Deep Learning and Computer Vision for Multiple Drone Media Production

(1)

(2)

2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2019)

Dec. 3-6, 2019, Taipei, Taiwan IEEE Catalog Number: CFP19580-ART

ISBN: 978-1-7281-3038-5

Copyright and Reprint Permissions: Abstracting is permitted with credit to the source. Libraries may photocopy beyond the limits of U.S. copyright law, for private use of patrons, those articles in this volume that carry a code at the bottom of the first page, provided that the per-copy fee indicated in the code is paid through the Copyright Clearance Center, 222 Rosewood Drive, Danvers, MA 01923.

(3)

(4)

On behalf of the ISPACS steering committee, I would like to cordially welcome you to ISPACS 2019 held during Dec. 3-6 at Beitou Hot Spring Resort, Taipei, Taiwan.

The ISPACS is a premium international forum for leading researchers especially from Asia-Pacific basin in the highly active fields of theory, design and implementation of signal processing and communication systems. The ISPACS has a long history. The ISPACS has been held in nine countries including USA. The first conference of ISPACS was held in Taipei, Taiwan in 1992. After 27 years, it is the third time for this significant event to be held in Taipei. As always, ISPACS aims to serve as a platform for all professionals to discuss the latest findings and state-of-the-art technologies, create opportunities for young scholars to participate in international academic activities, as well as stimulate commercial activities and industrial development. In addition, ISPACS 2019 provides a nice chance to participants from all around the world to visit the beautiful city, Taipei.

I would like to show my sincere appreciations to all the organizing committee members led by Prof. Jing-Ming Guo for their great contributions to ISPACS 2019. Welcome all participants to ISPACS 2019!

Akira Taguchi

Chair, International Steering Committee of ISPACS Tokyo City University, Japan

(5)

As the president of National Taiwan University of Science and Technology, I have the great honor to welcome leading experts, professors, friends and colleagues gathering here. It is our pleasure to host the event of the 2019 International Symposium on Intelligent Signal Processing and Communication Systems. I would like to thank all of you who work so hard as the educator of technology pioneer that stand at the front line of intelligent signal processing and communication systems issues. Your generous support has made significant contribution to Taiwan and the world.

Taiwan Tech was formerly known as the National Taiwan Institute of Technology, the first higher education institution of its kind within our nation's technical and vocational education system, seeking to develop highly trained engineers and managers. Over the last 40-plus years since its foundation, NTUST has focused on developing academic research, teaching, and learning services with an innovative spirit. The Department of Electrical Engineering was founded in 1978 with the mission of providing the society with high-quality education pertinent to the electrical engineering discipline, in response to the rapid growth of science and technology industries. To pursue excellence in research, teaching, and service in the area of electrical engineering, graduate programs were established in 1979 (MS) and 1982 (PhD). By incorporating a wide selection of advanced courses and opportunity of conducting independent research, students were trained to possess in-depth frontier knowledge, high technical skills, and planning ability that are vital to their future careers in industry or academia. It is much honored to have our Department of Electrical Engineering to make such great contribution to Taiwan, as well as to ISPACS 2019.

Again, I would also like to express my sincere gratitude to all of your fabulous dedication. Wish you can enjoy the conference and Taipei in the following days.

Best Regards,

Ching-Jong Liao

Honorary Chair of ISPACS 2019

President, National Taiwan University of Science and Technology, Taiwan

(6)

I would like to express a warm welcome to all of you joining the 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2019) held in Beitou, Taipei, Taiwan on December 3-6, 2019.

Since 1992, the ISPACS has become one of the major symposia in the signal processing and communication systems field. ISPACS provides excellent opportunities for researchers from academia and industries all around the world to report and discuss the latest applications on signal processing and communication systems technologies and innovations.

In view of the current technologies, artificial intelligence has made its way into many areas and become indispensable. To improve human welfare, we set up the main theme of ISPACS 2019 as “Impact of Artificial Intelligence: From Reality to Imagination, from Technologies to Applications”. Recently, the development and application of artificial intelligence has grown rapidly. Thus, ISPACS 2019 aims to keep on exploring and exchanging up-to-date techniques and findings, integrate and commercialize this research so as to bring the results into full play.

On behalf of the organizing committee, I would like to express the appreciation for your endeavors and contributions to this symposium to make it meaningful. On top of that, Beitou is a beautiful city with interesting things to do and enchanting places to visit. It is particularly famous for hot spring. We believe you will have marvelous experiences and memories at ISPACS 2019!

