• Home
  • Search
  • Robust Dual Quadric Initialization for Forward-Translating Camera Movements
  • Cite Icon13
  • https://doi.org/10.1109/lra.2021.3067868Copy DOI Icon

Robust Dual Quadric Initialization for Forward-Translating Camera Movements

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Herein, we present a novel approach for monocular dual quadric initialization that combines three-dimensional (3D) map points with two-dimensional (2D) object detection for forward-translating camera movements. The traditional approach using 2D detection bounding boxes in multiple views fails in straight vehicle motion scenarios as object observation is limited to few frames. Although single image initialization is possible when multiple constraints are introduced, such initialization is based on strong assumptions. In this letter, we incorporate constraints from 3D map points with single-view 2D object detection to robustly initialize the dual quadric. Constraints from 3D map points are converted to planar constraints from their convex hull. Together with the projective planar constraints from bounding boxes, the proposed method can infer accurate dual quadric parameters. Further, comparison studies with the state of the art (SOTA) show that the proposed approach achieves the same accuracy of center localization but outperforms the existing methods in shape estimation and success ratio of initialization. The proposed method dose not rely on assumptions of dimension and pose of 3D objects; hence, it is more generic and accurate. Based on the KITTI raw dataset, the initialization success ratio is up to 97.7% with an average position error of 1.58 m, and 2D IoU of 80% when the number of map points per object accumulates to 60. When applied to the TUM RGB-D dataset, the proposed approach yields an initialization success ratio of 92.7% when the number of map points per object accumulates to 30, revealing a 16.2% increment compared with the SOTA using an RGB-D camera. Finally, we integrate the initialization method into a simultaneous localization and mapping system.

Similar Papers
  • PDF
  • Research Article
  • Citations23

SLAM-Based Self-Calibration of a Binocular Stereo Vision Rig in Real-Time.

  • Jan 22, 2020
  • Sensors
  • Hesheng Yin +6
  • Conference Article
  • Citations27

MAV visual SLAM with plane constraint

  • May 01, 2011
  • Gim Hee Lee +2
  • Book Chapter
  • Citations27

3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings

  • Jan 01, 2021
  • Giorgia Pitteri +3
  • Conference Article
  • Citations104

Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data

  • Jun 01, 2022
  • Corentin Sautier +5
  • Conference Article

BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection

  • Aug 01, 2024
  • Huiqiang Chen +3
  • Conference Article
  • Citations9

EGO-SLAM: A Robust Monocular SLAM for Egocentric Videos

  • Jan 01, 2019
  • Suvam Patra +4
  • Conference Article
  • Citations2

Three-Dimensional Mapping System for Environment and Object Detection on an Unmanned Aerial Vehicle

  • Nov 01, 2019
  • Leonard Ambata +4
  • Research Article

딥러닝과 ICP 알고리즘을 이용한 링 모양의 소형 빈피킹 물체의 실시간 3차원 자세 추정

  • Sep 30, 2019
  • Journal of Institute of Control, Robotics and Systems
  • Junesuk Lee +3
  • Conference Article
  • Citations441

PointAugmenting: Cross-Modal Augmentation for 3D Object Detection

  • Jun 01, 2021
  • Chunwei Wang +3
  • Conference Article
  • Citations47

Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds

  • Jan 01, 2023
  • Georg Hess +5
  • Preprint Article
  • Citations2

A Crosscutting Three-Modes-Of-Operation Unique LiDAR-Based 3D Mapping System Generic Framework Architecture, Uncertainty Predictive Model And SfM Augmentation

  • Oct 26, 2021
  • Ashraf Mohamed Abdelaziz Elshorbagy
  • PDF
  • Research Article
  • Citations5

A Tightly-Coupled Positioning System of Online Calibrated RGB-D Camera and Wheel Odometry Based on SE(2) Plane Constraints

  • Apr 19, 2021
  • Electronics
  • Liling Zhou +6
  • Book Chapter
  • Citations2

Development of a ROS-Based Architecture for Intelligent Autonomous on Demand Last Mile Delivery

  • Jan 01, 2022
  • Georg Novotny +3
  • Research Article
  • Citations3

Portable 3D laser-camera calibration system with color fusion for SLAM

  • Mar 01, 2013
  • International Journal of Automation and Smart Technology
  • Javier Navarrete +2
  • PDF
  • Preprint Article

Efficient and Scalable Object Localization in 3D on Mobile Device

  • May 02, 2023
  • Neetika Gupta +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.