THI THI ZIN

写真a

Affiliation

Engineering educational research section Information and Communication Technology Program

Title

Professor

External Link

Degree 【 display / non-display

  • Doctor of Engineering ( 2007.3   Osaka City University )

  • Master of Engineering ( 2004.3   Osaka City University )

  • Master of Information Science ( 1999.5   University of Computer Studies, Yangon (UCSY) )

  • B.Sc (Hons) (Mathematics) ( 1995.5   University of Yangon (UY) )

Research Interests 【 display / non-display

  • Image Processing and Its Application

  • 工場での作業の見える化

  • 高度な画像処理技術やAI技術を活用した 研究開発

  • 24-hour monitoring system for the elderly to support independent living

  • ICT Farm Monitoring System

  • Perceptual information processing

Research Areas 【 display / non-display

  • Informatics / Perceptual information processing  / Image Processing

  • Informatics / Database

  • Life Science / Animal production science

 

Papers 【 display / non-display

  • DIFFUSION-BASED INPAINTING METHODS COMPARISON WITH DAMAGE AREA REDUCTION TECHNIQUES Reviewed International coauthorship

    Khant Khant Win Tint, Mie Mie Tin, Thi Thi Zin, Pyke Tin

    ICIC Express Letters, Part B: Applications   15 ( 3 )   303 - 309   2024.3

     More details

    Language:English   Publishing type:Research paper (scientific journal)   Publisher:ICIC Express Letters, Part B: Applications  

    Ancient murals beautifully reflect the social and religious characteristics of several cultural groups in a particular historical era. Unfortunately, the irreplaceable historical murals have been damaged by both natural and human-made deterioration. Image inpainting can restore the visual appeal of a mural. Image inpainting involves repairing any damaged or missing regions. In this paper, in order to address the issue of color bias, the gray scale image undergoes an inpainting process, resulting in a lack of noticeable color differences. For the mask generation, mask is generated automatically by using thresholding. That is why it prevents over-identifying damage or missing regions by user interaction. Experiments are conducted on mural images of Po-Win-Daung, Myanmar. To assess the inpainted results without the presence of a ground truth image, the paper puts forward the idea of using the damage area reduction technique for evaluation purposes. Comparisons are carried out on directional median diffusion and coherent transport methods.

    DOI: 10.24507/icicelb.15.03.303

    Scopus

  • Revolutionizing Cow Welfare Monitoring: A Novel Top-View Perspective with Depth Camera-Based Lameness Classification Reviewed

    San Chain Tun, T. Onizuka, Pyke Tin, M. Aikawa, I. Kobayashi, Thi Thi Zin

    Journal of Imaging   10 ( 3 )   2024.3

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Journal of Imaging  

    This study innovates livestock health management, utilizing a top-view depth camera for accurate cow lameness detection, classification, and precise segmentation through integration with a 3D depth camera and deep learning, distinguishing it from 2D systems. It underscores the importance of early lameness detection in cattle and focuses on extracting depth data from the cow’s body, with a specific emphasis on the back region’s maximum value. Precise cow detection and tracking are achieved through the Detectron2 framework and Intersection Over Union (IOU) techniques. Across a three-day testing period, with observations conducted twice daily with varying cow populations (ranging from 56 to 64 cows per day), the study consistently achieves an impressive average detection accuracy of 99.94%. Tracking accuracy remains at 99.92% over the same observation period. Subsequently, the research extracts the cow’s depth region using binary mask images derived from detection results and original depth images. Feature extraction generates a feature vector based on maximum height measurements from the cow’s backbone area. This feature vector is utilized for classification, evaluating three classifiers: Random Forest (RF), K-Nearest Neighbor (KNN), and Decision Tree (DT). The study highlights the potential of top-view depth video cameras for accurate cow lameness detection and classification, with significant implications for livestock health management.