Sincerely Yours,

Jing-Ming Guo

General Chair of ISPACS 2019

Distinguished Professor, Department of Electrical Engineering, National Taiwan University of Science and Technology, Taiwan

(7)

On behalf of the Technical Program Committee of the 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS 2019), we would like to take this opportunity to appreciate all of your participation in ISPACS 2019. We also want to express our gratitude to the Organizing Committee, especially the General Chair Prof. Jing-Ming Guo. This symposium would not have been possible without their guidance and effort.

This year, ISPACS 2019 attracted 295 submissions from 15 countries, from which 191 high-quality papers were accepted through a conscientious and careful review. Among 191 accepted papers, 161 papers are selected for oral presentation, and 30 papers for poster presentation.

During this four-day conference, we are going to experience different discussion sections and events, including 4 keynote speeches, 4 invited speeches, and various paper presentations through 28 lecture sessions and 2 poster sessions.

We hope that all participants will benefit from this symposium and gain new ideas for future research, while keeping abreast of the current development in the field of signal processing and communication systems.

Please enjoy the technical program and have a great time here in Beitou, Taipei!

Best Regards,

Prof. Chih-Hsien Hsia

Technical Program Chair of ISPACS 2019 National Ilan University, Taiwan

Prof. KokSheik Wong

Technical Program Chair of ISPACS 2019 Monash University Malaysia, Malaysia

(8)

Wednesday, Dec. 4, 2019 09:00-10:00 Pearl Banquet Hall

Prof. Ioannis Pitas

Department of Informatics Aristotle University of Thessaloniki Greece

IEEE Fellow / IEEE Distinguished Lecturer / EURASIP Fellow

Deep Learning and Computer Vision for Multiple Drone Media Production

The aim of drone cinematography is to develop innovative intelligent single-and multiple-drone platforms for media production to cover outdoor events (e.g., sports) that are typically distributed over large expanses, ranging, for example, from a stadium to an entire city. The drone or drone team, to be managed by the production director and his/her production crew, will have: a) increased multiple drone decisional autonomy, hence allowing event coverage in the time span of around one hour in an outdoor environment and b) improved multiple drone robustness and safety mechanisms (e.g., communication robustness/safety, embedded flight regulation compliance, enhanced crowd avoidance and emergency landing mechanisms), enabling it to carry out its mission against errors or crew inaction and to handle emergencies. Such robustness is particularly important, as the drones will operate close to crowds and/or may face environmental hazards (e.g., wind).

Therefore, it must be contextually aware and adaptive, towards maximizing shooting creativity and productivity, while minimizing production costs.

Drone vision plays an important role towards this end, covering the following topics: a) drone visual mapping and localization, b) drone visual analysis for target/obstacle/crowd/POI detection, c) 2D/3D target tracking and d) privacy protection technologies in drones (face de-identification).

This lecture will offer an overview of current research efforts on all related topics, ranging from visual semantic world mapping to multiple drone mission planning and control and to drone perception for autonomous target following, tracking and AV shooting.

Biography

Prof. Ioannis Pitas (IEEE fellow, IEEE Distinguished Lecturer, EURASIP fellow) received the Diploma and PhD degree in Electrical Engineering, both from the Aristotle University of Thessaloniki, Greece. Since 1994, he has been a Professor at the Department of Informatics of the same University. He served as a Visiting Professor at several Universities.

His current interests are in the areas of image/video processing, machine learning, computer vision, intelligent digital media, human centered interfaces, affective computing, 3D imaging and biomedical imaging. He has published over 1090 papers, contributed in 50 books in his areas of interest and edited or (co-)authored another 11 books. He has also been member of the program committee of many scientific conferences and workshops.

In the past he served as Associate Editor or co-Editor of 9 international journals and General or Technical Chair of 4 international conferences. He participated in 69 R&D projects, primarily funded by the European Union and is / was principal investigator/researcher in 41 such projects. He has 28600+ citations to his work and h-index 81+ (Google Scholar).

Prof. Pitas leads the big European H2020 R&D project MULTIDRONE: https://multidrone.eu/. He is chair of the Autonomous Systems initiative http://asi.politecnica.unige.it/.

(9)

Thursday, Dec. 5, 2019 09:00-10:00 Pearl Banquet Hall

Sr. Managing Director Tihao Chiang

Ambarella Taiwan Ltd.

