Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme

By Bernd Kitt, Andreas Geiger, Henning Lategahn. IEEE Intelligent Vehicles Symposium, 2010

475 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fee5c79243d99161f1128b3de322add6fe2b6987

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 sensor fusion approach for localization with cumulative error elimination (2012, methodology): “EXPERIMENTAL RESULTS AND DISCUSSION The vehicle platform is used from Karlsruhe dataset [9] which equipped with an OXTS RT 3000 GPS/IMU system (which provide the GPS data and the attitude of the vehicle, including the velocity and the rotation angle at each frame) with 10 frames/s.”
Learning Switching Models for Abnormality Detection for Autonomous Driving (2018, background): “State estimation is important for motion prediction [1], [2], tracking [3–5], identification”
AutoScaler: Scale-Attention Networks for Visual Correspondence (2016, background): “It is crucial for a plethora of applications, including optical ﬂow [54, 43, 36], structure-from-motion [1], visual SLAM [40, 27, 39], stereo matching [59, 34], non-rigid 3D reconstruction [14] as well as video segmentation [19].”
StereoScan: Dense 3d reconstruction in real-time (2011, methodology): “…35 40 GPS/IMU Kitt et al. 2010 our method x [meters] z [meters] (a) 2009 09 08 drive 0010 −120 −100 −80 −60 −40 −20 0 0 10 20 30 40 50 60 70 80 GPS/ IMU Kitt et al. 2010 our method x [meters] z [meters] (b) 2009 09 08 drive 0016 −20 −15 −10 −5 0 5 10 15 5 10 15 20 25 GPS/IMU Kitt et al. 2010 our…”
Augmented Reality meets Deep Learning (2017, background): “KITTI360 is unique compared to KITTI [14] or CityScapes [4] in that each frame comes with two 180◦ images taken by two fish-eye cameras on top of the recording platform.”
Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight (2017, methodology): “In addition, a circular matching similar to [33] is performed between the previous and current stereo image pairs to further remove outliers generated in the feature tracking and stereo matching steps.”
Nonparametric semantic segmentation for 3D street scenes (2013, methodology): “As camera pose estimation is not the primary focus of this work, we apply the modified stereo visual odometry system described in [21].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Kitt et al. (2010) for example use bucketing to obtain well distributed corner-like feature matches whereas Deigmoeller & Eggert (2016) use different heuristics on flow and depth estimation to reject non stable features.”
Evolution of Indoor Positioning Technologies: A Survey (2017, methodology): “[82], who used a sequence of stereo images and, with filtering techniques, were able to achieve good precision with less computational cost than competing methods.”