International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 07 | July 2023
p-ISSN: 2395-0072
www.irjet.net
Traffic sign recognition and detection using SVM and CNN Sai Jayanth Gollapudi, Harshith Singathala, Harsha Kata 1Sai Jayanth Gollapudi, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore –
632014, Tamil Nadu, India
2Harshith Singathala, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore –
632014, Tamil Nadu, India
3Harsha Kata, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore – 632014,
Tamil Nadu, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - For adding the safety of the drivers, pedestrians
robot navigation and safe driving. In this paper, they proposed a framework with two deep learning fragments that includes (FCN) Fully convolutional association guided traffic sign suggestions and deep (CNN) Convolutional neural association for object request. Their thinking is to use CNN to arrange traffic sign suggestions to perform fast and exact traffic sign detection and affirmation. To improve the identification, they are utilizing edge box strategy by utilizing prepared FCN. They utilized shading division, colour segmentation, shape location and sliding window examining to discover traffic regions. They additionally have utilized a FCN guided item strategy. They utilized this calculation on the Swedish Traffic signs Dataset. They accomplished a generally excellent exactness on this Swedish signs dataset (98.67). In future, the creators are arranging an end to end network to produce the proposed FCN guided recommendations and growing ongoing traffic sign framework dependent on the calculations utilized in this paper.
and vehicles as well, to the driver easement systems, traffic sign recognition feature is required. For developing TSR systems, we need the use of CV (Computer Vision) techniques, which could be viewed as principal in the field of pattern recognition all in all. We are going to use two latest architectures called Lenet-5 model and VGGNet model architectures in two different approaches. In this project, we are going to present the study of two major approaches which are required for developing traffic sign detection and recognition systems. We propose a methodology for traffic sign identification dependent on Convolutional Neural Networks (CNN). First, we are going to transform the original image into greyscale image with the help of SVM(support vector machine) and then use CNN(convolutional neural network) for detecting and recognizing things with fixed and learnable layers we use CNN(convolutional neural network). With fixed layers, we can lessen the measure of interest zones to identify, and trim the limits near the boundaries of traffic signs. The accuracy of detection can be increased with the help of learnable layers. By researching and study of many research papers, we want to give a real-time solution for this challenging problem called TSR (Traffic Sign detection and Recognition).
[2] There are very good results achieved in traffic sign detection. In this paper, they are detecting and classifying the traffic signs dataset by using multi scale CNN algorithm. They also used selective search edge box techniques and multi scale combinatorial grouping (MCG). In this paper, they prepared/trained two networks on this benchmark: one treats every sign class as a solitary classification and can be viewed as a traffic sign detector and the other network can all the while recognize and classify traffic signs. The two algorithms beat past works. They utilized a dataset in which they took 10 areas from 5 unique urban communities in China, d 100000 scenes from the Tencent Data Center. It gives 100000 pictures containing 30000 traffic-sign occurrences. They achieved 84percent accuracy tested on the 90000 panoramas that contained no traffic signs, and the network perfectly identified them all. In future, the authors are planning to seek out more traffic signs of the classes that rarely appear in present work and they are also planning to accelerate speed of process in order to run it on mobile phones etc.. in real life.
Key Words: CNN, Driving Assistance, Neural Networks, Q Learning Reinforcement Learning, RNN.
1.INTRODUCTION Researchers are trying to develop advanced driver easement systems and by it’s name, requires more assistance features in it. One of the features in it is traffic sign detection and recognition. This feature helps in detecting and recognizing different traffic signs and alert the driver as a warning signal which helps in adding safety of the drivers, pedestrians and vehicles as well. The main aim of our project is developing TSR(Traffic sign detection and recognition) by making it to detect different traffic signs and classify them from the live images captured by a sensor(Ex: Camera).
2. LITERATURE REVIEW
[3] In this paper, they are presenting a new method to detect and recognize the traffic signs. This is based on 3 steps. First step is image segmentation using thresholding of HIS colour space components and extracts ROIs. The subsequent
[1] Detecting traffic signs has become a vital point in artificial intelligence, computer vision and deep learning with applications, taking everything into account, for example
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 842