Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC
By Davide Scaramuzza, Friedrich Fraundorfer, Roland Yves Siegwart. IEEE International Conference on Robotics and Automation, 2009
341 citations recorded by the source corpus.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology
View Paper: https://www.semanticscholar.org/paper/d23d13442f066e4a45193f2facef786769692998
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
- Davide Scaramuzza
- Fatma Güney
- Andrew Markham
- Andreas Geiger
- Agostino Martinelli
- Joel Janai
- Aseem Behl
- Muhamad Risqi U. Saputra
In Computer Vision and Pattern Recognition
- Andreas Geiger
- Fatma Güney
- Joel Janai
- Aseem Behl
- Davide Scaramuzza
- Andrew Markham
- Agostino Martinelli
- Niki Trigoni
In Geology
- Agostino Martinelli
- Andreas Geiger
- Andrew Markham
- Muhamad Risqi U. Saputra
- Niki Trigoni
- Bernd Kitt
- Henning Lategahn
- Friedrich Fraundorfer
Citations in the corpus
- Vision and IMU Data Fusion: Closed-Form Solutions for Attitude, Speed, Absolute Scale, and Bias Determination (2012, methodology): “This allows us to design very efficient and robust computation methods, such as one-point RANdom Sample Consensus [27], [28], to prune false matches and outliers.”
- Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, background): “A performance evaluation of feature detectors and descriptors for indoor VO has been given in [18] and for outdoor environments in [9] and [19].”
- Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “Scaramuzza et al. (2009) estimate the essential matrix from monocular images with only one 2D feature correspondence using non-holonomic constraints of wheeled vehicles imposing a restrictive motion model.”
- Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme (2010, methodology): “Given a 3-dimensional point T in the camera coordinate frame is computed via: Combining equations (1) and (2) the mapping of a 3d object point onto the image plane is described as e where P = K · R | t is a 3 × 4 projection matrix [11].”
- Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “This has been extended in [133] by enforcing ego-motion constraints such that the camera motion and the moving object motions can be computed by using the one-point algorithm [136, 137] and the two-point algorithm [119], respectively.”