Next Article in Journal
Design and Control of Monolithic Compliant Gripper Using Shape Memory Alloy Wires
Next Article in Special Issue
Three-Dimensional Immersion Scanning Technique: A Scalable Low-Cost Solution for 3D Scanning Using Water-Based Fluid
Previous Article in Journal
The Effect of Soil-Structure Interaction on the Seismic Response of Structures Using Machine Learning, Finite Element Modeling and ASCE 7-16 Methods
Previous Article in Special Issue
Segmentation of Structural Elements from 3D Point Cloud Using Spatial Dependencies for Sustainability Studies
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 23
Issue 4
10.3390/s23042049
Review Report
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

Sensors 2023, 23(4), 2049; https://doi.org/10.3390/s23042049
by Chao Zeng 1,2, Xiaomei Chen 1,2,*, Yongtian Zhang 1,2 and Kun Gao 1,2
Reviewer 1:
Guobao Xiao
Reviewer 2:
Bilawal Mahmood
Sensors 2023, 23(4), 2049; https://doi.org/10.3390/s23042049
Submission received: 29 December 2022 / Revised: 7 February 2023 / Accepted: 8 February 2023 / Published: 11 February 2023
(This article belongs to the Special Issue 3D Sensing, Semantic Reconstruction and Modelling)

Round 1

Reviewer 1 Report

This paper tries to improve traditional iterative closest point (ICP) algorithm, by introducing high-level structural information for raw laser scans. The idea is interesting, but there are some serious problems:

1. The motivation and contributions are not very clear. The real contribution is "a combination of planar and edge-related features as well as the establishment of a fixed-point problem", If yes, the contribution is so limited.

2. The related work: it would be better to introduce some more recent references, such as:

(a) some outlier removal methods:

-Co-clustering on Bipartite Graphs for Robust Model Fitting, IEEE Transactions on Image Processing (TIP), 2022, 31, 6605-6620

Some Correspondence-based Methods:

-JRA-Net: Joint Representation Attention Network for Correspondence Learning, Pattern Recognition (PR), 2023

3. The experiment: The proposed method only compare a few competing methods. As we know, point cloud is a pupular topic, so it would be better to add more competing methods.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

overall structure of article is good and well written. article provide a good approach to speed up ICP initialization and optimization problem. However I have following concerns: 

In table 1 and table 2, run time for processing is presented however it is not mentioned either time for Feature Point Extraction  is included or not. kindly elaborate it. 

Kindly add discussion section to discuss limitations of methods (e.g. method can be used in only such scenes where planes and lines exist) and give a general overview how these limitations will be removed in future.

kindly improved the title of article for your application environment and method to make it more precise. it seems very generalized.  

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have considered my problems. This version is find for me.

Back to TopTop