An efficient animal detection system for smart cars using cascaded classifiers

2014 ◽  
Author(s):  
Abdelhamid Mammeri ◽  
Depu Zhou ◽  
Azzedine Boukerche ◽  
Mohammed Almulla
Keyword(s):  
Detection System ◽  
Cascaded Classifiers ◽  
Smart Cars ◽  
Animal Detection

scholarly journals Automated Pollution Detection System using IoT and AWS Cloud

2019 ◽  
Vol 8 (11) ◽  
pp. 3955-3960
Keyword(s):  
Mobile Application ◽  
Web Application ◽  
Detection System ◽  
Smart Cities ◽  
Traffic Monitoring ◽  
Traffic Lights ◽  
Pollution Detection ◽  
Smart Cars ◽  
Smart Traffic ◽  
The Web

Smart cities are one of the upcoming trends in the world. These smart cities include smart traffic light system, smart cars, smart homes, smart traffic monitoring system. As environmental pollution has become the major cause of various problems like climatic changes, improper irrigation methods, depletion of the ozone layer etc. “Automated Pollution Detection System using IoT and AWS Cloud” provides an architecture for integrating IoT and Cloud Computing and an application which is used to detect air pollution by fitting in arduino devices at public places like traffic lights, industrial areas, construction areas etc., and transferring the data using GSM modem to a cloud database server AWS RDS. The cloud server is linked with the EC2 instance (Ubuntu server) in order to publish the web application using EC2. Web Application which is created using Word press and a Mobile application using Android Studio. The Web application shows the value of pollutant at a particular place along with the map facility by using GPS in the Arduino. This is also linked to a mobile application which sends a push notification service (SNS) to our mobile application

A Proposal of an Animal Detection System Using Machine Learning

2019 ◽  
Vol 33 (13) ◽  
pp. 1093-1106 ◽  
Author(s):  
William H. S. Antônio ◽  
Matheus Da Silva ◽  
Rodrigo S. Miani ◽  
Jefferson R. Souza
Keyword(s):  
Machine Learning ◽  
Detection System ◽  
Animal Detection

scholarly journals Design of Precrash System for Smart Cars by using Li-Fi

2019 ◽  
Vol 9 (1) ◽  
pp. 2110-2114
Keyword(s):  
Visible Light ◽  
Collision Detection ◽  
Data Transmission ◽  
Detection System ◽  
Servo Motor ◽  
Light Spectrum ◽  
Range Sensor ◽  
Rear Light ◽  
Arduino Uno ◽  
Smart Cars

In this paper we proposed a system to avoid collision between vehicles by using light fidelity (Li-Fi) technology. The data transmission from one vehicle to another is facilitate with the help of car to car communication (C2C). The model consists of Li-Fi circuit, Arduino UNO, Ultrasonic Range Sensor, Servo Motor. The transmitter section will be placed on the rear light of the leading car and the receiver section will be placed on the front of the following car. The transmitter section placed on the leading car will sent the calculated speed to the receiver section placed on the following car and according to the data received the speed of the following car will change such that it avoids collision. The system makes use of the visible light spectrum for communication between vehicles. Hence the collision detection system become cheaper.

Wild Animal Detection from Highly Cluttered Images Using Deep Convolutional Neural Network

2018 ◽  
Vol 17 (04) ◽  
pp. 1850021
Author(s):  
Gyanendra K. Verma ◽  
Pragya Gupta
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Camera Trap ◽  
Wild Animal ◽  
Deep Convolutional Neural Network ◽  
Multimedia Data ◽  
Machine Learning Techniques ◽  
Wild Animals ◽  
Animal Detection

Monitoring wild animals became easy due to camera trap network, a technique to explore wildlife using automatically triggered camera on the presence of wild animal and yields a large volume of multimedia data. Wild animal detection is a dynamic research field since the last several decades. In this paper, we propose a wild animal detection system to monitor wildlife and detect wild animals from highly cluttered natural images. The data acquired from the camera-trap network comprises of scenes that are highly cluttered that poses a challenge for detection of wild animals bringing about low recognition rates and high false discovery rates. To deal with the issue, we have utilized a camera trap database that provides candidate regions utilizing multilevel graph cut in the spatiotemporal area. The regions are utilized to make a validation stage that recognizes whether animals are present or not in a scene. These features from cluttered images are extracted using Deep Convolutional Neural Network (CNN). We have implemented the system using two prominent CNN models namely VGGNet and ResNet, on standard camera trap database. Finally, the CNN features fed to some of the best in class machine learning techniques for classification. Our outcomes demonstrate that our proposed system is superior compared to existing systems reported in the literature.

Sign in / Sign up

Export Citation Format

Share Document