Detection of Partially Visible Objects
This addresses a common limitation in object detection for computer vision applications, offering incremental improvements in scene interpretation.
The paper tackles the problem of object detection for partially visible objects due to occlusion or truncation, proposing a method that models partial visibility as a latent variable and reports improved average precision on the PASCAL VOC 2010 dataset.
An "elephant in the room" for most current object detection and localization methods is the lack of explicit modelling of partial visibility due to occlusion by other objects or truncation by the image boundary. Based on a sliding window approach, we propose a detection method which explicitly models partial visibility by treating it as a latent variable. A novel non-maximum suppression scheme is proposed which takes into account the inferred partial visibility of objects while providing a globally optimal solution. The method gives more detailed scene interpretations than conventional detectors in that we are able to identify the visible parts of an object. We report improved average precision on the PASCAL VOC 2010 dataset compared to a baseline detector.