ODAM: Object Detection, Association, and Mapping using Posed RGB Video

08/23/2021
by   Kejie Li, et al.
9

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system relies on a deep learning front-end to detect 3D objects from a given RGB frame and associate them to a global object-based map using a graph neural network (GNN). Based on these frame-to-model associations, our back-end optimizes object bounding volumes, represented as super-quadrics, under multi-view geometry constraints and the object scale prior. We validate the proposed system on ScanNet where we show a significant improvement over existing RGB-only methods.

READ FULL TEXT

page 1

page 4

page 7

page 8

research
06/02/2021

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

In this paper, we introduce the task of multi-view RGB-based 3D object d...
research
12/22/2022

Monocular 3D Object Detection using Multi-Stage Approaches with Attention and Slicing aided hyper inference

3D object detection is vital as it would enable us to capture objects' s...
research
05/12/2023

An Object SLAM Framework for Association, Mapping, and High-Level Tasks

Object SLAM is considered increasingly significant for robot high-level ...
research
08/05/2020

Tiny-YOLO object detection supplemented with geometrical data

We propose a method of improving detection precision (mAP) with the help...
research
08/09/2022

Learning to Complete Object Shapes for Object-level Mapping in Dynamic Scenes

In this paper, we propose a novel object-level mapping system that can s...
research
03/23/2020

GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end

In this paper we propose an end-to-end learnable approach that detects s...
research
08/05/2021

Object-Augmented RGB-D SLAM for Wide-Disparity Relocalisation

We propose a novel object-augmented RGB-D SLAM system that is capable of...

Please sign up or login with your details

Forgot password? Click here to reset