A5007372289- Image Enhancement Techniques
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Simulation and Modeling Applications
- Remote-Sensing Image Classification
- Image Processing and 3D Reconstruction
- Food Supply Chain Traceability
- Infrared Target Detection Methodologies
- Geoscience and Mining Technology
- Adversarial Robustness in Machine Learning
- Advanced Computational Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Advanced Optical Sensing Technologies
Wuhan Institute of Technology
2023-2024
Yangtze University
2016
Underwater target detection is widely used in various applications such as underwater search and rescue, environment monitoring, marine resource surveying. However, the complex environment, including factors light changes background noise, poses a significant challenge to detection. We propose an improved algorithm based on YOLOv8n overcome these problems. Our focuses three aspects. Firstly, we replace original C2f module with Deformable Convnets v2 enhance adaptive ability of region...
To address the storage capacity limitations and high costs inherent in existing single-chain model of blockchain-based traceability systems, a strategy combining on-chain off-chain using IPFS as an alternative architecture is proposed. The goal to enhance while ensuring data stability. Storing frequently accessed information helps alleviate excessive pressure on blockchain caused by high-frequency queries, security immutability data. Additionally, technology expands reduces through its...
Using the theoretical Based on Cross-Plot, Fuzzy-Math to identify lithology, logging data processing softwar-e system was prepared, which is function of management and lithology identification.Using basic from oil data, Results correct rate can reach 90%, provi-de guidance for interpretation service late Oilfield, has a certain practical value.
In lithology identification method, artificial neural network recognition results du-e to its objective and reliable, be more widely used.Study selection of BP net-work, Shen 630-H1426 logging identification, prediction accuracy 90%, with a higher magmatic rocks metamorphic crocks.Through analysis sho-ws that predict is reliable method.
Remote sensing image target detection using deep neural network has emerged as a significant area of research in recent years. However, the context remote images, it is common to encounter complex content, arbitrary orientations targets, dense arrangement and small targets. Current object detectors are susceptible both false detections missed scenes. To improve recognition accuracy, we propose an enhanced model based on YOLOv5. Firstly, utilize new CNN component called SPDConv replace...