Location-Driven Image Retrieval for Images Collected by a Mobile Robot

Abstract

Mobile robot teleoperation is a method for a human user to interact with a mobile robot over time and distance. Successful teleoperation depends on how well images taken by the mobile robot are visualized to the user. To enhance the efficiency and flexibility of the visualization, an image retrieval system on such a robot's image database would be very useful. The main difference of the robot's image database from standard image databases is that various relevant images exist due to variety of viewing conditions. The main contribution of this paper is to propose an efficient retrieval approach, named location-driven approach, utilizing correlation between visual features and real world locations of images. Combining the location-driven approach with the conventional feature-driven approach, our goal can be viewed as finding an optimal classifier between relevant and irrelevant feature-location pairs. An active learning technique based on support vector machine is extended for this aim.

Learning Animal Concepts with Semantic Hierarchy-Based Location-Aware Image Browsing and Ecology Task Generator

“…For example, some mobile information systems that can captures the user's contextual information such as the location and time could help user specify their requirements and filter the relevant information for each user according to his/her changing needs in different contexts [7][8][9][10][11].…”

A Supervised Learning Approach to Robot Localization Using a Short-Range RFID Sensor

“…One of our main contribution is a proposal of a machine learning approach [36]- [38] to such a short-range application. This approach is based on a machine learning technique, Support Vector Machine (SVM) [40].…”