Extraction and segmentation method of laser stripe in linear structured light scanner

2021 ◽  
Vol 60 (04) ◽  
Author(s):  
Zhuo-Ren Wan ◽  
Lei-Jie Lai ◽  
Jian Mao ◽  
Li-Min Zhu
Keyword(s):  
Structured Light ◽  
Segmentation Method ◽  
Laser Stripe ◽  
Structured Light Scanner

Virtual skeletons: using a structured light scanner to create a 3D faunal comparative collection

2009 ◽  
Vol 36 (9) ◽  
pp. 2018-2023 ◽  
Author(s):  
Laura Niven ◽  
Teresa E. Steele ◽  
Hannes Finke ◽  
Tim Gernat ◽  
Jean-Jacques Hublin
Keyword(s):  
Structured Light ◽  
Structured Light Scanner

Real-Time Sensing of Sag Geometry During GTA Welding

1997 ◽  
Vol 119 (2) ◽  
pp. 151-160 ◽  
Author(s):  
Y. M. Zhang ◽  
R. Kovacevic
Keyword(s):  
Real Time ◽  
Vision System ◽  
Structured Light ◽  
Gta Welding ◽  
Seam Tracking ◽  
Image Processing Algorithm ◽  
3D Vision ◽  
Full Penetration ◽  
Laser Stripe ◽  
Penetration Control

Seam tracking and weld penetration control are two fundamental issues in automated welding. Although the seam tracking technique has matured, the latter still remains a unique unsolved problem. It was found that the full penetration status during GTA welding can be determined with sufficient accuracy using the sag depression. To achieve a new full penetration sensing technique, a structured-light 3D vision system is developed to extract the sag geometry behind the pool. The laser stripe, which is the intersection of the structured-light and weldment, is thinned and then used to acquire the sag geometry. To reduce possible control delay, a small distance is selected between the pool rear and laser stripe. An adaptive dynamic search for rapid thinning of the stripe and the maximum principle of slope difference for unbiased recognition of sag border were proposed to develop an effective real-time image processing algorithm for sag geometry acquisition. Experiments have shown that the proposed sensor and image algorithm can provide reliable feedback information of sag geometry for the full penetration control system.

scholarly journals DENSE 3D OBJECT RECONSTRUCTION USING STRUCTURED-LIGHT SCANNER AND DEEP LEARNING

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 777-783
Author(s):  
V. V. Kniaz ◽  
V. A. Mizginov ◽  
L. V. Grodzitkiy ◽  
N. A. Fomin ◽  
V. A. Knyaz
Keyword(s):  
Optical Flow ◽  
3D Model ◽  
Stereo Matching ◽  
Structured Light ◽  
Primary Source ◽  
Ground Truth ◽  
Complex Surface ◽  
Systems Model ◽  
Structured Light Scanner ◽  
Starting Point

Abstract. Structured light scanners are intensively exploited in various applications such as non-destructive quality control at an assembly line, optical metrology, and cultural heritage documentation. While more than 20 companies develop commercially available structured light scanners, structured light technology accuracy has limitations for fast systems. Model surface discrepancies often present if the texture of the object has severe changes in brightness or reflective properties of its texture. The primary source of such discrepancies is errors in the stereo matching caused by complex surface texture. These errors result in ridge-like structures on the surface of the reconstructed 3D model. This paper is focused on the development of a deep neural network LineMatchGAN for error reduction in 3D models produced by a structured light scanner. We use the pix2pix model as a starting point for our research. The aim of our LineMatchGAN is a refinement of the rough optical flow A and generation of an error-free optical flow B̂. We collected a dataset (which we term ZebraScan) consisting of 500 samples to train our LineMatchGAN model. Each sample includes image sequences (Sl, Sr), ground-truth optical flow B and a ground-truth 3D model. We evaluate our LineMatchGAN on a test split of our ZebraScan dataset that includes 50 samples. The evaluation proves that our LineMatchGAN improves the stereo matching accuracy (optical flow end point error, EPE) from 0.05 pixels to 0.01 pixels.

scholarly journals Application of Computer Modeling for Planning Plastic Surgeries

