A5101924784- Video Surveillance and Tracking Methods
- Distributed Sensor Networks and Detection Algorithms
- Higher Education and Teaching Methods
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Vision and Imaging
- Indoor and Outdoor Localization Technologies
- Image and Video Stabilization
- Computational Physics and Python Applications
- Advanced Image and Video Retrieval Techniques
- Face and Expression Recognition
- Gait Recognition and Analysis
- Education and Vocational Training
- Image Enhancement Techniques
- Face recognition and analysis
- Numerical Methods and Algorithms
- Digital Filter Design and Implementation
- Advanced Image Fusion Techniques
- Fault Detection and Control Systems
- Infrared Target Detection Methodologies
- Human Pose and Action Recognition
- Educational Technology and Pedagogy
- UAV Applications and Optimization
Linyi University
2024
Tianjin University
2023
Tianjin haihe hospital
2023
Capital Normal University
2013-2017
Beijing Advanced Sciences and Innovation Center
2016-2017
Embedded Systems (United States)
2014
Beijing University of Technology
2011
Kinship verification from facial images is an interesting and challenging problem in computer vision, there are very limited attempts on tackle this the literature. In paper, we propose a new neighborhood repulsed metric learning (NRML) method for kinship verification. Motivated by fact that interclass samples (without relation) with higher similarity usually lie more easily misclassified than those lower similarity, aim to learn distance under which intraclass (with pulled as close possible...
Multi-drone multi-target tracking aims at collabo- ratively detecting and targets across multiple drones associating the identities of objects from different drones, which can overcome shortcomings single-drone object tracking. To address critical challenges identity association target occlusion in multi-drone tasks, we collect an occlusion-aware dataset named MDMT. It contains 88 video sequences with 39,678 frames, including 11,454 IDs persons, bicycles, cars. The MDMT comprises 2,204,620...
In digital signal and image processing, it’s very common to calculate the value of certain transcendental functions, such as natural logarithmic function. This study introduces basic principles mode calculation hyperbolic systems by using CORDIC algorithm, then analyses Field-Programmable Gate Array (FPGA) core processing unit in detail. The biggest advantage algorithm is that its circuit structure simple, only adder shifter. It suitable for FPGA implementation. Based on iterative a...
It was the panoramic technology that extensively used in scopes of Video Compression, Virtual Reality, Pathology Medical Science, Teleconference System and so on. Panoramic mosaic perspective, taking both full view images a sight view, is critical figure merit for system. This paper introduces design camera, which special circumstances required with ambulant ability. The camera achieves perspective by analyzing optical structure using multiple image sensors. A algorithm to rapidly locate...
Abstract Whether it is the development trend of education in whole world or quality that being comprehensively promoted China, more and attention paid to students’ leading position entire process, respect for differences, importance personality development. This paper uses a distributed cloud computing platform construct clustering algorithm based on K-means-CE categorize language learner characteristics combined with Felder-Silverman style model. Then, ItemCF collaborative filtering...
This paper is devoted to the problem of state estimate discrete-time stochastic systems.A low-complexity and high accuracy algorithm presented reduce computational load traditional interacting multiple model with heterogeneous observations for location tracking.By decoupling x y dimensions simplify implementation location, updated information iteratively passed based on an adaptive fusion decision.Simulations show that more computationally attractive than existing methods.