Visual odometry

By David Nistér, Oleg Naroditsky, J. Bergen. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

2,064 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/59640289df0a0262bc3a71fb24cd37d62e7d17e5

How researchers see this paper

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

Citations in the corpus

Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, background): “and a description of the main motion-estimation pipelines for both monocular and binocular schemes, outlining the pros and cons of each implementation [87].”
Toward Reliable Off Road Autonomous Vehicles Operating in Challenging Environments (2006, methodology): “The visual odometry solution implemented here (Nistér, Naroditsky, and Bergen 2004), is closely related to the problem and the solution originally posed as structure from motion (Huang 1994).”
Real-time monocular SLAM: Why filter? (2010, methodology): “[6], [8]) which fuse measurements from all images sequentially by updating probability distributions over features and camera pose parameters; and bundle adjustment style optimisation over selected images from the live stream, such as a sliding window [18], [20], or in particular spatially distribut”
Visual SLAM algorithms: a survey from 2010 to 2016 (2017, background): “Camera based odometry called Visual Odometry (VO) is also one of the active research fields in the literature [16, 17].”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “A detailed tutorial to this topic was presented by Scaramuzza & Fraundorfer (2011) and Fraundorfer & Scaramuzza (2011).”
Visual Odometry and Mapping for Autonomous Flight Using an RGB-D Camera (2011, methodology): “we compare this approach to RANSAC-based methods [28, 22].”
Detailed Real-Time Urban 3D Reconstruction from Video (2007, methodology): “Our system provides two estimation methods for the camera: one based purely on visual inputs (Nistér 2004; Nistér et al. 2006) and an extended Kalman filter based approach that fuses visual data with GPS/INS data, if they are available. The former method can only provide the camera poses up to scale”
ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (2020, methodology): “One example is when the point cloud is computed through visual odometry [29] or Structure from Motion (SfM) [17] where 3D point positions are triangulated by estimating poses of a monocular camera in multiple views.”
Geometry-Aware Learning of Maps for Camera Localization (2017, methodology): “We can compute the relative poses v̂ij between consecutive frames with visual odometry algorithms [18, 19, 44].”
A mobile vision system for robust multi-person tracking (2008, background): “The majority of the work in visual odometry (VO) is based on local features and RANSACtype hypothesize-and-test frameworks [21] [25].”
Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme (2010, methodology): “[18]).”
Large-scale direct SLAM with stereo cameras (2015, methodology): “The term visual odometry has been coined in the seminal work of Nister et al. [1] who proposed sparse methods for estimating the motion of monocular as well as stereo cameras by sequential frame-to-frame matching.”
Two years of Visual Odometry on the Mars Exploration Rovers (2007, result): “Similar work has been reported elsewhere (Zhang et al., 1988; Lacroix et al., 1999; Nistér et al., 2004).”
High-precision, consistent EKF-based visual-inertial odometry (2013, methodology): “This task is similar to the well-known visualodometry (VO) problem (Nister et al., 2004), with the added characteristic that an IMU is available.”