A5054500885- Remote-Sensing Image Classification
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
- Industrial Vision Systems and Defect Detection
- Drilling and Well Engineering
- Infectious Aortic and Vascular Conditions
- Cervical Cancer and HPV Research
- Access Control and Trust
- Advanced SAR Imaging Techniques
- Image and Object Detection Techniques
- Image Enhancement Techniques
- Advanced Measurement and Detection Methods
- QR Code Applications and Technologies
- Underwater Acoustics Research
- Optical Systems and Laser Technology
- Cryptography and Data Security
- Security and Verification in Computing
- Oil and Gas Production Techniques
- Advanced biosensing and bioanalysis techniques
- AI in cancer detection
- Hydraulic Fracturing and Reservoir Analysis
- Advanced Computing and Algorithms
- E-commerce and Technology Innovations
- Robotics and Sensor-Based Localization
University of Electronic Science and Technology of China
2023-2024
Zhongyuan University of Technology
2022-2024
Shanghai Harbour Engineering Design & Research Institute
2024
Changchun University of Science and Technology
2023
University of Science and Technology of China
2022
Tsinghua University
2021
Taiyuan Maternity and Child Care Hospital
2020
Central Hospital of Wuhan
2020
Linyi University
2014
Beijing University of Posts and Telecommunications
2009
Accurate localization of objects interest in remote sensing images (RSIs) is great significance for object identification, resource management, decision-making and disaster relief response. However, many difficulties, like complex backgrounds, dense target quantities, large-scale variations, small-scale objects, which make the detection accuracy unsatisfactory. To improve accuracy, we propose an Adaptive Adjacent Context Negotiation Network (A 2 CN-Net). Firstly, composite fast Fourier...
Otsu segmentation algorithm is one of the most successful algorithms in field image processing,However, it has drawbacks such as poor dividing small object images. This paper propose a improved based on weighted smooth histogram which can ensure location threshold point more near to valley and at same time between-class variance maximum.The results show that effectively accomplish for multimodal image, get better images added Gaussian noise.
In order to reduce the loss of laser point cloud appearance contours by lightweighting, this paper takes data segment beam expressway viaduct as a sample. After comparing downsampling algorithm from many aspects and angles, voxel grid method is selected basic theory research. By combining characteristics normal vector cloud, top surface edge are extracted fused establish an optimized lightweighting algorithm. The research in shows that performs better than furthest sampling curvature...
Currently, Remote sensing object detection methods based on deep learning have been widely used in military investigation, ocean monitoring, urban planning and post-disaster relief. However, many difficulties, such as complex backgrounds, indistinguishable appearances, large-scale variations, non-uniform distributions, limit the accuracy of detectors. To deal with these problems, a key feature-enhanced network (KFENet) is proposed to improve accuracy. Specifically, multi-scale feature fusion...
In recent studies, remote sensing object detection methods based on deep learning have emerged as a primary concern in environmental monitoring, military investigation, and hazard response. However, many difficulties, such complex backgrounds, dense target quantities, large-scale variations, non-uniform distribution, lead to parameters network structures, thus limiting the accuracy of detector slowing inference speed. To address these issues, we propose lightweight efficient for images....
The modern information management systems are built on basis of the Internet, online system nearly includes all business an enterprise, and almost every employee has to complete some certain operations in system. Therefore, security plays important role running Access control is a significant component measures. We can see easily if mature reliable through its access module. RBAC96 relatively mechanism. This paper based model prototype, makes it improved with range restricted mechanism,...
A non-mechanical photoelectric tracking technology based on liquid crystal phased array was proposed. mathematical model of a closed-loop system established. The laser emits incident light specified wavelength. Incident enters the through polarizers, waveplates and other optical devices. difference between deflected beam is received with camera after array. adopts voltage control to achieve deflection purpose accurate tracking. motion state simulated target analyzed modern algorithm...
Real-time monitoring and evaluation of fractures is a core issue in the multi-stage hydraulic fracturing process for horizontal wells, which has long been focus many scholars. The pressure after pump-stopping includes water hammer seepage pressure. By installing high-frequency device at wellhead, not only drop curve, but also waveform can be completely collected. To discover information from optimize parameter Kaiser windowed cepstrum, numerical flow model fractured well (MFHW) presented...
Building detection from remote sensing images plays an important role in applications such as urban management and city planning. In recent years, deep learning basic building methods have become popular, many sophisticated are proposed with expectation of replacing tedious human labeling process. However, complex backgrounds diverse appearance impose great challenges to the detection. Automatic accurate on demand community. Considering that buildings distinct edge features, which enables...