International Journal of Computer and Applications

IEEE Antennas and Wireless Propagation Letters

Real-time automatic helmet detection of motorcyclists in urban traffic using improved YOLOv5 detector

The aim of thisexploration work is to analyze the presentation ofunsupervised classification algorithms ISODATA(Iterative Self-Organizing Data Analysis Technique Algorithm)andK-Means in remote sensing, to evaluate statistically by iterative techniques to automatically group pixels of similar spectral features into unique clusters. This investigation used SUPARCO(Space and Upper Atmosphere Research Commission (Pakistan)) obtained remotely sensed patch of Abbottabad Pakistan. The test patch of Abbottabad is divided into Five bands i.e. NDVI (Normalized Difference Vegetation Index), green, near infrared, far infrared, and green. The ROIs (regions of interest) selected for classification of Land Cover data comprises five different types of classes i.e. water bodies, agriculture, settled area, forest and barren land. In this research of remote sensing the first step was to preprocess Abbottabad test patch by filtering, to improve performance of classification andneighboring pixels homogeneity. The next step was to assess the accuracy of Two pixel based unsupervised classifiers i.e. ISODATA and k-means on the said test patch. Finally, the mentioned classifiers performance is evaluated by varying their different parameters to categorize the effect of the clustering algorithms and their class statisticson whole classification outcomes.

/pdf/k-means-and-isodata-clustering-algorithms-for-landcover-4adecoqnu3.pdf

K-Means and ISODATA Clustering Algorithms for Landcover Classification Using Remote Sensing

A deep heterogeneous feature fusion approach for automatic land-use classification

The predominant discrimination of an electric vehicle from the conventional gas vehicle is the use of suitable electric drive system. It introduces new elements such as inverters, electric motors, ...

Evaluation of electromagnetic intrusion in brushless DC motor drive for electric vehicle applications with manifestation of mitigating the electromagnetic interference

The great presumption of change detection has led to rapid development of diverse change detection algorithms. Unsupervised change detection has a vital role in a wide variety of applications like remote sensing, motion detection, environmental monitoring, medical diagnosis, damage assessment, agricultural surveys, surveillance etc. In this paper a systematic survey of the commonly used methodologies for unsupervised change detection is presented.

A survey on unsupervised change detection algorithms

As the number of bikes in India is increasing daily compared to that of the human population. The danger of demise has increased 2.5 times among the riders without using a helmet contrasted with person wearing a helmet. The presented video observation based system may be powerful but still it needs critical human help whose productivity diminishes with time and human biasing additionally comes into the image. This paper plans to unwind this issue by automating the technique for distinguishing the riders with and without helmets. The system takes a video of traffic on an open street as an information and recognizes the moving items inside the scene. This work proposes a system based on the location of individual or different riders taking a trip on bikes with no helmets. Inside the proposed approach, from the beginning stage, bike riders are recognized with the use of YOLOv3 model which is a consistent type of YOLO model, the forefront methodology for object distinguishing helps as such in distinguishing the riders with and without helmet. The vertical projection of binary image is used for counting the number of riders if it exceeds two.

Machine Learning based Surveillance System for Detection of Bike Riders without Helmet and Triple Rides

Remote sensing plays a vital role in overseeing the transformations on the earth surface. Unsupervised clustering has a indispensable role in an immense range of applications like remote sensing, motion detection, environmental monitoring, medical diagnosis, damage assessment, agricultural surveys, surveillance etc In this paper, a novel method for unsupervised classification in multitemporal optical image based on DWT Feature Extraction and K-means clustering is proposed. After preprocessing the optical image is feature extracted using the discrete wavelet transform. On the feature extracted image feature reduction is performed using energy based selection. Finally different K means clustering is performed and analyzed using Matlab and ground truth data for improving classification accuracy.

https://research.ijcaonline.org/volume84/number12/pxc3892981.pdf

Performance Analysis of K-Means Clustering For Remotely Sensed Images

Conventional classification algorithms makes the use of only multispectral information in remote sensing image classification Wavelet provides spatial and spectral characteristics of a pixel along with its neighbours and hence this can be utilized for an improved classification The major disadvantage of wavelet transform is the non availability of spatial frequency features in its directional components The contourlet transform based laplacian pyramid followed by directional filter banks is an efficient way of extracting features in the directional components In this paper different contourlet frame based feature extraction techniques for remote sensing images are proposed Principal component analysis (PCA) method is used to reduce the number of features Gaussian Kernel fuzzy C-means classifiers uses these features to improve the classification accuracy Accuracy assessment based on field visit data and cluster validity measures are used to measure the accuracy of the classified data The experimental result shows that the overall accuracy is improved to 173 % (for LISS-II), 181 % (for LISS-III) and 195 % (for LISS-IV) and the kappa coefficient is improved to 0933 (for LISS-II), 00103 (for LISS-III) and 00214 (for LISS-IV) and also the cluster validity measures gives better results when compared to existing method

K. Venkateswaran

Papers

Evaluation of electromagnetic intrusion in brushless DC motor drive for electric vehicle applications with manifestation of mitigating the electromagnetic interference

A survey on unsupervised change detection algorithms

Machine Learning based Surveillance System for Detection of Bike Riders without Helmet and Triple Rides

Performance Analysis of K-Means Clustering For Remotely Sensed Images

Performance Comparison of Wavelet and Contourlet Frame Based Features for Improving Classification Accuracy in Remote Sensing Images