A5103115583- Remote Sensing and LiDAR Applications
- Smart Agriculture and AI
- Advanced Vision and Imaging
- Remote Sensing in Agriculture
- Image and Video Stabilization
- Scientific Research and Philosophical Inquiry
- Image Processing Techniques and Applications
- 3D Shape Modeling and Analysis
- RNA and protein synthesis mechanisms
- Mass Spectrometry Techniques and Applications
- Advanced Sensor and Energy Harvesting Materials
- QR Code Applications and Technologies
- Explainable Artificial Intelligence (XAI)
- Advanced Measurement and Detection Methods
- Neuroscience and Neural Engineering
- 3D Surveying and Cultural Heritage
- Tactile and Sensory Interactions
- Anomaly Detection Techniques and Applications
- Advanced Welding Techniques Analysis
- Simulation and Modeling Applications
- Leaf Properties and Growth Measurement
- Sentiment Analysis and Opinion Mining
- Machine Learning in Bioinformatics
- Automated Road and Building Extraction
- Outsourcing and Supply Chain Management
Nanjing University of Aeronautics and Astronautics
2024
Donghua University
2019-2020
Changsha University of Science and Technology
2018
Fuzhou University
2017
Nanjing University
2005-2008
Beijing Institute of Technology
2002
University of South Carolina
2000
Learning and extracting high-level features from point cloud is the key to improving segmentation performances on clouds for many networks. At present, networks present very deep structures extract 3D perception. However, we argue that even better results can be achieved by (i) building feature vectors integrates multi-scale geometric features, (ii) exerting discriminative constraints learning of mid-levels features. In this paper, propose a Multi-scale Neighborhood Feature Extraction...
As a plant organ with the largest surface area, leaves are main place where photosynthesis and respiration take place. High-throughput phenotyping of crop is great significance for breeding, growth monitoring, increasing yield. Due to highly complex diversified structures, automated leaf segmentation phenotypic feature extraction remain be challenging tasks. In this article, we propose novel five-stage framework that comprises multiview stereo point cloud reconstruction, preprocessing, stems...
Automatic leaf segmentation, as well identification and classification methods that built upon it, are able to provide immediate monitoring for plant growth status guarantee the output. Although 3D point clouds contain abundant phenotypic features, leaves usually distributed in clusters sometimes seriously overlapped canopy. Therefore, it is still a big challenge automatically segment each individual from highly crowded canopy phenotyping purposes. In this work, we propose an...
The widespread use of barcode technology has led to the complexity application scenario. In traditional recognition method, there is no universal solution problems uneven illumination, distortion, and sheltered. this paper, deep learning theory used solve problem detection under above situation. And on basis, correcting linear distortion Data Matrix code solved, key complex situation broken through. After testing, speed reached 125ms, accuracy about 93%. system uses CCD camera collect...
Point-of-Interest (POI) recommendation, an important research hotspot in the field of urban computing, plays a crucial role construction. While understanding process users’ travel decisions and exploring causality POI choosing is not easy due to complex diverse influencing factors scenarios. Moreover, spurious explanations caused by severe data sparsity, i.e., misrepresenting universal relevance as causality, may also hinder us from decisions. To this end, article, we propose factor-level...
A tactile sensor with both very high resolution and compliance is presented. The utilizes the properties of optical reflection mechanical clear rubber, has a compact structure. gripper two sensors linked to image processing system been designed. It can be used acquire binary sequences. contact shape recovery gripping force estimate, based on sequences, are also discussed.
This paper presents a hybrid cameras visual servo robot system, which combines both Eye-in-hand and Eye-to-hand cameras, to perform the task of picking precise placing for moving workpieces on conveyor belt. The camera is applied capture images that evaluate velocity detect position error gripper workpieces. measured by using geometry algorithm calculated pinhole imaging mode. Since lots errors, including image processing, structure gripper, calculation velocity, etc, exist in it necessary...
With the increasing development of software outsourcing (SO) in many countries, competition between different vendees is very fierce. This paper provides a nontechnical analysis ways that competitive intelligence (CI) system can be used by SO receivers to acquire information competitors, market and industry order gain perpetual advantages. A conceptual model designed with an insightful structure both intangible tangible measures. Detailed measures are enunciated 3 parts: environmental...
Automatic leaf segmentation, as well identification and classification methods that built upon it, are able to provide immediate monitoring for plant growth status guarantee the output. Although 3D point clouds contain abundant phenotypic features, leaves usually distributed in clusters sometimes seriously overlapped canopy. Therefore, it is still a big challenge automatically segment each individual from highly crowded canopy phenotyping purposes. In this work, we propose an...