MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

World University root node

School of Electronics & Communication Engineering

Engineering and Technology

Implementation of Autonomous Driving Algorithms on a Miniature Robot

Pedestrian Intent Detection using Skeleton-based Prediction for Road Safety

To calculate the response physical circuit for the unknown condition, it is necessary to understand the physical circuit using mathematical model. The mathematical model is useful in case of design the control system or fault detection system for the external circuit. The proposed system deals with implementation of the mathematical model of the physical circuit using artificial neural network algorithms on FPGA. In the proposed system, the circuit under test (CUT) is connected to FPGA. FPGA applied test pattern input to the physical circuit, generate the weights and calculate the activation function. As the testing inputs are applied to the FPGA after successful training, the outcome results of the system are logically similar with a comparison of the external test circuit. To reduce the Register transfer level (RTL) logic design Vedic multiplier and divider using subtract and increment method is implemented in proposed system.

International Journal of Applied Engineering Research

Optimized Mathematical Model of Digital Circuit using ANN on FPGA

In recent years, the research on the anomaly detection has been rapidly increasing. The researchers were worked on different anomalies in videos. This work focuses on fall as an anomaly as it is an emerging research topic with application in elderly safety areas including home environment. The older population staying alone at home is prone to various accidental events including falls which may lead to multiple harmful consequences even death. Thus, it is imperative to develop a robust solution to avoid this problem. This can be done with the help of video surveillance along with computer vision. In this paper, a simple yet efficient technique to detect fall with the help of inexpensive depth camera was presented. Frame differencing method was applied for background subtraction. Various features including orientation angle, aspect ratio, silhouette features, and motion history image (MHI) were extracted for fall characterization. The training and testing were successfully implemented using SVM and SGD classifiers. It was observed that SGD classifier gives better fall detection accuracy than the SVM classifier in both training and testing phase for SDU fall dataset. © Springer Nature Singapore Pte Ltd. 2019.

Advances in Intelligent Systems and Computing

An intelligent video surveillance system for anomaly detection in home environment using a depth camera

The detection of unnatural falls among older adults living alone at home is an essential requirement of the day. Injury after a fall is common, and immediate medication is often necessary. A fall detection system using the following features such as orientation angle, aspect ratio, Motion History Image and object below the threshold line is proposed. The combination of these features can lead to a robust fall detection system. These features are used as an input for fall detection systems using machine-learning techniques such as Support Vector Machine, K-Nearest Neighbors, Stochastic Gradient Descent, Decision Tree and Gradient Boosting. The effect of using different classifiers and feature sets for the performance of fall detection is observed. This approach provided a promising F-measure value of 96% for Decision Tree algorithm on Coffee room environment.

Journal of Engineering Science and Technology

Indoor Human Fall Detection System Based On Automatic Vision Using Computer Vision And Machine Learning Algorithms

The automatic detection and recognition of anomalous events in crowded and complex scenes on video are the research objectives of this paper. The main challenge in this system is to create models for detecting such events due to their changeability and the territory of the context of the scenes. Due to these challenges, this paper proposed a novel HOME FAST (Histogram of Orientation, Magnitude, and Entropy with Fast Accelerated Segment Test) spatiotemporal feature extraction approach based on optical flow information to capture anomalies. This descriptor performs the video analysis within the smart surveillance domain and detects anomalies. In deep learning, the training step learns all the normal patterns from the high-level and low-level information. The events are described in testing and, if they differ from the normal pattern, are considered as anomalous. The overall proposed system robustly identifies both local and global abnormal events from complex scenes and solves the problem of detection under various transformations with respect to the state-of-the-art approaches. The performance assessment of the simulation outcome validated that the projected model could handle different anomalous events in a crowded scene and automatically recognize anomalous events with success.

Fulltext

J. Imaging

Deep learning with a spatiotemporal descriptor of appearance and motion estimation for video anomaly detection

The incident of fall of elder people increases day by day. Falls are one of the greatest risks for seniors living alone. Sometimes people may get serious injury to the spinal cord and hip region. In such cases, an injured elder people may remain on the ground for several hours after a fall incident has occurred. So there is a need of fall detection system to avoid such incident. This paper propose a novel method to detect falls which combines four features, Orientation angle, ratio of fitted ellipse, Motion Coefficient, Silhouette threshold. These features act as inputs to K-Nearest Neighbor classifier which recognizes fall events. This algorithm gives accuracy above 95% on stored video sequences of activities and real time environment. © 2015 IEEE.

Proceedings - IEEE International Conference on Information Processing, ICIP 2015

Fall detection using k-nearest neighbor classification for patient monitoring

Fall is an unusual activity and it is a serious problem among the elderly people. In the proposed system, we present an automatic approach for detecting and recognizing falls of elderly people in the home environments using video based technology. The focus is on the protection and assistance to the elderly people. Fall causes a very high risk of the elderly's life that may cause death. The fall incident is automatically extracted from the video data represents itself, unique information that can be used to alert emergency or to make a decision whether the fall is confirmed. The main motivation of this work is to provide such a system which automatically detects the fall and intimate the respective authority. Proposed method uses background subtraction to detect the moving object and mark those objects with a rectangular and elliptical bounding box followed by extracting the features like aspect ratio, fall angle, silhouette height. In the proposed system, an Adaboost classifier to classify the normal and fall event is used. The system is implemented using OpenCV libraries and Python. The accuracy of the proposed system on Le2i dataset is 79.31%. © 2016 IEEE.

Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016

Automated unusual event detection in video surveillance

Adaptive Filters are generally implemented in the time domain which works well in most scenarios however in many applications the impulse response becomes too long, increasing the complexity of the filter beyond a level where it can no longer be implemented efficiently in the time domain. An example of where this can happen would be in acoustic echo cancellation applications in hands free telephony. However there exists an alternative solution and that is to implement the filters in the frequency domain. The Discrete Fourier Transform or more specifically the Fast Fourier Transform (FFT) allows the conversion of signals from the time domain to the frequency domain in an efficient manner. Acoustic echo cancellation of the frequency domain adaptive filter is compared with time domain adaptive filter. Again results are compared for both frequency domain and time domain adaptive filters with different step sizes. © 2010 IEEE.