A5059339041- Remote Sensing and LiDAR Applications
- Optical Systems and Laser Technology
- Adaptive optics and wavefront sensing
- 3D Surveying and Cultural Heritage
- Remote-Sensing Image Classification
- Satellite Image Processing and Photogrammetry
- Robotics and Sensor-Based Localization
- Remote Sensing in Agriculture
- Advanced Measurement and Metrology Techniques
- Astronomical Observations and Instrumentation
- Infrared Target Detection Methodologies
- Land Use and Ecosystem Services
- Advanced Neural Network Applications
- Advanced Computational Techniques and Applications
- Microfluidic and Bio-sensing Technologies
- Antenna Design and Optimization
- Iterative Learning Control Systems
- Supply Chain and Inventory Management
- Radio Astronomy Observations and Technology
- Image Enhancement Techniques
- Advanced Vision and Imaging
- Sustainable Supply Chain Management
- Advanced Surface Polishing Techniques
- Sensorless Control of Electric Motors
- Advanced Image and Video Retrieval Techniques
Xinxiang Medical University
2024-2025
PLA Information Engineering University
2014-2025
China Southern Power Grid (China)
2025
Harbin Institute of Technology
2021-2024
Qingdao University of Science and Technology
2022-2024
Nanjing Agricultural University
2023
Dalian Maritime University
2019-2023
Jilin Province Science and Technology Department
2021-2023
Jilin University
2021-2023
Ocean University of China
2019-2023
Recently, LiDAR (Light Detection and Ranging)-based place recognition, has been widely concerned because of its robustness to light conditions, seasonal changes, viewpoint variations. Unlike most existing methods which represent the whole point cloud scenes with global descriptors, we treat LiDAR-based recognition problem as a scene overlap prediction task propose an end-to-end network, consists feature learning backbone, enhancement module, module. Based on result for each point,...
Detecting topographic changes in an urban environment and keeping city-level point clouds up-to-date are important tasks for planning monitoring. In practice, remote sensing data often available only different modalities two epochs. Change detection between airborne laser scanning photogrammetric is challenging due to the multi-modality of input dense matching errors. This paper proposes a method detect building multimodal acquisitions. The inputs converted fed into light-weighted...
<title>Abstract</title> The gross primary productivity (GPP) of Shanxi Province, China, plays an important role in the carbon cycle Loess Plateau ecosystem. However, Province lacks flux stations, leading to imprecise GPP estimation results. Additionally, few studies have explored drivers long-term change Province. Therefore, this study, we aimed estimate from 2001 2022 and determine driving factors trends. To end, proposed improved method based on CatBoost model. Our model reduces...
Robust segmentation in adverse weather conditions is crucial for autonomous driving. However, these scenes struggle with recognition and make annotations expensive, resulting poor performance. As a result, the Segment Anything Model (SAM) was recently proposed to finely segment spatial structure of provide powerful prior information, thus showing great promise resolving problems. SAM cannot be applied directly different geographic scales non-semantic outputs. To address issues, we propose...
Detecting topographic changes in the urban environment has always been an important task for planning and monitoring. In practice, remote sensing data are often available different modalities at time epochs. Change detection between multimodal can be very challenging since show characteristics. Given 3D laser scanning point clouds 2D imagery from epochs, this paper presents a framework to detect building tree changes. First, transformed image patches, respectively. A Siamese CNN is then...
The accurate detection of relevant vehicles, pedestrians, and other targets on the road plays a crucial role in ensuring safety autonomous driving. In recent years, object detectors based Transformers or CNNs have achieved excellent performance fully supervised paradigm. However, when trained model is directly applied to unfamiliar scenes where training data testing different distributions statistically, model’s may decrease dramatically. To address this issue, unsupervised domain adaptive...
Building extraction and change detection are two important tasks in the remote sensing domain. Change between airborne laser scanning data photogrammetric is vulnerable to dense matching errors, mis-alignment errors gaps. This paper proposes an unsupervised object-based method for integrated building detection. Firstly, terrain, roofs vegetation extracted from precise point cloud, based on “bottom-up” segmentation clustering. Secondly, performed bidirectional manner: Heightened buildings...
Oil is an important resource for the development of modern society. Accurate detection oil wells great significance to investigation exploitation status and formulation plan. However, detecting small objects in large-scale high-resolution remote sensing images, such as wells, a challenging task due problems large number, limited pixels, complex background. In order overcome this problem, first, we create our own well dataset conduct experiments given lack public dataset. Second, provide...
With the rapid construction of high-speed railways (HSR), supply structure transportation modes in China has changed greatly. In order to seek sustainable development HSR and air transport from perspective passenger mode choice behavior, this paper applied a binary logit model explore patterns Beijing–Shanghai corridor, which most successfully operated line China. By using data collected airports stations two cities, flow composition behavior was analyzed. It found that passengers’...
Automatic image registration for multi-sensors has always been an important task remote sensing applications. However, images with large resolution differences not fully considered. A coarse-to-fine strategy in is presented. The consists of three phases. First, the feature-base method applied on resampled sensed and reference image. Edge point features acquired from edge strength map (ESM) are used to pre-register two quickly robustly. Second, normalized mutual information-based more...
When in orbit, spliced satellite optical cameras are affected by various factors that degrade the actual image stitching precision and accuracy of their data products. This is a major bottleneck current remote sensing technology. Previous geometric calibration research has mostly focused on stitched images largely ignored inter-chip relationship among original multi-chip images, resulting loss subsequent Therefore, this paper, novel method proposed for cameras. The integral model was...