An efficient direct approach to visual SLAM

G Silveira, E Malis, P Rives - IEEE transactions on robotics, 2008 - ieeexplore.ieee.org
The majority of visual simultaneous localization and map** (SLAM) approaches consider
feature correspondences as an input to the joint process of estimating the camera pose and …

Efficient homography-based tracking and 3-D reconstruction for single-viewpoint sensors

C Mei, S Benhimane, E Malis… - IEEE Transactions on …, 2008 - ieeexplore.ieee.org
This paper addresses the problem of motion estimation and 3-D reconstruction through
visual tracking with a single-viewpoint sensor and, in particular, how to generalize tracking …

Real-time plane extraction from depth images with the randomized hough transform

D Dube, A Zell - 2011 IEEE International Conference on …, 2011 - ieeexplore.ieee.org
Depth cameras, like the Microsoft Kinect system, are valuable sensors for mobile robotics
since their data enables a highly detailed perception of the environmental structure …

[PDF][PDF] Unifying planar and point map** in monocular slam.

J Martínez-Carranza, A Calway - BMVC, 2010 - Citeseer
Map** planar structure in vision-based SLAM can increase robustness and significantly
improve efficiency of map representation. However, previous systems have implemented …

Structure extraction in urbanized aerial images from a single view using a CNN-based approach

JAJ Osuna-Coutiño… - International Journal of …, 2020 - Taylor & Francis
ABSTRACT High-Level Structure (HLS) extraction in aerial images consists of recognizing
Three-Dimensional (3D) elements on human-made surfaces (objects, buildings, ground …

An efficient direct method for improving visual SLAM

G Silveira, E Malis, P Rives - Proceedings 2007 IEEE …, 2007 - ieeexplore.ieee.org
Traditionally in monocular SLAM, interest features are extracted and matched in successive
images. Outliers are rejected a posteriori during a pose estimation process, and then the …

Fast detection of arbitrary planar surfaces from unreliable 3D data

M Heracles, B Bolder, C Goerick - 2009 IEEE/RSJ International …, 2009 - ieeexplore.ieee.org
Man-made real-world environments are dominated by planar surfaces many of which
constitute behavior-relevant entities. Thus, the ability to perceive planar surfaces is vital for …

Distributed multi-camera visual map** using topological maps of planar regions

E Montijano, C Sagues - Pattern Recognition, 2011 - Elsevier
This paper presents a multi-agent solution for cooperative visual map** using planar
regions. Each agent is assumed to be equipped with a conventional camera and has limited …

High level 3D structure extraction from a single image using a CNN-based approach

JAJ Osuna-Coutiño, J Martinez-Carranza - Sensors, 2019 - mdpi.com
High-Level Structure (HLS) extraction in a set of images consists of recognizing 3D elements
with useful information to the user or application. There are several approaches to HLS …

Accurate and fast extraction of planar surface patches from 3D point cloud

HH Nguyen, J Kim, Y Lee, N Ahmed… - Proceedings of the 7th …, 2013 - dl.acm.org
Planar surface patches, extracted for instance from a captured 3D point cloud, play an
important role as a feature in modeling and/or recognizing objects and environments. In …