A5101700978- Image Enhancement Techniques
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- Water Quality Monitoring Technologies
- Image and Signal Denoising Methods
- Pharmaceutical and Antibiotic Environmental Impacts
- Advanced Image Fusion Techniques
- Image Processing Techniques and Applications
- Underwater Vehicles and Communication Systems
- Advanced Neural Network Applications
- Robotic Path Planning Algorithms
- Underwater Acoustics Research
- Effects and risks of endocrine disrupting chemicals
- Face and Expression Recognition
- Hand Gesture Recognition Systems
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Visual Attention and Saliency Detection
- Blind Source Separation Techniques
- Advanced Measurement and Detection Methods
- Medical Image Segmentation Techniques
- Color Science and Applications
- Microplastics and Plastic Pollution
Hohai University
2014-2025
Changzhou Architectural Research Institute Group (China)
2025
Nanjing Tech University
2023
Wuhan University
2023
Shanghai Academy of Spaceflight Technology
2021
Shell (Netherlands)
2020
Wuhan Technology and Business University
2020
Everbright International (China)
2019
Qingdao University of Science and Technology
2019
Rutgers, The State University of New Jersey
2015-2018
In this paper, we consider water surface object detection in natural scenes. Generally, background subtraction and image segmentation are the classical methods. The former is highly susceptible to variable scenes, so its accuracy will be greatly reduced when detecting objects due changing of sunlight waves. latter more sensitive selection features, which lead poor generalization as a result, it cannot applied widely. Consequently, methods based on deep learning have recently been proposed....
Object detection is widely used in robot navigation, intelligent security and industrial detection, but it rarely water conservancy industry. In the aspect of river lake health management, important to clean out floating objects time, which prevents pollution caused by accumulation objects. The early methods surface object such as background subtraction frame difference, are greatly affected change shape background, resulting poor robustness. Therefore, we propose a real-time method based on...
Using coal fly ash from one thermal power plant in Ningxia, China as the raw material, aluminum hydroxide powder was successfully extracted by pre-desilication , calcination, dissolution and carbonation precipitation processes. The research results indicated that mullite, Quartz glass phase could be changed into NaSiO3, NaAlO2 Na2CaSiO4 after treated desilication calcination. SiO2and Al2O3 components were mainly separated dissolving calcined sample using water. rate of is 91%. bayerite with...
Due to the widespread use of bisphenol analogues (BPs) as alternatives A (BPA), considerable attention for health risk has been shown in aquatic ecosystems. The occurrence and distribution six BPs were researched a soluble phase (<10−3 μm), colloidal (10−3 μm 1 µm), suspended particulate matter (SPM >1 µm) water diversion project Nanjing, China. Except Z, all detected two or three phases, where total concentrations 161–613 ng/L, 5.19–77.2 47.5–353 ng/g phase, SPM, respectively. Among...
Understanding the mechanical behaviour of carbonate sand–fine mixtures is crucial for modelling geotechnical-related gas exploitation problems in potential hydrate reservoirs. This paper presents a laboratory investigation with sand content no more than 40%. By means computer tomography, internal porosity grains was measured, and interfine void ratio modified. For similar ratio, all exhibited strain-softening behaviour, peak strength decreased increasing content. Compared to mixture whose...
A hybrid optical-acoustic underwater wireless sensor network (OA-UWSN) was proposed to solve the problem of high-speed transmission real-time video and images in marine information detection. This paper proposes a novel energy-efficient contention-based media access control (MAC) protocol (OA-CMAC) for OA-UWSN. Based on fusion technology, our OA-CMAC combines postponed mechanism carrier sense multiple with collision avoidance (CSMA/CA) multiplexing-based spatial division (SDMA) technology...
A seizure is a neurological disorder caused by abnormal neuronal discharges in the brain, which severely reduces quality of life patients and often endangers their lives. Automatic detection an important research area treatment prerequisite for intervention. Deep learning has been widely used automatic seizures, many related works decomposed electroencephalogram (EEG) raw signal with time window to obtain EEG slices, then performed feature extraction on represented obtained features as input...
Recently, Distributed Energy Resources (DERs) have been utilized with increasing frequency in Industrial Internet of Things (IIoT) to deal energy and environmental challenges. IIoT wireless communication technology, which is easy be intercepted, often facing various attack. For the safety network, more complex algorithms need run on IIoT, but action energy. In addition, some application scenarios, location where packets were generated indicates that an event occurred. An attacker can find...
Underwater moving object detection is the key for many underwater computer vision tasks, such as recognizing, locating, and tracking. Considering super ability in visual sensing of habitats, mechanism aquatic animals generally regarded cue establishing bionic models which are more adaptive to environments. However, low accuracy rate absence prior knowledge learning limit their adaptation applications. Aiming solve problems originated from inhomogeneous lumination unstable background,...
Underwater images often suffer from color cast, poor contrast, and detail loss owing to the scattering absorption of light in water. To solve these problems, we propose what believe be a novel underwater image enhancement method based on correction dual multi-scale fusion. We first use problem compensate other two-color channels with highest mean value channel; further, all are dynamically stretched. Next, complementary fusion is used improve pairs adaptive gamma weighted distribution...
Fashion coordinates recommendation focuses on coordinating the pattern and colors of fashion items. For example, which shirt out candidates matches pants best? The traditional recommender system based Latent Factor Model (LFM) uses user behavior features to deal with two matching item, but it is weak in recommending more than items because problem cold start becomes significant. Furthermore, are correlated visual directly, another factor that can be imported into calculation.