Object Detection Mobile Application

This project is a component of another project in robotics. The project empowers robots ability to move through obstacles on their own using power of Computer Vision.

Introduction

Computers are constantly pushed to interpret and understand the content of images and videos. Object detection is a fundamental computer vision technique that tackles this challenge. It allows us to identify and locate objects within an image or video stream.

Object Detection Techniques used:

This project uses two models: YOLOV8 and MobileNet SSD, to detect obstacles along the robot path.

Project Implementation:

Data used

The models were trained on custom dataset.

Model training

The models were trained using Google Colab GPUs

Model Deployment

Both models were converted to TF lite files. TF Lite ensures compatibility and leverages mobile-optimized operations.

Tools used

Android Studio, for mobile application development

Roboflow, for data labelling

Google Colab, for model training