2022
DOI: 10.1109/jstars.2022.3194537
|View full text |Cite
|
Sign up to set email alerts
|

A High-Precision Recognition Method of Circular Marks Based on CMNet Within Complex Scenes

Abstract: Accurate recognition of circular marks is crucial for calibration, object tracking, and threedimensional reconstruction in videogrammetry. However, most existing studies were designed under single or relatively simple scenes. When the existing algorithms are applied to more complex scenarios, it will result in higher false detection and miss-detection rate. In this article, we present a high-precision recognition method based on a novel deep learning model, Circular-MarkNet (CMNet) to solve this problem. The p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
4
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 64 publications
0
4
0
Order By: Relevance
“…Stereo correspondence for the circular targets must be established from different camera views to acquire each camera's extrinsic parameters and unify the coordinate system with the total station. First, the CMNet (Circular-MarkNet) is used to recognize and locate the centers of the circular targets [12]. The method is trained using a substantial dataset of circular mark images captured in diverse environments, resulting in a high recognition rate and detection accuracy within a relatively short time.…”
Section: Stereo Calibrationmentioning
confidence: 99%
“…Stereo correspondence for the circular targets must be established from different camera views to acquire each camera's extrinsic parameters and unify the coordinate system with the total station. First, the CMNet (Circular-MarkNet) is used to recognize and locate the centers of the circular targets [12]. The method is trained using a substantial dataset of circular mark images captured in diverse environments, resulting in a high recognition rate and detection accuracy within a relatively short time.…”
Section: Stereo Calibrationmentioning
confidence: 99%
“…Early research on saliency prediction mainly relies on hand-crafted features. The limitation of these hand-crafted features is their ineffectiveness towards complex scenes, i.e., natural images with multiple objects or multiple salient regions [10].…”
Section: Introductionmentioning
confidence: 99%
“…In the field of ellipse detection, there are three generalized methods without designing for specific scenarios, including the Hough transform method [25,26], deep-learning methods [27] and point-fitting methods [28][29][30][31]. The basic idea of the Hough transform method is that arbitrary edge pixels are voted into a 5D parameter space and then detecting the ellipse when the local peak occurs.…”
Section: Introductionmentioning
confidence: 99%