Search

Your search keyword '"Chen, Zongyang"' showing total 12 results
Start Over Author "Chen, Zongyang"
12 results on '"Chen, Zongyang"'

1. ReLoc-PDR: Visual Relocalization Enhanced Pedestrian Dead Reckoning via Graph Optimization

Author

Chen, Zongyang, Pan, Xianfei, and Chen, Changhao

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition
Abstract

Accurately and reliably positioning pedestrians in satellite-denied conditions remains a significant challenge. Pedestrian dead reckoning (PDR) is commonly employed to estimate pedestrian location using low-cost inertial sensor. However, PDR is susceptible to drift due to sensor noise, incorrect step detection, and inaccurate stride length estimation. This work proposes ReLoc-PDR, a fusion framework combining PDR and visual relocalization using graph optimization. ReLoc-PDR leverages time-correlated visual observations and learned descriptors to achieve robust positioning in visually-degraded environments. A graph optimization-based fusion mechanism with the Tukey kernel effectively corrects cumulative errors and mitigates the impact of abnormal visual observations. Real-world experiments demonstrate that our ReLoc-PDR surpasses representative methods in accuracy and robustness, achieving accurte and robust pedestrian positioning results using only a smartphone in challenging environments such as less-textured corridors and dark nighttime scenarios., Comment: 11 pages, 14 figures

Published
2023

3. Deep Learning Based Visual-Inertial Odometry with External Attention Mechanism

Author

Tu, Zheming, Chen, Changhao, Pan, Xianfei, Chen, Zongyang, Chu, Chaoqun, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Yan, Liang, editor, and Deng, Yimin, editor

Published
2023
Full Text
View/download PDF

8. Research on Detection Method of Coating Defects Based on Machine Vision

Author

Chen Zongyang, Ruihui Peng, Guangping Wang, Yongsheng Lv, Zhao Hui, and Jianjun Sha

Subjects
Accuracy and precision, Artificial neural network, Machine vision, business.industry, Computer science, Feature extraction, Process (computing), Pattern recognition, engineering.material, Convolutional neural network, Machine vision system, Coating, engineering, Artificial intelligence, business
Abstract

Aiming at the problems in the current coating surface defects detection that it is difficult to characterize the defect features, furthermore the detection accuracy and efficiency are hard to meet industrial demand, in this paper, a machine vision system for coating defects detection is designed; then, a coating defects classification method based on convolutional neural network which is trained and tested through cross-validation to realize the classification of multi-type coating defects, is proposed. According to the collected coating dataset including defect-free coating and four types coating defects: crack coating, running coating, orange peeling coating and adhesion failure coating, the classification performance of multi-type convolutional neural networks is analyzed experimentally. Among the five convolutional neural networks, Resnet50 achieves the best detection effect, precision: 95.0% and accuracy: 97.9%. The detection performance of Densenet121 is similar to Resnet50’s, but the model size of Densenet121 is only 1/3 of former’s; furthermore, these two types of networks are tested on captured coating defects in actual spraying process, the average precision and accuracy of classification were 93.3% and 97.3%, 91.8% and 96.7%, respectively, and the detection time for each image is 0.028s and 0.025s, respectively. Therefore, Experiments prove that the purposed method is convenient and quick to detect coating surface defects, and it has high precision and accuracy. Thus, the method can be used for industrial site detection.

Published
2021

12. Fine‐grained gravity flow deposits and their depositional processes: A case study from the Cretaceous Nenjiang Formation, Songliao Basin, NE China.

Author

Tian, Xing, Gao, Yuan, Li, Zhiyang, Carlos, Zavala, Chen, Zongyang, Huang, Yongjian, Yu, Enxiao, and Wang, Chengshan

Subjects
SEDIMENTARY structures, MUDSTONE, LITHOFACIES, GRAVITY, GRAIN size
Abstract

The Songliao Basin in NE China is a large rift basin filled with Cretaceous terrestrial sediments. Lacustrine mudstones of the Nenjiang Formation form an important source rock in the Cretaceous Songliao Basin. These shales are commonly thought to have been deposited in deep, quiet, and anoxic environments. Samples obtained from the core of the SK‐2 scientific borehole provide critical insights to understand the hydrodynamic and hydroclimatic environments, which are, however, different from the traditional views regarding the deposition of these rocks. By following a mudstone description guide, five different mudstone lithofacies (LF) transported and deposited by muddy hyperpycnal flows and muddy debris flows were recognized. They are laminated fine mudstone (LF1), laminated medium mudstone (LF2), and laminated coarse mudstone (LF3) showing pairs of inverse grading (Ha) and normal grading (Hb) under the microscope, graded coarse mudstone (LF4) and massive coarse mudstone (LF5). We found that mudstones of the First Member of the Nenjiang Formation are dominated by siliciclastic detritus and argillaceous components and show frequent variations in grain size. Because large‐scale sub‐lacustrine channels travelling long distance (>80 km) were widely distributed in the Songliao palaeolake during the deposition of the Nenjiang Formation, fluctuations in mudstone grain size might have been caused by velocity fluctuations in flows. Sedimentary structures and textures preserved in mudstones of the First Member of the Nenjiang Formation indicate that the majority of these lithofacies were accumulated by muddy hyperpycnal flows and muddy debris flows. Therefore, a depositional model dominantly influenced by muddy hyperpycnal flows and debris flows is proposed. This work not only provides a new view for the depositional process of mudstones of the Songliao Basin, NE China, but also give insights to understand lacustrine palaeoenvironment and terrestrial palaeoclimate. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results