In this paper, a new algorithm for extracting the laser fringe center is proposed. Based on a deep learning skeleton extraction network, the laser stripe center can be extracted quickly and accurately. Skeleton extraction is the process of reducing the shape image to its approximate central axis representation while maintaining the image's topological and geometric shape. Skeleton extraction is an important step in topological and geometric shape analysis. According to the characteristics of the wheelset laser curve dataset, a new skeleton extraction network, a hierarchical skeleton network (LuoNet), is proposed. The proposed architecture has three levels of the encoder-decoder network, and YE Module interconnection is designed between each level of the encoder and decoder network. In the wheelset laser curve dataset, the F1_score can reach 0.714. Compared with the traditional laser curve center extraction algorithm, the proposed LuoNet algorithm has the advantages of short running time, high accuracy, and stable extraction results.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8838502PMC
http://dx.doi.org/10.3390/s22030859DOI Listing

Publication Analysis

Top Keywords

skeleton extraction
20
laser curve
16
extraction network
12
extraction
8
based deep
8
deep learning
8
learning skeleton
8
topological geometric
8
geometric shape
8
wheelset laser
8

Similar Publications

The fibula, despite being traditionally overlooked compared to the femur and the tibia, has recently received attention in primate functional morphology due to its correlation with the degree of arboreality (DOA). Highlighting further fibular features that are associated with arboreal habits would be key to improving palaeobiological inferences in fossil specimens. Here we present the first investigation on the trabecular bone structure of the primate fibula, focusing on the distal epiphysis, across a vast array of species.

View Article and Find Full Text PDF

Background: Given the risks associated with autologous bone transplantation and the limitations of allogeneic bone transplantation, scaffolds in bone tissue engineering that incorporate bioactive peptides are highly recommended. Teriparatide (TPTD) plays a significant role in bone defect repair, although achieving controlled release of TPTD within a bone tissue engineering scaffold remains challenging. This work reports a new approach for treatment of teriparatide using a water-in-oil-in-water (w/o/w) microspheres be equipped on gelatin (GEL)/Poly lactic-glycolic acid (PLGA)/attapulgite (ATP) scaffold.

View Article and Find Full Text PDF

Background: The limitation in spatial resolution of bone scintigraphy, combined with the vast variations in size, location, and intensity of bone metastasis (BM) lesions, poses challenges for accurate diagnosis by human experts. Deep learning-based analysis has emerged as a preferred approach for automating the identification and delineation of BM lesions. This study aims to develop a deep learning-based approach to automatically segment bone scintigrams for improving diagnostic accuracy.

View Article and Find Full Text PDF

Efficient capture of TcO/ReO via node and linker bifunctional anion exchange covalent organic frameworks.

J Hazard Mater

January 2025

State Key Laboratory of Pollution Control and Resource Reuse, School of the Environment, Nanjing University, Nanjing 210023, China. Electronic address:

In nuclear wastewater treatment, ion-scavenging materials designed to trap TcO is urgently needed. However, strong acid/base, high radiation and high salt concentration of nuclear wastewater usually result in inadequate stability and adsorption capacity of the adsorbent. Herein, we report a new class of bifunctional anion-exchange olefin-linked COF (BPDC-MTMP) prepared via Knoevenagel condensation reactions, the first example exploring the synergistic integration of positively charged fragments at both nodes and linkers.

View Article and Find Full Text PDF

The present study investigates the potential contribution of Photobiomodulation (PBM) to the regeneration of the bone following the extraction of the first mandibular molar in rats. The study evaluates the efficacy of PBM, using both Low-Level Laser Therapy (LLLT) and Light-Emitting Diode Therapy (LEDT), as promotors of osteoblastic activity and the formation of new bone. Study design, setting, and sample: 45 male Wistar rats were divided randomly into three groups of 15 individuals - (i) control group (left lower molar removed only), (ii) the LLL group (molar removed, followed by LLLT), and (iii) the LED group (molar removed, followed by LEDT).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!