Visual-lidar odometry and mapping: low-drift, robust, and fast

By Ji Zhang, Sanjiv Singh. IEEE International Conference on Robotics and Automation, 2015

701 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/ac7215af97ed57f073dd3bb03188ac313e62e5fb

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

1. Shaojie Shen
2. Shaozu Cao
3. Fatma Güney
4. Jie Pan
5. Daniela Rus
6. Tong Qin
7. Joel Janai
8. Aseem Behl

In Computer Vision and Pattern Recognition

1. Shaojie Shen
2. Fatma Güney
3. Joel Janai
4. Aseem Behl
5. Shaozu Cao
6. Daniela Rus
7. Jie Pan
8. Andreas Geiger

In Electrical and Electronic Engineering

1. Shaozu Cao
2. Jie Pan
3. Shaojie Shen
4. Daniela Rus
5. Tong Qin
6. Javier Alonso-Mora
7. Wilko Schwarting
8. Homayoun Najjaran

Citations in the corpus

• A Review of Visual-LiDAR Fusion based Simultaneous Localization and Mapping (2020, background): “Creating a common SLAM framework using visual information and laser range seems to be a real challenge.”
• A General Optimization-based Framework for Global Pose Estimation with Multiple Sensors (2019, methodology): “There are also some multi-sensor fusion methods, such as visual-inertial fusion [6]–[11, 15, 16] and visual-LiDAR fusion [17].”
• Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review (2020, positive): “The V-LOAM algorithm [151] is ranked first because of having the smallest reported translational and rotational errors.”
• Low-drift and real-time lidar odometry and mapping (2017, methodology): “, 800m lengthes based on 3D coordinates, as averaged percentages of the segment lengthes estimation and the proposed method for motion refinement (Zhang and Singh 2015).”
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Zhang & Singh (2015) extend this work by combining visual odometry at high frequency with LiDAR-mapping at low frequency which allows them to further improve.”
• Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, positive): “The top-ranked localization method on KITTI’s odometry data set is V-LOAM [105] which combines visual odometry for motion estimation with a slower 3D laser odometry.”
• Planning and Decision-Making for Autonomous Vehicles (2018, positive): “While the current leaders in the KITTI Visual Odometry benchmark are based on lidar or a combination of vision and lidar (51), fast and lightweight approaches based purely on vision, such as ORB-SLAM2 (50), SVO (Semidirect Visual Odometry) 2.”
• The Architectural Implications of Autonomous Driving: Constraints and Acceleration (2018, positive): “Therefore, prior map-based localization has beenwidely used to provide localization capability at centimeter-level precision [44, 53, 64, 78, 79, 83], where the surrounding view is transformed into feature descriptions to map the feature points stored in the prior map to identify the location of the”