Description
1) [10 points] Read and summarize the main points of Explore video analytics in the cloud in a
paragraph or two.
2) [15 points] Test your Jetson embedded Linux and OpenCV installation by downloading the
example code and example images from the Explore video analytics in the cloud paper and
build the code in capture-transformer. If you have any errors with the build, double check
your Jetson Nano Getting Started, OpenCV installation for R-Pi3 or the JetPack 3.x install
for NVIDIA Jetson TK1, TX1, TX2 or generic install instructions for OpenCV Linux or
Windows. Run the Sobel transform (sobel) on Trees.jpg found in example images and
provide the image in your report. Read the OpenCV online tutorial for Sobel and provide
your best simple English description of how the Sobel tranform works and what it does.
3) [15 points] To better understand the concept of convolution and the application of a pixel
level transform, now download the sharpen-psf example code. Build it and run it and make
sure your read and understand it. Now, make modifications if needed to run sharpen on
Trees.jpg and use GIMP to save Trees as a PPM (Portable Pixmap) so the code can load the
image file (like the Cactus-120kpixel.ppm). Provide the sharpened Trees.ppm image in your
report and describe any code modifications you made (if needed). Why does the PSF (Point
Spread Function) provide edge sharpening? (You may want to refer to the Engineer’s DSP
Handbook, Chapter 24). Read the sharpen_grid.c code and run it and describe how it is
different from the simpler sharpen.c and why it might be a better implementation for realtime frame transformation.
4) [20 points] Build the code in faceDetect and run it on the lena.jpg image (the demo from
Laz’s installation test). Now run it on a download of my CU faculty picture and provide the
face detection image in your report. Read the OpenCV tutorial page on Haar Cascades for
face detection for OpenCV 3.x, or OpenCV 2.x and describe in your own words how this
works.
5) [20 points] Author your own simple OpenCV code to open a window with an image in it and
draw a 4 pixel width border around the image and a single pixel YELLOW cross-hairs down
the middle column of the image (as close to center as possible) and through the middle row
of the image (as close to center as possible). Provide you graphically annotated image in
your report with180x320 resolution (you may want to refer to the simple-cv example code to
help get you started). Note that the example code provides an example of the use of the Mat
object and an IplImage object along with a simple method to directly access the multichannel array associated with both the IplImage and the Mat.
[20 points] Overall, provide a well-documented professional report of your findings, output, and
tests so that it is easy for a colleague (or instructor) to understand what you’ve done. Include any
C/C++ source code you write (or modify) and Makefiles needed to build your code and make
sure your code is well commented, documented and follows coding style guidelines. I will look
at your report first, so it must be well written and clearly address each problem providing clear
and concise responses to receive credit.
In this class, you’ll be expected to consult the Linux and OpenCV manual pages and to do some
reading and research on your own, so practice this in this first lab and try to answer as many of
your own questions as possible, but do come to office hours and ask for help if you get stuck.
Upload all code and your report completed using MS Word or as a PDF to D2L and include all
source code (ideally example output should be integrated into the report directly, but if not,
clearly label in the report and by filename if test and example output is not pasted directly into
the report). Your code must include a Makefile so I can build your solution on an embedded
Linux system (R-Pi 3b+ or Jetson). Please zip or tar.gz your solution with your first and last
name embedded in the directory name and/or provide a GitHub public or private repository
link. Note that I may ask you or SA graders may ask you to walk-through and explain your
code. Any code that you present as your own that is “re-used” and not cited with the original
source is plagiarism. So, be sure to cite code you did not author and be sure you can explain it
in good detail if you do re-use, you must provide a proper citation and prove that you
understand the code you are using.
Grading Rubric
[10 points] Read and summarize the main points…
[2 pts] main point #1 ______________________________________________________
[2 pts] main point #2 ______________________________________________________
[2 pts] main point #3 ______________________________________________________
[4 pts] summary overall ____________________________________________________
[15 points] Test your VB-Linux and OpenCV installation…
[3 pts] example #1 ______________________________________________________
[3 pts] example #2 ______________________________________________________
[3 pts] example #3 ______________________________________________________
[6 pts] Sobel description __________________________________________________
[15 points] Work with example sharpen PSF code…
[3 pts] build, run, test ____________________________________________________
[3 pts] trees or similar ____________________________________________________
[4 pts] explanation of PSF ________________________________________________
[6 pts] sharpen_grid vs. sharpen ___________________________________________
[20 points] Build the code in faceDetect…
[5 pts] build, run, test ____________________________________________________
[5 pts] picture example ____________________________________________________
[10 pts] explanation of Haar ________________________________________________
[20 points] Author your own simple OpenCV code to open a window with an image in it…
[5 pts] build, run, test ____________________________________________________
[5 pts] 180×320 graphics __________________________________________________
[10 pts] cross hairs and annotation ___________________________________________
[20 points] Quality of reporting and code quality and originality:
[10 pts] Professional quality of reporting, testing and analysis (0…6 is below average, 7
is average, 8 is good, 9 excellent, and 10 is best
overall.)_________________________________________________________________
[10 pts] Code quality including style, commenting, originality, proper citation for re-used
code, modified code, etc.___________________________________________________