keerthi kiran - Academia.edu (original) (raw)

Papers by keerthi kiran

Research paper thumbnail of Vehicle Recognition using extensions of Pattern Descriptors

IOP Conference Series: Materials Science and Engineering, 2021

Vehicle identification and classification for still images are incredibly useful and can be exten... more Vehicle identification and classification for still images are incredibly useful and can be extended to a range of traffic surveillance operations. Reliable and accurate recognition of vehicles is however a challenging issue due to changes in vehicle appearance and illumination difference in real time scene. In this paper, we present a simple and effective way of vehicle recognition technique based on vehicle’s local texture features extraction and classification. The local features are extracted individually using the Local Binary Pattern (LBP), Median Binary Pattern (MBP), Gradient directional pattern (GDP), and Local Arc Pattern (LAP) descriptors and feed into Support Vector Machine (SVM) for classification. We also focus on vehicle classification using various color spaces like RGB, HSV, YCbCr for the texture descriptors extraction. The primary focus is to observe the effect of colour information on vehicle classification efficiency across different colour spaces. Initially, exp...

Research paper thumbnail of Embedded Monitoring of Industrial Process through Wireless Communication

This paper proposes an advanced system for process management via a credit card sized single boar... more This paper proposes an advanced system for process management via a credit card sized single board computer called raspberry pi based multi parameter monitoring hardware system designed using RS232 and microcontroller that measures and controls various global parameters. The system comprises of a single master and multiple slaves with wireless mode of communication and a raspberry pi system that can either operate on windows or linux operating system. The parameters that can be tracked are current, voltage, temperature, light intensity and water level. The hardware design is done with the surface mount devices (SMD) on a double layer printed circuit board (PCB) to reduced the size and improve the power efficiency. The various interesting features are field device communication via USB-OTG enabled Android devices, on field firm ware update without any specific hardware and remote monitoring and control.

Research paper thumbnail of “Optimizing Data Encoding technique for Dynamic Power reduction in Network on Chip”

Research paper thumbnail of Edge preserving noise robust deep learning networks for vehicle classification

Concurrency and Computation: Practice and Experience

SummaryFor controlling and managing the traffic and to help traffic surveillance, the vehicles cl... more SummaryFor controlling and managing the traffic and to help traffic surveillance, the vehicles classification is a matter of great importance. In the last few decades, vehicle classification systems based on pattern recognition have been utilized to enhance the efficiency for traffic monitoring systems. In the literature many deep learning networks are suggested for vehicle classification. Even though deep learning algorithms are fascinating and growing research area. However, there are several barriers that slow down its progress. The greatest factor that reduces the progress of deep learning systems is the quality of the image. The available vehicle image datasets are affected by noise, weather, and illumination variations. To overcome these issues, we suggest a robust deep learning system by combining bilateral filter individually with three different networks for the improvement of the robustness of vehicle classification in real‐time application. For validation the suggested ne...

Research paper thumbnail of Improvement on Deep Features through Various Enhancement Techniques for Vehicles Classification

Sensing and Imaging

In the smart transport network, the classification of vehicles plays a significant role. However,... more In the smart transport network, the classification of vehicles plays a significant role. However, the traditional classification systems of vehicles can not satisfy the specifications of real-time applications because of disparities such as luminescence, weather, noise, and many more factors. Convolutional neural network (CNN) has gained more attraction since it boosts the recognition performance considerably. CNN comprises various types of pre-trained networks through which features can be extracted. The focus of the paper is to enhance the features of the existing pre-trained networks by integrating with most advanced enhancement techniques for increasing the vehicle recognition rate. This work utilizes different enhancement techniques to achieve improved features. Different CNN networks chosen in this work are Residual networks (ResNet-18, 50, 101), AlexNet, GoogLeNet, DenseNet-201, VGG-19. The enhancement techniques like Discrete Wavelet Transform (DWT), Histogram Equalization (HE), Adaptive gamma correction with a weighting distribution function (AGCWD), Homomorphic Filter (HF), and Joint Histogram Equalization (JHE) are chosen for the suggested method. SoftMax layer of CNN and Support Vector Machine (SVM) are used for the classification task. Extensive experiments are conducted using 1510 images with 10 different classes of Comprehensive Cars-Surveillance view (CompCars) dataset. The results show that the suggested approaches deliver higher recognition rate than the different traditional CNN networks. Among all the suggested integrated models, the best classification result is achieved mostly for the AGCWD integrated with different networks. The suggested approaches outperform many existing methods.

Research paper thumbnail of Vehicle Detection and Classification: A Review

Advances in Intelligent Systems and Computing

Smart traffic and information systems require the collection of traffic data from respective sens... more Smart traffic and information systems require the collection of traffic data from respective sensors for regulation of traffic. In this regard, surveillance cameras have been installed in monitoring and control of traffic in the last few years. Several studies are carried out in video surveillance technologies using image processing techniques for traffic management. Video processing of a traffic data obtained through surveillance cameras is an instance of applications for advance cautioning or data extraction for real-time analysis of vehicles. This paper presents a detailed review of vehicle detection and classification techniques and also discusses about different approaches detecting the vehicles in bad weather conditions. It also discusses about the datasets used for evaluating the proposed techniques in various studies.

