This paper describes a game where players make gestures to cast spells against opponents with a dueling wizards theme. Different gestures can be combined in series to make different sorts of spells. They use the Wii controller and feed its accelerometer data into an HMM gesture recognition package. They had 7 users perform each gesture over 40 times, and they found that having 10 states for a gesture in the HMM gave over 90% accuracy. After 20 training gestures from one user, recognition is over 95% (or 80% for 10 gestures). Recognition without user-dependent training data was found to be around 50%. Evaluating gestures in their system works at near real-time for 250 gestures, but training HMMs takes more time.
Discussion:
This sounds like it would be an interesting game to try, though I don't know how well you could convince all players to input a lot of training data so as to get remotely palatable recognition rates. It could work for a single-player game, if the design of the training session was sufficiently clever and fun, but as the focus is on being a multiplayer game, you don't want to make players who have played before wait for an hour while the new player goes through tons of sample gestures. It might be worth trying to have important features of a given gesture that can be communicated to the user, e.g. the most important features of this spiral gesture are that it is circular, on a plane, and never crosses itself, and since the user is playing a game, they might be okay with learning these things. Then recognition could be based in significant part on these purposely chosen features as well.
Subscribe to:
Post Comments (Atom)
3 comments:
yeah, I would think a simple feature-based classifier could give good results, especially since all of the gestures are really 2-D gestures. I bet using a simple Rubine classifier would work just fine with their gesture set.
True, the training procedure for this game could be disguised for the single-player. Perhaps the training process could be masked as some sort of tutorial stage. Your comments also hit the point in being problematic for multi-player. Even if they decide to use the training data that was used for building their application, their paper had really low recognition rates for this sort of thing. And like Brandon said, the SR algorithms would be fine for the types of gestures discussed in this paper. I say we create a Wiizards 2 game. :D
You /might/, as Paul points out, be able to hide the training of the system as a "training of the user" phase. Let's teach you how to make all the spells and put them together, etc.
And lol, you said palatable. People aren't going to be eating their Wii, silly. ;P
Post a Comment