ICS2018

Keynote Speaker : Prof. Reinhard Klette

(Auckland University of Technology, Fellow of the Royal Society of New Zealand, Quancheng Friendship Award, Helmholtz Fellow) made significant contributions to two major areas, digital geometry and computer vision. He is the director of the Centre for Robotics & Vision (CeRV).

Title

Towards Self-driving Cars: Test Fields, Visual Odometry, Stixels and Road-surface Analysis

Abstract

Self-driving cars use various sensors, to be tested on extensive test fields under location-, weather-, and traffic-specific conditions. One test field (N3T) is currently developing near Whangarei in New Zealand, in collaboration with the German Air- and Space Centre (DLR) and Auckland University of Technology (AUT). In the context of test field studies, the talk informs especially about computer-vision based components towards self-driving cars. Visual odometry supports exact geo-localisation of vehicles on the road, and in particular also accurate 3-dimensional roadside reconstruction, thus improving GPS/IMU-only based approaches.

Different camera configurations (mono, bi, or tri-nocular) contribute to the options for sensor configurations in self-driving cars. The talk discusses results for visual odometry and stixel calculations (stixels are an important intermediate result within a semantic segmentation framework) for evaluating different camera configurations. It is also demonstrated how visual odometry provides important information for improved road-surface distress analysis.

The talk reports about joint work with colleagues and students at AUT, DLR, and N3T.

Biographical Sketch

Professor Klette has been working in the area of computer vision for more than 30 years. In 2003 he published with the late Professor Azriel Rosenfeld of University of Maryland, USA, the first comprehensive monography on digital geometry (published by Morgan Kaufmann, San Francisco). He has become internationally renouned for his work in vision-based driver assistance since 2006, with important contributions on performance evaluation and improvements of correspondence algorithms (for stereo matching and optical flow) on realworld video data, supporting, for example, 3D scene reconstruction from a mobile platform.

In 2008 he co-authored (with two of his former PhD students) a research monograph on panoramic vision (with Wiley, UK), in 2011 a research monograph (also co-authered with a former PhD student) on shortest paths in Euclidean spaces (with Springer, UK), and in 2017 a research monograph (also co-authered with a former PhD student) on vision-based driver assistance (with Springer, The Netherlands). His book entitled “Concise Computer Vision” has been published by Springer, London (UK), on 5 January 2014. In August 2018, the number of downloads of e-copies of this book, or parts of it, from Springer’s website surpassed the 61,000 mark. This is an exceptional high number for any computer science textbook published by Springer.

Since 1995, Professor Klette has been invited as a keynote or plenary speaker to international conferences worldwide. Between April 2011 and October 2013 he has been the founding Editorin- Chief of the Journal of Control Engineering and Technology (JCET). He was an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) between 2001 and 2008, which is a top-ranked journal in all engineering and computer science disciplines. He is a life-time honorary steering committee member of the biennial conferences on Computer Analysis of Images and Patterns, taking place in Europe, and a steering committee member of the Pacific- Rim Symposium on Image and Video Technology.

Professor Klette supervised already 30 PhD students to the successful completion of their PhD program.


Keynote Speaker : Yi-Bing Lin

Title

CampusTalk: IoT Devices and Their Interesting Features on Campus Applications

Abstract

Internet of Things (IoT) allows interactive learning of students by inspiring their innovation everywhere on the campus. This paper proposes CampusTalk that provides convenient access to cyber and physical devices through the web technology. In this way, the campus applications can be accessed anywhere in the world through any computing device with a display and a browser without installing any mobile app. CampusTalk unifies the concepts of automatic creation of “mirror device features” (simulated counterpart) and talkPal device features, which are nicely demonstrated through several applications on campus. The core application of CampusTalk is SmartPhoneTalk that allows other applications to be accessed by students through their smartphones without installing any mobile apps. We describe three CampusTalk applications, including MusicTalk, PingPongTalk and SkeletonTalk, to demonstrate cyber and physical interaction with SmartPhoneTalk. After the IoT devices of these applications have been developed and are accommodated in CampusTalk, the students can use the CampusTalk GUI to connect them with various combinations for innovative applications without extra programming effort.

Biographical Sketch

Yi-Bing Lin received his Bachelor’s degree from National Cheng Kung University, Taiwan, in 1983, and his Ph.D. from the University of Washington, USA, in 1990. From 1990 to 1995 he was a Research Scientist with Bellcore (Telcordia). He then joined the National Chiao Tung University (NCTU) in Taiwan, where he remains. In 2011, Lin became the Vice President of NCTU. Since 2014, Lin has been appointed as the Deputy Minister of Ministry of Science and Technology, Taiwan. After 2016, he become a lifetime Chair Professor of NCTU.Lin is also an Adjunct Research Fellow, Institute of Information Science, Academia Sinica, Research Center for Information Technology Innovation, Academia Sinica, and a member of board of directors, Chunghwa Telecom. He serves on the editorial boards of IEEE Trans. on Vehicular Technology. He is General or Program Chair for prestigious conferences including ACM MobiCom 2002. He is Guest Editor for several journals including IEEE Transactions on Computers. Lin is the author of the books Wireless and Mobile Network Architecture (Wiley, 2001), Wireless and Mobile All-IP Networks (John Wiley,2005), and Charging for Mobile All-IP Telecommunications (Wiley, 2008). Lin received numerous research awards including 2005 NSC Distinguished Researcher, 2006 Academic Award of Ministry of Education and 2008 Award for Outstanding contributions in Science and Technology, Executive Yuen, 2011 National Chair Award, and TWAS Prize in Engineering Sciences, 2011 (The World Academy of Sciences). He is in the advisory boards or the review boards of various government organizations including Ministry of Economic Affairs, Ministry of Education, and Ministry of Transportation and Communications. Lin is AAAS Fellow, ACM Fellow, IEEE Fellow, and IET Fellow.


