Neckerworld is an open source software product hosted on Github. The main project repo can be found at the Launch URL. Clone the code and follow the directions for installation. For the Backdrop Build a major new section of the repo was added: custom object-identification neural net training, found at https://github.com/hankster/Neckerworld/tree/main/train which was missing. Not only does this improve the completeness of the repo (in terms of its overall educational impact) but the new PyTorch inference model has proven vary effective and increased the level and performance of game play.
About
Neckerworld is a computer vision game designed to teach students about human and computer vision systems, object detection and identification, visual field construction, autonomous movement and strategy. All players and resources in the game are cubes. The cube players are guided solely through autonomous computer vision programs. No human manual control or input is permitted during gameplay. To successfully play the game requires a competent program to do object detection and identification, playing field knowledge representation and strategic decision making. The Neckerworld consists of a playing field server and one or more remote client players. The server places predators and food resources on the field and controls their activity and movement. The client player programs exchange messages (JSON files) with the server.
