Senior Associate Professor
- Department of Computer Science and Engineering/Division of Computer Engineering
- Senior Associate Professor
- Web site
- Courses - Undergraduate
- Logic Circuit Design (Exercise), Advanced Logic Circuit Design (Exercise)，Semiconductor Devices (Lecture), Integrated excercise on Systems II
- Courses - Graduate
- Sensing and Control Engineering, Embedded Real-Time Systems
- Highly-Efficient Video Analysis and Its Hardware Acceleration
- Educational Background, Biography
Apr. 2019 -- Senior Associate Professor, The University of Aizu
Apr. 2015 -- Associate Professor, The University of Aizu
Nov. 2009 -- Mar. 2015 Assistant Professor, Tokyo University of Agriculture and Technology
Jul. 2009 - Oct. 2009 PD, research fellowship for young scientists by JSPS
Apr. 2007 to Jun. 2009 DC1, research fellowship for young scientists by JSPS
Jan. 2007 to May. 2007 Visiting scholar, University of Illinois at Urbana-Champaign, Illinois Jun. 2009 Ph.D, Tokyo Institute of Technology
Sep. 2006 M.E, Tokyo Institute of Technology
Mar. 2005 B.E, Tokyo Institute of Technology
- Current Research Theme
- Efficient image recognition and its hardware accleeration, Deep learning acceletrator, Source camera identification and forgery detection for digital images
- Key Topic
- Deep learning, Machine learning, Video processing, FPGA, high performance computing, surveillance robot, Image sensor noise
- Affiliated Academic Society
- IEEE, IEICE, IPSJ, JSAI
- School days' Dream
- Current Dream
- Favorite Books
- Messages for Students
- Publications other than one's areas of specialization
- Identification Technologies for Digital Cameras Using Image Sensor’s Noise
It is known that DNA and finger print are useful for identifying a human. A camera also has unique noise and it is included in an image taken by the camera though it is very small. By using the unique noise, we can know which camera took an image and which part was falsified in an image. In this research project, we aim to realize methods to extract the unique noise precisely in an image and their applications.
- Realization of Sustainable Efficient AI Systems
In mission-critical systems of infrastructure and medical systems, and so on, AI failures can cause serious malfunctions that can affect human lives, and thus AI must be fault tolerant. However, applying existing fault tolerant technologies to AI systems has problems that significantly increase area, power consumption, and cost. This project will establish a technology to realize a fault-tolerant AI that can detect sudden failures and continue to recognize them with sufficient accuracy with low computational power and a small area.
- Video Analysis for Safety and Security
In recent years, a great number of cameras have been operated. To use these cameras effectively, it is important to reduce the burden of watchmen by video analysis and to protect the privacy of people in video scene. In this research project, we work on video analysis and its hardware acceleration to realize a safe and secure social environment.
Dissertation and Published Works
Shota Saito, Yoichi Tomioka, Hitoshi Kitazawa, "A Theoretical Framework for Estimating False Acceptance Rate of PRNU-based Camera Identification"， IEEE Trans. on Information Forensics and Security, Vol. 12, Issue 9, pp. 2026-2035, Sep. 2017.
Yoichi Tomioka, Tetsuaki Matsunawa, Chikaaki Kodama, Shigeki Nojima, "Lithography hotspot detection by two-stage cascade classifier using histogram of oriented light propagation", IEEE Asia and South Pacific Design Automation Conference and Systems, pp.81--86, January. 2017.
Ning Li, Shunpei Takaki, Yoichi Tomioka, and Hitoshi Kitazawa, "A MULTISTAGE DATAFLOW IMPLEMENTATION OF A DEEP CONVOLUTIONAL NEURAL NETWORK BASED ON FPGA FOR HIGH-SPEED OBJECT RECOGNITION", IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION (SSIAI), March. 2016.
Tetsuya Okuda, Yoichi Tomioka, Hitoshi Kitazawa, "Robust Moving Object Extraction and Tracking Method based on Matching Position Constraints", IEICE Trans. on Information and Systems, Vol.E98-D, No.8, pp.1571-1579, 2015.
Ryota Takasu, Yoichi Tomioka, Takashi Aoki and Hitoshi Kitazawa, "An FPGA Implementation of Multi-stream Tracking Hardware using 2D SIMD Array" (Abstract Only), International Symposium on Field-Programmable Gate Arrays (FPGA), pp. 266. Feb. 2015.
Yoichi Tomioka, Hikaru Murakami, Hitoshi Kitazawa, "Sunshine-Change-Tolerant Moving Object Masking for Realizing both Privacy Protection and Video Surveillance"， IEICE Trans. on Information and Systems, Vol.E97-D, No.9, pp.2483-2492, 2014.
