Di Yuan

Di Yuan
Xidian University · Guangzhou Institute of Technology

Doctor of Engineering

About

43
Publications
14,531
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
715
Citations
Citations since 2016
43 Research Items
714 Citations
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300
2016201720182019202020212022050100150200250300
Introduction
I am a Lecturer at Guangzhou Institute of Technology, XDU. I obtained my master's degree & Ph.D. degree from Harbin Institute of Technology, Shenzhen in 2017 & 2021. My master's and doctor's supervisors are Prof. Xinming Zhang and Prof. Zhenyu He respectively. From 2019 to 2021, I was supported by China Scholarship Council and worked with Prof. Xiaojun Chang as a joint-training Ph.D. student at Monash University, Clayton. My works focus on computer vision and object tracking.
Additional affiliations
September 2019 - March 2021
Monash University
Position
  • Visitor
June 2017 - November 2021
Harbin Institute of Technology Shenzhen Graduate School
Position
  • PhD Student
September 2015 - June 2017
Harbin Institute of Technology Shenzhen Graduate School
Position
  • PhD Student
Education
September 2017 - November 2021
Harbin Institute of Technology, Shenzhen
Field of study
  • Computer Science and Technology
September 2015 - June 2017
Harbin Institute of Technology Shenzhen Graduate School
Field of study
  • Applied Mathematics
August 2011 - June 2015
Harbin University of Commerce
Field of study
  • Mathematics

