A Robust System for Road Sign Detection and Classification Using LeNet Architecture Based on Convolutional Neural Network

In this chapter, the authors report a system for detection and classification of road signs. This system consists of two parts. The first part detects the road signs in real time. The second part classifies the German traffic signs (GTSRB) dataset and makes the prediction using the road signs detected in the first part to test the effectiveness. The authors used HOG and SVM in the detection part to detect the road signs captured by the camera. Then they used a convolutional neural network based on the LeNet model in which some modifications were added in the classification part. The system obtains an accuracy rate of 96.85% in the detection part and 96.23% in the classification part.

Download Full-text

A Research Paper on Convolutional Neural Network (CNN) Theory based Automated Traffic and Road Sign Detection and Recognition System

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.37195 ◽

2021 ◽

Vol 9 (VII) ◽

pp. 3775-3783

Author(s):

Parkavi J.

Keyword(s):

Road Safety ◽

Road Network ◽

Good Accuracy ◽

Recognition System ◽

Accuracy Rate ◽

Traffic System ◽

The Road ◽

Road Signs ◽

Road Sign ◽

Sign Detection

India is a country with a dense road network and has a complex system to maintain road safety. As we all know that we have a complex traffic system in which we have more than 100 types of traffic symbols in it. While driving, it is tough to take care of all the symbols placed at the road end. Sometimes the driver does not know what that symbol says. In this system sometimes the driver misses the road signs because the attention of the driver is overdriving the vehicle safe which leads to an accident or issuing Challan. Sometimes the traffic signs don't notice by the driver. So all the drivers or the vehicle need a system which is capable to read and recognize the traffic symbol placed at the road end and the system must be capable of giving simple instruction to the driver. So that system can automatically detect which type of symbol is this and can notify the driver. The system must have a good accuracy rate, as well as the system, must have a very good speed of working. This system can also be used in driverless cars to notify the system about the road signals and hence the system can tackle all the symbols carefully.

Download Full-text

A robust system for road sign detection and classification using LeNet architecture based on convolutional neural network

Soft Computing ◽

10.1007/s00500-019-04307-6 ◽

2019 ◽

Vol 24 (9) ◽

pp. 6721-6733 ◽

Cited By ~ 4

Author(s):

Amal Bouti ◽

Med Adnane Mahraz ◽

Jamal Riffi ◽

Hamid Tairi

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Road Sign ◽

Sign Detection ◽

Robust System

Download Full-text

Deep Neural Networks for Road Sign Detection and Embedded Modeling Using Oblique Aerial Images

Remote Sensing ◽

10.3390/rs13050879 ◽

2021 ◽

Vol 13 (5) ◽

pp. 879

Author(s):

Zhu Mao ◽

Fan Zhang ◽

Xianfeng Huang ◽

Xiangyang Jia ◽

Yiping Gong ◽

...

Keyword(s):

Neural Networks ◽

Smart Cities ◽

Geometric Constraints ◽

Small Object ◽

The Road ◽

Road Signs ◽

Road Sign ◽

Synthesis Strategy ◽

Urban Models ◽

Sign Detection

Oblique photogrammetry-based three-dimensional (3D) urban models are widely used for smart cities. In 3D urban models, road signs are small but provide valuable information for navigation. However, due to the problems of sliced shape features, blurred texture and high incline angles, road signs cannot be fully reconstructed in oblique photogrammetry, even with state-of-the-art algorithms. The poor reconstruction of road signs commonly leads to less informative guidance and unsatisfactory visual appearance. In this paper, we present a pipeline for embedding road sign models based on deep convolutional neural networks (CNNs). First, we present an end-to-end balanced-learning framework for small object detection that takes advantage of the region-based CNN and a data synthesis strategy. Second, under the geometric constraints placed by the bounding boxes, we use the scale-invariant feature transform (SIFT) to extract the corresponding points on the road signs. Third, we obtain the coarse location of a single road sign by triangulating the corresponding points and refine the location via outlier removal. Least-squares fitting is then applied to the refined point cloud to fit a plane for orientation prediction. Finally, we replace the road signs with computer-aided design models in the 3D urban scene with the predicted location and orientation. The experimental results show that the proposed method achieves a high mAP in road sign detection and produces visually plausible embedded results, which demonstrates its effectiveness for road sign modeling in oblique photogrammetry-based 3D scene reconstruction.

