):  
Training Data ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Synthetic Training Data

Traffic Sign Recognition Using a Synthetic Data Training Approach

2020 ◽  
Vol 29 (05) ◽  
pp. 2050013
Author(s):  
Oualid Araar ◽  
Abdenour Amamra ◽  
Asma Abdeldaim ◽  
Ivan Vitanov
Keyword(s):  
Neural Networks ◽  
Synthetic Data ◽  
Real Data ◽  
Training Data ◽  
Traffic Sign Recognition ◽  
Driver Assistance ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Crucial Component ◽  
Training Approach

Traffic Sign Recognition (TSR) is a crucial component in many automotive applications, such as driver assistance, sign maintenance, and vehicle autonomy. In this paper, we present an efficient approach to training a machine learning-based TSR solution. In our choice of recognition method, we have opted for convolutional neural networks, which have demonstrated best-in-class performance in previous works on TSR. One of the challenges related to training deep neural networks is the requirement for a large amount of training data. To circumvent the tedious process of acquiring and manually labelling real data, we investigate the use of synthetically generated images. Our networks, trained on only synthetic data, are capable of recognising traffic signs in challenging real-world footage. The classification results achieved on the GTSRB benchmark are seen to outperform existing state-of-the-art solutions.

scholarly journals Transfer Learning Based Traffic Sign Recognition System for Surveillance Application

2019 ◽  
Vol 8 (3) ◽  
pp. 573-576
Keyword(s):  
Transfer Learning ◽  
Road Traffic ◽  
Recognition System ◽  
Vehicle Tracking ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition ◽  
Wide Range ◽  
Traffic Recognition ◽  
Surveillance Application

Road Traffic Recognition is very important in many applications, such as automated deployment, traffic mapping, and vehicle tracking. Proposed traffic sign recognition system tails the transfer learning method that is frequently used in neural network uses. The benefit of expending this technique is that the initially network has been trained with a rich set of features appropriate to a wide range of images. Once the network is trained , learning can be transferred to the new activity adjustment to the network. Firsthand Indian traffic sign dataset is used.New results exhibit that the suggested method can accomplish modest outcomes when matched with other related techniques.

scholarly journals New Dark Area Sensitive Tone Mapping for Deep Learning Based Traffic Sign Recognition

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3776 ◽  
Author(s):  
Jameel Khan ◽  
Donghoon Yeo ◽  
Hyunchul Shin
Keyword(s):  
Recognition Performance ◽  
Recognition System ◽  
Tone Mapping ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Sign Recognition ◽  
Sign Detection ◽  
Illumination Preprocessing ◽  
Traffic Sign Detection

In this paper, we propose a new Intelligent Traffic Sign Recognition (ITSR) system with illumination preprocessing capability. Our proposed Dark Area Sensitive Tone Mapping (DASTM) technique can enhance the illumination of only dark regions of an image with little impact on bright regions. We used this technique as a pre-processing module for our new traffic sign recognition system. We combined DASTM with a TS detector, an optimized version of YOLOv3 for the detection of three classes of traffic signs. We trained ITSR on a dataset of Korean traffic signs with prohibitory, mandatory, and danger classes. We achieved Mean Average Precision (MAP) value of 90.07% (previous best result was 86.61%) on challenging Korean Traffic Sign Detection (KTSD) dataset and 100% on German Traffic Sign Detection Benchmark (GTSDB). Result comparisons of ITSR with latest D-Patches, TS detector, and YOLOv3 show that our new ITSR significantly outperforms in recognition performance.

scholarly journals The Implications of Weather and Reflectivity Variations on Automatic Traffic Sign Recognition Performance

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Mudasser Seraj ◽  
Andres Rosales-Castellanos ◽  
Amr Shalkamy ◽  
Karim El-Basyouny ◽  
Tony Z. Qiu
Keyword(s):  
Object Detection ◽  
Real World ◽  
System Analysis ◽  
Recognition Performance ◽  
Weather Conditions ◽  
Recognition System ◽  
Warning Signs ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Sign Recognition

Automatic recognition of traffic signs in complex, real-world environments has become a pressing research concern with rapid improvements of smart technologies. Hence, this study leveraged an industry-grade object detection and classification algorithm (You-Only-Look-Once, YOLO) to develop an automatic traffic sign recognition system that can identify widely used regulatory and warning signs in diverse driving conditions. Sign recognition performance was assessed in terms of weather and reflectivity to identify the limitations of the developed system in real-world conditions. Furthermore, we produced several editions of our sign recognition system by gradually increasing the number of training images in order to account for the significance of training resources in recognition performance. Analysis considering variable weather conditions, including fair (clear and sunny) and inclement (cloudy and snowy), demonstrated a lower susceptibility of sign recognition in the highly trained system. Analysis considering variable reflectivity conditions, including sheeting type, lighting conditions, and sign age, showed that older engineering-grade sheeting signs were more likely to go unnoticed by the developed system at night. In summary, this study incorporated automatic object detection technology to develop a novel sign recognition system to determine its real-world applicability, opportunities, and limitations for future integration with advanced driver assistance technologies.

scholarly journals Modification of the Pre-Processing Stage of a Traffi Sign Recognition System Taking into Account the Characteristics of the Subject Area

Vestnik NSUEM ◽  
2020 ◽  
pp. 235-249
Author(s):  
S. Yu. Pchelintsev
Keyword(s):  
Processing Speed ◽  
Recognition System ◽  
Subject Area ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Road Signs ◽  
Sign Recognition ◽  
The Subject ◽  
Recognition Systems ◽  
High Level

Traffic sign recognition systems require a high level of responsiveness and accuracy with limited use of computing resources. The process of image pre-processing precedes the process of directly recognizing images, therefore, the recognition results depend on its effectiveness. When conducting pre-processing, it is important to take into account the features of the subject area, within which recognition is performed. The article discusses the process of pre-processing and preparing images in the context of creating a system for recognizing road signs. The main problems that arise during the operation of such a system are identified. Their solutions are proposed. Own combination of these solutions allowed us to create a new system for recognizing road signs, which gives a gain in processing speed by cutting off images of no interest before entering the classifier, and also taking into account the peculiarities of operation in an urban environment – more difficult conditions compared with recognition of road signs on tracks or on artificially created training grounds.

Sign in / Sign up

Export Citation Format

Share Document