A5101654064- Advanced Image and Video Retrieval Techniques
- Infrared Target Detection Methodologies
- Robotics and Sensor-Based Localization
- Advanced Aircraft Design and Technologies
- Computational Geometry and Mesh Generation
- Chromosomal and Genetic Variations
- Advanced Neural Network Applications
- Multimodal Machine Learning Applications
- Optical Systems and Laser Technology
- Fire effects on ecosystems
- Advanced Measurement and Detection Methods
- Soil Carbon and Nitrogen Dynamics
- Electrohydrodynamics and Fluid Dynamics
- Advanced Graph Neural Networks
- Peatlands and Wetlands Ecology
- Microtubule and mitosis dynamics
- Medical Image Segmentation Techniques
- 3D Surveying and Cultural Heritage
- Remote-Sensing Image Classification
- Combustion and flame dynamics
- Image and Video Stabilization
- Genomics and Chromatin Dynamics
Chinese Academy of Sciences
2018-2025
Northeastern University
2022-2025
Liaoning University of Technology
2025
Shenyang Institute of Automation
2022-2025
University of Chinese Academy of Sciences
2024
Hefei National Center for Physical Sciences at Nanoscale
2018
Morehouse School of Medicine
2018
Northeast Forestry University
2016
In recent years, the continuous advancement of deep learning has led to significant progress in object-detection technology for remote-sensing images. However, most current detection methods passively perform on input image without considering relationship between imaging configurations and detection-algorithm performance. Therefore, when factors such as poor lighting conditions, extreme shooting angles, or long acquisition distances degrade quality, passive framework limits effectiveness...
Spray booms can often tilt during operation due to factors such as uneven ground, tires deformation and crop canopy structure height, adversely affecting droplet deposition. Therefore, it is crucial study understand how spray height nozzle angle affect deposition enhance the effectiveness of Plant Protection Products (PPPs) application. The TeeJet®XR8002 was selected research object, simulations tests were conducted at three heights (0.5, 0.6, 0.8 m) 10 angles (1°~10°). film length used...
Remote sensing image analysis has drawn more attentions in the field of computer vision. At present, methods commonly used remote are mainly at a low level semantically. The scene graph is an abstraction objects and their relationships, which high understanding task. To fully comprehend meanings images, this paper, we propose novel <i>Segmentation-based model to generate Scene Graphs (SRSG)</i>. In SRSG model, complete accurate generated with segmentation results as inputs, while shapes...
Active reconstruction can be considered as an intelligent perception problem that seeks to optimize the efficiency of modeling tasks by adjusting configuration vision system on robotic platform automatically. We consider a feature several local surfaces have same kinds characteristics. A standard geometry defined attributes abstracted from set features. For regular category, descriptions and topological relations about these objects' features are known before tasks. In order maximize...
Little is known about how N deposition affects greenhouse gas balances in different temporal patterns (daytime and nighttime),and few studies have been conducted to quantify the effects of on soil CH 4 uptake CO 2 emission a typical temperate forests.To investigate emission, simulated experiment was initiated forests Northeastern China May 2011.In this study, NH NO 3 fertilizer applied throughout growing season at four treatment levels (three replicates): control (CK), no added N; low-N (T L...