Automatic subway tunnel crack detection system based on line scan camera

2021 ◽  
Author(s):  
Qimin Gong ◽  
Liqiang Zhu ◽  
Yaodong Wang ◽  
Zujun Yu
Keyword(s):  
Crack Detection ◽  
Detection System ◽  
Subway Tunnel ◽  
Line Scan ◽  
Tunnel Crack ◽  
On Line

Design of On-Line Detection System for Paper Defects Based on Line-Scan Camera

2014 ◽  
Vol 536-537 ◽  
pp. 268-271
Author(s):  
Ping He ◽  
Chao Liu ◽  
Meng Wang ◽  
Sheng Mei Cao
Keyword(s):  
High Efficiency ◽  
Detection System ◽  
Low Cost ◽  
Digital Camera ◽  
Line Detection ◽  
Detection Scheme ◽  
Line Scan ◽  
On Line ◽  
Increasing Demand ◽  
Technology Level

Paper defects mean that there are some defects in the paper such as hole, emboss, and fold during the paper production, which mainly results from the limitation of technological level. In the past time, artificial visual inspection and off-line checking were often used to detect the paper defects. However, its shortcoming was highlighted along with the improvement of industrial technology level and increasing demand for paper. In order to realize the online detection and markers for paper defects, the project designs the on-line detection system based on line-scan digital camera. Firstly, the principle and detection scheme of the system for the paper defects was presented. Then the overall structure of the system was designed. After that, the hardware circuit of the system was designed using TMS320F2812 as main control chip. It mainly consists of the function of each module and the working process of the system. Finally, the software of the image acquisition system was presented. With the experimental verification, the system has advantages of low cost, high efficiency and strong resistance to interference. The functions and indexes achieved the design requirements.

The Application of DSP in Eggshell Quality Online Detection System

2010 ◽  
Vol 43 ◽  
pp. 68-71
Author(s):  
Li Sun ◽  
Shi Qing Zhang ◽  
Jian Rong Cai ◽  
Hao Lin ◽  
Gen Gen Fang
Keyword(s):  
Crack Detection ◽  
Detection System ◽  
Digital Signal ◽  
Acoustic Resonance ◽  
Motor Drive ◽  
Response Signal ◽  
Line System ◽  
Eggshell Quality ◽  
On Line ◽  
Signal Conditioning Circuit

An on-line system which based on acoustic resonance employed digital signal processer (DSP) as its core device for eggshell crack detection. The system consists of the IR trigger for detecting the egg’s coming, the motor drive for driving the DC motor, the signal conditioning circuit for signal amplification and filter and DSP for control and signal processing. Based on the analysis of response signal of eggshell which excited with a light mechanical, four featured descriptors were exacted for discriminating intact and cracked eggs. By using the on-line system for detection of cracked eggs, the identification rates of intact eggs and cracked eggs were 93.75% and 96.25%, respectively. This system can detect 5 eggs within one second, it completely meet the needs of on-line detection.

Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection

2021 ◽  
pp. 1-17
Author(s):  
Xin Wen Gao ◽  
ShuaiQing Li ◽  
Bang Yang Jin ◽  
Min Hu ◽  
Wei Ding
Keyword(s):  
Large Scale ◽  
Crack Detection ◽  
Detection System ◽  
Semantic Segmentation ◽  
Detection Algorithm ◽  
Shield Tunnel ◽  
False Detection ◽  
Adaptive Selection ◽  
Detection Algorithms ◽  
Tunnel Crack

With the large-scale construction of urban subways, the detection of tunnel cracks becomes particularly important. Due to the complexity of the tunnel environment, it is difficult for traditional tunnel crack detection algorithms to detect and segment such cracks quickly and accurately. The article presents an optimal adaptive selection model (RetinaNet-AOS) based on deep learning RetinaNet for semantic segmentation on tunnel crack images quickly and accurately. The algorithm uses the ROI merge mask to obtain a minimum detection area of the crack in the field of view. A scorer is designed to measure the effect of ROI region segmentation to achieve optimal results, and further optimized with a multi-dimensional classifier. The algorithm is compared with the standard detection based on RetinaNet algorithm with an optimal adaptive selection based on RetinaNet algorithm for different crack types. The results show that our crack detection algorithm not only addresses interference due to mash cracks, slender cracks, and water stains but also the false detection rate decreases from 25.5–35.5% to about 3.6%. Meanwhile, the experimental results focus on the execution time to be calculated on the algorithm, FCN, PSPNet, UNet. The algorithm gives better performance in terms of time complexity.

Based on line scan CCD print image detection system

2015 ◽  
Author(s):  
Lifeng Zhang ◽  
Kai Xie ◽  
Tong Li
Keyword(s):  
Detection System ◽  
Image Detection ◽  
Line Scan ◽  
On Line

Traffic Flow Video Detection System Based on Line Scan CMOS Sensor

2012 ◽  
Vol 7 (1) ◽  
pp. 478-483 ◽  
Author(s):  
Zhanwen Liu ◽  
Shan Lin ◽  
Kunlun Li ◽  
Anguo Dong
Keyword(s):  
Traffic Flow ◽  
Detection System ◽  
Line Scan ◽  
Cmos Sensor ◽  
Video Detection ◽  
On Line

Acquisition of EELS spectra for high-resolution spectroscopy

1993 ◽  
Vol 51 ◽  
pp. 578-579
Author(s):  
Maoxu Qian ◽  
Mehmet Sarikaya ◽  
Edward A. Stern
Keyword(s):  
Energy Loss ◽  
Detection System ◽  
High Resolution Spectroscopy ◽  
High Signal ◽  
Short Report ◽  
Edge Structure ◽  
High Background ◽  
Gain Variation ◽  
Sufficient Energy ◽  
On Line

It is difficult, in general, to perform quantitative EELS to determine, for example, relative or absolute compositions of elements with relatively high atomic numbers (using, e.g., K edge energies from 500 eV to 2000 eV), to study ELNES (energy loss near edge structure) signal using the white lines to determine oxidation states, and to analyze EXELFS (extended energy loss fine structure) to study short range ordering. In all these cases, it is essential to have high signal-to-noise (S/N) ratio (low systematical error) with high overall counts, and sufficient energy resolution (∽ 1 eV), requirements which are, in general, difficult to attain. The reason is mainly due to three important inherent limitations in spectrum acquisition with EELS in the TEM. These are (i) large intrinsic background in EELS spectra, (ii) channel-to-channel gain variation (CCGV) in the parallel detection system, and (iii) difficulties in obtaining statistically high total counts (∽106) per channel (CH). Except the high background in the EELS spectrum, the last two limitations may be circumvented, and the S/N ratio may be attained by the improvement in the on-line acquisition procedures. This short report addresses such procedures.

Development of Glucose On-line Detection System for Fermentation Process

2013 ◽  
Vol 40 (12) ◽  
pp. 1945-1949
Author(s):  
Xue-Jin GAO ◽  
Guang-Sheng LIU ◽  
Li CHENG ◽  
Ling-Xiao GENG ◽  
Ji-Xing XUE ◽  
...  
Keyword(s):  
Fermentation Process ◽  
Detection System ◽  
Line Detection ◽  
On Line
Sign in / Sign up

Export Citation Format

Share Document