Pixie-fruit

Main objective of the application was to run object detection models on mobile CPU and GPUs for offline inference in agriculture farms where internet is not available. This Application will deal in counting the fruits using two different methods of contour detection on low end devices and yolov5 on high end devices (method is chosen automatically by the application based on device as farmers are not good users of phone) on a tree and based upon sample it will estimate the total yield of the garden using DNN based regression with L2 regularization.

Project Poster

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

What things you need to install the software and how to install them

Android Studio
Gradle
Opencv-Java SDK

##Preview