    DOI: 10.3390/jimaging10030067

    Scopus

    PubMed

  • Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments Reviewed

    Wai Hnin Eaindrar Mg, Pyke Tin, M. Aikawa, I. Kobayashi, Y. Horii, K. Honkawa, Thi Thi Zin

    Sensors   24 ( 4 )   2024.2

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (scientific journal)   Publisher:Sensors  

    Ensuring precise calving time prediction necessitates the adoption of an automatic and precisely accurate cattle tracking system. Nowadays, cattle tracking can be challenging due to the complexity of their environment and the potential for missed or false detections. Most existing deep-learning tracking algorithms face challenges when dealing with track-ID switch cases caused by cattle occlusion. To address these concerns, the proposed research endeavors to create an automatic cattle detection and tracking system by leveraging the remarkable capabilities of Detectron2 while embedding tailored modifications to make it even more effective and efficient for a variety of applications. Additionally, the study conducts a comprehensive comparison of eight distinct deep-learning tracking algorithms, with the objective of identifying the most optimal algorithm for achieving precise and efficient individual cattle tracking. This research focuses on tackling occlusion conditions and track-ID increment cases for miss detection. Through a comparison of various tracking algorithms, we discovered that Detectron2, coupled with our customized tracking algorithm (CTA), achieves 99% in detecting and tracking individual cows for handling occlusion challenges. Our algorithm stands out by successfully overcoming the challenges of miss detection and occlusion problems, making it highly reliable even during extended periods in a crowded calving pen.

    DOI: 10.3390/s24041181

    Scopus

    PubMed

  • Digital Transformation (DX) Solution for Monitoring Mycoplasma Infectious Disease in Calves: A Worldwide Health Challenge Reviewed

    Cho Nilar Phyo, Pyke Tin, H. Hama, Thi Thi Zin

    Lecture Notes in Electrical Engineering   1114 LNEE   218 - 226   2024

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Lecture Notes in Electrical Engineering  

    The Mycoplasma bovis (M. bovis) is a serious threat to cattle health, resulting in significant economic losses worldwide, particularly in veal calf sector. While the disease can circulate undetected, early identification of subclinical carriers is crucial. To this end, a fully automated monitoring system for Mycoplasma Infectious Disease in Calves was proposed using digital transformation technologies and AI advances. The proposed system will consist of four stages. In the first stage, an image processing technique will be developed to automatically or manually record behavioral or physiological parameters in calves while feeding at milk feeding robots. The second stage will integrate multiple data resources, such as DX records and image data, to analyze the data for detection and diagnosis of mycoplasma infection. The third stage will employ DX and AI advances to enforce the proposed monitoring system for making accurate decisions, such as whether to treat or not and what to treat calves for. In fourth stage, some experimental results will be displayed. In conclusion, the proposed automated monitoring system will provide a valuable tool for early detection of Mycoplasma Infectious Disease in calves, leading to reduce economic losses and offer timely information to address major worldwide problem.

    DOI: 10.1007/978-981-99-9412-0_23

    Scopus

  • AI Driven Movement Rate Variability Analysis Around the Time of Calving Events in Cattle Reviewed

    Wai Hnin Eaindrar Mg, Pyke Tin, M. Aikawa, I. Kobayashi, Y. Horii, K. Honkawa, Thi Thi Zin

    Lecture Notes in Electrical Engineering   1114 LNEE   227 - 237   2024

     More details

    Authorship:Last author, Corresponding author   Language:English   Publishing type:Research paper (international conference proceedings)   Publisher:Lecture Notes in Electrical Engineering  

    In modern cattle management, the timely detection of cattle events is crucial for ensuring both animal welfare and farm profitability. This paper introduces an innovative approach that leverages AI-driven movement rate variability analysis to predict calving events in cattle. By harnessing advanced motion tracking technologies and machine learning algorithms, this methodology offers a non-intrusive and automated means of detecting physiological and behavioral changes associated with impending calving events. Through a comprehensive exploration of data collection, pre-processing, and feature engineering, this paper establishes the foundation for training accurate AI models. These models utilize distinct movement patterns, including changes in speed, frequency, direction, and rest behavior, as predictive indicators of calving events. Real-world validation on cattle farms underscores the practical viability of the proposed approach, demonstrating its potential to revolutionize calving event detection. By transcending traditional methods, this AI-driven solution exhibits superior accuracy and efficiency, thereby contributing to enhanced animal care, optimized farm operations, and improved economic outcomes. The paper concludes by highlighting future research avenues and underscoring the transformative implications of AI-driven movement analysis for calving event prediction in the realm of agricultural technology.

