MultifunctionalDrone

MultiFunctional-Drone

Group Name: 1+e^πi=0

Project Description: We are going to explain our “MultiFunctional-Drone” with the explanation of the functions that we will make, includes area calculations, distance calculations, route calculations and face recognition. To provide these functions we are going to use calculus. We can use that drone for the military, medical aid, map drawing, and relocation. There are three main reasons why we had chosen this topic. The first reason for this project is our desire to turn technology into human benefit. The second reason is providing the usage of drone technology in wide fields. The last reason is that when we have seen videos about drones and we had been inspired. For these reasons, we want to start this project.

WEEKLY PLAN

Week I

Setting a topic
Task distribution
Why we chose it

Week II

Giving tasks to drone
Adding functions to drone

Week III

Giving more tasks to drone
Flowchart creating

Week IV

Editing the final report
Preparing the presentation

Outline

Why we have chose this problem.
Difficulties and Problems of Drone Project
What we did during 1st 2nd and 3rd weeks.
What we did the final week to complete Drone Project.

Week - 1

We defined what our problem is.
We explained description of our Drone Project.
We created the Weekly Plan.
We distributed everybody’s duties.

Week - 2

We defined which program we will use.
We found two different algorithms that are called Floyd and Dijkstra and two different programmes that are called YOLO and Bristol Multi-Object Detector.

YOLO

You only look once (YOLO) is a state-of-the-art, real-time object detection system.
Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.
This system use a totally different approach. We apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.
This model has several advantages over classifier-based systems.
It looks at the whole image at test time so its predictions are informed by global context in the image.
It also makes predictions with a single network evaluation unlike systems like R-CNN which require thousands for a single image.
This makes it extremely fast, more than 1000x faster than R-CNN and 100x faster than Fast RCNN.

Week - 3

In this week, we assigned the task to the drone we designed. The task is about sketching buildings and making the 3d drawing in the defined area. While performing these tasks, it used the methods and software of the last week.

The final product

Basis working principle of drone is that:

First, Drone is sent to the area to explore the highest building.
Finds the height of the highest building (h) and rounds it up and adds 10 meters. This is drone’s height (h(rounded) + 10 m)
Gets the edge lengths of the area to be scanned (a, b).
Defines number of frames a/(2h + 20) * b/(2h + 20).
Starting point is (h + 10, h + 10)
Every (2h + 20) meters, it marks a picture or video frame.
It keeps until the all frames completed. Then it returns to the center (0, 0)

For Example: In a field (210, 300) that the highest buildings' height is 15 meters, how will drone works?

First, it rounds 15 meters to 20 meters. Then adds 10 meters. This is drone's height (30 meter).
The number of frames is determined. 300/30 * 210/30 = 70
Starting point is (30, 30).
By using the pathfinding algorithms, it completes 210 meters by taking 1 photo (frame) per 60 meters. If there are decelerators like wind, it uses Djikstra's algorithm to finds most sensible route.
It works until the taking of all frames completed and when it ends it returns to center.

Calculation of volume by using the drone

Page updated

Google Sites

Report abuse