A5100613917- Remote Sensing and LiDAR Applications
- Remote-Sensing Image Classification
- Oil Palm Production and Sustainability
- Automated Road and Building Extraction
- Energy Efficient Wireless Sensor Networks
- Remote Sensing in Agriculture
- Cellular and Composite Structures
- Opportunistic and Delay-Tolerant Networks
- Domain Adaptation and Few-Shot Learning
- Advanced Image and Video Retrieval Techniques
- Mobile Ad Hoc Networks
- Energy Harvesting in Wireless Networks
- Remote Sensing and Land Use
- Acoustic Wave Phenomena Research
- Video Surveillance and Tracking Methods
- Parallel Computing and Optimization Techniques
- Date Palm Research Studies
- Security in Wireless Sensor Networks
- Composite Structure Analysis and Optimization
- Advanced Neural Network Applications
- Hydraulic and Pneumatic Systems
- Industrial Technology and Control Systems
- Recycling and utilization of industrial and municipal waste in materials production
- Wildlife-Road Interactions and Conservation
- Advanced Sensor and Control Systems
Sun Yat-sen University
2022-2024
Jimei University
2023-2024
Huazhong University of Science and Technology
2012-2024
Guangxi University
2023-2024
Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)
2024
Lanzhou Jiaotong University
2024
Guangzhou University
2024
Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)
2024
Henan Polytechnic University
2023
Beijing Jiaotong University
2023
Oil palm trees are important economic crops in Malaysia and other tropical areas. The number of oil a plantation area is information for predicting the yield oil, monitoring growing situation maximizing their productivity, etc. In this paper, we propose deep learning based framework tree detection counting using high-resolution remote sensing images Malaysia. Unlike previous studies, our study more crowded crowns often overlap. We use manually interpreted samples to train optimize...
Automatic extraction of building footprints from high-resolution satellite imagery has become an important and challenging research issue receiving greater attention. Many recent studies have explored different deep learning-based semantic segmentation methods for improving the accuracy extraction. Although they record substantial land cover use information (e.g., buildings, roads, water, etc.), public geographic system (GIS) map datasets rarely been utilized to improve results in existing...
Land-cover mapping is an important research topic with broad applicability in the remote-sensing domain. Machine learning algorithms such as Maximum Likelihood Classifier (MLC), Support Vector (SVM), Artificial Neural Network (ANN), and Random Forest (RF) have been playing role this field for many years, although deep neural networks are experiencing a resurgence of interest. In article, we demonstrate early efforts to apply learning-based classification methods large-scale land-cover...
Being an important economic crop that contributes 35% of the total consumption vegetable oil, remote sensing-based quantitative detection oil palm trees has long been a key research direction for both agriculture and environmental purposes. While existing methods already demonstrate satisfactory effectiveness small regions, performing large region with accuracy is still challenging. In this study, we proposed two-stage convolutional neural network (TS-CNN)-based method using high-resolution...
The target of person re-identification (ReID) and gait recognition is consistent, that to match the pedestrian under surveillance cameras. For cloth-changing problem, video-based ReID rarely studied due lack a suitable benchmark, often researched controlled conditions. To tackle this we propose Cloth-Changing benchmark for Person Gait (CCPG). It dataset, there are several highlights in CCPG, (1) it provides 200 identities over 16K sequences captured indoors outdoors, (2) each identity has...
Extracting building footprints from aerial images is essential for precise urban mapping with photogrammetric computer vision technologies. Existing approaches mainly assume that the roof and footprint of a are well overlapped, which may not hold in off-nadir as there often big offset between them. In this paper, we propose an vector learning scheme, turns extraction problem into instance-level joint prediction its corresponding "roof to footprint" vector. Thus can be estimated by...
Abstract Accurate building extraction is crucial for urban understanding, but it often requires a substantial number of samples. While some datasets are available model training, there remains lack high-quality covering and rural areas in China. To fill this gap, study creates high-resolution GaoFen-7 (GF-7) Building dataset utilizing the Chinese GF-7 imagery from six cities. The comprises 5,175 pairs 512 × image tiles, 573.17 km 2 . It contains 170,015 buildings, with 84.8% buildings 15.2%...
Oil palm plantation mapping is an important task in land planning and management Malaysia. Most existing studies were based on satellite images using traditional machine learning or image segmentation methods. In order to obtain finer oil maps from high spatial-resolution images, we proposed a novel deep learning-based semantic approach, named Residual Channel Attention Network (RCANet). It consists of encoder-decoder architecture post-processing component. The Unit (RCAU) designed our...
This paper describes our proposed building extraction method in DeepGlobe - CVPR 2018 Satellite Challenge. We a semantic segmentation and ensemble learning based for high resolution satellite images. Several public GIS map datasets were utilized through combining with the multispectral WorldView- 3 image improving results. Our achieves overall prediction score of 0.701 on test dataset Building Extraction
Oil palm is of great importance in agricultural productivity for many tropic developing countries and accordingly investigating as well counting oil palms a meaningful valuable research. In this paper, we firstly apply Faster-RCNN, one the most popular object detection algorithms, to detect tree crowns from satellite images. Although Faster-RCNN has an excellent performance well-known datasets general detection, it does not have obvious advantages study compared with other classical machine...
Conical shell structures are commonly used in many engineering systems, and vibration suppression is very important to realize the desired function. In this study, piezoelectric ceramics were as actuators/sensors with a multimodal fuzzy sliding mode controller suppress vibrations of conical structure for first time. The structure’s natural frequencies shapes obtained through modal analysis using finite element method verified by tests. agreement between test results was appropriate. A...