2017 IEEE International Conference on Image Processing (ICIP) 2017
DOI: 10.1109/icip.2017.8296674
|View full text |Cite
|
Sign up to set email alerts
|

High quality reconstruction of dynamic objects using 2D-3D camera fusion

Abstract: In this paper, we propose a complete pipeline for high quality reconstruction of dynamic objects using 2D-3D camera setup attached to a moving vehicle. Starting from the segmented motion trajectories of individual objects, we compute their precise motion parameters, register multiple sparse point clouds to increase the density, and develop a smooth and textured surface from the dense (but scattered) point cloud. The success of our method relies on the proposed optimization framework for accurate motion estimat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
5
1
1

Relationship

3
4

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 27 publications
0
5
0
Order By: Relevance
“…Thanks to the proposed 3D-SFC, the detected moving objects can be separated according to their specific motion subspace. The detected moving objects are then individually registered with texture mapping to produce photo-realistic 3D modelling [Jiang et al, 2017a]. For more experimental results, readers are recommended to view this video (https://youtu.be/LewA8Lhn5Xo).…”
Section: Static-map and Rigid Object Reconstructionmentioning
confidence: 99%
“…Thanks to the proposed 3D-SFC, the detected moving objects can be separated according to their specific motion subspace. The detected moving objects are then individually registered with texture mapping to produce photo-realistic 3D modelling [Jiang et al, 2017a]. For more experimental results, readers are recommended to view this video (https://youtu.be/LewA8Lhn5Xo).…”
Section: Static-map and Rigid Object Reconstructionmentioning
confidence: 99%
“…Considering the mentioned drawbacks of supervised approaches, completing point cloud by tracking interests us most. [7], [5], [16] jointly use LiDAR and camera for this task. [15], [31] are closest to our objective in using LiDAR only: Held et al [15] aggregates the observed point clouds, while Ushani et al [31] directly optimizes a point cloud model.…”
Section: Point Cloud Completionmentioning
confidence: 99%
“…Point cloud based algorithms: detection algorithms based on Iterative Closest Point (ICP) match current segments of a point cloud to a previous point cloud to reveal their motion [11,23,30]. This approach works best for rigid objects like cars and considerably decreases in performance for deforming objects like humans.…”
Section: Related Workmentioning
confidence: 99%