Keynote Speaker : Hitoshi KIYA

Title

Privacy-Preserving Image Compression and Learning for Untrusted Cloud Environments –Toward Compressible and Learnable Encryption

Abstract

With the wide/rapid spread of distributed systems for information processing, such as cloud computing and social networking, not only transmission but also processing is done on the internet. However, cloud environments have some serious issues for end users, such as unauthorized access, data leaks, and privacy compromise, due to unreliability of providers and some accidents. Accordingly, we first focus on compressible image encryption schemes, which have been proposed for encryption-then-compression (EtC) systems, although the traditional way for secure image transmission is to use a compression-then encryption (CtE) system. EtC systems allow us to close unencrypted images to network providers, because encrypted images can be directly compressed even when the images are multiply recompressed by providers. Next, we address the issue of learnable encryption. Huge training data sets are required for machine learning and deep learning algorithms to obtain high performance. However, it requires large cost to collect enough training data while maintaining people’s privacy.

Biographical Sketch

Hitoshi Kiya received his B.E and M.E. degrees from Nagaoka University of Technology, in 1980 and 1982 respectively, and his Dr. Eng. degree from Tokyo Metropolitan University in 1987. In 1982, he joined Tokyo Metropolitan University, where he became a Full Professor in 2000. From 1995 to 1996, he attended the University of Sydney, Australia as a Visiting Fellow. He is a Fellow of IEEE, IEICE and ITE. He currently serves as President-Elect of APSIPA, and he served as Inaugural Vice President (Technical Activities) of APSIPA from 2009 to 2013, and as Regional Director-at-Large for Region 10 of the IEEE Signal Processing Society from 2016 to 2017. He was also President of the IEICE Engineering Sciences Society from 2011 to 2012, and he served there as a Vice President and Editor-in-Chief for IEICE Society Magazine and Society Publications. He was Editorial Board Member of eight journals, including IEEE Trans. on Signal Processing, Image Processing, and Information Forensics and Security, Chair of two technical committees and Member of nine technical committees including APSIPA Image, Video, and Multimedia Technical Committee (TC), and IEEE Information Forensics and Security TC. He has organized a lot of international conferences, in such roles as TPC Chair of IEEE ICASSP 2012 and as General Co-Chair of IEEE ISCAS 2019. He has received numerous awards, including six best paper awards.


Keynote Speaker : Raul Catena

Title

Extracting Insights and Automating Computational Pathology Using Deep Learning

Abstract

During the recent years, image digitization and unprecedented means of connectivity have transformed the medical field. Currently, a majority of hospitals utilize digital image storage and diagnosis reporting, enabling faster and cheaper acquisition of second opinions and speeding the pathology laboratory routine. The next challenge entails the medical image analysis itself, which is yet done mainly manually by human operators. Quantitative measurements and search of well-defined patterns across large image areas are repetitive tasks that are limited by doctors throughput and bias. At IBM, we are developing image analysis pipelines that automate many aspects of the pathology laboratory routine, expose multiple accurate quantitative measurements to the doctor to aid his/her decision, report rare patterns and motifs found through whole slide analysis, which could be otherwise easily overlooked by manual inspection, and suggest grading and diagnosis as a digital second opinion. Over the next years, computational pathology platforms such as IBM´s will provide pathologists a wealth of data and automation that will ease and improve their routine work and improve outcomes.

Biographical Sketch

I am a molecular biologist and histologist with years of experience in cancer research. My main focus areas have been the tumour microenvironment and drug discovery to target non-cancer cells, especially immune components, involved in the disease. Examples of that is my research on VEGF isoforms and VEGF inhibitors to target angiogenesis, discovery of pathways to target cancer using known TKIs, such as Sunitinib, to block metas tasis through targeting bone-marrow stromal cells, or neutrophil protease inhibition to block metastasis spread in the lung. This latter work has started a full effort on using such inhibitors for dual targeting of emphysema, COPD, and lung cancer, which is associated with the former conditions. My work has spanned preclinical models and clinical sample analysis. During the last years, I have also entered the fascinating world of Artificial Intelligence to analyse multiparametric molecular data from patient tissue samples. Having experienced by myself multiple times that target discovery (and in some cases, rediscovery) can open real opportunities for the patients, and in today ́s new scenario of multiple data sources and omics being integrated in a holistic manner, partly with the help of the upcoming AI-based technologies, I envision a new era of target discovery and rediscovery led by computational analysis with machine learning and other AI-based technologies. This is an exciting area of research and development that I feel ready to join and contribute with my dual experience as an oncology experimentalist and computational biologist.