Optical-Based Scene Detection and Audio Extraction

In analyzing a scene, a projection device may project an image onto surfaces or objects within the scene. The image may include user interface elements as well as structured light patterns for analyzing shapes of the surfaces and objects. The intensity of the reflection of the projected light may be monitored and used to derive an audio signal representing sound that occurs within the scene. The audio signal may be analyzed to detect and recognize user utterances and speech, which may be interpreted as commands.