Query-based occupancy map for SVM-CBIR on mobile robot image database

Hirayama, M.; Kondo, Fumiya

doi:10.1109/iros.2005.1545430

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another line of our studies is focused on the use of such accurate viewpoint information for the robot's image retrieval problem. One of recent progress in the research is presented in another paper (4) . Compared with these studies, it can be said that the location uncertainty is quite large in this experiment.…”

Section: Methodsmentioning

confidence: 99%

“…Very few systems could visualize a large set of history images, which are common in real world applications and inherent in large-scale environments. To visualize such a large set of images, it would be very useful to have a function of image retrieval, and with this motivation, we have been developing a sensor image retrieval system (4) . Our image retrieval system aims at retrieving the target images (relevant images) that the user is interested in through a sequence of interactions with the user, while minimizing the number of interactions so as to reduce the load of the user.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Hirayama

Okada

Kondo

2006

JSME Int. J., Ser. C

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%