scholarly journals Dynamic Workpiece Modeling with Robotic Pick-Place Based on Stereo Vision Scanning Using Fast Point-Feature Histogram Algorithm

2021 ◽  
Vol 11 (23) ◽  
pp. 11522
Author(s):  
Quoc-Trung Do ◽  
Wen-Yang Chang ◽  
Li-Wei Chen
Keyword(s):  
Stereo Vision ◽  
Point Cloud ◽  
Intelligent System ◽  
Rapid Development ◽  
Average Error ◽  
Automatic Production ◽  
Depth Cameras ◽  
Dynamic Task ◽  
Cloud Models ◽  
Point Feature

In the era of rapid development in industry, an automatic production line is the fundamental and crucial mission for robotic pick-place. However, most production works for picking and placing workpieces are still manual operations in the stamping industry. Therefore, an intelligent system that is fully automatic with robotic pick-place instead of human labor needs to be developed. This study proposes a dynamic workpiece modeling integrated with a robotic arm based on two stereo vision scans using the fast point-feature histogram algorithm for the stamping industry. The point cloud models of workpieces are acquired by leveraging two depth cameras, type Azure Kinect Microsoft, after stereo calibration. The 6D poses of workpieces, including three translations and three rotations, can be estimated by applying algorithms for point cloud processing. After modeling the workpiece, a conveyor controlled by a microcontroller will deliver the dynamic workpiece to the robot. In order to accomplish this dynamic task, a formula related to the velocity of the conveyor and the moving speed of the robot is implemented. The average error of 6D pose information between our system and the practical measurement is lower than 7%. The performance of the proposed method and algorithm has been appraised on real experiments of a specified stamping workpiece.

scholarly journals SEMANTIC SEGMENTATION OF INDOOR 3D POINT CLOUD WITH SLENET

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 785-791
Author(s):  
Y. Ding ◽  
X. Zheng ◽  
H. Xiong ◽  
Y. Zhang
Keyword(s):  
Point Cloud ◽  
Graphical Model ◽  
Rapid Development ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
3D Point Cloud ◽  
3D Point Clouds ◽  
Cloud Models ◽  
Semantic Transfer ◽  
Class Segmentation

<p><strong>Abstract.</strong> With the rapid development of new indoor sensors and acquisition techniques, the amount of indoor three dimensional (3D) point cloud models was significantly increased. However, these massive “blind” point clouds are difficult to satisfy the demand of many location-based indoor applications and GIS analysis. The robust semantic segmentation of 3D point clouds remains a challenge. In this paper, a segmentation with layout estimation network (SLENet)-based 2D&amp;ndash;3D semantic transfer method is proposed for robust segmentation of image-based indoor 3D point clouds. Firstly, a SLENet is devised to simultaneously achieve the semantic labels and indoor spatial layout estimation from 2D images. A pixel labeling pool is then constructed to incorporate the visual graphical model to realize the efficient 2D&amp;ndash;3D semantic transfer for 3D point clouds, which avoids the time-consuming pixel-wise label transfer and the reprojection error. Finally, a 3D-contextual refinement, which explores the extra-image consistency with 3D constraints is developed to suppress the labeling contradiction caused by multi-superpixel aggregation. The experiments were conducted on an open dataset (NYUDv2 indoor dataset) and a local dataset. In comparison with the state-of-the-art methods in terms of 2D semantic segmentation, SLENet can both learn discriminative enough features for inter-class segmentation while preserving clear boundaries for intra-class segmentation. Based on the excellence of SLENet, the final 3D semantic segmentation tested on the point cloud created from the local image dataset can reach a total accuracy of 89.97%, with the object semantics and indoor structural information both expressed.</p>

scholarly journals OICP: An Online Fast Registration Algorithm Based on Rigid Translation Applied to Wire Arc Additive Manufacturing of Mold Repair

Materials ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 1563
Author(s):  
Ruibing Wu ◽  
Ziping Yu ◽  
Donghong Ding ◽  
Qinghua Lu ◽  
Zengxi Pan ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Point Cloud ◽  
Point Clouds ◽  
Iterative Closest Point ◽  
Multiple Point ◽  
Icp Algorithm ◽  
Registration Algorithm ◽  
Cloud Models ◽  
Comparison Results ◽  
Wire Arc Additive Manufacturing

As promising technology with low requirements and high depositing efficiency, Wire Arc Additive Manufacturing (WAAM) can significantly reduce the repair cost and improve the formation quality of molds. To further improve the accuracy of WAAM in repairing molds, the point cloud model that expresses the spatial distribution and surface characteristics of the mold is proposed. Since the mold has a large size, it is necessary to be scanned multiple times, resulting in multiple point cloud models. The point cloud registration, such as the Iterative Closest Point (ICP) algorithm, then plays the role of merging multiple point cloud models to reconstruct a complete data model. However, using the ICP algorithm to merge large point clouds with a low-overlap area is inefficient, time-consuming, and unsatisfactory. Therefore, this paper provides the improved Offset Iterative Closest Point (OICP) algorithm, which is an online fast registration algorithm suitable for intelligent WAAM mold repair technology. The practicality and reliability of the algorithm are illustrated by the comparison results with the standard ICP algorithm and the three-coordinate measuring instrument in the Experimental Setup Section. The results are that the OICP algorithm is feasible for registrations with low overlap rates. For an overlap rate lower than 60% in our experiments, the traditional ICP algorithm failed, while the Root Mean Square (RMS) error reached 0.1 mm, and the rotation error was within 0.5 degrees, indicating the improvement of the proposed OICP algorithm.

