Active perception

TLDR

Active perception studies modeling and control strategies for perception, distinguishing local methods that focus on optical distortions and spatial resolution from global models that predict overall performance and module interactions. The authors formulate control strategies as a search over step sequences that minimize a loss function while maximizing information gain. They demonstrate the theory by obtaining range from focus and stereo/vergence for 2‑D image segmentation and 3‑D shape parameterization. No additional metadata provided.

Abstract

Active perception (active vision specifically) is defined as a study of modeling and control strategies for perception. Local methods are distinguished from global models by their extent of application in space and time. The local models represent procedures and parameters such as optical distortions of the lens, focal lens, spatial resolution, bandpass filter, etc, The global models, on the other hand, characterize the overall performance and make predictions on how the individual modules interact. The control strategies are formulated as a search of such sequences of steps that would minimize a loss function while still seeking the most information. Examples are shown as the existence proof of the proposed theory on obtaining range from focus and stereo/vergence on 2-D segmentation of an image and 3-D shape parameterization. >