GPU-accelerated Hierarchical Panoramic Image Feature Retrieval for Indoor Localization
This work addresses indoor localization for applications like LBS and robotic navigation, presenting an incremental improvement through GPU acceleration and multi-image strategies.
The paper tackles indoor localization by formulating it as a multimedia retrieval problem using panoramic image features and a GPU-accelerated parallel algorithm, achieving real-time responses at 14fps with robust localization in experiments on campus building data.
Indoor localization has many applications, such as commercial Location Based Services (LBS), robotic navigation, and assistive navigation for the blind. This paper formulates the indoor localization problem into a multimedia retrieving problem by modeling visual landmarks with a panoramic image feature, and calculating a user's location via GPU- accelerated parallel retrieving algorithm. To solve the scene similarity problem, we apply a multi-images based retrieval strategy and a 2D aggregation method to estimate the final retrieval location. Experiments on a campus building real data demonstrate real-time responses (14fps) and robust localization.