Image Processing Based on Three-Dimensional Stereo Vision

2014 ◽  
Vol 556-562 ◽  
pp. 5017-5020
Author(s):  
Ting Ting Wang
Keyword(s):  
Image Processing ◽  
Binocular Vision ◽  
Stereo Vision ◽  
Error Rate ◽  
Three Dimensional ◽  
Processing Method ◽  
Stereoscopic Vision ◽  
Average Error ◽  
Traditional Model ◽  
Average Error Rate

Three-dimensional stereo vision technology has the capability of overcoming drawbacks influencing by light, posture and occluder. A novel image processing method is proposed based on three-dimensional stereoscopic vision, which optimizes model on the basis of camera binocular vision and in improvement of adding constraints to traditional model, moreover ensures accuracy of later location and recognition. To verify validity of the proposed method, firstly marking experiments are conducted to achieve fruit location, with the result of average error rate of 0.65%; and then centroid feature experiments are achieved with error from 5.77mm to 68.15mm and reference error rate from 1.44% to 5.68%, average error rate of 3.76% while the distance changes from 300mm to 1200mm. All these data of experiments demonstrate that proposed method meets the requirements of three-dimensional imageprocessing.

scholarly journals Prediction Study of Tianjin Port Throughput Based on GM (1, 1) Extended Model

2021 ◽  
Vol 2066 (1) ◽  
pp. 012089
Author(s):  
Yahui Wang ◽  
Zhuoyi Zhang
Keyword(s):  
Large Scale ◽  
Raw Materials ◽  
Rapid Development ◽  
Development Planning ◽  
Average Error ◽  
Extended Model ◽  
Container Transportation ◽  
Important Indicator ◽  
Change Trend ◽  
Cargo Throughput

Abstract Tianjin Port is the largest comprehensive main hub port and one of the main transshipment ports for energy and raw materials transportation in northern China. It has freight business with many countries. At the same time, Tianjin Port is the first port to carry out international maritime container transportation in China’s coastal areas. Tianjin Port was built in the 1950s, and the container business has been started since 1973, In recent years, with the rapid development of large-scale, intensive and intelligent container ships in Tianjin Port, cargo throughput is an important indicator in the comprehensive evaluation of port development, which represents the development level of a port. At the same time, it also brings new tasks to the navigation guarantee work, in particular, it puts forward systematic requirements for port and wharf construction, navigation aids layout, navigation aids efficiency display and navigation aids base layout. The annual throughput of port cargo or container is one of the bases of world ports. As an output index, port enterprises, shipping companies, navigation guarantee departments and shipping economic analysis departments attach great importance to it. Therefore, the prediction of Tianjin Port cargo throughput can provide reference for Tianjin Port’s next development planning, waterway use and navigation guarantee planning and layout, navigation aids setting, wharf construction, route mapping, etc. the article constructs of Tianjin Port. The average error is 0.29%, and the prediction accuracy is first class. This model can better predict the change trend of cargo for Tianjin Port, which is a better way to analyze the change trend for Tianjin port.

scholarly journals VISUALIZATION OF POINT CLOUD MODELS IN MOBILE AUGMENTED REALITY USING CONTINUOUS LEVEL OF DETAIL METHOD

2020 ◽  
Vol XLIV-4/W1-2020 ◽  
pp. 167-170
Author(s):  
L. Zhang ◽  
P. van Oosterom ◽  
H. Liu
Keyword(s):  
Augmented Reality ◽  
Point Cloud ◽  
Cloud Model ◽  
Point Clouds ◽  
Level Of Detail ◽  
Mobile Augmented Reality ◽  
Cloud Models ◽  
Point Cloud Model ◽  
Visual Artifacts ◽  
Mobile Ar

Abstract. Point clouds have become one of the most popular sources of data in geospatial fields due to their availability and flexibility. However, because of the large amount of data and the limited resources of mobile devices, the use of point clouds in mobile Augmented Reality applications is still quite limited. Many current mobile AR applications of point clouds lack fluent interactions with users. In our paper, a cLoD (continuous level-of-detail) method is introduced to filter the number of points to be rendered considerably, together with an adaptive point size rendering strategy, thus improve the rendering performance and remove visual artifacts of mobile AR point cloud applications. Our method uses a cLoD model that has an ideal distribution over LoDs, with which can remove unnecessary points without sudden changes in density as present in the commonly used discrete level-of-detail approaches. Besides, camera position, orientation and distance from the camera to point cloud model is taken into consideration as well. With our method, good interactive visualization of point clouds can be realized in the mobile AR environment, with both nice visual quality and proper resource consumption.