Taiwan Fellow of IEEE

Ultra HD Computer Vision Processor for Autonomous Driving Applications

Low power computer vision processor has found its wide applications such as sports camera, cell phone, flying camera and automotive camera for ADAS and autonomous driving applications. To achieve a computer vision processor with high quality, ultra HD definition image processing and encoding, it is critical to consider various design parameters such as features, complexity, die size, power while maintaining maximal flexibility for the system designers to innovate and customize for product differentiation. We will describe how to perform trade- off considerations in designing a cost-effective computer vision multimedia processor for mobile and low power applications. We will also discuss the possible applications for such processors.

Biography

Tihao Chiang received the Ph.D. degree from Columbia University in 1995. In 1995-1999, he was a program manager at David Sarnoff Research Center (formerly RCA laboratory). In 1999-2008, he was an associate professor at National Chiao-Tung University in Taiwan, R.O.C. He is now with the Ambarella Taiwan Ltd. Dr. Chiang is currently a Fellow of IEEE and holder of over 50 US and worldwide patents. He published over 100 technical journal and conference papers in the field of video and signal processing.

(10)

Mr. Pat Hsu

Business Consultant & Head of Enterprise and IIOT Service Unit Nokia Networks

Taiwan

Making 5G Use Case a Commercial Reality

In the mobility space, three major forces will make smart, green and cognitive networks essential over the next five years: 5G, IoT and AI. The intersection of AI, 5G and IoT technologies will bring intelligent connectivity to the world. Nokia is “creating the technology to connect the world”. Soon people will see those vertical applications coming to their daily life once commercial 5G service launch such as:

1. Autonomous driving: AI, connectivity and data will be as important as the vehicle itself, from driving safety to connected autonomous driving.

2. Smart manufacturing: large-scale adoption of robotics and AI-based solutions adds new network requirements.

3. Mobile operators are deploying 5G with AI to create AI-as-a-service or analytics-as-a-service solutions such

as video surveillance and analytics for Smart City, Seaport or Airport etc..

During our sharing, the latest 5G technology development, market deployment, ecosystem buildup and commercial ready use cases will be introduced and discussed.

Biography

Mr. Pat Hsu re-joined Nokia Networks Greater China in 2014, as the head of Strategy and Business Operations for China Telecom Customer Business Team, he had successfully to expand the China Telecom customer business from multi-million sales per annum in 2014 to global tier 1 customer in 2017, he was relocated to Taipei since 2018 to lead Business Consulting service team and now is head of Enterprise and IIoT Service Unit in Nokia Networks. He is currently working with key partners for 5G Use Cases implementation in Connected Car (Autonomous Driving & C-V2X) deployment and Industry 4.0 ecosystem build up in Taiwan and Greater China regions. Prior to rejoin Nokia Network Greater China, he worked with Accenture to serve Huawei technologies in Next Generation Service Delivery Platform consulting service transformation program as lead SME and Project manager since October, 2013. He spent past 30 years work for HP, Ericsson, Nokia Networks, China ComService and various business development, sales and marketing management roles. He holds M.S. in Computer Science from Florida State University in Tallahassee, Florida USA, and Master of Business Administration (MBA) from Kellogg School of Management, Northwestern University Evanston, Illinois, USA and Hong Kong University of Science & Technology, Hong Kong, China.

(11)

Friday, Dec. 6, 2019 09:00-10:00 Pearl Banquet Hall

Prof. Pierre Moulin

Department of Electrical and Computer Engineering University of Illinois

USA

IEEE Fellow / Editorial Boards, IEEE Transactions on Information Theory / IEEE Transactions on Image Processing/ Proceedings of IEEE

Forgery Detectors for Adversarial Machine Learning

Deep neural networks achieve state-of-the-art performance for several image classification problems but have been shown to be easily fooled by adversarial perturbations which slightly modify a legitimate image in a specific direction and are visually indistinguishable from the original. This presents a security risk for applications such as autonomous systems. We tackle the problem of detecting such "forgeries" by constructing a locally optimal detector that is well suited to detecting weak signal perturbations. Our general approach is closely related to steganalysis. To illustrate the approach, we present a procedure for learning the forgery detector from a training set, using generative models for image patches. A random ensemble of patches is used for detection of the forgery. The reliability of such detectors is assessed theoretically and experimentally.

Biography

Prof. Pierre Moulin received his doctoral degree in 1990, after which he joined at Bell Communications Research as a Research Scientist.

In 1996, he joined the University of Illinois at Urbana-Champaign, where he is currently Professor in the Department of Electrical and Computer Engineering, Research Professor at the Coordinated Science Laboratory and the Beckman Institute and the Coordinated Science Laboratory, and affiliate professor in the Department of Statistics.