Publications

Publications (43)
Article
Thermal infrared (TIR) target tracking is susceptible to occlusion and similarity interference, which obviously affects the tracking results. To resolve this problem, we develop an Aligned Spatial-Temporal Memory network-based Tracking method (ASTMT) for the TIR target tracking task. Specifically, we model the scene information in the TIR target tr...
Article
Full-text available
When dealing with complex thermal infrared (TIR) tracking scenarios, the single category feature is not sufficient to portray the appearance of the target, which drastically affects the accuracy of the TIR target tracking method. In order to address these problems, we propose an adaptively multi-feature fusion model (AMFT) for the TIR tracking task...
Article
Thermal InfraRed (TIR) target trackers are easy to be interfered by similar objects, while susceptible to the influence of the target occlusion. To solve these problems, we propose a structural target-aware model (STAMT) for the thermal infrared target tracking tasks. Specifically, the proposed STAMT tracker can learn a target-aware model, which ca...
Article
Follow-up experimental designs are widely used in various scientific investigations and industrial applications to discuss the relationship between inputs and outputs at various stages. Due to the limitation of run size, the desired experimental purpose may not be achieved through one stage of the experiment, so additional runs should be considered...
Article
Full-text available
Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a maximum overlap method based on an intersection-over-union (IoU) loss to mitigate this problem, there are defect...
Article
Full-text available
The feature models used by existing Thermal InfraRed (TIR) tracking methods are usually learned from RGB images due to the lack of a large-scale TIR image training dataset. However, these feature models are less effective in representing TIR objects and they are difficult to effectively distinguish distractors because they do not contain fine-grain...
Article
The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthe...
Article
Integrating multi-feature based on multi-layer features from the convolutional network or based on multiple hand-crafted features has been proved to be an effective way for improving tracking performance. In this work, we investigate how to integrate multi-layer convolutional features with hand-crafted features. Specifically, an adaptive multi-feat...
Preprint
Full-text available
Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly affect the representational capability of the trained model. However, this approach is restricti...
Article
Tracking in the unmanned aerial vehicle (UAV) scenarios is one of the main components of target tracking tasks. Different from the target tracking task in the general scenarios, the target tracking task in the UAV scenarios is very challenging because of factors such as small scale and aerial view. Although the DCFs-based tracker has achieved good...
Preprint
Full-text available
The current Siamese network based on region proposal network (RPN) has attracted great attention in visual tracking due to its excellent accuracy and high efficiency. However, the design of the RPN involves the selection of the number, scale, and aspect ratios of anchor boxes, which will affect the applicability and convenience of the model. Furthe...
Article
Full-text available
The training of a feature extraction network typically requires abundant manually annotated training samples, making this a time-consuming and costly process. Accordingly, we propose an effective self-supervised learning-based tracker in a deep correlation framework (named: self-SDCT). Motivated by the forward-backward tracking consistency of a rob...
Preprint
Full-text available
In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTBTIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over...
Conference Paper
Full-text available
In this paper, we present a Large-Scale and high-diversity general Thermal InfraRed (TIR) Object Tracking Benchmark, called LSOTB-TIR, which consists of an evaluation dataset and a training dataset with a total of 1,400 TIR sequences and more than 600K frames. We annotate the bounding box of objects in every frame of all sequences and generate over...
Article
Full-text available
While part-based methods have been shown effective in the person re-identification task, it is unreasonable for most of them to treat each part equally, due to the retrieved image may be affected by deformation, occlusion and other factors, which makes the feature information of some parts unreliable. Instead of using the same weight of each part f...
Article
Full-text available
Correlation filter-based trackers (CFTs) have recently shown remarkable performance in the field of visual object tracking. The advantage of these trackers originates from their ability to convert time-domain calculations into frequency domain calculations. However, a significant problem of these CFTs is that the model is insufficiently robust when...
Article
Full-text available
Existing deep Thermal InfraRed (TIR) trackers only use semantic features to represent the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images. To address this issue, we propose a multi-level similarity model under a Siamese frame...
Preprint
Full-text available
Most existing tracking methods are based on using a classifier and multi-scale estimation to estimate the state of the target. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While the ATOM \cite{ATOM} tracker adopts a maximum overlap method based on an intersection-over-union (IoU) loss to mit...
Conference Paper
Full-text available
Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific di...
Article
Discriminative correlation filters (DCFs) have been widely used in the tracking community recently. DCFs-based trackers utilize samples generated by circularly shifting from an image patch to train a ridge regression model, and estimate target location using a response map generated by the correlation filters. However, the generated samples produce...
Article
Convolutional Neural Networks (CNN) have been demonstrated to achieve state-of-the-art performance in visual object tracking task. However, existing CNN-based trackers usually use holistic target samples to train their networks. Once the target undergoes complicated situations (e.g., occlusion, background clutter, and deformation), the tracking per...
Article
Discriminative correlation filters (DCFs) have been widely used in the visual tracking community in recent years. The DCFs-based trackers determine the target location through a response map generated by the correlation filters and determine the target scale by a fixed scale factor. However, the response map is vulnerable to noise interference and...
