# ObjectTracker

**Repository Path**: xll_98/ObjectTracker

## Basic Information

- **Project Name**: ObjectTracker
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-09-07
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ObjectTracker
A real-time object tracking application using edge detection per frame built using OpenACC

Installation of opencv dependency

# Install OpenCV

Sadly, C++ does not come with a nativa package manager, and we are not versed in any of the tools of the industry, so we decided to do a clean install of OpenCV.

## Linux
Relevant steps from the instructions [here](https://docs.opencv.org/master/d7/d9f/tutorial_linux_install.html)

1. Download source for opencv-4.3.0 from the [download page](https://opencv.org/releases/)
2. Run the following commands in the terminal

```
    ## build and install openCV
    $ cd ~/opencv
    $ mkdir build
    $ cd build
    $ cmake -D CMAKE_BUILD_TYPE=Release -D -DOPENCV_GENERATE_PKGCONFIG=ON CMAKE_INSTALL_PREFIX=/usr/local ..
    $ make -j7
    $ sudo make install
    
    
    ## check your installation by running
    $ pkg-config --cflags --libs opencv4
    
    ## it should print something like this:
    # -I/usr/local/include/opencv4/opencv -I/usr/local/include/opencv4 
    # -L/usr/local/lib -lopencv_dnn -lopencv_gapi -lopencv_highgui -lopencv_ml 
    # -lopencv_objdetect -lopencv_photo -lopencv_stitching -lopencv_video 
    # -lopencv_calib3d -lopencv_features2d -lopencv_flann -lopencv_videoio 
    # -lopencv_imgcodecs -lopencv_imgproc -lopencv_core
    
    
    ## to load the installed shared object libraries
    $ sudo ldconfig -v

```

3. Run your serial code as

```
    $ g++ -o main main.cpp `pkg-config --cflags --libs opencv4`
    $ ./main

```

4. Run your mpi code as

```
    $ mpic++ -std=c++11 `pkg-config --cflags --libs opencv4` -o mpi_main mpi_main.cpp
    $ ./mpi_main

```


    
## Analysis
1. The serial code by default uses 1/8 available thread on Ubuntu Linux
2. Canny out_Video does not run on Ubuntu?


## Other references

Please follow the below link,

1. for mac: https://medium.com/@jaskaranvirdi/setting-up-opencv-and-c-development-environment-in-xcode-b6027728003
2. for ubuntu: http://www.codebind.com/cpp-tutorial/install-opencv-ubuntu-cpp/
3. for windows: https://www.deciphertechnic.com/install-opencv-with-visual-studio/ 	[Needs to be tested]