    DOI: 10.1007/978-981-99-9412-0_24

    Scopus

display all >>

Books 【 display / non-display

  • Big Data Analysis and Deep Learning Applications: Proceedings of the First International Conference on Big Data Analysis and Deep Learning (Advances in Intelligent Systems and Computing Book 744)

    Thi Thi Zin (Editor), Jerry Chun-Wei Lin (Editor) ( Role: Joint editor)

    Springer  2018.6 

     More details

    Total pages:Springer   Language:English

    Other Link: https://www.amazon.com/Data-Analysis-Deep-Learning-Applications-ebook/dp/B07DL46RJX

  • Systems and Computing: A New Look into Web Page Ranking Systems

    Thi Thi Zin, Pyke Tin, H. Hama, T. Toriu( Role: Joint author)

    Springer International Publishing  2014.10 

     More details

    Language:English Book type:Scholarly book

MISC 【 display / non-display

  • A Study on the Possibility of Distinguishing between Parkinson's disease and Essential Tremor using Motor Symptoms Observed by an RGB camera

    Proceedings of the 34th Annual Conference of Biomedical Fuzzy Systems Association (BMFSA2022)   2022.12

     More details

    Authorship:Corresponding author   Language:Japanese   Publishing type:Research paper, summary (national, other academic conference)   Publisher:Biomedical Fuzzy Systems Association  

  • Tracking A Group of Black Cows Using SORT based Tracking Algorithm

    Cho Cho Aye, Thi Thi Zin, M. Aikawa, I. Kobayashi

    第 35 回バイオメディカル・ファジィ・システム学会年次大会 講演論文集 (BMFSA2022)   2022.12

     More details

    Authorship:Corresponding author   Language:English   Publishing type:Research paper, summary (national, other academic conference)   Publisher:バイオメディカル・ファジィ・システム学会  

  • Artificial Intelligence Topping on Spectral Analysis for Lameness Detection in Dairy Cattle

    Thi Thi Zin, Ye Htet, San Chain Tun and Pyke Tin

    第 35 回バイオメディカル・ファジィ・システム学会年次大会 講演論文集 (BMFSA2022)   2022.12

     More details

    Authorship:Lead author, Corresponding author   Language:English   Publishing type:Research paper, summary (national, other academic conference)   Publisher:バイオメディカル・ファジィ・システム学会  

  • Introduction to IEEE LifeTech 2022 Overview Invited International coauthorship

    Thi Thi Zin and Ryota Nishimura

    IEEE LifeTech2022 Abstract Book   2022.3

     More details

    Language:English   Publishing type:Research paper, summary (international conference)   Publisher:IEEE CT Soc  

    DOI: 10.1109/LifeTech53646.2022.9754806

    Scopus

  • 高度な画像処理技術やAI技術を活用した研究開発 Invited

    Thi Thi Zin

    ICT研究開発支援セミナーin九州   2022.2

     More details

    Authorship:Lead author, Corresponding author   Language:Japanese   Publishing type:Lecture material (seminar, tutorial, course, lecture, etc.)   Publisher:戦略的情報通信研究開発推進事業(SCOPE)  

    高齢化、大規模化する現代の畜産で、24時間365日にわたり家畜の健康管理を適切に行い、異常や変化に留意し続けながら経営を継続することは容易でない。本研究開発では、家畜生産性の改善と地域活性化の実現を目的とする牛のモニタリングシステム構築に必要な要素技術の開発を行う。

display all >>

Presentations 【 display / non-display

  • Automatic Cattle Detection and Tracking for Lameness Classification Using a Single Side-View Camera International conference

