Rules
​
Basic Rules
​
​
-
can use existing code, but with attribution and without violating any licensing. Entries will be checked for plagiarism, or violations of intellectual property, and will be discarded accordingly.
-
can program in any language (because that will be transparent to the responder)
-
must submit their code integrated into a CVER GitHub branch and the code can run without internet access on Windows machine
-
In case of ties, priority is given to the youngest students.
​
Entries will be scored by a volunteer committee of at least three responders who have wilderness missing person experience and at least two computer vision experts. The committee will be identified by the Center for Robot-Assisted Search and Rescue. The scoring will be based on:
​
-
verification and validation: is it buggy? Does it do what it says it will do? (lives are at stake, so let’s get this code right!)
-
usability: easy for responders to quickly understand its value and how to use it effectively (they’re too busy to have to hunt for information about the program) and can provide any type of camera resolution, not just 4K (different UAS have cameras with different resolutions)
-
value to responders (for the Open category, we already know that they want the category 1 and 2 algorithms.)
-
documentation enabling other programmers to modify and extend (because we all want to see CVER grow!)
-
documentation for users on how to best use the algorithm (because the point is for them to be able to get the most out of the software with the least amount of effort!)
​
registration link is here
Prizes
​
IEEE RAS-SIGHT is providing $3,000 in prizes, with the levels of awards reflecting the expected difficulty. The judges will reserve the right not to make awards in the Open category if the entries are not of sufficient caliber to merit integration into the CVER toolkit.
​
-
$500 for the top 3 entries in Category 1 ($300, $150, $50)
-
$1,000 for the top 3 entries in Category 2 ($500; $300; $200)
-
$1,500 for the top 3 entries in Category 3 ($750; $500; $250)
All entrants whose programs pass the initial screening will receive a certificate and the results of their scoring and appreciation!
Category 1​
​
Basic Operations: In this category, coders provide the following three basic algorithms. These are straightforward, entry-level programming projects and a good introduction to computer vision.
-
image enhancement through histogram equalization, which can be applied to electro-optical (visible light cameras) and thermal imagery
-
color segmentation for a range
-
grayscale segmentation for a range in a thermal image
Category 2​
GIS operations: In this category, coders must provide a system that for each image in a set does the following. This requires more mathematical analysis and also helps the students connect computer vision to the camera payload and that different small UAS will have different cameras. It also introduces them to the USNG and that different groups use different geographical coordinate systems.​
-
if given FOV, altitude, and tilt, and overlays a USNG grid for a user-specified interval (e.g., every 100 meters)
-
give the GPS coordinates of each pixel if a cursor is rolled over the image
-
if given a set of images with the GPS or USNG coordinate and a bounding box, find all images that have a pixel intersecting that location (this would be used if a responder thought they saw something in an image but wanted to see other views to help confirm or disambiguate)
-
dataset link: https://www.dropbox.com/s/nd6fbo8qwm66908/Michael%20Dataset%20%28Missing%20Person%20Contest%29.xlsx?dl=0
Category 3​
Open: In this category, entrants can submit any algorithm they believe will be of value. For example, they may use the CRASAR imagery datasets (hrail.crasar.org) for wilderness search and rescue to train a machine learning algorithm. This allows more advanced students to be creative or implement algorithms from papers.
​
​
​