Viewpoint Adaptation for Rigid Object Detection
This work addresses the problem of viewpoint mismatch in object detection for applications like surveillance, though it is incremental as it builds on existing single-view detectors.
The paper tackles the problem of object detectors performing poorly when applied to images from viewpoints different from training by presenting a viewpoint adaptation algorithm that transforms feature spaces based on known homographies. It shows substantial performance improvements in person detection tasks, reducing computational complexity.
An object detector performs suboptimally when applied to image data taken from a viewpoint different from the one with which it was trained. In this paper, we present a viewpoint adaptation algorithm that allows a trained single-view object detector to be adapted to a new, distinct viewpoint. We first illustrate how a feature space transformation can be inferred from a known homography between the source and target viewpoints. Second, we show that a variety of trained classifiers can be modified to behave as if that transformation were applied to each testing instance. The proposed algorithm is evaluated on a person detection task using images from the PETS 2007 and CAVIAR datasets, as well as from a new synthetic multi-view person detection dataset. It yields substantial performance improvements when adapting single-view person detectors to new viewpoints, and simultaneously reduces computational complexity. This work has the potential to improve detection performance for cameras viewing objects from arbitrary viewpoints, while simplifying data collection and feature extraction.