Seeing Unseeability to See the Unseeable
This addresses the challenge of perceiving hidden objects in robotics or vision systems, presenting an incremental extension to existing occlusion reasoning methods.
The paper tackles the problem of inferring occluded parts of a structure from visible image evidence by jointly estimating occlusions and hidden portions using a maximum-likelihood framework, and extends this to assess confidence and plan robotic actions for optimal observation.
We present a framework that allows an observer to determine occluded portions of a structure by finding the maximum-likelihood estimate of those occluded portions consistent with visible image evidence and a consistency model. Doing this requires determining which portions of the structure are occluded in the first place. Since each process relies on the other, we determine a solution to both problems in tandem. We extend our framework to determine confidence of one's assessment of which portions of an observed structure are occluded, and the estimate of that occluded structure, by determining the sensitivity of one's assessment to potential new observations. We further extend our framework to determine a robotic action whose execution would allow a new observation that would maximally increase one's confidence.