- Optical measurement and interference techniques
- Advanced Measurement and Detection Methods
- 3D Surveying and Cultural Heritage
- Remote Sensing and LiDAR Applications
- Advanced Optical Sensing Technologies
- Optical Systems and Laser Technology
- Image Processing Techniques and Applications
- Industrial Vision Systems and Defect Detection
- Water Quality Monitoring and Analysis
- Robotics and Sensor-Based Localization
- Advanced Measurement and Metrology Techniques
- Underwater Vehicles and Communication Systems
- Image Enhancement Techniques
- Privacy-Preserving Technologies in Data
- Marine and coastal ecosystems
- Flood Risk Assessment and Management
- Hydrology and Watershed Management Studies
- Sensor Technology and Measurement Systems
- CCD and CMOS Imaging Sensors
- Ocean Acidification Effects and Responses
- Gas Sensing Nanomaterials and Sensors
- Robotic Path Planning Algorithms
- Advanced Vision and Imaging
- Hydrological Forecasting Using AI
- Image and Object Detection Techniques
Ocean University of China
2006-2023
Qingdao University
2023
In this study, a laser line auto-scanning system was designed to perform underwater close-range 3D reconstructions with high accuracy and resolution. The changes the plane direction galvanometer automatic scanning obtain continuous strips for reconstruction. parameters were calibrated homography constraints between target image plane. A cost function defined optimize galvanometer's rotating axis equation. Compensation carried out refraction of incident emitted light at interface. spatial...
Analytic federated learning (AFL) which updates model weights only once by using closed-form least-square (LS) solutions can reduce abundant training time in gradient-free (FL). The current AFL framework cannot support deep neural network (DNN) training, hinders its implementation on complex machine tasks. Meanwhile, it overlooks the heterogeneous data distribution problem that restricts single global from performing well each client's task. To overcome first challenge, we propose an...
Depth completion aims to recover pixelwise depth from incomplete and noisy measurements with or without the guidance of a reference RGB image. This task attracted considerable research interest due its importance in various computer vision-based applications, such as scene understanding, autonomous driving, 3-D reconstruction, object detection, pose estimation, trajectory prediction, so on. As system input, an map is usually generated by projecting points collected ranging sensors, LiDAR...
For a long time the complete measurement of parts with complex structure and features has been bottleneck 3D in reverse engineering. This paper presents laser sensor that is mainly composed three CCD cameras four line projectors. With principle projecting planes from directions receiving reflected stripes other directions, can measure complicated multi views. A concise approach for calibrating proposed. The orientation each plane determined first. Then according to calibration points are...
Abstract Measuring and reconstructing the shape of workpieces have been considered as a fundamental step in both reverse engineering product quality control. Owing to increasing structural complexity recent products, measurements from multiple directions are typically required current scanning techniques. Specifically, plane structured light can be applied measure one area part at time, with an additional algorithm merge collected data each area. Alternatively, line sensor integrated on CNC...
At present, there is no rapid, stable and effective approach of total organic carbon (TOC) measurement in the Marine environmental online monitoring field. Therefore, this paper proposes an TOC monitor chemiluminescence signal processing method. The weak optical detected by photomultiplier tube can be enhanced converted a series module: phase-locked amplifier module, fourth-order band pass filter module AD conversion module. After long time comparison test & measurement, compared with...
The non-uniform reflectance characteristics of the object surface and underwater environment disturbances during laser measurement can have a great impact on stripe center extraction, we propose normalized grayscale gravity method for this problem, First, build an structured light dataset different illumination, turbidity reflective object, compare several state-of-the-art semantic segmentation models, including Deeplabv3, Deeplabv3plus, MobilenetV3, Pspnet, FCNnet, which results in...
Ma, R.; Xie, Z.-X.; Zhang, S.-W.; Chu, D.-Z.; Cao, X.; Wu, N., and Liu, Y.,2018. The orthogonal reference method for in-situ analysis of ammonia nitrogen content in seawater. In: Wang, D. Guido-Aldana, P.A. (eds.), Select Proceedings from the 3rd International Conference on Water Resource Environment (WRE2017). Journal Coastal Research, Special Issue No. 84, pp. 36–43. Coconut Creek (Florida), ISSN 0749-0208.A novel seawater is proposed. based joint application “water + reagent” blending...