Research paper thumbnail of Vehicle Recognition using extensions of Pattern Descriptors

IOP Conference Series: Materials Science and Engineering, 2021

Vehicle identification and classification for still images are incredibly useful and can be exten... more Vehicle identification and classification for still images are incredibly useful and can be extended to a range of traffic surveillance operations. Reliable and accurate recognition of vehicles is however a challenging issue due to changes in vehicle appearance and illumination difference in real time scene. In this paper, we present a simple and effective way of vehicle recognition technique based on vehicle’s local texture features extraction and classification. The local features are extracted individually using the Local Binary Pattern (LBP), Median Binary Pattern (MBP), Gradient directional pattern (GDP), and Local Arc Pattern (LAP) descriptors and feed into Support Vector Machine (SVM) for classification. We also focus on vehicle classification using various color spaces like RGB, HSV, YCbCr for the texture descriptors extraction. The primary focus is to observe the effect of colour information on vehicle classification efficiency across different colour spaces. Initially, exp...

Research paper thumbnail of Embedded Monitoring of Industrial Process through Wireless Communication

This paper proposes an advanced system for process management via a credit card sized single boar... more This paper proposes an advanced system for process management via a credit card sized single board computer called raspberry pi based multi parameter monitoring hardware system designed using RS232 and microcontroller that measures and controls various global parameters. The system comprises of a single master and multiple slaves with wireless mode of communication and a raspberry pi system that can either operate on windows or linux operating system. The parameters that can be tracked are current, voltage, temperature, light intensity and water level. The hardware design is done with the surface mount devices (SMD) on a double layer printed circuit board (PCB) to reduced the size and improve the power efficiency. The various interesting features are field device communication via USB-OTG enabled Android devices, on field firm ware update without any specific hardware and remote monitoring and control.

Research paper thumbnail of “Optimizing Data Encoding technique for Dynamic Power reduction in Network on Chip”

Research paper thumbnail of Edge preserving noise robust deep learning networks for vehicle classification

Concurrency and Computation: Practice and Experience

SummaryFor controlling and managing the traffic and to help traffic surveillance, the vehicles cl... more SummaryFor controlling and managing the traffic and to help traffic surveillance, the vehicles classification is a matter of great importance. In the last few decades, vehicle classification systems based on pattern recognition have been utilized to enhance the efficiency for traffic monitoring systems. In the literature many deep learning networks are suggested for vehicle classification. Even though deep learning algorithms are fascinating and growing research area. However, there are several barriers that slow down its progress. The greatest factor that reduces the progress of deep learning systems is the quality of the image. The available vehicle image datasets are affected by noise, weather, and illumination variations. To overcome these issues, we suggest a robust deep learning system by combining bilateral filter individually with three different networks for the improvement of the robustness of vehicle classification in real‐time application. For validation the suggested ne...

Research paper thumbnail of Improvement on Deep Features through Various Enhancement Techniques for Vehicles Classification

Sensing and Imaging

In the smart transport network, the classification of vehicles plays a significant role. However,... more In the smart transport network, the classification of vehicles plays a significant role. However, the traditional classification systems of vehicles can not satisfy the specifications of real-time applications because of disparities such as luminescence, weather, noise, and many more factors. Convolutional neural network (CNN) has gained more attraction since it boosts the recognition performance considerably. CNN comprises various types of pre-trained networks through which features can be extracted. The focus of the paper is to enhance the features of the existing pre-trained networks by integrating with most advanced enhancement techniques for increasing the vehicle recognition rate. This work utilizes different enhancement techniques to achieve improved features. Different CNN networks chosen in this work are Residual networks (ResNet-18, 50, 101), AlexNet, GoogLeNet, DenseNet-201, VGG-19. The enhancement techniques like Discrete Wavelet Transform (DWT), Histogram Equalization (HE), Adaptive gamma correction with a weighting distribution function (AGCWD), Homomorphic Filter (HF), and Joint Histogram Equalization (JHE) are chosen for the suggested method. SoftMax layer of CNN and Support Vector Machine (SVM) are used for the classification task. Extensive experiments are conducted using 1510 images with 10 different classes of Comprehensive Cars-Surveillance view (CompCars) dataset. The results show that the suggested approaches deliver higher recognition rate than the different traditional CNN networks. Among all the suggested integrated models, the best classification result is achieved mostly for the AGCWD integrated with different networks. The suggested approaches outperform many existing methods.

Research paper thumbnail of Vehicle Detection and Classification: A Review

Advances in Intelligent Systems and Computing

Smart traffic and information systems require the collection of traffic data from respective sens... more Smart traffic and information systems require the collection of traffic data from respective sensors for regulation of traffic. In this regard, surveillance cameras have been installed in monitoring and control of traffic in the last few years. Several studies are carried out in video surveillance technologies using image processing techniques for traffic management. Video processing of a traffic data obtained through surveillance cameras is an instance of applications for advance cautioning or data extraction for real-time analysis of vehicles. This paper presents a detailed review of vehicle detection and classification techniques and also discusses about different approaches detecting the vehicles in bad weather conditions. It also discusses about the datasets used for evaluating the proposed techniques in various studies.