scholarly journals Point-Cloud Models of Historical Barns – Spatial Discrepancies of Laser Scanning versus Robotic Total Station

10.29007/2493 ◽  
2020 ◽  
Author(s):  
Gustavo Maldonado ◽  
Marcel Maghiar ◽  
Brent Tharp ◽  
Dhruv Patel
Keyword(s):  
Service Learning ◽  
Point Cloud ◽  
Laser Scanning ◽  
3D Point Cloud ◽  
Spatial Accuracy ◽  
Total Station ◽  
Cloud Models ◽  
Bulloch County ◽  
Southern University ◽  
Robotic Total Station

This study considers the generation of virtual, 3D point-cloud models of seven deteriorating historical, agricultural barns in Bulloch County, Georgia, USA, for preservation purposes. The work was completed as a service-learning project in a course on Terrestrial Light Detection and Ranging (T-LiDAR), offered at Georgia Southern University. The resulting models and fly-through videos were donated to Bulloch County Historical Society and to the Georgia Southern Museum, to make them available to the general public and future generations. Additionally, one of the seven barns was selected to be extensively measured to estimate the relative spatial accuracy of all seven resulting 3D point-cloud models, with respect to measurements completed with a highly accurate instrument. Three accurate benchmarks were established around it for georeferencing purposes. The positions of 44 points were measured in the field via an accurate, one- second, robotic total-station (RTS) instrument. Also, the coordinates of the same points were acquired from within georeferenced and non-georeferenced point-cloud models. These points defined 259 distances. They were compared to determine their discrepancy statistics. It was observed that this process produced virtual models with an approximate maximum spatial discrepancy of one-half inch (0.5 in) with respect to measurements performed by a highly accurate RTS device. There were no substantial differences in the relative accuracies of the georeferenced and non-georeferenced models.

Parameter Estimation of an High Performance I.M. Drive for Sensorless Operation

2016 ◽  
pp. 325-346
Author(s):  
Monika Dixit ◽  
Smita Shandilya
Keyword(s):  
High Performance ◽  
Intelligent System ◽  
Rapid Development ◽  
Electric Energy ◽  
Digital Signal ◽  
Motor Drive ◽  
Switching Converters ◽  
Processing Power ◽  
Ac Motor ◽  
Energy Processing

A modern AC motor drive is a very intelligent system which covers a wide range of different electro technical apparatus and a wide scope of electrical engineering skills. A modern AC motor drive consists of four closely acting main parts: the AC machine, the power electronics, the motor control algorithm and the control hardware, i.e. the signal electronics. The advances in semiconductors and microelectronics have made the rapid development of AC motor drives possible. Semiconductors used in the switching converters provide the electric energy processing capability and microcontrollers and digital signal processors provide the data processing power for complex control algorithms.

Point Cloud Registration Algorithm Based on Extended Point Feature Histogram Feature

2019 ◽  
Vol 56 (24) ◽  
pp. 241503
Author(s):  
汤慧 Tang Hui ◽  
周明全 Zhou Mingquan ◽  
耿国华 Geng Guohua
Keyword(s):  
Point Cloud ◽  
Point Cloud Registration ◽  
Registration Algorithm ◽  
Histogram Feature ◽  
Extended Point ◽  
Point Feature

The Study of Prediction of Agricultural Source Pollution Emissions of Ammonia Nitrogen (AN) and Chemical Oxygen Demand (COD) Based on Bionic Neural Network Algorithm

2013 ◽  
Vol 461 ◽  
pp. 544-552 ◽  
Author(s):  
Hong Peng Guo ◽  
Gan Yu Feng ◽  
Chun Xia Liu ◽  
Xiao Yi Zhang
Keyword(s):  
Neural Network ◽  
Chemical Oxygen Demand ◽  
Rapid Development ◽  
Oxygen Demand ◽  
Ammonia Nitrogen ◽  
Average Error ◽  
Research Results ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Pollution Emissions

Nearly 40% of Chinese water pollution comes from agricultural sources of pollution, and the annual emissions are difference. If we want to control pollution emissions effectively, we need to accurately predict the amount of agricultural emissions of Ammonia Nitrogen (AN) and Chemical Oxygen Demand (COD). Due to the complex mechanism of the agricultural non-point source pollution, its emissions are very difficult to measure. Currently, the Bionics Research is in a stage of rapid development, and it continues to expand into many new areas of research. So the comprehensive study of Bionics and pollutant control study will be a good choice. This research used bionic BP（Back Propagation） neural network algorithm, and used pollution census data from 2002 to 2007 and established neural network model with neural network algorithm. And we predicted the agricultural sources of emissions of AN and COD with the data from 2008 to 2010. Finally we compared the predicted value and the actual value. Research results showed that, with using the bionic BP neural network, agricultural sources emissions of AN and COD are evaluated actually and the results indicate that the average error is under 5.0%. Research results proved that the model is effective. The neural network is a scientific predict method for the agricultural sources emissions of AN and COD. It can be widely used in the prediction of agricultural sources emissions of AN and COD.

Sign in / Sign up

Export Citation Format

Share Document