Gaussian Processes with Context-Supported Priors for Active Object Localization
This work addresses inefficiencies in object localization for computer vision, though it appears incremental as it builds on existing Bayesian optimization and contextual data methods.
The paper tackles the problem of inaccurate and inefficient object localization in still images by proposing an algorithm that uses contextual visual data and Bayesian optimization, resulting in substantial improvement over a state-of-the-art baseline method for pedestrian localization.
We devise an algorithm using a Bayesian optimization framework in conjunction with contextual visual data for the efficient localization of objects in still images. Recent research has demonstrated substantial progress in object localization and related tasks for computer vision. However, many current state-of-the-art object localization procedures still suffer from inaccuracy and inefficiency, in addition to failing to provide a principled and interpretable system amenable to high-level vision tasks. We address these issues with the current research. Our method encompasses an active search procedure that uses contextual data to generate initial bounding-box proposals for a target object. We train a convolutional neural network to approximate an offset distance from the target object. Next, we use a Gaussian Process to model this offset response signal over the search space of the target. We then employ a Bayesian active search for accurate localization of the target. In experiments, we compare our approach to a state-of-theart bounding-box regression method for a challenging pedestrian localization task. Our method exhibits a substantial improvement over this baseline regression method.