Jie Liu

ORCID: 0000-0002-4440-2162
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Video Surveillance and Tracking Methods
  • Fire Detection and Safety Systems
  • Advanced Neural Network Applications
  • Geotechnical Engineering and Analysis
  • Geology and Paleoclimatology Research
  • Human Pose and Action Recognition
  • Oceanographic and Atmospheric Processes
  • Water Quality Monitoring and Analysis
  • Water Quality Monitoring Technologies
  • Climate variability and models
  • Geoscience and Mining Technology
  • Grouting, Rheology, and Soil Mechanics
  • Fire dynamics and safety research
  • Face recognition and analysis
  • Civil and Geotechnical Engineering Research
  • Evacuation and Crowd Dynamics
  • Advanced Sensor and Control Systems
  • Spectroscopy and Chemometric Analyses
  • Geomechanics and Mining Engineering
  • Mineral Processing and Grinding
  • Fire effects on ecosystems
  • Geotechnical Engineering and Underground Structures

China Three Gorges University
2024

Nanjing University of Information Science and Technology
2019-2023

Shandong Jianzhu University
2023

China Construction Eighth Engineering Division (China)
2023

Kunming University of Science and Technology
2013-2022

Since remote sensing images of post-fire vegetation are characterized by high resolution, multiple interferences, and similarities between the background target area, it is difficult for existing methods to detect segment burned area in these with sufficient speed accuracy. In this paper, we apply Salient Object Detection (SOD) segmentation, first time has been done, propose an efficient segmentation network (BASNet) improve performance unmanned aerial vehicle (UAV) high-resolution image...

10.1109/tgrs.2022.3197647 article EN IEEE Transactions on Geoscience and Remote Sensing 2022-01-01

Person re-identification (re-ID) aims to match the same person across different cameras. However, most existing re-ID methods assume that people wear clothes in views, which limit their performance identifying target pedestrians who change clothes. Cloth-changing is a quite challenging problem as occupying large number of pixels an image becomes invalid or even misleads information. To tackle this problem, we propose novel Multi-biometric Unified Network (MBUNet) for learning robustness...

10.1109/tip.2023.3279673 article EN IEEE Transactions on Image Processing 2023-01-01

Oceanic mesoscale cyclonic (anticyclonic) eddies usually have cold (warm) cores and counterclockwise (clockwise) flow fields in the Northern Hemisphere. However, “abnormal” with warm (cold) recently been identified Kuroshio-Oyashio Extension (KOE) region. Here, traditional cold-core (CCEs) anticyclonic warm-core (AWEs) are termed normal eddies, (CWEs) (ACEs) called abnormal eddies. Applying a vector geometry-based automatic eddy detection method to Ocean General Circulation Model for Earth...

10.3389/fmars.2022.984244 article EN cc-by Frontiers in Marine Science 2022-08-26

Person re-identification (re-ID) aims at matching the same person across different cameras. Most of existing meth-ods for re- ID assume that people wear clothes on However, Cloth-Changing is a quite challenging problem since are likely to change as time span increases. To tackle this problem, Multi-Biometric Unified Network (MBUNet) proposed ex-ploit clothing-unrelated cues. We firstly introduce multi-biological feature branch extracting variety biological features, such head, neck, and...

10.1109/icme52920.2022.9859702 article EN 2022 IEEE International Conference on Multimedia and Expo (ICME) 2022-07-18

The North Pacific Subtropical Countercurrent area (STCC) is high in mesoscale eddy activities. According to the rotation direction of flow field and sign temperature anomaly within eddy, they can be divided into four categories: cyclonic cold-core (CCE), anticyclonic warm-core (AWE), (CWE) (ACE). CCE AWE are called normal eddies, CWE ACE named abnormal eddies. Based on OFES data vector geometry automatic detection method, we find that at sea surface, maximum monthly number CCE, AWE, CWE,...

10.3389/fmars.2023.1121731 article EN cc-by Frontiers in Marine Science 2023-01-24

Ultraviolet-visible (UV-Vis) spectroscopy technology is used to measure chemical oxygen demand (COD) of water. The standard samples are prepared using potassium hydrogen phthalate. With different pretreatment methods and various modeling methods, the COD prediction models' performance based on raw spectra compared, sensitive wavelengths selected basis results. In order build models with optimal performance, water quality parameters' effects detection also researched, experiments carried out...

10.1117/12.2548522 article EN 2019-11-13

High-ground stress soft rock tunnels have experienced large deformations. Yielding and pressure relief fluid-filled lining support technology is an effective method for solving tunnel deformation due to the characteristics of high-ground tunnels. To give surrounding a certain amount space, layer fluid filling set up at reserved tunnel. By creating force test model inflatable carcass water-filled carcass, straight section structure simulated. When supporting tunnels, carcasses produce...

10.24200/sci.2024.61505.7350 article EN Scientia Iranica 2024-04-28

By combining artificial neural network with deep learning technology, convolution is characterized by local perception, adaptive feature extraction and end-to-end application, etc., it has been used in image recognition target detection more recent years. Problems are existing widely the traditional safety helmet algorithm generally such as severe background interference, complex computing, high time-complexity largely fluctuant accuracy. A detective method for based on was proposed this...

10.1117/12.2564896 article EN Sixth Symposium on Novel Optoelectronic Detection Technology and Applications 2020-04-17

The safety and reliability of a ventilation system relies on an accurate friction resistance coefficient (α), but obtaining α requires great deal tedious measurement work in order to determine the result, many erroneous data are obtained. Therefore, it is vital that be obtained quickly accurately for design. In this study, passive active support indicator was constructed prediction α. An RF model, GSCV-RF model BP were using algorithm, GSCV algorithm neural network, respectively, prediction....

10.3390/app122312487 article EN cc-by Applied Sciences 2022-12-06

A large amount of processing data was accumulated within plant processing. And its necessary to use this for as well administration. In article the mining technology and utilization were discussed, according research results, fitting relationship is:Cu recovery (%)= -1.1221*lime dosage (Kg/t)+92.6, lime alteration effect on copper are 1.41% absolutely 1.66% relatively. The concentrate grade 0.0554*lime (Kg/t)+19.271, 0.070% 0.36% It can be concluded that has a great recovery, is relative...

10.4028/www.scientific.net/amm.411-414.1040 article EN Applied Mechanics and Materials 2013-09-01

Abstract The construction of shield tunnel will adversely affect the surrounding soil and is prone to safety accidents. This paper focuses on problem deformation induced by construction. Based theoretical mechanics Mindlin solution, caused frontal thrust, friction force formation loss linearly superimposed, accurate calculation formula derived in time space. Relying finite element software Midas GTS NX, three-dimensional dynamic simulation double-line was carried out, law stratigraphic...

10.1088/1742-6596/2468/1/012177 article EN Journal of Physics Conference Series 2023-04-01

The droplet analysis technology and the detection principles of water quality parameters are combined to achieve quantitative multi-parameter water. platform is designed based on fiber capacitance technology, which mainly composed sensor, dissolved oxygen probe, liquid supply pump, photoelectric conversion elements, signal processing circuit. three (refractive index, turbidity oxygen) carried out this through experiments. For water, sample's rainbow-peak value fingerprint obtained with...

10.1117/12.2548545 article EN 2019-11-13
Coming Soon ...