ANDROID CONTROL WILD LIFE OBSERVATION ROBOT by IRJET Journal

International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 05 | May 2022 www.irjet.net

e-ISSN: 2395-0056 p-ISSN: 2395-0072

ANDROID CONTROL WILD LIFE OBSERVATION ROBOT K T Navaneetha Krishnan1 , K Manoj Kumar2, S Manjunathan3, Dr. K Kalaiselvi4 1,2,3 UG Scholar, 4 Associate Professor 1,2,3,4Department of Electronics and Communication Engineering,

Hindusthan College of Engineering and Technology, Othakalmandapam, Coimbatore, India. --------------------------------------------------------------------***-------------------------------------------------------------------the author used ATT Squeeze U-Net for segmentation and Abstract: By entering the habitats of wild animals, wildlife watchers may get up close and personal with them. It is true that getting near to all wild creatures is not always safe. As a result, we propose this wildlife monitoring robot using IOT. Users may watch live activities using their android phones. So, by using this robotic vehicle, wildlife observers may get up and personal with wild creatures. An ESP32 is used in this system. The system receives these orders using a Wi-Fi module. We required our robot to be able to move silently and purposefully when monitoring a natural target without being recognised as we developed the technology to allow our robot to deal with the problems of keeping constant surveillance of a target. The data is subsequently processed by the microprocessor, which then sends signals to the motors to operate them. The motors are now operated by the driver motors, which provide necessary signal outputs to drive the vehicle movement. Key Words: Wildlife Monitoring, live streaming, Fire Detection, Object Detection, Movement Tracking

1.INTRODUCTION Wildlife observation robot is an autonomous or androidcontrolled robot that is used to observe animals more effectively. Poaching and animal smuggling have posed a threat to biodiversity in recent years, putting the majority of species in jeopardy. Several endangered species are on the verge of extinction. The use of automated technology for wildlife observation has grown quite prevalent, and various modern cameras are now available for this purpose. Fieldwork in biology is time-consuming, but it is becoming increasingly advanced. Thousands of wildlife photographers are out and about photographing animals in the magnificent forests around us. It's crucial to keep the camera in situations where it can appear impossible to get great images. Camera traps, which are stationary cameras activated by motion, have been employed in the past. This strategy necessitates a great deal of luck, patience, and perseverance. Many significant data about the surroundings may be found through wildlife observation.

Impact Factor value: 7.529

recognition. The incorporated Squeeze Net architecture with modified Fire module on ATT U-Net, which enabled more effective feature learning based on limited data. Subsequently, another recognition model adopting a portion of the newly established encoding path was utilized for classification.

“A Dual-Isolation-Forests-Based Attack Detection Framework for Industrial Control Systems” in this reference paper, the cyber-attack detection framework is composed of two isolation forest models that are trained independently using the normalized raw data and a preprocessed version of the data using Principal Component Analysis (PCA), respectively, to detect attacks by separating-away anomalies. The performance of the proposed method is compared with the previous works, and it demonstrates improvements in terms of the attack detection capability, computational requirements, and applicability to high dimensional systems. “A New Approach for Smoking Event Detection Using a Variational Autoencoder and Neural Decision Forest“ int this reference paper, they present a wireless body area network-based system consisting of two off-the-shelf devices, one smartphone and one smart watch, to detect smoking events by mining the inertial sensor data from both devices. The variational auto encoder is adopted to learn the feature representation and deal with the class imbalance problem, and the stochastic decision forest is adopted “An Attention Enhanced Bidirectional LSTM for Early Forest Fire Smoke Recognition“, in this reference paper, the ABi-LSTM has been inspired by the attention mechanism in neural machine translation, which can adaptively focus on discriminative frames. As a result, this framework may be suitable for early forest fire smoke detection. An interesting question is whether attention mechanism can be used in a single frame image to enable the model “Evaluation of Random Forest for Complex Human Activity Recognition Using Wearable Sensors” , in this reference paper, the accurately recognizing human activities plays a central role in a variety of real-world applications that range from smart home and ambient assisted living

ISO 9001:2008 Certified Journal

Page 1834