Design of Detection System of Traction Motor Commutator Based on Computer Vision

2012 ◽  
Vol 466-467 ◽  
pp. 1290-1294
Author(s):  
Jian Hui Zhang ◽  
Ying Ying Xu
Keyword(s):  
Computer Vision ◽  
Real Time ◽  
High Performance ◽  
Cutting Tool ◽  
Detection System ◽  
Numerical Control ◽  
Traction Motor ◽  
Charge Couple Device Camera ◽  
Localization Signal ◽  
Automatic Detection System

The paper presents a new automatic detection system of DC traction motor commutator, which captures the image of traction motor commutator through CCD (Charge Couple Device) camera in real time, and recognizes the eigenvalue of commutator image by utilizing image processing technology. Meantime, the system takes it as the localization signal of numerical control machine. Therefore, computer vision controls cutting tool working instead of eyes in this system. The system has high-performance of precision and real time proved by experiment, so which has a certain value of practicality.

scholarly journals Artificial Intelligence-Assisted Colonoscopy for Detection of Colon Polyps: a Prospective, Randomized Cohort Study

2020 ◽  
Author(s):  
Yuchen Luo ◽  
Yi Zhang ◽  
Ming Liu ◽  
Yihong Lai ◽  
Panpan Liu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
High Performance ◽  
Detection System ◽  
Random Order ◽  
Colon Polyps ◽  
Clinical Environment ◽  
Polyp Detection ◽  
Link Type ◽  
Polyp Detection Rate

Abstract Background and aims Improving the rate of polyp detection is an important measure to prevent colorectal cancer (CRC). Real-time automatic polyp detection systems, through deep learning methods, can learn and perform specific endoscopic tasks previously performed by endoscopists. The purpose of this study was to explore whether a high-performance, real-time automatic polyp detection system could improve the polyp detection rate (PDR) in the actual clinical environment. Methods The selected patients underwent same-day, back-to-back colonoscopies in a random order, with either traditional colonoscopy or artificial intelligence (AI)-assisted colonoscopy performed first by different experienced endoscopists (> 3000 colonoscopies). The primary outcome was the PDR. It was registered with clinicaltrials.gov. (NCT047126265). Results In this study, we randomized 150 patients. The AI system significantly increased the PDR (34.0% vs 38.7%, p < 0.001). In addition, AI-assisted colonoscopy increased the detection of polyps smaller than 6 mm (69 vs 91, p < 0.001), but no difference was found with regard to larger lesions. Conclusions A real-time automatic polyp detection system can increase the PDR, primarily for diminutive polyps. However, a larger sample size is still needed in the follow-up study to further verify this conclusion. Trial Registration clinicaltrials.gov Identifier: NCT047126265

A high performance real-time edge detection system with NEON

2017 ◽  
Author(s):  
Kaixuan Zhang ◽  
Li Ding ◽  
Yujie Cai ◽  
Wenbo Yin ◽  
Fan Yang ◽  
...  
Keyword(s):  
Edge Detection ◽  
Real Time ◽  
High Performance ◽  
Detection System

scholarly journals Application of deep learning in automatic detection of technical and tactical indicators of table tennis

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0245259
Author(s):  
Fufeng Qiao
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Short Term Memory ◽  
Detection System ◽  
Minimum Mean Square Error ◽  
Automatic Detection ◽  
Table Tennis ◽  
Time Dynamic ◽  
Time Motion ◽  
Automatic Detection System

A DCNN-LSTM (Deep Convolutional Neural Network-Long Short Term Memory) model is proposed to recognize and track table tennis’s real-time trajectory in complex environments, aiming to help the audiences understand competition details and provide a reference for training enthusiasts using computers. Real-time motion features are extracted via deep reinforcement networks. DCNN tracks the recognized objects, and the LSTM algorithm predicts the ball’s trajectory. The model is tested on a self-built video dataset and existing systems and compared with other algorithms to verify its effectiveness. Finally, an overall tactical detection system is built to measure ball rotation and predict ball trajectory. Results demonstrate that in feature extraction, the Deep Deterministic Policy Gradient (DDPG) algorithm has the best performance, with a maximum accuracy rate of 89% and a minimum mean square error of 0.2475. The accuracy of target tracking effect and trajectory prediction is as high as 90%. Compared with traditional methods, the performance of the DCNN-LSTM model based on deep learning is improved by 23.17%. The implemented automatic detection system of table tennis tactical indicators can deal with the problems of table tennis tracking and rotation measurement. It can provide a theoretical foundation and practical value for related research in real-time dynamic detection of balls.