Ryota Takasu, Yoichi Tomoka, Yutaro Ishigaki, Ning Li, Tsugimichi Shibata, Mamoru Nakanishi, Hitoshi Kitazawa，"An FPGA Implementation of the Two-Dimensional FDTD Method and Its Performance Comparison with GPGPU"， IEICE Trans. on Electronics, Vol.E97-C, No.7, pp.697-706, 2014.
Sumitaka Ogino, Yoichi Tomioka, Hitoshi Kitazawa, "Patrol course planning and battery station placement for mobile surveillance cameras", 2014 IEEE International Conference on Multimedia and Expo (ICME), July 2014.
Yoichi Tomoka, Ryota Takasu, Takashi Aoki, Eiichi Hosoya, Hitoshi Kitazawa，"FPGA Implementation of Exclusive Block Matching for Robust Moving Object Extraction and Tracking"， IEICE Trans. on Information and Systems, Vol.E97-D, No.3, pp.573-582, 2014.
Yoichi Tomoka, Yuya Ito, Hitoshi Kitazawa，"Robust Digital Camera Identification Based on Pairwise Magnitude Relations of Clustered Sensor Pattern Noise"， IEEE Trans. on Information Forensics and Security, Vol.8 Issue 12, 2013.
Zhu LI, Yoichi TOMIOKA, Hitoshi KITAZAWA, "Extraction and Tracking Moving Objects in Detail Considering Visual Feature Constraint and Structure Constraint"， IEICE Trans. on Information and Systems, Vol.E96-D. No.5. pp.1745--1361, 2013．
Zhu Li, Kojiro Tomotsune, Yoichi Tomioka, Hitoshi Kitazawa, "Template Matching Method based on Visual Feature Constraint and Structure Constraint", IEICE Trans. on Information and Systems. Vol.E95-D. No.8. pp.2105--2115, 2012.
Yoichi Tomioka, Atsushi Takara, and Hitoshi Kitazawa, "Generation of an Optimum Patrol Course for Mobile Surveillance Camera", IEEE Trans. on Circuits and Systems for Video Technology, vol.22, issue 2, pp.216--224, 2012.,Kuan-Yu Chen, Jungpil Shin, Md. Al Mehedi Hasan, Jiun-Jian Liaw, Okuyama Yuichi, and Yoichi Tomioka, "Fitness Movement Types and Completeness Detection Using a Transfer-Learning-Based Deep Neural Network", Sensors, 22(15), July, 2022.
Stanislav SEDUKHIN, Yoichi TOMIOKA, and Kohei YAMAMOTO, "In Search of the Performance- and Energy-Efficient CNN Accelerators", IEICE Trans. on Electronics, Vol.E105-C, No.6, pp.209-221, Jun. 2022.
Reon Sato, Hiroshi Saito, Yoichi Tomioka, and Yukihide Kohira, "Energy Reduction Methods for Wild Animal Detection Devices", IEEE Access, Vol.10, pp.24149-24161, Feb. 2022.
Hiroshi SAITO, Tatsuki OTAKE, Hayato KATO, Masayuki TOKUTAKE, Shogo SEMBA, Yoichi TOMIOKA, and Yukihide KOHIRA, "Battery-powered Wild Animal Detection Nodes with Deep Learning"， IEICE Trans. on Communications, Vol.103-B, No.12, pp. 1394-1402, 2020.
Masayuki Tokutake, Kaisei Shimura, Yoichi Tomioka, Hiroshi Saito, and Yukihide Kohira, “Reliable and Efficient Bear-presence Detection based on Region Proposal of Low-resolution”, In Proc. of IEEE International Conference on Systems, Man and Cybernetics (SMC), Dec. 2020.
Kai Su, Chowdhury MD Intisar, Qiangfu Zhao, Yoichi Tomioka, “Knowledge Distillation for Real-time On-Road Risk Detection”, In Proc. of IEEE Cyber Science and Technology Congress, Aug. 2020.
Kazuki Hozumi and Yoichi Tomioka, “Low-latency Block-wise Object Detection Method using SSD for High Resolution Video”, In Proc. of International Conference on Digital Signal Processing, June. 2020.
Stanislav Sedukhin and Yoichi Tomioka, “Massively-Parallel Computing of Multi-Channel 2D Convolution”, In Proc. of SIAM Conference on Parallel Processing for Scientific Computing, Feb. 2020.
Tiantian Cai, Zhanjian Shao, and Yoichi Tomioka, Yuanyuan Liu, Zhu Li, “CNN-Based Camera Model Identification Using Image Noise in Frequency Domain”, In Proc. of IEEE International Conference on Systems, Man and Cybernetics (SMC), Oct. 2019.
4. Stanislav Sedukhin, Kazuya Matsumoto and Yoichi Tomioka, “Brain-inspired Co-design of Algorithm/Architecture for CNN Accelerators”, In Proc. of International Congress on Advanced Applied Informatics, July, 2019.