His fields of professional interest include statistical decision theory, statistical signal processing and modeling, machine learning, information security, and Shannon theory. Dr. Moulin has served on the editorial boards of the IEEE Transactions on Information Theory, the IEEE Transactions on Image Processing, and the Proceedings of IEEE. He was co-founding Editor-in-Chief of the IEEE Transactions on Information Forensics and Security (2005- 2008), member of the IEEE Signal Processing Society Board of Governors (2005-2007), member of the IEEE Information Theory Society Board of Governors (2016-present) and has served IEEE in various other capacities.

He is co-recipient of two best paper awards from the IEEE Signal processing Society and was plenary speaker for ICASSP, ICIP, and several other conferences.

He is an IEEE Fellow (2003) and was Distinguished Lecturer of the IEEE Signal Processing Society for 2012-2013 and co-chair of the technical program for ISIT 2015. He was UIUC Sony Faculty Scholar and is the recipient of the 2018 Ronald W. Pratt Faculty Outstanding Teaching Award.

(12)

Prof. Juichi Kosakaya

Graduate Electrical, Electronic & Computer Eng.

Hachinohe Institute of Tech.

Japan

Automated Music Scoring System Based on Deep-Leaning Method for Japanese Traditional Instruments Tsugaru-Shamisen

Aomori is located in the most northern pref. of main land in Japan. And it is uniquely situated within the amalgam of local instruments Tsugaru traditional local arts. Recently, the city’s traditional music preservation society and schools have eagerly wished a technology to precisely score local music, especially traditional Tsugaru Shamisen.

This music will be preserved as Western & Shamisen scores, which avoid relying individually on the oral education of this kind of traditional local music for trainees. In this research, “Electronic Shamisen” has been invented with pick-up microphones attached with strings and automated scoring equipment, which automatically records scores from the sound resources by Deep learning / cooperative agent method.

Biography

Prof. Juichi Kosakaya received his PhD degree in Electronic Eng. at Tokyo Institute of Tech. in 2002, after which he joined at Hitachi Engineering Co., Ltd. as a Researcher & Engineer.

In 1976, he started his career as an Engineer on fields of Computer Systems, Remote Control Supervisory Systems, Water Control Systems, Artificial Intelligent Systems, etc., at Hitachi Engineering Co., Ltd.

He has invented more than 50 patents on that field in Japan and Foreign countries.

In 2005, he joined the Hachinohe Institute of Tech., where he is currently a Professor in the Department of Electrical Electronic and Computer Engineering at Graduate School as a Research Professor on the field of Sound Engineering, Artificial Intelligence and System Engineering.

His current interests are in the areas of an Automated Music Scoring System based on Deep-Learning Method /Cooperative Multi-Agent Method for Japanese traditional instruments such as Tsugaru-Shamisen.

He would like to utilize this technology to the scoreless local music fields in East Asia.

He has recently donated more than 60 music scores (Western & Local) made by this system to Japanese prefectural governments. Also, he is very interested in various instruments of local music in east Asia.

He would like to make appropriate scores from the scoreless local music instruments in East Asia in the future.

In 2019, he received the Cultural Encouragement Award of Tohoku district in Japan.

(13)

Prof. Yuei-An Liou

National Central University Taiwan

Formulas for Defining Dual-Typhoon Interactions and Eco-Environmental Vulnerability Assessment Frameworks with Earth Observations & GIS

This speech presents examples of the use of remote sensing data and GIS for investigating critical environmental issues that can be considered by the community in the field of Artificial Intelligence for further study. The first example is the analysis and interpretation of dual-typhoon interactions and super-typhoon formation with emphasis on the development of the Liou-Liu empirical formulas. The formulas successfully quantify the threshold distance for defining dual-vortex interactions based on a variety cases. Secondly, the speech introduces the development of eco-environmental vulnerability assessment frameworks for various spatial scales from region to globe. The outputs of the frameworks are the mapping of vulnerability level of the study area for the authority to consider the planning of the possible measures for environmental protection and management.

