Piston error detection technology for optical sparse aperture system via transfer learning

2021 ◽  
Author(s):  
Jiawen Li ◽  
Rongzhu Zhang
Keyword(s):  
Transfer Learning ◽  
Error Detection ◽  
Detection Technology ◽  
Sparse Aperture

scholarly journals A Two-Phase Fashion Apparel Detection Method Based on YOLOv4

2021 ◽  
Vol 11 (9) ◽  
pp. 3782
Author(s):  
Chu-Hui Lee ◽  
Chen-Wei Lin
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Detection Method ◽  
Phase Transfer ◽  
Recognition Task ◽  
Phase Detection ◽  
Target Domain ◽  
Two Phase ◽  
Detection Technology ◽  
Fashion Apparel

Object detection is one of the important technologies in the field of computer vision. In the area of fashion apparel, object detection technology has various applications, such as apparel recognition, apparel detection, fashion recommendation, and online search. The recognition task is difficult for a computer because fashion apparel images have different characteristics of clothing appearance and material. Currently, fast and accurate object detection is the most important goal in this field. In this study, we proposed a two-phase fashion apparel detection method named YOLOv4-TPD (YOLOv4 Two-Phase Detection), based on the YOLOv4 algorithm, to address this challenge. The target categories for model detection were divided into the jacket, top, pants, skirt, and bag. According to the definition of inductive transfer learning, the purpose was to transfer the knowledge from the source domain to the target domain that could improve the effect of tasks in the target domain. Therefore, we used the two-phase training method to implement the transfer learning. Finally, the experimental results showed that the mAP of our model was better than the original YOLOv4 model through the two-phase transfer learning. The proposed model has multiple potential applications, such as an automatic labeling system, style retrieval, and similarity detection.

scholarly journals Overview of Machine Tool Error Detection Technology

2020 ◽  
Vol 1550 ◽  
pp. 032152
Author(s):  
Xinkai Li ◽  
Dehua Li ◽  
Yingying Lao ◽  
Ruijie Zhang ◽  
Yi Han ◽  
...  
Keyword(s):  
Machine Tool ◽  
Error Detection ◽  
Detection Technology

Study on the Method of Error Identification and Compensation for Gear Measuring Center

2012 ◽  
Vol 482-484 ◽  
pp. 1821-1828
Author(s):  
Peng Wan ◽  
Jun Jie Guo ◽  
Hai Tao Li
Keyword(s):  
High Precision ◽  
Error Detection ◽  
Geometric Error ◽  
Precision Measurements ◽  
Tooth Surface ◽  
Geometric Errors ◽  
Detection Technology ◽  
Accuracy Of Measurement ◽  
Measuring Machine ◽  
Multi Body

Gear Measuring Center(GMC) is commonly used to test error of the tooth surface of the gear, whose geometric accuracy directly impacts on the accuracy of measurement. How to quickly and accurately detect space geometric error of the measuring machine and compensate becomes the essential means of high-precision measurements. According to the problem above, in the paper, three-beams laser detection technology is proposed. The detection of the geometric errors of the linear axis was achieved. The accurate measurement for the position and attitude of the plane mirror on measurement seat was achieved based on laser telemetry principle. The positioning error, the pitching angle errors, the deflection angle errors and the straightness errors were separated. And then based on multi-body system theory, by using of homogeneous coordinate transformation, the error compensation model of 4-axis measuring machine which includes three shifting pairs and one revolute pair was established, and the algorithm was given in the paper. The theoretical foundation for real-time compensation of 4-axis GMC was established. The geometric errors of GMC can be improved by the method of the error detection and compensation. The method plays a very important role in high-precision measurements.

scholarly journals Large-Aperture Real-Time Compensated Collimating Wavefront Error Detection Method

2019 ◽  
Vol 9 (11) ◽  
pp. 2370
Author(s):  
Xueliang Zhu ◽  
Dasen Wang ◽  
Fengming Nie ◽  
Bingcai Liu ◽  
Hongjun Wang ◽  
...  
Keyword(s):  
Real Time ◽  
Error Detection ◽  
Detection Method ◽  
Three Dimensional ◽  
Surface Measurement ◽  
Dimensional Error ◽  
Detection Technology ◽  
Wavefront Error ◽  
Scanning Detection ◽  
Wavefront Detection

This paper proposes a real-time compensated pentaprism scanning wavefront detection method to achieve real-time compensation for scanning errors occurring during prism movement along a guide rail. The method is based on existing pentaprism scanning wavefront detection technology and it is realized by applying self-collimation-based three-dimensional error compensation. Using theoretical and data analyses of a detection experiment, the reliability of the optimized pentaprism scanning detection method is verified, thus effectively ensuring the reasonable estimation of the interferometry surface measurement uncertainty.

Large-range piston error detection technology based on dispersed fringe sensor

2021 ◽  
Author(s):  
Pengfei Wang ◽  
Hui Zhao ◽  
Xiaopeng Xie ◽  
Yating Zhang ◽  
Chuang Li ◽  
...  
Keyword(s):  
Error Detection ◽  
Large Range ◽  
Detection Technology

scholarly journals Abnormal detection technology of industrial control system based on transfer learning

2022 ◽  
Vol 412 ◽  
pp. 126539
Author(s):  
Weiping Wang ◽  
Chunyang Wang ◽  
Zhen Wang ◽  
Manman Yuan ◽  
Xiong Luo ◽  
...  
Keyword(s):  
Control System ◽  
Transfer Learning ◽  
Industrial Control System ◽  
Industrial Control ◽  
Abnormal Detection ◽  
Detection Technology
Sign in / Sign up

Export Citation Format

Share Document