|
Affiliation |
Engineering educational research section Information and Communication Technology Program |
|
Title |
Professor |
|
External Link |
|
THI THI ZIN
|
|
|
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 】
-
Development of a real-time cattle lameness detection system using a single side-view camera. Reviewed
Bo Bo Myint, T. Onizuka, Pyke Tin, M. Aikawa, I. Kobayashi, Thi Thi Zin
Scientific reports 14 ( 1 ) 13734 2024.6
Authorship：Last author, Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：Scientific Reports
Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and classification. This research investigates the application of deep learning for cattle lameness detection in dairy farming. Our study employs image processing techniques and deep learning methods for cattle detection, tracking, and lameness classification. We utilize two powerful object detection algorithms: Mask-RCNN from Detectron2 and the popular YOLOv8. Their performance is compared to identify the most effective approach for this application. Bounding boxes are drawn around detected cattle to assign unique local IDs, enabling individual tracking and isolation throughout the video sequence. Additionally, mask regions generated by the chosen detection algorithm provide valuable data for feature extraction, which is crucial for subsequent lameness classification. The extracted cattle mask region values serve as the basis for feature extraction, capturing relevant information indicative of lameness. These features, combined with the local IDs assigned during tracking, are used to compute a lameness score for each cattle. We explore the efficacy of various established machine learning algorithms, such as Support Vector Machines (SVM), AdaBoost and so on, in analyzing the extracted lameness features. Evaluation of the proposed system was conducted across three key domains: detection, tracking, and lameness classification. Notably, the detection module employing Detectron2 achieved an impressive accuracy of 98.98%. Similarly, the tracking module attained a high accuracy of 99.50%. In lameness classification, AdaBoost emerged as the most effective algorithm, yielding the highest overall average accuracy (77.9%). Other established machine learning algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and Random Forests, also demonstrated promising performance (DT: 75.32%, SVM: 75.20%, Random Forest: 74.9%). The presented approach demonstrates the successful implementation for cattle lameness detection. The proposed system has the potential to revolutionize dairy farm management by enabling early lameness detection and facilitating effective monitoring of cattle health. Our findings contribute valuable insights into the application of advanced computer vision methods for livestock health management.
-
Ye Htet, Thi Thi Zin, Pyke Tin, H. Tamura, K. Kondo, S. Watanabe, E. Chosa
IEEE Access 12 74499 - 74523 2024.5
Authorship：Corresponding author Language：English Publishing type：Research paper (scientific journal) Publisher：IEEE Access
The global rise in the elderly population, which presents challenges to healthcare systems owing to labor shortages in caregiving facilities, necessitates innovative solutions for elderly care services. Smart aging technologies such as robotic companions and digital home gadgets, offer a solution to these challenges by improving the elderly's quality of life and assisting caregivers. However, limitations in data privacy, real-time processing, and reliability often hinder the effectiveness of the existing technologies. Among these, privacy concerns are a major barrier to ensuring user trust and ethical implementation. Therefore, this study proposes a more effective approach for smart aging through elderly activity monitoring that prioritizes data privacy. The proposed system utilizes stereo depth cameras to monitor the activities of the elderly. Data were collected from real-world environments with the participation of six elderly individuals from a care center and hospital. This system focuses on recognizing common daily actions of the elderly including sitting, standing, lying down, and seated in a wheelchair. Additionally, it recognizes transition states (in-between actions such as changing from sitting to standing) that are crucial for assessing balance issues. By integrating motion information with a deep-learning architecture, the system achieved a high accuracy of 99.42% in recognizing daily actions in real-time. This high accuracy was maintained even with minimal data from new environments through transfer learning, and the adaptability of this model ensured its potential for real-world applications. For intuitive interaction between the caregivers and the system, a user-friendly graphical interface (GUI) was also designed in the proposed approach.
-
San Chain Tun, T. Onizuka, Pyke Tin, M. Aikawa, I. Kobayashi, Thi Thi Zin
Journal of Imaging 10 ( 3 ) 2024.3
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.
-
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
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.
-
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
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
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
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
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
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
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
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
Authorship：Lead author, Corresponding author Language：English Publishing type：Research paper, summary (international conference) Publisher：IEEE CT Soc
-
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
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。
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
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
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
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
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
Event date： 2024.2.27 - 2024.3.1
Language：English Presentation type：Oral presentation (general)
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
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
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
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
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
Award type：Award from international society, conference, symposium, etc. Country：Japan
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)
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）
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
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)
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
Authorship：Principal investigator
Available Technology 【 display / non-display 】
-
ICTを活用した牛のモニタリングシステムの開発に関する研究
安全・安心のための24時間自動見守り・監視システムの開発に関する研究
工場の作業効率化のための作業グループ検出に関する研究Home Page： 研究者データベース
Related fields where technical consultation is available：ビッグデータからの新しい知見の獲得・発見を体系的に行える数理的道具の開発
牛のモニタリング情報分析システム
高度な画像処理技術とAI活用による身体・精神機能低下患者の行動認識に関する研究
ビデオ画像を利用した新生児運動モニタリングシステムの開発に関する研究
画像処理技術を用いた疾病の特徴を示すエビを検出するシステムMessage：『画像処理を用いて様々な問題を解決すること』を目的として、農学や医学の分野に係わる学際領域の研究を幅広く行っています。多種多様な課題に対して各分野の専門家と協力して、画像処理分野からの貢献を目指して、研究・開発を行っています。