scholarly journals Improving Real-Time Performance of U-Nets for Machine Vision in Laser Process Control

2019 ◽  
Author(s):  
Przemysław Dolata ◽  
Jacek Reiner
Keyword(s):  
Process Control ◽  
Machine Vision ◽  
Real Time ◽  
Laser Process ◽  
Time Performance

Real-time process control by machine vision

2011 ◽  
Author(s):  
Christoph Franz ◽  
Peter Abels ◽  
Michael Merz ◽  
Holger Singpiel ◽  
Johannes Trein
Keyword(s):  
Process Control ◽  
Machine Vision ◽  
Real Time ◽  
Time Process

The Application of Machine Vision in Automatic Assembly of Locks

2013 ◽  
Vol 646 ◽  
pp. 158-163
Author(s):  
Qing Min Liu ◽  
Cheng Zhang Gu ◽  
Zhi Kui Liu ◽  
Ling Zhao
Keyword(s):  
Machine Vision ◽  
Real Time ◽  
Production Efficiency ◽  
Assembly System ◽  
Automatic Assembly ◽  
Time Performance ◽  
System Requirements ◽  
The Difference ◽  
Assembly Precision

In the automatic assembly of locks system the pins’ selection depends on depth of key’s groove. Although the kinds of groove’s depth are fixed, the arrangements are random and they can’t be unpredictable. The difference in depth of key’s groove is very small, so it can’t be judged by eyes accurately. To solve the problem that the pins assembly is tried frequently, the depth of keys’ groove can be measured accurately by the machine vision. So the problem of the serious influence production efficiency is solved successfully. This kind lock is widely used and machine’s cost is very low by allocation. The experiments show that this method fully met the locks automatic assembly system requirements from the assembly precision, real time performance and robustness and other aspects, solving the problems encountered in the lock assembly.

Real-time Performance Monitoring of MPC Based on Covariance Index Prediction

2014 ◽  
Vol 39 (5) ◽  
pp. 658-663 ◽  
Author(s):  
Xue-Min TIAN ◽  
Ya-Jie SHI ◽  
Yu-Ping CAO
Keyword(s):  
Real Time ◽  
Performance Monitoring ◽  
Time Performance

Single Depth View Based Real-Time Reconstruction of Hand-Object Interactions

2021 ◽  
Vol 40 (3) ◽  
pp. 1-12
Author(s):  
Hao Zhang ◽  
Yuxiao Zhou ◽  
Yifei Tian ◽  
Jun-Hai Yong ◽  
Feng Xu
Keyword(s):  
Real Time ◽  
Synthetic Data ◽  
Real Data ◽  
Depth Image ◽  
Real Time System ◽  
The Real ◽  
Time Performance ◽  
Contact Constraint ◽  
Object Shapes ◽  
Object Interactions

Reconstructing hand-object interactions is a challenging task due to strong occlusions and complex motions. This article proposes a real-time system that uses a single depth stream to simultaneously reconstruct hand poses, object shape, and rigid/non-rigid motions. To achieve this, we first train a joint learning network to segment the hand and object in a depth image, and to predict the 3D keypoints of the hand. With most layers shared by the two tasks, computation cost is saved for the real-time performance. A hybrid dataset is constructed here to train the network with real data (to learn real-world distributions) and synthetic data (to cover variations of objects, motions, and viewpoints). Next, the depth of the two targets and the keypoints are used in a uniform optimization to reconstruct the interacting motions. Benefitting from a novel tangential contact constraint, the system not only solves the remaining ambiguities but also keeps the real-time performance. Experiments show that our system handles different hand and object shapes, various interactive motions, and moving cameras.

Sign in / Sign up

Export Citation Format

Share Document