scholarly journals Vehicle Classification and Detection using Deep Learning

2019 ◽  
Vol 9 (1S5) ◽  
pp. 24-28
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Convolution Neural Network ◽  
Vehicle Classification ◽  
Hard Problem ◽  
Bounding Box ◽  
Probability Estimates

Intelligent transportation systems have acknowledged a ration of attention in the last decades. In this area vehicle classification and localization is the key task. In this task the biggest challenge is to discriminate the features of different vehicles. Further, vehicle classification and detection is a hard problem to identify and locate because wide variety of vehicles don’t follow the lane discipline. In this article, to identify and locate, we have created a convolution neural network from scratch to classify and detect objects using a modern convolution neural network based on fast regions. In this work we have considered three types of vehicles like bus, car and bike for classification and detection. Our approach will use the entire image as input and create a bounding box with probability estimates of the feature classes as output. The results of the experiment have shown that the projected system can considerably improve the accuracy of the detection.

scholarly journals Convolutional Neural Network Based Vehicle Classification in Adverse Illuminous Conditions for Intelligent Transportation Systems

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Muhammad Atif Butt ◽  
Asad Masood Khattak ◽  
Sarmad Shafique ◽  
Bashir Hayat ◽  
Saima Abid ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Intelligent Transportation Systems ◽  
Classification System ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Classification Systems ◽  
Vehicle Classification ◽  
Real Time Applications

In step with rapid advancements in computer vision, vehicle classification demonstrates a considerable potential to reshape intelligent transportation systems. In the last couple of decades, image processing and pattern recognition-based vehicle classification systems have been used to improve the effectiveness of automated highway toll collection and traffic monitoring systems. However, these methods are trained on limited handcrafted features extracted from small datasets, which do not cater the real-time road traffic conditions. Deep learning-based classification systems have been proposed to incorporate the above-mentioned issues in traditional methods. However, convolutional neural networks require piles of data including noise, weather, and illumination factors to ensure robustness in real-time applications. Moreover, there is no generalized dataset available to validate the efficacy of vehicle classification systems. To overcome these issues, we propose a convolutional neural network-based vehicle classification system to improve robustness of vehicle classification in real-time applications. We present a vehicle dataset comprising of 10,000 images categorized into six-common vehicle classes considering adverse illuminous conditions to achieve robustness in real-time vehicle classification systems. Initially, pretrained AlexNet, GoogleNet, Inception-v3, VGG, and ResNet are fine-tuned on self-constructed vehicle dataset to evaluate their performance in terms of accuracy and convergence. Based on better performance, ResNet architecture is further improved by adding a new classification block in the network. To ensure generalization, we fine-tuned the network on the public VeRi dataset containing 50,000 images, which have been categorized into six vehicle classes. Finally, a comparison study has been carried out between the proposed and existing vehicle classification methods to evaluate the effectiveness of the proposed vehicle classification system. Consequently, our proposed system achieved 99.68%, 99.65%, and 99.56% accuracy, precision, and F1-score on our self-constructed dataset.

scholarly journals Light Field Image Quality Enhancement by a Lightweight Deformable Deep Learning Framework for Intelligent Transportation Systems

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1136
Author(s):  
David Augusto Ribeiro ◽  
Juan Casavílca Silva ◽  
Renata Lopes Rosa ◽  
Muhammad Saadi ◽  
Shahid Mumtaz ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Intelligent Transportation Systems ◽  
Light Field ◽  
State Of The Art ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Machine Learning Algorithms ◽  
Learning Framework ◽  
Reconstruction Methods

Light field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time.

DwaRa: A Deep Learning-Based Dynamic Toll Pricing Scheme for Intelligent Transportation Systems

2020 ◽  
Vol 69 (11) ◽  
pp. 12510-12520
Author(s):  
Arpit Shukla ◽  
Pronaya Bhattacharya ◽  
Sudeep Tanwar ◽  
Neeraj Kumar ◽  
Mohsen Guizani
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Toll Pricing ◽  
Pricing Scheme

scholarly journals Driver’s Drowsiness Detection Based on Behavioural Changes using ResNet

2019 ◽  
Vol 8 (3) ◽  
pp. 5708-5712
Keyword(s):  
Deep Learning ◽  
Intelligent Transportation Systems ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Motor Vehicles ◽  
Steering Wheel ◽  
Road Accidents ◽  
Drowsiness Detection ◽  
Behavioural Changes ◽  
The Road

Recently there has been growing interest in intelligent transportation system because the road accidents become biggest problems of mankind and the casualties of accident also increases rapidly every year. The casualties are very often witnessed in heavy and light motor vehicles. Moreover, the accidents occur mainly due to carelessness and drowsy feeling of the driver. Intelligent transportation systems use deep learning mechanism to detect drowsiness of the driver and alert the same to driver. It results in reduction of accidents. The driver’s behaviour during drowsiness is detected by three types of approaches. One approach deploys the sensors in steering wheel and accelerator of the vehicle and analyzes the signal sent by the sensors to detect the drowsiness. Second approach focuses on measuring the heart rate, pulse rate and brain signals etc to predict the drowsiness. Third approach uses the facial expression of the driver such as blinking rate of eye, eye closure and yawning etc. The cause for most of the road accidents is driver’s drowsiness. Therefore, in this paper, the behavioural changes of driver is accounted to detect the drowsiness of the driver. Eye movement and yawning are two behavioural changes of driver is considered in this paper. There are many CNN based deep learning architectures such AlexNet, VGGNet, ResNet. In this paper, we propose the drowsiness detection using ResNet because this method works on the principle of passing the output to the next la. The performance of proposed mechanism detects the drowsiness of the driver better than AlexNet and VGGNet.

Sign in / Sign up

Export Citation Format

Share Document