Problem D
Chicken Jockey
Languages
en
sv
As a child, Barvid yearned for the mines. For someone as experienced as Barvid, the monsters are no match for him. However, there is still one type of monster he fears: the Chicken Jockeys. In order to avoid Chicken Jockeys, Barvid has decided to map out the location of all the Chicken Jockeys. To do this, he has convinced the chickens to send images from their point of view to you. From these images, you are tasked with determining the location of the Chicken Jockeys. To help you in this task, Barvid has also provided you with a bunch of images he has taken of the beautiful environment. For these images, Barvid knows exactly where they were taken.
![\includegraphics[width=0.7\textwidth ]{qr.png}](/problems/chickenjockey/file/statement/en/img-0001.png)
Input
Download the file with test and training data. This can be found at the bottom of this page, under "attachments". In this zip file, you will find all the images in folders with different resolutions. Along with the images, you will find a file called "train.csv" and one called "test.csv". In these files, each row contains three comma separated integers: an id, yaw (the rotation from left to right), and pitch (the rotation up and down). The train CSV will also contain two additional comma separated integers: the x- and z-coordinates of the image ($0 \leq x, z \leq 2500$).
Output
You should print the coordinates in the order they are given in the test.csv file. For each testcase you should print the two coordinate on their own line, $x$ first, then $z$.
Scoring
Your solution will be evaluated based on how well it predicts the location of the Chicken Jockeys.
Your final points are calculated as
following:
Where $avg\_ dist$ is the average euclidean distance between the predicted and the correct coordinates of the Chicken Jockeys.
At the end of the competition, all solutions will be retested on the remaining 70% of the data. Your final score at the end of the competition will only be based on the remaining 70% of the data; the 30% tested during the competition will have no effect. It is guaranteed that the 30% tested during the competition were chosen uniformly at random and are entirely disjoint from the 70% tested at the end. Therefore, the results on the 30% tested during the competition should be seen as a strong indicator of how well your solution performs. At the same time, it is detrimental to overfit your solution to the test data.
