Task for AI/ML contest. Recognize image coordintates. Constructor.
We are a team of company "Constructor" and we develop cutting edge cartographic systems. Recently the amount of image data skyrocketed so we want to give our users the ability to tie images to places automatically. For that, we want to use AI/ML technologies and we have a cool task for you.
There are three collections of datasets and in each you have:
Image from the original camera with no position information and set of images made from different points of view near this original camera with position information (list_files_info.json)
There are two tasks: 1) Find and get the ID of the most similar image from the set of images to the original image; 2) analyze the set of images and their position information and find the position information for the original camera (answer you can check in original_coordinates_for_check.txt)
Position information in JSON:
"coordX": 37.663572323286128, //longitude "coordY": 55.759883629330989, //latitude "pitch": 2, //coefficient of the camera up and down tilt "heading": 9, //coefficient of the camera rotation around "hight": 2, //coefficient of the camera position "id": 55 //camera image id
If you have any questions, please contact me: