V.O.R.L.A.R.P.

From MCS Wiki
Jump to: navigation, search

Visual Object Recognition and Location by Autonomous Remote Platforms

The purpose of this project is to take on the development of a system that is capable of performing the series of tasks involved with visually recognizing an object and its characteristics. Then with that object as a template find it by searching a given operational area in which the object has been placed. Methodologies for accomplishing this project will involve the completion of four milestones that will encompass resource evaluation, modeling, and acquisition in the first steps, followed by hardware configuration and testing, next will be software research ,development and testing, and last a compiled, configured system test. In resource evaluation, modeling, and acquisition the goal will be to find key components that will compose the system. This mainly relates to hardware devices that will handle the capture and transmission of data from remote platform to processing station and the return of pertinent system guidance information. It will be attempted to find said class of hardware tools that can do this efficiently and at a general consumer level cost. Hardware configuration and testing will encompass the initialization, configuration, and training of tools that were found in the previous milestone. This will be to ensure consistent performance from the system and try to reduce risk in later stages of the project where delays could prove too cumbersome or costly and prevent further development. This milestone will also allow for information to be gathered that will be used in determining the best software approach to take in milestone three.Software research, development and testing takes information gleaned from other stages and with that information decides what the best approach will be in terms of language, libraries and computational methods (Eg. Algorithms) for processing the data in the system in the most efficient way possible given time constraints for development. Additionally the configuration of chosen packages will occur in this stage along with the testing of software produced before integration into the platform. End product for this stage is a piece of software capable of recognizing a given object and directing the remote platform in the search and acquisition of said object in a given area. Milestone four will be a full systems test in which the fully integrated components of the system will be tested to ensure functionality, accuracy, and reliability of the objective activities. Success in this final area will mark the completion of the project and its goals. If time allows further refinement may still take place even if success is reached.


MILESTONE TIME TABLE:

  • 1-2 Months; Research,Eval,Modeling
  • 2 Months: Hardware Config, Acquisition
  • 3-4 Months: Software Dev, Configuration, Research
  • 1-2 Months: System Integration,Testing
  • Total: 10 Months: Finished V.O.R.L.A.R.P.



COST ESTIMATION TABLE PER MILESTONE:

  • Research,Eval,Modeling: 0$
  • Hardware Config, Acquisition: 200-300$
  • Software Dev, Configuration, Research: 100$<
  • System Integration,Testing: 0$
  • Total: V.O.R.L.A.R.P.: 300-400$


POSSIBLE RESOURCES BY MILESTONE:

  • Research,Eval,Modeling: N/A
  • Hardware Config, Acquisition: Video transmission/receive units, Camera, Cabling, Adapters for video input
  • Software Dev, Configuration, Research: OpenCV,C,PYTHON,CPP,Generic Video Processing algorithms
  • System Integration,Testing: N/A

TOOLS

___OpenCV2.4.3 Install Script___

#!/usr/bin/env bash
echo "Start OpenCV 2.4.3 install with Python 2.7, and V4l support on ! Known to Run on Ubuntu 12.04 LTS and Mint 11."
apt-get install build-essential
apt-get install cmake 
apt-get install git
apt-get install pkg-config
apt-get install python-dev
apt-get install python-tk
apt-get install python-numpy
apt-get install ffmpeg
apt-get install libjpeg-dev
apt-get install libpng-dev
apt-get install libtiff-dev
apt-get install libjasper-dev
apt-get install libv4l-dev
apt-get install libavcodec-dev libavformat-dev libswscale-dev
apt-get install libgtk2.0-dev
apt-get install libtbb-dev
tar -xvf OpenCV-2.4.3.tar.bz2 
cd OpenCV-2.4.3/
mkdir release
cd release/
cmake -D WITH_V4L=ON -D BUILD_PYTHON_SUPPORT=ON -D WITH_TBB=ON -D WITH_GSTREAMER=ON CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local ..
make
make install
echo "Install Finished !"
#run with install permissions in folder containing OpenCV2.4.3
Personal tools