15 datasets found

The VPR-NuScenes dataset is a large-scale dataset for visual place recognition, consisting of 850 annotated scenes with 20s-long sequences of consecutive frames.

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame.

Combined dataset used for testing the proposed BNN for VPR.

Old City dataset used for testing the proposed BNN for VPR.

A dataset for mobile robotics place recognition, consisting of 3000 km journey across all four seasons.

Cross-Season sequence from RobotCar used for testing the proposed BNN for VPR.

Specific Places Dataset (SPED) used for testing the proposed BNN for VPR.

Visual Place Recognition (VPR) dataset used for testing the proposed binary neural network (BNN) for VPR.

Extended version of the TB-Places data set, containing images recorded in real gardens in different seasons, with varying light conditions.

The Oxford RobotCar Dataset is a collection of images and videos of a car driving on various roads and conditions.

A visual place recognition dataset for embodied agents.

A visual place recognition dataset for embodied agents.

A visual place recognition dataset for embodied agents.

Visual place recognition datasets for testing the proposed Patch-DrosoNet algorithm

The KAIST dataset is a collection of video sequences captured in the campus of Korea Advanced Institute of Science and Technology (KAIST). The dataset is used for visual place...