A Micro Electrical Machining CNC System Based on RTAI

2007 ◽  
Author(s):  
Rui Guo ◽  
Wansheng Zhao ◽  
Gang Li
Keyword(s):  
Real Time ◽  
High Performance ◽  
Detection Algorithm ◽  
Numerical Control ◽  
Cnc System ◽  
Good Surface ◽  
Micro Holes ◽  
On Line ◽  
Hard Real Time ◽  
Micro Structures

Micro Electrical Machining (μ-EM) has been regarded as a key technology for micro-machining because of the high precision and good surface quality that it can achieve. This paper presents the development of a Computer Numerical Control (CNC) system dedicated for μ-EM. RTAI which is a hard real-time operating system based on Linux is applied to meet the requirements of the μ-EM CNC. RTAI offers high performance compared with commercial real-time operating systems. To deal with the difficulties in micro electrodes online fabrication and compensation, an on-line measurement subsystem which has a resolution of 1.61 μm and an overall magnification ranges from 113 to 729 is integrated into the CNC system. The contour of micro electrodes can be extracted by means of the Canny edge detection algorithm. The micro electrodes’ dimension can be measured on-line manually or automatically. Machining verifications demonstrate that a μ-EM machine equipped with the RTAI based CNC system has a good potential of manufacturing not only micro-holes and micro-shafts but also complex 3D micro structures and parts.

Design and Implementation of an Interpolation Processor for CNC Machining

2013 ◽  
Vol 819 ◽  
pp. 322-327
Author(s):  
Jing Chuan Dong ◽  
Tai Yong Wang ◽  
Bo Li ◽  
Xian Wang ◽  
Zhe Liu
Keyword(s):  
Real Time ◽  
High Speed ◽  
High Performance ◽  
Low Cost ◽  
Parallel Architecture ◽  
Cnc Machining ◽  
Numerical Control ◽  
Experimental Result ◽  
Interpolation Algorithm ◽  
Asynchronous Instruction

As the demand for high speed and high precision machining increases, the fast and accurate real-time interpolation is necessary in modern computerized numerical control (CNC) systems. However, the complexity of the interpolation algorithm is an obstacle for the embedded processor to achieve high performance control. In this paper, a novel interpolation processor is designed to accelerate the real-time interpolation algorithm. The processor features an advanced parallel architecture, including a 3-stage instruction pipeline, very long instruction word (VLIW) support, and asynchronous instruction execution mechanism. The architecture is aimed for accelerating the computing-intensive tasks in CNC systems. A prototype platform was built using a low-cost field programmable gate array (FPGA) chip to implementation the processor. Experimental result has verified the design and showed the good computing performance of the proposed architecture.

Multipurpose Detecting System for Automotive Switch Function Based on Virtual Instrument (LabVIEW) and Embedded Technology (ARM)

2012 ◽  
Vol 490-495 ◽  
pp. 937-941
Author(s):  
Hong He ◽  
Xing Su ◽  
Pei Pei Yang ◽  
Jian Wen Li ◽  
Shao Hua Shi
Keyword(s):  
Control System ◽  
Real Time ◽  
Virtual Instrument ◽  
High Performance ◽  
Detection System ◽  
Material Resources ◽  
Instrument Technology ◽  
Ethernet Controller ◽  
And Performance ◽  
And Control

Contrary to the problem that automobile switches have various kinds and large differences in the structure and performance so that traditional testing methods have been unable to meet the testing requirements of high performance switches, the paper designs a new detection system used to detect the functions of general auto switches which applies the developing environment LabVIEW based on virtual instrument technology and adopts the technology of embedded observe and control system. Using PC as the host computer, the system adopts the LabVIEW8.5 to compile a real-time monitoring system with good human-computer interface; S3C2440-ARM9 processor is used as the main controller of observe and control system in the inferior computer which collects output current signal when the circuit is conducted after switch is pressed. After the coding process of LwIP software protocol and the drive of Ethernet controller DM9000, the signal is transmitted to PC through Ethernet interface. Compared with conventional testing measures, this system greatly improves the real-time performance as well as working efficiency of detecting switch functions and reduces the corresponding human and material resources.

The Real Time System of Hair Detection in Mushroom Based on Computer Vision

2012 ◽  
Vol 588-589 ◽  
pp. 1199-1203
Author(s):  
Tong Qiang Li ◽  
Cai Feng Zheng ◽  
Jian Peng Gan
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Real Time ◽  
Detection System ◽  
Contour Detection ◽  
Time System ◽  
Real Time System ◽  
Extraction Algorithm ◽  
Structure Extraction ◽  
Line Direction

By analysing the Mushroom image, the paper puts forward a kind of line-structure extraction algorithm combination of local gray value and continuity of line direction .After the operations in many aspects of basis image processing, such as gray-scale, denoising , segmentation, contour detection and morphological, this article has developed a set of hair detection system based on computer vision for the Mushroom. The experimental results show this system could well meet the actual needs, and has a broad market prospect.

Sign in / Sign up

Export Citation Format

Share Document