Deep-trained illumination-robust precision positioning for real-time manipulation of embedded objects

Li, Chih-Hung G.; Huang, Yihao

doi:10.1007/s00170-020-06185-x

Cited by 11 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Qin et al (2013) use gray and texture features to detect and remove the shadows around the workpiece and localize the workpiece without interference from image shadows. Li and Huang (2020) proposed an automated training data generation scheme to enhance the performance of the visual positioning ConvNet in the high-contrast shadow.…”

Section: Fast Workpiece Detection Methodsmentioning

confidence: 99%

A fast workpiece detection method based on multi-feature fused SSD

Shi

Zhang

Zeng

2021

View full text Add to dashboard Cite

Purpose Workpiece sorting is a key link in industrial production lines. The vision-based workpiece sorting system is non-contact and widely applicable. The detection and recognition of workpieces are the key technologies of the workpiece sorting system. To introduce deep learning algorithms into workpiece detection and improve detection accuracy, this paper aims to propose a workpiece detection algorithm based on the single-shot multi-box detector (SSD). Design/methodology/approach Propose a multi-feature fused SSD network for fast workpiece detection. First, the multi-view CAD rendering images of the workpiece are used as deep learning data sets. Second, the visual geometry group network was trained for workpiece recognition to identify the category of the workpiece. Third, this study designs a multi-level feature fusion method to improve the detection accuracy of SSD (especially for small objects); specifically, a feature fusion module is added, which uses “element-wise sum” and “concatenation operation” to combine the information of shallow features and deep features. Findings Experimental results show that the actual workpiece detection accuracy of the method can reach 96% and the speed can reach 41 frames per second. Compared with the original SSD, the method improves the accuracy by 7% and improves the detection performance of small objects. Originality/value This paper innovatively introduces the SSD detection algorithm into workpiece detection in industrial scenarios and improves it. A feature fusion module has been added to combine the information of shallow features and deep features. The multi-feature fused SSD network proves the feasibility and practicality of introducing deep learning algorithms into workpiece sorting.

show abstract

Section: Fast Workpiece Detection Methodsmentioning

confidence: 99%

A fast workpiece detection method based on multi-feature fused SSD

Shi

Zhang

Zeng

2021

View full text Add to dashboard Cite

show abstract

“…Therefore, FDM is also widely used in orthopedics, maxillofacial surgery, and other related medical fields. In terms of geometry, the triangle itself is a relatively special figure, with the characteristics of regional continuity, scan line continuity, and edge continuity [36]. The triangle itself is a single convex area of the plane, and there is no need to prove the continuity of the area.…”

Section: Sla Light-curingmentioning

confidence: 99%

DLP-Based 3D Printing for Automated Precision Manufacturing

Deng

Xie

Liu

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

As a new type of rapid prototyping technology, 3D printing technology effectively solves the problems of large errors and waste of resources in traditional manufacturing technology. Compared with other technologies, DLP technology has the following advantages: high reliability, high brightness, rich and gorgeous colors, and is very suitable for portable devices. This article aims to study the application of embedded microprocessor-based DLP3D printing in automated precision manufacturing. This article puts forward the idea of applying DLP3D technology to more automated precision manufacturing. This article introduces the embedded microprocessor, 3D printing technology, and related algorithms in detail. At the same time, this article also conducts experiments on DLP3D printing technology. Through the analysis of samples printed by DLP3D technology, the experimental results show that the material deviation value of DLP3D printing based on embedded microprocessor is generally small, compared with other technology printing the deviation value of the material is also reduced by 15.6%.

show abstract

Textil-5k: A Real-World Dataset for Textile Surface Defects Detection

Shu

2023

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Deep-trained illumination-robust precision positioning for real-time manipulation of embedded objects

Cited by 11 publications

References 16 publications

A fast workpiece detection method based on multi-feature fused SSD

A fast workpiece detection method based on multi-feature fused SSD

DLP-Based 3D Printing for Automated Precision Manufacturing

Textil-5k: A Real-World Dataset for Textile Surface Defects Detection

Contact Info

Product

Resources

About