2014 ◽  
Vol 5 (4) ◽  
pp. 18-25
Author(s):  
Klaudia Jamrozik ◽  
Jakub Rusek ◽  
Dominik Szozda ◽  
Krzysztof Karbowski
Keyword(s):  
Reverse Engineering ◽  
Plastic Surgery ◽  
Computer Modeling ◽  
Structured Light ◽  
Visualization Method ◽  
Engineering Technology ◽  
Structured Light Scanner ◽  
Surgery First

Abstract The paper presents the application results of reverse engineering technology for planning the plastic surgery. First step is digitalization of the patient body. It is realized by 3D structured light scanner. The scanning data are transferred into 3dsMax software and used for planning plastic surgery. The planning effect is shown using stereoscopy visualization method.

scholarly journals Co-registration Comparison of On-Scalp Magnetoencephalography and Magnetic Resonance Imaging

2021 ◽  
Vol 15 ◽  
Author(s):  
Fuzhi Cao ◽  
Nan An ◽  
Weinan Xu ◽  
Wenli Wang ◽  
Yanfei Yang ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Source Localization ◽  
Structured Light ◽  
Laser Scanner ◽  
High Signal ◽  
Resonance Imaging ◽  
Registration Error ◽  
Structured Light Scanner ◽  
Reference Phantom

Magnetoencephalography (MEG) can non-invasively measure the electromagnetic activity of the brain. A new type of MEG, on-scalp MEG, has attracted the attention of researchers recently. Compared to the conventional SQUID-MEG, on-scalp MEG constructed with optically pumped magnetometers is wearable and has a high signal-to-noise ratio. While the co-registration between MEG and magnetic resonance imaging (MRI) significantly influences the source localization accuracy, co-registration error requires assessment, and quantification. Recent studies have evaluated the co-registration error of on-scalp MEG mainly based on the surface fit error or the repeatability error of different measurements, which do not reflect the true co-registration error. In this study, a three-dimensional-printed reference phantom was constructed to provide the ground truth of MEG sensor locations and orientations relative to MRI. The co-registration performances of commonly used three devices—electromagnetic digitization system, structured-light scanner, and laser scanner—were compared and quantified by the indices of final co-registration errors in the reference phantom and human experiments. Furthermore, the influence of the co-registration error on the performance of source localization was analyzed via simulations. The laser scanner had the best co-registration accuracy (rotation error of 0.23° and translation error of 0.76 mm based on the phantom experiment), whereas the structured-light scanner had the best cost performance. The results of this study provide recommendations and precautions for researchers regarding selecting and using an appropriate device for the co-registration of on-scalp MEG and MRI.

scholarly journals Automated markerless registration of point clouds from TLS and structured light scanner for heritage documentation

2019 ◽  
Vol 35 ◽  
pp. 16-24 ◽  
Author(s):  
Jie Shao ◽  
Wuming Zhang ◽  
Nicolas Mellado ◽  
Pierre Grussenmeyer ◽  
Renju Li ◽  
...  
Keyword(s):  
Structured Light ◽  
Point Clouds ◽  
Structured Light Scanner

scholarly journals A Robust Laser Stripe Extraction Method for Structured-Light Vision Sensing

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4544
Author(s):  
Congyang Zhao ◽  
Jianing Yang ◽  
Fuqiang Zhou ◽  
Junhua Sun ◽  
Xiaosong Li ◽  
...  
Keyword(s):  
Structured Light ◽  
Point Clouds ◽  
Visual Navigation ◽  
Optimal Parameters ◽  
Main Research ◽  
Vision Sensing ◽  
Laser Stripe ◽  
Vision Sensors ◽  
The Cost ◽  
Structured Light Vision

Environmental sensing is a key technology for the development of unmanned cars, drones and robots. Many vision sensors cannot work normally in an environment with insufficient light, and the cost of using multiline LiDAR is relatively high. In this paper, a novel and inexpensive visual navigation sensor based on structured-light vision is proposed for environment sensing. The main research contents of this project include: First, we propose a laser-stripe-detection neural network (LSDNN) that can eliminate the interference of reflective noise and haze noise and realize the highly robust extraction of laser stripes region. Then we use a gray-gravity approach to extract the center of laser stripe and used structured-light model to reconstruct the point clouds of laser center. Then, we design a single-line structured-light sensor, select the optimal parameters for it and build a car–platform for experimental evaluation. This approach was shown to be effective in our experiments and the experimental results show that this method is more accurate and robust in complex environment.

Sign in / Sign up

Export Citation Format

Share Document