Drones-IoT-Visual-Recognition

Visual Recognition of Drone Imagery Hands on Lab

Introduction

This hands on lab uses drone aerial images, Watson Studio and Watson Visual Recognition to survey neighborhoods and countrysides. Example datasets for Flooding, WildFires and Scottish landscapes are provided. The IBM Developer Tutorial uses the Wildfire training set. Call for Code developers might be interested in the Flooding training set.

Learning objectives

After completing this tutorial you will be able to:

• Create a Visual Recognition model in Watson Studio running in IBM Cloud
• Capture images from a drone and zip them into a class (provided)
• Train a model to identify objects in the images
• Score and identified objects

Prerequisites

This tutorial can be completed using an IBM Cloud Lite account.

• Create an IBM Cloud account
• Log into IBM Cloud

Estimated time

You can complete this task in no more than 45 minutes.

Hands on Lab Overview

The instructions in this Hands on Lab can be used in many scenarios. Drone imagery can be used to identify homes, buildings, neighborhoods, landscape, agricultural farms, and industrial sites.

Several examples of these drone image instructions are included :

• Flooding - Survey flooded neighborhoods, detect survivors on rooftops and identify rescue boats.
• Wild Fires - Survey wildfire damaged neighborhoods and identify burned homes and intact homes.
• Scotland - Survey Scottish countryside and identify Castles and traditional earthen / grass covered Black Houses.

Quick links : Home - Flooding - Wild Fires - Scotland