scholarly journals Traffic Sign Classification and Detection of Indian Traffic Signs using Deep Learning

2021 ◽  
pp. 215-219
Author(s):  
Manjiri Bichkar ◽  
Suyasha Bobhate ◽  
Prof. Sonal Chaudhari
Keyword(s):  
Classification Model ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Electric Cars ◽  
Blob Detection ◽  
Sign Recognition ◽  
Testing Dataset ◽  
Self Driving Cars ◽  
Traffic Sign Classification

This paper presents an effective solution to detecting traffic signs on road by first classifying the traffic sign images us-ing Convolutional Neural Network (CNN) on the German Traffic Sign Recognition Benchmark (GTSRB)[1] and then detecting the images of Indian Traffic Signs using the Indian Dataset which will be used as testing dataset while building classification model. Therefore this system helps electric cars or self driving cars to recognise the traffic signs efficiently and correctly. The system involves two parts, detection of traffic signs from the environment and classification based on CNN thereby recognising the traffic sign. The classification involves building a CNN model of different filters of dimensions 3 × 3, 5 × 5, 9 × 9, 13 × 13, 15 × 15,19 × 19, 23 × 23, 25 × 25 and 31 ×31 from which the most efficient filter is chosen for further classifying the image detected. The detection involves detecting the traffic sign using YOLO v3-v4 and BLOB detection. Transfer Learning is used for using the trained model for detecting Indian traffic sign images.

scholarly journals Learning Region-Based Attention Network for Traffic Sign Recognition

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 686
Author(s):  
Ke Zhou ◽  
Yufei Zhan ◽  
Dongmei Fu
Keyword(s):  
High Resolution ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Attention Network ◽  
Sign Recognition ◽  
Learning Region ◽  
Robust Network ◽  
Traffic Sign Classification

Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this paper, we propose an ice environment traffic sign recognition benchmark (ITSRB) and detection benchmark (ITSDB), marked in the COCO2017 format. The benchmarks include 5806 images with 43,290 traffic sign instances with different climate, light, time, and occlusion conditions. Second, we tested the robustness of the Libra-RCNN and HRNetv2p on the ITSDB compared with Faster-RCNN. The Libra-RCNN performed well and proved that our ITSDB dataset did increase the challenge in this task. Third, we propose an attention network based on high-resolution traffic sign classification (PFANet), and conduct ablation research on the design parallel fusion attention module. Experiments show that our representation reached 93.57% accuracy in ITSRB, and performed as well as the newest and most effective networks in the German traffic sign recognition dataset (GTSRB).

Traffic Sign Recognition Based on SIFT Features

2010 ◽  
Vol 121-122 ◽  
pp. 596-599 ◽  
Author(s):  
Ni An Cai ◽  
Wen Zhao Liang ◽  
Shao Qiu Xu ◽  
Fang Zhen Li
Keyword(s):  
Traditional Method ◽  
Euclidean Distance ◽  
Experimental Results ◽  
Traffic Sign Recognition ◽  
Recognition Method ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Sign Recognition ◽  
Good Ability ◽  
Sift Features

A recognition method for traffic signs based on an SIFT features is proposed to solve the problems of distortion and occlusion. SIFT features are first extracted from traffic signs and matched by using the Euclidean distance. Then the recognition is implemented based on the similarity. Experimental results show that the proposed method, superior to traditional method, can excellently recognize traffic signs with the transformation of scale, rotation, and distortion and has a good ability of anti-noise and anti-occlusion.

Traffic Sign Recognition Method in Intelligent Transport System Based on the Low-Rank Approximation

2013 ◽  
Vol 644 ◽  
pp. 16-19
Author(s):  
Ming Xi Xiao ◽  
Han Ling Zhang
Keyword(s):  
Low Rank ◽  
Intelligent Transport System ◽  
Traffic Sign Recognition ◽  
Low Rank Approximation ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Intelligent Transport ◽  
Sign Recognition ◽  
Rank Approximation ◽  
Internal Texture

This paper presents a new method for traffic sign recognition in Intelligent Transport System,which base on low-rank approximation and support vector machine (SVM),the method including traffic signs correction and SVM identification.first we extraction traffic sign region and internal texture,according to the characteristics of internal texture,combine with the spare and low-rank approximation,to correct the texture automatically ,next to extract the feature vectors of traffic signs texture,finally identification in the database.The experimental results show: the method base on low-rank approximation can corrected the deformation traffic signs effectively and accurately,improve the recognition rate of the SVM,it has good feasibility and real-time.

scholarly journals Traffic Sign Classification Using CNN

2021 ◽  
Vol 9 (8) ◽  
pp. 1952-1956
Author(s):  
Kolachalama Venkata Naga Sreya
Keyword(s):  
Neural Network ◽  
Electric Vehicles ◽  
Efficiency Index ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Conventional Model ◽  
Sign Recognition ◽  
Index Terms ◽  
Traffic Sign Classification ◽  
Autonomous Electric Vehicles

Abstract: With the increasing necessity of autonomous electric vehicles as time passes by, there are a lot of technical prospects within the structure that have a lot of scope for advancement. One such prospect is traffic sign recognition. Several models have already been developed and are in practice but it is evident to everyone within this field that there is still a lot of untapped potential. In this project we implement feature classification using convolutional neural networks to achieve an efficiency and accuracy higher than that of a conventional model. The system first converts the image into grayscale and then three layers of the image are created. By using skilled convolutional neural network which incorporates crucial data of traffic signs and images, they are parallelly assigned to corresponding classes. Results have shown that this system works with great efficiency. Index Terms: Traffic sign, GTSRB, ALVINN, Neural Network, CNN, LeNet, ReLU, Evaluation, Epoch

