A5101875709- Video Surveillance and Tracking Methods
- Image and Signal Denoising Methods
- Seismic Imaging and Inversion Techniques
- Vehicle License Plate Recognition
- Autonomous Vehicle Technology and Safety
- Sleep and Work-Related Fatigue
- Heart Rate Variability and Autonomic Control
- Image Processing Techniques and Applications
- Advanced Neural Network Applications
- Image and Video Stabilization
- Brain Tumor Detection and Classification
- Retinal Imaging and Analysis
- AI in cancer detection
- Non-Invasive Vital Sign Monitoring
- Advanced Image and Video Retrieval Techniques
- Multimodal Machine Learning Applications
- Advanced Image Processing Techniques
- Seismic Waves and Analysis
- Medical Image Segmentation Techniques
- Advanced Computing and Algorithms
- Handwritten Text Recognition Techniques
- Image and Object Detection Techniques
- Visual Attention and Saliency Detection
- Human Pose and Action Recognition
Suqian University
2025
Anhui University
2019
Beijing Jiaotong University
2017-2018
China Telecom (China)
2018
Samsung (China)
2018
Center for Excellence in Brain Science and Intelligence Technology
2016
Chinese Academy of Sciences
2016
Jilin University
2015
Southwest University of Political Science & Law
2011
Inform (Germany)
2005
It is well known that blink, yawn, and heart rate changes give clue about a human's mental state, such as drowsiness fatigue. In this paper, image sequences, the raw data, are captured from smart phones which serve non-contact optical sensors. Video streams containing subject's facial region analyzed to identify physiological sources mixed in each image. We then propose method extract blood volume pulse eye blink yawn signals multiple independent simultaneously by multi-channel second-order...
Vehicle detection and identification techniques have been widely applied in traffic scene to acquire information depending on various sensors, such as video camera, induction loop, magnetic sensor. The quantity category of vehicles are the key components intelligent transportation systems they provide original data for further analysis. Compared with inductive loop sensor can measure field distortion caused by movement vehicles. precise amount a vehicle be obtained through reasonable A novel...
Diabetic retinopathy (DR) has long been recognized as a common complication of diabetes, making accurate automated grading its severity essential. Color fundus photographs play crucial role in the DR. With advancement artificial intelligence technologies, numerous researchers have conducted studies on DR based deep features and radiomic extracted from color photographs. We combine to design feature fusion algorithm. First, we utilize convolutional neural networks extract employ methodologies...
An appearance model adaptable to changes in object is critical visual tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original structure. We design two graphs for characterizing intrinsic local geometrical structure of samples and background. Graph embedding used reduce dimensions tensors while preserving graphs. Then, discriminant space constructed. prove propositions finding transformation matrices are map tensor-based graph space. order encode...
Seismic random noise suppression presents two main challenges: achieving thorough while simultaneously ensuring complete restoration of effective signal content. However, due to the complexity noise, existing denoising methods often only achieve an awkward balance between removing and restoring signals. In this paper, we propose a novel model based on downsampling super-resolution. By decoupling processes, our method reduces difficulty addressing these challenges mitigates likelihood...
Multiple vehicle detection and identification techniques have been widely applied to acquire road traffic information depending on various sensors, such as video camera, induction loop magnetic sensor. Magnetic sensor can measure field distortion caused by the movement of vehicles record reliable data. The precise volume component flow be obtained through reasonable data analysis. A novel algorithm is proposed based short-term variance sequence transformed from raw signal. parking-sensitive...
ABSTRACT Radial‐trace time–frequency peak filtering filters a seismic record along the radial‐trace direction rather than conventional channel direction. It takes spatial correlation of reflected events between adjacent channels into account. Thus, performs well in denoising and enhancing continuity events. However, there is often random noise whose energy concentrated certain directions; these directions correlative. We refer to this kind (that distributed randomly time but correlative...
This paper proposes a new unsupervised fuzzy feature mapping method based on fMRI data and combines it with multi-view support vector machine to construct classification model for computer-aided diagnosis of autism. Firstly, multi-output TSK system is adopted map the original linear separable high-dimensional space. Then manifold regularization learning framework introduced, proposed. Finally, SVM algorithm used tasks. The experimental results show that in this can effectively extract...