A5101668671- Robotics and Sensor-Based Localization
- Advanced Image and Video Retrieval Techniques
- Power Line Inspection Robots
- Advanced Vision and Imaging
- Advanced SAR Imaging Techniques
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- Image Processing Techniques and Applications
- Cryospheric studies and observations
- Advanced Image Fusion Techniques
- Icing and De-icing Technologies
- Remote Sensing and Land Use
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- Advanced Computational Techniques and Applications
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Sparse and Compressive Sensing Techniques
- Remote Sensing in Agriculture
- Evaluation Methods in Various Fields
- Image Enhancement Techniques
- 3D Surveying and Cultural Heritage
- Soft Robotics and Applications
- Medical Image Segmentation Techniques
- Advanced Sensor and Control Systems
- Infrastructure Maintenance and Monitoring
Shanghai Jiao Tong University
2003-2024
University of Electronic Science and Technology of China
2022-2024
Anhui Business College
2022
Huzhou University
2022
Xihua University
2019-2021
Central South University
2018
Central South University of Forestry and Technology
2018
Yuncheng University
2012
Automatic registration for infrared, and visible images of power equipment has become a challenging work in intelligent diagnosis system the grid. Existing methods usually fail accurately aligning because resolutions, spectrums, viewpoints differences. To solve this problem, we propose novel main orientation feature points named contour angle (CAO), describe an automatic image method CAO-Coarse to Fine (CAO-C2F). CAO is based on images, invariant viewpoints, scales C2F matching obtain...
This paper studies the visual servoing problem with sensory feedback from uncalibrated stereo cameras. The linear image Jacobian matrix is used to describe spatial and temporary approximation of differential movement relation between space robotic workspace. We suggest construct an instrumental dynamic system state variables formed elements matrix. Thus a Kalman-Bucy filter estimate constructed online, which robust noise external disturbances. A 3D tracking task by robot manipulator cameras...
Intelligent inspection robots widely applied in substations are required to capture the image consistent with calibration during routine of electrical equipment. However, it is a challenging work for robot meeting requirement due navigation error and mechanical wear. To address this problem, an active pose relocalization (APR) method proposed article. Specifically, model describing relationship between pixel plane established. Then, decoupling three-stage proportional–integral control...
Image fusion has become an active and promising research topic in image processing. It provides effective way to combine several source images form a composite with more detailed information than any one of the images. An FDST-PCNN framework, which integrates finite discrete shearlet transform (FDST) pulse-coupled neural network (PCNN), is proposed possess higher ability enhance effects. We first propose structure-based saliency (SBS) map clear important features image. The SBS combines...
Conventional feature detection algorithms are largely based on clustered two-dimensional (2D) blocks of information. However, corners located at the centre gradually greying information cannot be extracted using these algorithms. The edge points described by often affected background changes, leading to significant differences in descriptors for same feature. These issues detrimental subsequent matching processes. Therefore, we propose a new method that will provide more useful corner...
Inspired by classical feature descriptors in motion matching, this paper proposes a multimodal failure matching point collection method, which is defined as FMP. FMP is, fact, of unstable features with low degree the conventional task. Based on FMP, novel model for saliency detection object developed. Models are evaluated DAVIS and SegTrackv2 datasets compared recently advanced algorithms. The comparison results demonstrate availability effectiveness saliency.
Airborne synthetic aperture radar images are easily smeared by the phase error due to unsteady platform movement. Autofocusing traditional methods is unsatisfied in critical condition of homogenous targets with large degree defocusing. This paper proposes a one-step end-to-end autofocus method base on Unet residual blocks (Res-Unet). We use SAR image certain area one scene for model training and test trained network remaining areas. Numerical experiments conducted real airborne data results...
Fisher classification and distance measurement methods are method commonly used for remote sensing monitoring of forest resources. With the advent era big data, there more related studies, but is a lack research on relationship between two. This paper takes botanical garden Central South University Forestry Technology, Hunan Province as study area. Five imaging hyperspectral images taken by SOC710 spectrometer in October November 2016 were data sources. Four samples selected from each image...