Large-Scale Visual Odometry for Rough Terrain

By Kurt Konolige, Motilal Agrawal, Joan Solà. International Symposium of Robotics Research, 2007

446 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4db999f7e3f9f7152f45ae1c56664bfba7136d54

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A benchmark for the evaluation of RGB-D SLAM systems (2012, background): “All sequences and movies are available on our website [1].”
Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization (2013, methodology): “[10], the IMU measurements are incorporated as independent inclinometer and relative yaw measurements into the stereo vision optimization.”
High-precision, consistent EKF-based visual-inertial odometry (2013, methodology): “Alternatively, IMU measurements can be processed separately for extracting rotation estimates, and fused in an image-based estimation algorithm (Oskiper et al., 2007; Konolige et al., 2011; Brockers et al., 2012).”
Visual-inertial navigation, mapping and localization: A scalable real-time causal approach (2011, background): “(2006) and Lazebnik et al. (2006). However, this assumes that the ordinate axis of the image is the reference orientation, which is a safe assumption for human-captured images uploaded from the web, but it is definitely not wise for robot-captured images, especially for unmanned aerial vehicles (UAV”
Incremental smoothing and mapping (2008, unknown): “While accuracy of the presented system can further be improved by applying fixedlag smoothing [111], by using key frames to prevent drift [89], and by using landmarks to provide longer range constraints [138], in our case visual SLAM takes care of the long range consistency.”
Evaluating Egomotion and Structure-from-Motion Approaches Using the TUM RGB-D Benchmark (2012, background): “It can either be used to evaluate the drift of a visual odometry system [43], [44] or the accuracy at loop closures of SLAM systems [45], [46] which is especially useful if only sparse, relative relations are available as ground truth.”
LOAM: Lidar Odometry and Mapping in Real-time (2014, methodology): “Another set of methods use odometry measurements such as from wheel encoders or visual odometry systems [4], [5] to register the laser points.”
Quadrotors and Accelerometers: State Estimation with an Improved Dynamic Model (2014, background): “Many researchers, for example [27]–[29], have shown that using one of these methods to fuse accelerometers with an exteroceptive sensor increases performance compared to using the exteroceptive sensor alone.”
Keyframe-based visual–inertial odometry using nonlinear optimization (2015, methodology): “Konolige et al. (2011) integrate IMU measurements as independent inclinometer and relative yaw measurements into an optimization problem using stereo vision measurements.”
FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping (2008, methodology): “The visual odometry backbone that underlies frameSLAM is capable of errors of less than 1% over many hundreds of meters [23], which has not yet been matched by global feature-based systems.”
Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera (2011, methodology): “we compare this approach to RANSAC-based methods [28, 22].”