    Bo Bo Myint, T. Onizuka, Pyke Tin, M. Aikawa, I. Kobayashi, Thi Thi Zin

    Second International Symposium on Data-Driven Intelligent Optimization for Decision Making (DIODM2024)  2024.3.26 

     More details

    Event date: 2024.3.24 - 2024.3.27

    Language:English   Presentation type:Oral presentation (general)  

  • 画像処理技術を用いた歩行状態の数値化に関する研究

    丹野 龍晟、ティティズイン

    動的画像処理実利用化 ワークショップ2024 (DIA 2024)  2024.3.4 

     More details

    Event date: 2024.3.4 - 2024.3.5

    Language:Japanese   Presentation type:Poster presentation  

  • Transition-Aware Elderly Action Recognition: Unveiling Insights with CNN-RNN Integration, International conference

    Ye Htet, Thi Thi Zin, H. Tamura, K. Kondo, E. Chosa

    2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'24)  2024.2.29 

     More details

    Event date: 2024.2.27 - 2024.3.1

    Language:English   Presentation type:Oral presentation (general)  

  • Kalman Velocity-based Multi-Stage Classification Approach for Recognizing Black Cow Actions International conference

    Cho Cho Aye, Thi Thi Zin, M. Aikawa, I. Kobayashi

    2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'24)  2024.2.29 

     More details

    Event date: 2024.2.27 - 2024.3.1

    Language:English   Presentation type:Oral presentation (general)  

  • A Novel Stochastic Model for Analysing Heart Rate Variability in the Heart-Brain Signal Communication System International conference

    Thi Thi Zin, Tunn Cho Lwin, Pyke Tin

    2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'24)  2024.2.29 

     More details

    Event date: 2024.2.27 - 2024.3.1

    Language:English   Presentation type:Oral presentation (general)  

display all >>

Awards 【 display / non-display

  • Student paper Award

    2024.3   2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing   Enhancing Precision Agriculture: Innovative Tracking Solutions for Black Cattle Monitoring

    Su Myat Noe, Thi Thi Zin, Pyke Tin, and Ikuo Kobayashi

     More details

    Award type:Award from international society, conference, symposium, etc. 

  • Student paper Award

    2024.3   2024 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing   Kalman Velocity-based Multi-Stage Classification Approach for Recognizing Black Cow Actions

    Cho Cho Aye, Thi Thi Zin, M. Aikawa, I. Kobayashi

     More details

    Award type:Award from international society, conference, symposium, etc. 

  • Best Paper Award

    2023.11   The 9th International Conference on Science and Technology (ICST UGM 2023)   An Innovative Framework for Cattle Activity Monitoring: Combining AI-Based Markov Chain Model with IoT Devices

    Y. Hashimoto, Thi Thi Zin, Pyke Tin, I. Kobayashi and H. Hama

     More details

    Award type:Award from international society, conference, symposium, etc. 

  • IEEE GCCE 2022 Excellent Student Paper Awards (Outstanding Prize)

    2022.10   2022 IEEE 11th Global Conference on Consumer Electronics (GCCE2022)   Video-Based Automatic Cattle Identification System

    Su Larb Mon, Thi Thi Zin, Pyke Tin, I. Kobayashi

     More details

    Award type:Award from international society, conference, symposium, etc.  Country:Japan

    In this paper, we propose a method to identify the cattle by using video sequences. In order to do so, we first collect 360-degree top-view video sequences to form dataset. The proposed system is composed of two parts: cattle detection and cattle identification. In the detection process, we utilize YOLOv5(You Only Look Once) model to detect the cattle region in the lane. In this stage, cattle’s location and region information are extracted and the cropped images of detected cattle regions are saved for the next stage. We then apply Convolutional Neural Network model (VGG16) to extract the features which will be used to identify individual cattle. For the classification, the proposed system used two supervised machine learning methods, Random Forest and SVM (Support Vector Machine). The accuracy of Random Forest is 98.5% and the accuracy of SVM is 99.6%. After comparing the accuracy rate of two methods, SVM get the better accuracy result. The proposed system achieved the accuracy of over 90% for both cattle detection and identification.

