presented by hugo groening

12
ECE 172A ECE 172A SIMPLE OBJECT DETECTOR WITH SIMPLE OBJECT DETECTOR WITH INDICATOR WHEN A NEW OBJECT HAS INDICATOR WHEN A NEW OBJECT HAS BEEN ADDED TO OR MISSING IN A ROOM BEEN ADDED TO OR MISSING IN A ROOM Presented Presented by by Hugo Groening Hugo Groening

Upload: elias

Post on 06-Jan-2016

21 views

Category:

Documents


0 download

DESCRIPTION

ECE 172A SIMPLE OBJECT DETECTOR WITH INDICATOR WHEN A NEW OBJECT HAS BEEN ADDED TO OR MISSING IN A ROOM. Presented by Hugo Groening. INTRODUCTION. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Presented  by  Hugo Groening

ECE 172AECE 172A

SIMPLE OBJECT DETECTOR WITH SIMPLE OBJECT DETECTOR WITH INDICATOR WHEN A NEW OBJECT HAS INDICATOR WHEN A NEW OBJECT HAS

BEEN ADDED TO OR MISSING IN A BEEN ADDED TO OR MISSING IN A ROOMROOM

PresentedPresented

by by

Hugo GroeningHugo Groening

Page 2: Presented  by  Hugo Groening

INTRODUCTIONINTRODUCTION

In the security industry, there has always been the In the security industry, there has always been the demand for simple, accurate and economical systems demand for simple, accurate and economical systems that allow the prevention or ability to track through that allow the prevention or ability to track through footage when a security breach has occurred. The footage when a security breach has occurred. The project to be presented targets locations such as project to be presented targets locations such as museums, stores, homes, Banks, etc. museums, stores, homes, Banks, etc.

Page 3: Presented  by  Hugo Groening

AGENDAAGENDA

Objective Objective

Related Research Related Research

MethodMethod

ResultsResults

Future work or improvementsFuture work or improvements

ConclusionConclusion

Page 4: Presented  by  Hugo Groening

ObjectiveObjective

- To create an object recognition and detector in a room To create an object recognition and detector in a room using AVI files.using AVI files.

- To train detector to indicate when an object is missing or To train detector to indicate when an object is missing or possibly about to be taken.possibly about to be taken.

Page 5: Presented  by  Hugo Groening

Related Work and ResearchRelated Work and Research

References:

- A. Torralba, K. P. Murphy and W. T. Freeman. (2004). "Sharing features: efficient boosting procedures for multiclass object detection". Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). pp 762- 769

- B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman. Labelme: a database and web-

based tool for image annotation. Technical Report AIM-2005-025, MIT AI Lab Memo, September, 2005.

Can be found at: http://people.csail.mit.edu/brussell/research/AIM-2005-025-new.pdf Location of Code and Database: http://people.csail.mit.edu/torralba/shortCourseRLOC/boosting/boosting.html

IndustryIndustry

- Geovision: - Geovision: http://www.geovision.com.tw/demo/vid/demo4.htmhttp://www.geovision.com.tw/demo/vid/demo4.htm

Page 6: Presented  by  Hugo Groening

GoalGoal

Edited from Edited from http://www.geovision.com.tw/demo/vid/demo4.htm, Geovision Inc. , Geovision Inc.

Page 7: Presented  by  Hugo Groening

MethodMethod

Detect if object count changes from previous frameDetect if object count changes from previous frame

Nothing change, keeps countingNothing change, keeps counting

Choose Video to be Choose Video to be

analyzedanalyzed

Look at 1Look at 1stst frame to find size frame to find size

Initialize Video outputInitialize Video output

loops into framesloops into frames

and makes copy of current and makes copy of current frameframe

Count Objects in frameCount Objects in frame

Find centroid of objects and Find centroid of objects and

tracks themtracks them

Change to Grey and invert to BWChange to Grey and invert to BW

Erodes, dilatesErodes, dilates

If differentIf different

WARNINGWARNING

Page 8: Presented  by  Hugo Groening

ResultsResults-Count ObjectsCount Objects-Find ObjectsFind Objects-Warns when object count changesWarns when object count changes-Storages Video Output for Future analysisStorages Video Output for Future analysis

Page 9: Presented  by  Hugo Groening

LimitationsLimitations

- Hard drive Space for memory allocation of DatabaseHard drive Space for memory allocation of Database- ProcessorProcessor- AVI files taken from other video cameras AVI files taken from other video cameras - Objects and background colorObjects and background color- Time frameTime frame

Page 10: Presented  by  Hugo Groening

Output Footage Output Footage

Page 11: Presented  by  Hugo Groening

Future Work or ImprovementsFuture Work or Improvements

- Minimize the memory size of DatabaseMinimize the memory size of Database- Funding for continuation of Labelme DatabaseFunding for continuation of Labelme Database- Access to individual Objects within DatabaseAccess to individual Objects within Database- Research other Algorithm options for Object detection and Research other Algorithm options for Object detection and

ClassificationClassification- Find more adequate video Recorder for surveillance Find more adequate video Recorder for surveillance

purposespurposes- Live Object tracking detectorLive Object tracking detector- To become more knowledgeable with Matlab and other To become more knowledgeable with Matlab and other

Programming languages.Programming languages.

Page 12: Presented  by  Hugo Groening

ConclusionConclusion

The background and knowledge obtained through the practice The background and knowledge obtained through the practice of the information previously researched, had developed a of the information previously researched, had developed a strong awareness of how digital image processing can be strong awareness of how digital image processing can be directly applied to needs in society. In even the most simple directly applied to needs in society. In even the most simple cases, such as in the security or surveillance industry, high cases, such as in the security or surveillance industry, high end technology will be needed for accuracy. Continuous end technology will be needed for accuracy. Continuous development and improvements will also be necessary.development and improvements will also be necessary.