Design of image acquisition system of online verification device for ship engine spare parts packing

Chunhua Zang; Jiajun Song; Taowen Chen; Guixiong Liu

doi:10.1117/12.2611344

14 October 2021 Design of image acquisition system of online verification device for ship engine spare parts packing

Chunhua Zang, Jiajun Song, Taowen Chen, Guixiong Liu

Proceedings Volume 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation; 119300G (2021) https://doi.org/10.1117/12.2611344
Event: International Conference on Mechanical Engineering, Measurement Control, and Instrumentation (MEMCI 2021), 2021, Guangzhou, China

Abstract

Ship engine spare parts are very important. The manual inspection method for spare parts preparation is highly subjective, and there may be problems such as missed installation, multiple installations, and wrong installations. This paper designed an image acquisition system for deep learning target detection of ship engine spare parts, which could stably collect spare parts images suitable for deep learning target detection. Firstly, it analyzed the problems in the acquisition of ship engine spare parts verification images, and pointed out the problems of perspective artifacts and low CNN feature mapping output response; secondly, it designed a base plate that could avoid perspective artifacts and improve the response of the convolutional neural network. It proposed 4 spare parts placement rules, including Centered placement rule, Feature face up rule, Long side horizontal rule, and Left center of gravity rule. It reduced the number of samples of each type of spare parts used to train the deep learning target detection network from 216 to 3. The experimental results showed that the average accuracy of the Mask R-CNN model for detecting ship engine spare parts was 96.8%, and the detection time did not exceed 0.11s, which met the online verification requirements of the spare parts packing process.

Citation Download Citation

Chunhua Zang, Jiajun Song, Taowen Chen, and Guixiong Liu "Design of image acquisition system of online verification device for ship engine spare parts packing", Proc. SPIE 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation, 119300G (14 October 2021); https://doi.org/10.1117/12.2611344

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image acquisition

Cameras

Target detection

Light sources

Imaging systems

Convolutional neural networks

Detection and tracking algorithms

Show All Keywords

Keywords/Phrases

Search In:

Publication Years