  • Best Presentation Award

    2022.9   The 16th International Conference on Innovative Computing, Information and Control (ICICIC2022)   Comparative Study on Color Spaces, Distance Measures and Pretrained Deep Neural Networks for Cow Recognition

    Cho Cho Mar, Thi Thi Zin, Pyke Tin, I. Kobayashi, K. Honkawa, Y. Horii

     More details

    Award type:Award from international society, conference, symposium, etc.  Country:Japan

display all >>

Grant-in-Aid for Scientific Research 【 display / non-display

  • 画像処理技術と非接触センサを用いた牛の発情検知及び分娩監視システムの開発

    2017.04 - 2021.03

    科学研究費補助金  基盤研究(C)

      More details

    Authorship:Principal investigator 

     畜産は全国農業総生産額の3 割以上を占める重要な産業であるが、不適切な家畜管理による生産性の低下が大きな問題となっている。その主たる原因は飼養形態の変化による1 頭あたり観察時間の短縮であり、飼養頭数の多頭化・農家の高齢化が進む畜産現場において、365 日24 時間にわたり家畜の異常や変化を観察し続けることは困難である。
     申請者らは、主に非接触・非侵襲センサ情報のアルゴリズム解析技術に着目し、距離画像とビデオ画像を用いて牛の発情を検知できる独自アルゴリズムの開発に取り組んできた。本研究では、これらの技術を応用することで、牛の発情や分娩監視時の異常を自動検知できる省力的な24 時間
    家畜管理システムを開発する。

  • 牛の分娩監視システムに関する研究

    2018.04 - 2020.03

    科学研究費補助金  特別研究員奨励費

    須見 公祐、Thi Thi Zin(受入研究者)

      More details

    Authorship:Coinvestigator(s) 

    精度や耐久性が不十分な割に高価なウェラブル型センサの装着や、肉体的・精神的に大きな負担を強いられる目視によるカメラ映像のモニタリング等は、大規模化する畜産現場において現実的なコストで利用できるものが極めて少ない。そこで本研究では、監視カメラから得られる映像を用いて非接触型の分娩管理システムを開発することで、農家そして牛、両方の負担を減らすことを目的とする。
    本来、牛は牛群と呼ばれるグループで行動を行う。そして、分娩が間近になると分娩室という分娩専用の牛舎に移される。分娩室には2 頭以上を同時に入れるケースも多く、どの牛で分娩が始まったかを識別する必要があることから、個体識別と追跡処理が必要となる。次に、分娩行動の段階を追って検知を行う。抽出する特徴としては、尻尾が上がっているかどうか、牛が立っているか座っているか、落ち着きがなくなり移動量が増加するか、子牛を出産したかどうか、親牛が子牛を舐めているかどうかなど、それぞれの過程で自動的に異常を見つけ通報を行うアルゴリズムの開発を進める。分娩行動が起きたかどうかの判断は、これらのデータから各特徴の重要度(重み)を学習させることによって行う。そして、最終目標として難産など異常行動の検知を行うために事例を蓄積しながら知識ベースを充実させ、異常事態の検知を行い、分娩の各段階を監視して異常事態の検知ならびに通報が可能なシステムの開発を目指す。

  • Development of forensic imaging modality for person identification using integration method of feature correspondences between heterogeneous images

    2015.04 - 2018.03

    Grant-in-Aid for Scientific Research  Grant-in-Aid for challenging Exploratory Research

      More details

    Authorship:Coinvestigator(s) 

  • Study of interactive teaching systems using an image processing techniques

    2015.04 - 2018.03

    Grant-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research(C)

      More details

    Authorship:Coinvestigator(s) 

  • Development of automatic estrus detection systems of cattle using complementary the plane distance image and video footage

    2015.04 - 2017.03

    Grant-in-Aid for Scientific Research  Grant-in-Aid for challenging Exploratory Research

      More details

    Authorship:Principal investigator 

display all >>

Available Technology 【 display / non-display