Hardware Efficient Modified CNN Architecture for Traffic Sign Detection and Recognition

2021 ◽  
pp. 2250017
Author(s):  
Bhaumik Vaidya ◽  
Chirag Paunwala
Keyword(s):  
Feature Fusion ◽  
Detection Accuracy ◽  
Field Calculation ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Traffic Signs ◽  
Sign Recognition ◽  
Adverse Weather ◽  
Sign Detection ◽  
Traffic Sign Detection

Traffic sign recognition is a vital part for any driver assistance system which can help in making complex driving decision based on the detected traffic signs. Traffic sign detection (TSD) is essential in adverse weather conditions or when the vehicle is being driven on the hilly roads. Traffic sign recognition is a complex computer vision problem as generally the signs occupy a very small portion of the entire image. A lot of research is going on to solve this issue accurately but still it has not been solved till the satisfactory performance. The goal of this paper is to propose a deep learning architecture which can be deployed on embedded platforms for driver assistant system with limited memory and computing resources without sacrificing on detection accuracy. The architecture uses various architectural modification to the well-known Convolutional Neural Network (CNN) architecture for object detection. It uses a trainable Color Transformer Network (CTN) with the existing CNN architecture for making the system invariant to illumination and light changes. The architecture uses feature fusion module for detecting small traffic signs accurately. In the proposed work, receptive field calculation is used for choosing the number of convolutional layer for prediction and the right scales for default bounding boxes. The architecture is deployed on Jetson Nano GPU Embedded development board for performance evaluation at the edge and it has been tested on well-known German Traffic Sign Detection Benchmark (GTSDB) and Tsinghua-Tencent 100k dataset. The architecture only requires 11 MB for storage which is almost ten times better than the previous architectures. The architecture has one sixth parameters than the best performing architecture and 50 times less floating point operations per second (FLOPs). The architecture achieves running time of 220[Formula: see text]ms on desktop GPU and 578 ms on Jetson Nano which is also better compared to other similar implementation. It also achieves comparable accuracy in terms of mean average precision (mAP) for both the datasets.

scholarly journals A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4850
Author(s):  
Mingyu Gao ◽  
Chao Chen ◽  
Jie Shi ◽  
Chun Sing Lai ◽  
Yuxiang Yang ◽  
...  
Keyword(s):  
Recognition Accuracy ◽  
Gaussian Mixture ◽  
Traffic Sign Recognition ◽  
Recognition Method ◽  
Traffic Sign ◽  
Data Set ◽  
Traffic Signs ◽  
Automatic Driving ◽  
Sign Recognition ◽  
Accuracy Tradeoff

Effective traffic sign recognition algorithms can assist drivers or automatic driving systems in detecting and recognizing traffic signs in real-time. This paper proposes a multiscale recognition method for traffic signs based on the Gaussian Mixture Model (GMM) and Category Quality Focal Loss (CQFL) to enhance recognition speed and recognition accuracy. Specifically, GMM is utilized to cluster the prior anchors, which are in favor of reducing the clustering error. Meanwhile, considering the most common issue in supervised learning (i.e., the imbalance of data set categories), the category proportion factor is introduced into Quality Focal Loss, which is referred to as CQFL. Furthermore, a five-scale recognition network with a prior anchor allocation strategy is designed for small target objects i.e., traffic sign recognition. Combining five existing tricks, the best speed and accuracy tradeoff on our data set (40.1% mAP and 15 FPS on a single 1080Ti GPU), can be achieved. The experimental results demonstrate that the proposed method is superior to the existing mainstream algorithms, in terms of recognition accuracy and recognition speed.

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 Cautionary Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique

2018 ◽  
Vol 7 (3.14) ◽  
pp. 233
Author(s):  
Mohd Safirin Karis ◽  
Nursabillilah Mohd Ali ◽  
Nur Aisyah Abdul Ghafor ◽  
Muhamad Aizuddin Akmal Che Jusoh ◽  
Nurasmiza Selamat ◽  
...  
Keyword(s):  
Mean Value ◽  
Traffic Sign Recognition ◽  
Traffic Sign ◽  
Data Set ◽  
Traffic Signs ◽  
Recognition Process ◽  
Sign Recognition ◽  
Anticlockwise Rotation ◽  
The Impact ◽  
Detection And Recognition

In this paper, 19 cautionary traffic signs were selected as a database and 3 types of conditions have been proposed. The conditions are 5 different time of image taken; hidden region and anticlockwise rotation are all the experiments design that will shows all the errors in producing the it’s mean value and the performance of traffic sign recognition. Initial hypothesis was made as the error will become larger as the interruption getting bigger. Based on the results of the five-different time of image taken, the error gives the best performance; less error when time is between 8am to 12am due to the brightness factors and the sign can be recognize clearly during noon session. The hidden region conditions show good performances of the detection and recognition of the system depend on the lesser coverage of the hidden region introduce on traffic sign because if the hidden region coverage is huge the database will get confuse and take a longer time to do the recognition process. Lastly, in anticlockwise rotation shows that 90o gave large value of error causing the system unable to recognize sign perfectly rather than 135o angle. To sum-up, detection and recognition process are not depending on higher number of angle but the process solely depending on their value of sample for each traffic signs. The error will give the impact towards traffic sign recognition and detection process. In conclusion, SNN can perform the detection and recognition process to all objects as in the future the system will become more stable with the right technique on spiking models and well-developed technology in this field.  

Sign in / Sign up

Export Citation Format

Share Document