• Miss.Sayali Vijay Chavan
• Mr.R.G.Mevekari

Deep Learning algorithms are gaining popularity day by day because of its high accuracy compared to other traditional algorithms. Animal classification system is helpful in different fields like in wildlife surveillance, for students and researchers.This paper contains Implementation of Deep learning based Convolutional Neural Network(CNN) algorithm using Single Shot Multi-Box Detector(SSD) with MobileNetV2 on Raspberry Pi 3B+ with Picamera interfaced so that to make system real time. Images of cats and dogs were trained on google colab and then trained file is deployed on Raspberry Pi to implement it using TensorFlowLite. Raspberry Pi(RPi) was wirelessly connected to laptop using VNC Viewer so that to access RPi remotely. So, this makes RPi as handy device to observe interested animals in remote areas where humans want to study animals without disturbing animals to capture real data. Experimental results shows that Raspberry pi, an inexpensive way can be used to observe animals from remote areas and classify them in real time using deep learning.

Deep Learning, Raspberry Pi, CNN, SSD with MobileNetV2, Google Colab , TensorFlowLite, VNC Viewer.

"Design and Development of Deep Learning for Animal Classification.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 8, page no.f88-f91, August-2021, Available :http://www.jetir.org/papers/JETIR2108612.pdf

"Design and Development of Deep Learning for Animal Classification.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 8, page no. ppf88-f91, August-2021, Available at : http://www.jetir.org/papers/JETIR2108612.pdf