Download Full-text

Multi-Pole Road Sign Detection Based on Faster Region-based Convolutional Neural Network (Faster R-CNN)

2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS) ◽

10.1109/aims52415.2021.9466014 ◽

2021 ◽

Author(s):

Achmad Zulfajri Syaharuddin ◽

Zahir Zainuddin ◽

Andani

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Road Sign ◽

Sign Detection

Download Full-text

Real-Time Video Road Sign Detection and Tracking using Image Processing and Autonomous Car

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.l1094.10812s219 ◽

2019 ◽

Vol 8 (12S2) ◽

pp. 495-500

Keyword(s):

Image Processing ◽

Real Time ◽

Template Matching ◽

High Rate ◽

Image Processing Technique ◽

Video Frame ◽

Road Signs ◽

Detection And Tracking ◽

Road Sign ◽

Sign Detection

Detection and monitoring of real-time road signs are becoming today's study in the autonomous car industry. The number of car users in Malaysia risen every year as well as the rate of car crashes. Different types, shapes, and colour of road signs lead the driver to neglect them, and this attitude contributing to a high rate of accidents. The purpose of this paper is to implement image processing using the real-time video Road Sign Detection and Tracking (RSDT) with an autonomous car. The detection of road signs is carried out by using Video and Image Processing technique control in Python by applying deep learning process to detect an object in a video’s motion. The extracted features from the video frame will continue to template matching on recognition processes which are based on the database. The experiment for the fixed distance shows an accuracy of 99.9943% while the experiment with the various distance showed the inversely proportional relation between distances and accuracies. This system was also able to detect and recognize five types of road signs using a convolutional neural network. Lastly, the experimental results proved the system capability to detect and recognize the road sign accurately.

Download Full-text

Hierarchical-Matching-Based Online and Real-Time Multi-Object Tracking with Deep Appearance Features

Algorithms ◽

10.3390/a13040080 ◽

2020 ◽

Vol 13 (4) ◽

pp. 80 ◽

Cited By ~ 1

Author(s):

Qingge Ji ◽

Haoqiang Yu ◽

Xiao Wu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Object Tracking ◽

Real Time ◽

Large Scale ◽

Accuracy Rate ◽

Position Information ◽

Matching Strategy ◽

Online Methods ◽

Different Levels

Based on tracking-by-detection, we propose a hierarchical-matching-based online and real-time multi-object tracking approach with deep appearance features, which can effectively reduce the false positives (FP) in tracking. For the purpose of increasing the accuracy rate of data association, we define the trajectory confidence using its position information, appearance information, and the information of historical relevant detections, after which we can classify the trajectories into different levels. In order to obtain discriminative appearance features, we developed a deep convolutional neural network to extract the appearance features of objects and trained it on a large-scale pedestrian re-identification dataset. Last but not least, we used the proposed diverse and hierarchical matching strategy to associate detection and trajectory sets. Experimental results on the MOT benchmark dataset show that our proposed approach performs well against other online methods, especially for the metrics of FP and frames per second (FPS).

Download Full-text

An ECG Signal Classification Method Based on Dilated Causal Convolution

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/6627939 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Hao Ma ◽

Chao Chen ◽

Qing Zhu ◽

Haitao Yuan ◽

Liming Chen ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Recurrent Neural Network ◽

Signal Classification ◽

Accuracy Rate ◽

Ecg Signals ◽

Convolutional Networks ◽

Fully Convolutional Networks ◽

Output Time

The incidence of cardiovascular disease is increasing year by year and is showing a younger trend. At the same time, existing medical resources are tight. The automatic detection of ECG signals becomes increasingly necessary. This paper proposes an automatic classification of ECG signals based on a dilated causal convolutional neural network. To solve the problem that the recurrent neural network framework network cannot be accelerated by hardware equipment, the dilated causal convolutional neural network is adopted. Given the features of the same input and output time steps of the recurrent neural network and the nondisclosure of future information, the network is constructed with fully convolutional networks and causal convolution. To reduce the network depth and prevent gradient explosion or gradient disappearance, the dilated factor is introduced into the model, and the residual blocks are introduced into the model according to the shortcut connection idea. The effectiveness of the algorithm is verified in the MIT-BIH Atrial Fibrillation Database (MIT-BIH AFDB). In the experiment of the MIT-BIH AFDB database, the classification accuracy rate is 98.65%.

Download Full-text

Method of Automated Detection of Traffic Violation with a Convolutional Neural Network

EPJ Web of Conferences ◽

10.1051/epjconf/201922404004 ◽

2019 ◽

Vol 224 ◽

pp. 04004

Author(s):

S.R. Ibadov ◽

B.Y. Kalmykov ◽

R.R. Ibadov ◽

R.A. Sizyakin

Keyword(s):

Neural Network ◽

Object Detection ◽

Convolutional Neural Network ◽

Real Time ◽

Video Sequence ◽

Motor Vehicle ◽

Automated Detection ◽

The Road ◽

Traffic Violation ◽

Pedestrian Crossing

This article describes the relevance of developing methods and systems for detection photo-video violations of the Rules of the road. The proposed method includes several steps: 1) detecting of the three classes of objects on a video sequence (pedestrian crossing, a motor vehicle and a human on the pedestrian crossing; 2) tracking the trajectories of the vehicle and the human on the pedestrian crossing; 3) comparing the paths of the pedestrian and the vehicle and determining whether there has been a violation of the Rules of the road for a certain period of time. For real-time object detection, we used neural network YOLO V3.

Download Full-text