Chapter
The Vision Meets Drone (VisDrone2020) Single Object Tracking is the third annual UAV tracking evaluation activity organized by the VisDrone team, in conjunction with European Conference on Computer Vision (ECCV 2020). The VisDrone-SOT2020 Challenge presents and discusses the results of 13 participating algorithms in detail. By using ensemble of dif...
Data
Multi-Task Driven Feature Models for Thermal Infrared Tracking--Supplementary Materials
Conference Paper
Full-text available
Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However , these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific d...
Preprint
Full-text available
Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific di...
Article
Full-text available
Common tracking algorithms only use a single feature to describe the target appearance, which makes the appearance model easily disturbed by noise. Furthermore, the tracking performance and robustness of these trackers are obviously limited. In this paper, we propose a novel multiple feature fused model into a correlation filter framework for visua...
Article
Full-text available
In the field of engineering technology, many problems can be transformed into the first kind Fredholm integral equation, which has a prominent feature called “ill-posedness”. This property makes it difficult to find the analytical solution of first kind Fredholm integral equation. Therefore, how to find the numerical solution of first kind Fredholm...
Preprint
Full-text available
Existing deep Thermal InfraRed (TIR) trackers only use semantic features to describe the TIR object, which lack the sufficient discriminative capacity for handling distractors. This becomes worse when the feature extraction network is only trained on RGB images.To address this issue, we propose a multi-level similarity model under a Siamese framewo...
Article
Full-text available
Most of the correlation filter based tracking algorithms can achieve good performance and maintain fast computational speed. However, in some complicated tracking scenes, there is a fatal defect that causes the object to be located inaccurately, which is the trackers excessively dependent on the maximum response value to determine the object locati...
Article
Full-text available
Graph-based methods have been widely applied in clustering problems. The mainstream pipeline for these methods is to build an affinity matrix first, and then use the spectral clustering methods to construct a graph. The existing studies about such a pipeline mainly focus on how to build a good affinity matrix, while the spectral method has only bee...
Article
Full-text available
To overcome the premature problem of the traditional flower pollination algorithm, a novel niche flower pollination algorithm is proposed by combining the niche strategy with flower pollination algorithm. It is designed for the parameter inversion of the space fractional order diffusion equation, so as to provide some theoretical basis for the poll...
Article
Full-text available
In the most tracking approaches, a score function is utilized to determine which candidate is the optimal one by measuring the similarity between the candidate and the template. However, the representative samples selection in the template update is challenging. To address this problem, in this paper, we treat the template as a linear combination o...
Conference Paper
Full-text available
The accurate localization of a object target is a challenging research issue in visual tracking. Most correlation filter based tracking algorithms has been degraded their performances because of the weaknesses of their search strategy. This paper investigates the problem of accurate location the object target in visual tracking sequences. We propos...
Conference Paper
Full-text available
Robust visual object tracking is one of the most challenging issues in the field of computer vision. Because of the circular shifts strategy, correlation filter-based trackers show a great efficiency in tracking task and thus receive lots of attentions. However, most of the correlation filter-based trackers fix the scale of the targets in each fram...
Conference Paper
Full-text available
The general tracking algorithm is vulnerable to noise because of using a single feature, makes the performance and robustness of the those algorithms greatly limited. In this paper, in order to achieve the robust and pretty performance, we propose a novel multiple feature fused model in correlation filter framework for visual tracking. The adoption...
Conference Paper
Full-text available
In this paper, we propose a novel thermal infrared (TIR) tracker via a deep Siamese convolutional neural network (CNN), named Siamese tir. Different from the most existing discriminative TIR tracking methods which treat the tracking problem as a classification problem, we treat the TIR tracking problem as a similarity verification problem. Specific...
Article
Full-text available
In this paper, based on the space fractional order diffusion equation, we estimate the equation parameters by using an improved ant colony algorithm, that is, the Niche Ant Colony Algorithm (NACA) based on fitness sharing principle. Its efficiency is verified by application of 20 standard test functions of 1-20 variables compared with standard ant...
Article
Full-text available
Occlusion is one of the most challenging problems in visual object tracking. Recently, a lot of discriminative methods have been proposed to deal with this problem. For the discriminative methods, it is difficult to select the representative samples for the target template updating. In general, the holistic bounding boxes that contain tracked resul...
Article
Full-text available
The paper analyses the dynamic relationship between the quantity of employment in three major industries and GDP in Hunan Province from 1952 to 2014 through VAR model. The result shows that there exists the bidirectional Granger Causality relationship between the GDP growth and the quantity of employment in Hunan Province. The development of GDP ha...
Article
Full-text available
Some nature of the skew commutative matrix was given in this paper. And some necessary and sufficient conditions about some skew commutative matrixes were given.

Questions

Questions (6)
Question
Is there any machine learning course worth recommending?
Question
It should not be a simple accuracy rate on the test benchmark.
Question
Put forward a problem or solve a problem, which one is important?
Question
How to choose and quickly master a programming language for deep learning and computer vision?
Question
Deep feature, color feature, gray feature, HOG or others?
What are the advantages of these features?

Network

Cited By

Projects

Projects (6)
Archived project
Research on some nature of the skew commutative matrix.