PRE2017 4 Groep3

Group members

• Stijn Beukers
• Marijn v.d. Horst
• Rowin Versteeg
• Pieter Voors
• Tom v.d. Velden

AP

Pieter

• Do research into the Users of the project

Marijn

• Do research into Tensorlow image recognition

Tom

• Do research into Environment mapping

Stijn

• Do research into voice recognition
• Fix wiki

Rowin

• Do research into privacy matter

next deadline: 26-4-2018

Brainstorm

We have discussed several ideas that we may want to implement.

• An AI and GUI for a board game, in which you can play with different AIs and maybe integrate a multiplayer environment the GUI could also give tips to the users.
• A filter for notifications on your smartphone to not get distracted by non-urgent notifications while still being available for urgent notifications.
• A simple way to connect multiple interfaces like doorbells, music, notifications or your alarm to the lights in your house.
• An artificial intelligence that automatically switches between camera angles in live broadcasts.
• A program that stitches together recorded videos like vlogs automatically.
• A program that makes music compilations where music flows together naturally the way DJs mix together music as if it is one big song rather than fading in one song and starting the next.
• A system of cameras in homes for blind people that keeps track of where they have left certain items such that they can ask the system where they left it when they lose an object.
• A model of a robot which learns to walk/pick up objects using machine learning.
• A system that sorts music based on its genre.

---

Can be removed?

The main subject that group 3 wishes to focus on is artificial intelligence (AI). There is a myriad of applications for AI and we would like to explore some of these applications. One such an application is to create a walking robot. This would provide the group with experiencing in the field of AI and could provide a good basis to create further more advanced AI. Another idea was to create a robot that could pick up an object which could then be further evolved into a robot to pick up the elderly. A simpler use of AI is to sort music on genre based on the files it gets.

Chosen Subject

Group 3 has chosen to do research in the field of image recognition with the purpose being to have cameras that can search for objects within a room/house. Using voice recognition a user can ask the system the location of a certain object, the system can than return the location of the object that was being searched for via a speaker. This would be of great help to elderly people or people with a mental handicap that frequently forget where they have left their belongings.

Goals

The goals of group 3 are as follows:

• Do research into the state of the art of AI picture recognition
• Decide on algorithm to choose
• To build an AI that can effectively classify certain objects based on pictures
• Expand AI capabilities by having it classify objects correctly within video footage
• Have the AI classify objects within live camera footage
• Have the AI Classify an object on command
• Find and interview relevant users

Interviews

Possible interview questions:

• Do you often lose items in your house?
• Would you be willing to install this system in your home, if it would it be free of charge?
• If answer yes: How much would you be willing to pay for it? (if it works correctly)
• If answer is no because privacy: Ask again when you say that people get blurred on camera, or that it is not connected to the internet, or that it is like a security camera.
• ...
• ...

Week 1

In week 1 the group mainly concerned itself with identifying a problem to work on and finding ways to create a solution for the aforementioned problem. The problem the group wished to tackle was one concerning AI to improve some daily life activities that may be hard for some people due to some deficiencies. The group eventually settled for creating an AI that could differentiate objects from live video footage as to find an object that is lost by the user. The groups means to achieve this goal is to apply tensor flow as to properly classify images of objects. This will than be expanded upon by having this same AI classify objects in live camera footage.

Sources

Privacy:

• http://journals.sagepub.com/doi/abs/10.1177/154193120605000203 (Benefits and Privacy Concerns of a Home Equipped with a Visual Sensing System: A Perspective from Older Adults) (Smart homes, privacy and elderly)
• http://journals.sagepub.com/doi/abs/10.1177/154193120404800209 (Potential Intrusiveness of Aware Home Technology: Perceptions of Older Adults) (Smart homes and elderly)
• https://ieeexplore.ieee.org/abstract/document/6032273/ (Medical Technology in Smart Homes: Exploring the User's Perspective on Privacy, Intimacy and Trust) (Smart homes and privacy)
• http://heinonline.org/HOL/LandingPage?handle=hein.journals/valur31&div=50&id=&page= (Scowl Because You're on Candid Camera: Privacy and Video Surveillance) (Privacy and cameras)
• http://heinonline.org/HOL/LandingPage?handle=hein.journals/uhawlr27&div=17&id=&page= (Don't Smile, Your Image Has Just Been Recorded on a Camera-Phone: The Need for Privacy in the Public Sphere) (Privacy and cameras)
• https://pdfs.semanticscholar.org/87fe/3f64cff36969acbe52fce091c0c3bf8d47ce.pdf (Blinkering Surveillance: Enabling Video Privacy through Computer Vision) (Hiding identidy on cameras!)