Biography

YUEI-AN LIOU received the M.S.E. degree in electrical engineering (EE), the M.S. degree in atmospheric and space sciences, and the double Ph.D. degree in EE and atmospheric, oceanic, and space sciences from the University of Michigan, Ann Arbor, in 1992, 1994, and 1996, respectively. Dr. Liou is a Distinguished Professor and Head of Hydrology Remote Sensing Laboratory, Center for Space and Remote Sensing Research, National Central University, Taiwan; Founder & Honorary President, Taiwan Group on Earth Observations (2016/8~); Vice President, Chinese Federation of Surveying & Mapping (2016/2~); Honorary President, Vietnamese Experts Association in Taiwan (2017/1~). Dr. Liou received numerous awards: Foreign Member, Prokhorov Russian Academy of Engineering Sciences in 2008; Outstanding Alumni Awards, University of Michigan Alumni Association in Taiwan & National Sun Yat-sen University in 2008; Member, International Academy of Astronautics in 2014; Fellow, The Institution of Engineering and Technology in 2015; Crystal Achievement Award, Vietnam Academy of Science and Technology, Vietnam, in November 2019.

(14)

Prof. Toshihisa Tanaka

Institute of Global Innovation Research

Department of Electrical and Electronic Engineering Tokyo University of Agriculture and Technology (TUAT) Japan

Development of a Diagnostic-Aid Platform for Epileptic Electroencephalogram

Epilepsy is a chronic disorder that causes unprovoked, recurrent seizures. Epilepsy accounts for a significant proportion of the world’s disease burden, affecting around 50 million people worldwide, and the estimated proportion of the general population with active epilepsy at a given time is between 4 and 10 per 1000 people (World Health Organization; WHO). To diagnose epilepsy, the most common test is to measure electroencephalogram (EEG).

Brain abnormalities appears as abnormal signal patterns in the recorded EEG. However, the recording typically lasts hours, sometimes days. This yields a heavy burden for clinical specialists, and the number of specialists are relatively small for the number of patients. For example, in Japan, there are about 700 authorized specialists over a whole country, while there are about a million epilepsy patients. In this talk, I would like to introduce our project on development of the platform for AI-based diagnostic-aid to help specialists to interpret EEG signals.

One of the topics in the project is to detect characteristic spikes, which are often observed in the EEG of epileptic patients in order to diagnose the disorder. Several methods have been investigated to automatically detect such spikes. The most common methods employ sub-band decomposition with discrete wavelet transform (DWT) or other filters to preprocess the EEG data before feeding it into a machine learning model. I would like to introduce a fully data-driven method that automatically determines EEG frequency bands of interest. The raw signal is fed into a convolutional layer to detect suitable frequency bands, followed by a feedforward convolutional neural network (CNN) model or recurrent neural network (RNN) models for epileptic spike and non-spike classification. Fitting data of six patients, annotated by an epilepsy specialist, resulted in a convolutional layer with a frequency characteristic similar to bandpass filters. This result strongly justifies limiting the bandwidth of a signal, as done in previous studies.

Moreover, results of the cross-subject validation indicate that a classical support vector machine with fixed preprocessing achieves comparable performance in the classification with fully data-driven models.

Biography

Toshihisa Tanaka received the B.E., the M.E., and the Ph.D. degrees from the Tokyo Institute of Technology in 1997, 2000, and 2002, respectively. From 2000 to 2002, he was a JSPS Research Fellow. From October 2002 to March 2004, he was a Research Scientist at RIKEN Brain Science Institute. In April 2004, he joined Department of Electrical and Electronic Engineering, the Tokyo University of Agriculture and Technology, where he is currently a Professor. In 2005, he was a Royal Society visiting fellow at the Communications and Signal Processing Group, Imperial College London, U.K. From June 2011 to October 2011, he was a visiting faculty member in Department of Electrical Engineering, the University of Hawaii at Manoa.

His research interests include a broad area of signal processing and machine learning including brain and biomedical signal processing, brain-machine interfaces and adaptive systems. He is a co-editor of Signal Processing Techniques for Knowledge Extraction and Information Fusion (with Mandic, Springer), 2008 and a leading co-editor of Signal Processing and Machine Learning for Brain-Machine Interfaces (with Arvaneh, IET, UK), 2018.

He served as an associate editor and a guest editor of special issues in journals including Neurocomputing and IEICE Transactions on Fundamentals and Computational Intelligence and Neuroscience (Hindawi). Currently he serves as an associate editor of IEEE Transactions on Neural Networks and Learning Systems, Applied Sciences (MDPI), and Advances in Data Science and Adaptive Analysis (World Scientific). Furthermore, he serves as a member-at-large, board of governors (BoG) of Asia-Pacific Signal and Information Processing Association (APSIPA). He was a chair of the Technical Committee on Biomedical Signal Processing, APSIPA. He is a senior member of IEEE, and a member of IEICE, APSIPA, Japan Epilepsy Society, and Society for Neuroscience.

