Day 1 :
Keynote Forum
K Asari Vijayan
University of Dayton, USA
Keynote: Visual perception for autonomy application to object detection and behavior analysis in complex environmental conditions
Time : 09:15-10:00
Biography:
Vijayan K Asari is a Professor in Electrical and Computer Engineering and Ohio Research Scholars Endowed Chair in Wide Area Surveillance at the University of Dayton (UD), Dayton, Ohio, USA. He is the Director of the Center of Excellence for Computer Vision and Wide Area Surveillance Research at UD. He received his PhD in Electrical Engineering from the Indian Institute of Technology, Madras in 1994. Prior to joining UD in February 2010, he worked as Professor in Electrical and Computer Engineering at Old Dominion University, Norfolk, Virginia for 10 years. He holds three patents and has published more than 600 research papers in the areas of image processing, pattern recognition, machine learning, neural networks and high performance embedded systems. He has supervised 26 PhD dissertations and 40 MS theses in electrical and computer engineering. Currently several Masters and Doctoral level graduate students are working with him. He has received several teaching, research, advising and technical leadership awards including the University of Dayton, School of Engineering Vision Award for Excellence in August 2017, the Sigma Xi George B Noland Award for Outstanding Research in April 2016, and the Outstanding Engineers and Scientists Award for Technical Leadership from The Affiliate Societies Council of Dayton in April 2015. He is a Senior Member of IEEE and SPIE, and is a co-organizer of several SPIE and IEEE conferences and workshops.
Abstract:
Automated visual monitoring involves data acquisition, analysis, and interpretation for understanding objects and object behaviors. Automated visual data analysis systems are mostly used for military, law enforcement and commercial applications. Sensors of different types and characteristics in various platforms are used for the acquisition of data. In recent years, there has been a spurt in the development of palm-sized cameras for the consumer market that are equipped with fish eye lenses on front and back sides to deliver 360 degree spherical views. Intelligent analysis of these data is an important task in applications such as automatic human detection, identification, activity recognition, behavior analysis, anomaly detection, alarming, etc. Object motion analysis and interpretation are integral components for activity monitoring and situational awareness. We present the development of a robust automated system which can detect and identify people using imagery captured using visible, infrared and omnidirectional cameras in a mobile platform and track their actions and activities by a spatiotemporal feature tracking mechanism. The automated visual analysis procedure includes preprocessing of data for distortion correction, novel methods for feature extraction, and machine learning based approaches for object classification.
Keynote Forum
Christl Lauterbach
Future-Shape GmbH, Germany
Keynote: SensFloor®: Human movement tracking and more
Time : 10:00-10:45
Biography:
Christl Lauterbach founded the Future-Shape GmbH, Germany in 2005 and is Managing Director since then. Main product of Future-Shape is SensFloor, a large-area sensor floor. From 1999 until 2005 she was at Infineon Technologies AG, Corporate Research, Senior Staff Engineer for Emerging Technologies, and Project Manager for Smart Textiles. Before that, she worked 22 years at Siemens AG, Corporate Research and Technology, as a developer for Semiconductor Technology and Circuit Design. Education: Assistance Degree in Electrical/Communication Engineering. She has more than 200 patents and patent pending, and >100 scientific publications
Abstract:
The described sensor floor is a textile-based large-area sensor system, which is installed as an underlay beneath the flooring. It detects people moving across the floor, calculates their trajectories and distinguishes between foot steps and a fall. The use of capacitive proximity sensing instead of pressure sensing gives high flexibility in floor design: even non-elastic flooring, like laminate parquet or tiles are suitable. The installed system is invisible and unobtrusive compared to camera systems. The SensFloor system enables a variety of different applications in the domain of ambient assisted living (AAL) like fall detection, activity monitoring, energy savings, control of automatic doors, intrusion alarm and access control. Presence detection and human movement tracking provide valuable data for Internet of things (IoT) scenarios like i.e. behavioral analysis in retail, workspace, living or healthcare. For example, it allows care organizations to optimize their workflows and improve quality of care. In future, artificial intelligence will provide means to evaluate the health status of people walking on the floor. The proposed processing scheme is able to extract behavioral information from the sensor data, which is fed into a learning algorithm that internally represents typical patterns, and outputs a measure for the divergence of current behavior from typical behavior. Gait pattern analysis by SensFloor provides objective data for medical diagnosis by medical experts like neurologists or physiotherapists. Gait parameters like walking speed, step length, and straightness are important factors for the health status of patients. Regular assessments during the treatment indicate the success of medication and rehabilitation.
Keynote Forum
Andreas Greilhuber
Chief Operating Officer Anyline.com, Austria.
Keynote: The journey from convolutional neural network to real customer value
Time : 11:05-11:50
Biography:
Andreas Greilhuber is a Computer Scientist by Profession and maker of large-scale services business units (gained experience with IBM, PricewaterhouseCoopers - 20 years’ experience with Technology and Consulting Firms, managed large- scale services business units in Europe, Middle-East and Africa). Overlooking an information technology era from PC to Artificial Intelligence with an experience in a wide range of disruptive technologies and business models (e.g., early adoption of IBM Watson in German-Speaking Market in the Health Industry), he decided to leave corporates and make AI real with an Austrian start- up. He is currently engaged as Chief Operations Officer with ANYLINE, Business Developing and Advisor of an innovation platform Innovation 4.x. located in Linz, Tel Aviv and Belin.
Abstract:
Anyline.com is one of the most promising AI companies in Europe. Founded in 2013 – Anyline teaches smart phones reading. The start was a specific use-case and customer need to read the blood sugar devices for diabetes patients – a clear need and customer pain with a solution to bridge the analog and digital world with the smart phone camera. The solution was patented. We were struggling what to do next with our patented solution and decided to develop an offering for the utilities industry. Similar to the blood sugar devices there are more enough analog and digital electricity, water, heat and gas meters around the world. Even compelling events like the European smart meter roll-out existed, but where is the real customer value of a vertical integrated solution powered by AI and why B2B customers shall pay for. Step by step we evolved our business model from solving mobile app developer’s pain to use AI based technologies like TensorFlow to the right vertical integrates solutions for law enforcement, automotive, border control and finally developed a successful product and solution approach to generate the funds needed to further push the AI adoption together with our customers.