(15)

Friday, Dec. 6, 2019 10:20-10:40 Pearl Banquet Hall

Prof. Chee Seng Chan

University of Malaya Malaysia

Intellectual Property Protection of Deep Learning Models

With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. Following recent progresses along this line, we investigate a number of watermark-based DNN ownership verification methods in the face of ambiguity attacks, which aim to cast doubts on the ownership verification by forging counterfeit watermarks. It is shown that ambiguity attacks pose serious threats to existing DNN watermarking methods. As remedies to the above-mentioned loophole, this paper proposes novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks. The gist of embedding digital passports is to design and train DNN models in a way such that, the DNN inference performance of an original task will be significantly deteriorated due to forged passports. In other words, genuine passports are not only verified by looking for the predefined signatures, but also reasserted by the unyielding DNN model inference performances. Extensive experimental results justify the effectiveness of the proposed passport-based DNN ownership verification schemes. Code and models are available at https://github.com/kamwoh/DeepIPR.

Biography

Chee Seng Chan received the Ph.D. degree from University of Portsmouth, U.K. in 2008. Currently, he is a Associate Professor at the Faculty of Computer Science and Information Technology, University of Malaya.

His research interests include computer vision and machine learning with focus on scene understanding. He is also interested in the interplay between language and vision: generating sentential descriptions about complex scenes. He published over 100 technical journal and conference papers in the field of computer vision and machine learning. He is a Senior Member of IEEE, a Chartered Engineer of IET.

(16)

P1-1

Residual Concatenated Network for ODBTC Image Restoration

Alim Wicaksono, Heri Prasetyo, Indonesia; Jing-Ming Guo, Taiwan P1-2

Trend Prediction of Influenza and the Associated Pneumonia in Taiwan Using Machine Learning

Sing-Ling Jhuo, Mi-Tren Hsieh, Ting-Chien Weng, Mei-Juan Chen, Chieh-Ming Yang and Chia-Hung Yeh, Taiwan

P1-3

A Modified Structural Similarity Index with Low Computational Complexity

Woei-Tan Loh and David Bong, Malaysia P1-4

Quality Enhancement of DDBTC Decoded Image Joni Welman Simatupang and Heri Prasetyo, Indonesia P1-5

A 10-bit 100-MHz Current-Steering DAC with Randomized Thermometer Code Calibration Scheme

Hsin-Liang Chen, Ming-Han Hsieh and Jem-Shiun Chiang, Taiwan P1-6

Reconfirm Gestalt Principles from Scan-Path Analysis on Viewing Photos

Hsien Chih Chuang and Da Lun Tang, Taiwan P1-7

Controlling Myopia Progression in Children by the Rotary Prism Eye Exercise Device

Der-Chin Chen, Jih-Yi Liao, Wei-Hsin Chen, Po-Ting Liu and Shih- Tsung Chang, Taiwan

P1-8

Merge Mode-Based Data Embedding in SHVC Compressed Video

Kok Sheik Wong, Lie Lin Pang and Ryoma Ito, Malaysia P1-9

Unpaired Object Transformation Based on Generative Adversarial Networks

Jing-Ming Guo, Yun-Fu Liu and Chang-Chun Chu, Taiwan P1-10

An End to End Single Image Dehazing System Based on Dense Block and Hybrid Loss Function

Jing-Ming Guo and Yen-Chia Su, Taiwan P1-11

Nighttime Image Dehazing Based on Improved Erosion Dark Channel and Multi-Scale Clipping Limit Histogram

Equalization

Jing-Ming Guo and Chia-Hsiang Lin, Taiwan P1-12

Reconstruction of Ordered Dithering Halftone Image Jing-Ming Guo, Hung Le and Sankarasrinivasan Seshathiri, Taiwan P1-13

User Trajectory Analysis within Intelligent Social Internet-of- things (SIoT)

Guang Xing Lye, Wai Khuen Cheng, Teik Boon Tan, Zeng-Wei Hong, Malaysia; Yen-Lin Chen, Taiwan

P1-14

Crowd Behavior Classification Based on Generic Descriptors Pei Voon Wong, Norwati Mustapha, Lilly Suriani Affendey, Fatimah Khalid, Malaysia; Yen-Lin Chen, Taiwan

P1-15

Actived Edge Strength for Image Quality Assessment Minjuan Gao and Xuande Zhang, China