Corporate Donors
Friday, Sept. 2
- 08:00
- Registration
- 09:00 — 09:15
- Welcome Industrial Surveillance Day
Helmut Leopold, Head of Safety & Security Department, AIT Austrian Institute of Technology - 09:15 — 10:15
- Keynote lecture
Michele Genisio (more...) - 10:15 — 10:30
- Coffee Break
- 10:30 — 12:00
- ISD Demo and Exhibit Teasers
-
Searching in large Video-Archives
AIT Austrian Institute of TechnologyAbstract
We present a query concept to facilitate and improve the search for a specific person in large video surveillance archives. The query is defined as a combination of a conventional rule-based system and a synthetic human model or avatar. The presented framework includes a graphical synthesis tool capable of generating avatar images based on a 3D human model capturing pose and view variations and a range of appearance variations. The generated synthetic image is used in a query-by-sample fashion to perform the search. A highly optimized implementation utilizing GPU and parallel CPUs allows a fast response on large archive datasets (hours of videos).
People flow analysis
Blue Eye Video, SonyAbstract
Based on a unique video stream analysis and combined with the Sony Smartcamera architecture, Blue Eye Video stand alone solution is able to determine how many persons are waiting in a queue, the customer behaviour when moving in a department store, airports, theatre or stadium.
PRIMA-S zur Maskierung von Privatzonen in Videobildern
Funkwerk plettacAbstract
The Demo from Funkwerk plettac shows an innovative system for masking of privacy zones in video surveillance systems in order to meet the requirements of data privacy, especially in public areas.
A Systems Level Approach to Perimeter Protection
General Electric, Inha University, Korean Aeronautics University, University of Southern CaliforniaAbstract
not available
People and Object Sensing Solutions based on 3D MLI Sensor(TM) Technology
IEE S.A.Abstract
IEE has developed a vision sensor based on 3D MLI Sensor™ technology. This sensor is the basis for a number of people and object sensing solutions aimed at enhancing building safety, security and management. This paper provides details about the nature of the technology, as well as the challenges faced by building and security professionals to solve safety issues, and how the sensor aids in facing those challenges.
GPU Enabled Smart Video Node
intuVisionAbstract
This paper presents an All-in-One video analytics system, a compact, multi-channel, real-time, video monitoring, event detection, alarm notification, event recording and browsing solution implemented on low cost hardware, taking advantage of NVIDIA’s GPU CUDA platform. An inventive distribution of video object detection and tracking processing chain between the GPUs and the CPU provides maximum efficiency at the lowest cost.
Interactive Person-Retrieval in a Distributed Camera Network
Fraunhofer Institute of Optronics, KITAbstract
Tracking and identifying persons in videos are important building blocks in many applications. For interactive investigation of surveillance footage it is often not even necessary to uniquely identify a person. It rather suffices to find occurrences of a person indicated by the user with an exemplary image sequence. We present a system in which the search for a specific person can be initiated by a sample image sequence and then be further refined by interactive feedback by the operator. The demonstrated system will track people online in multiple cameras and make the sequences immediately searchable from a central station.
A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video
DARPA, Kitware, MIT, Rensselaer Polytechnic Institute, University of California Irvine, University of California Riverside, University of Central Florida, University of Maryland, University of TexasAbstract
We introduce to the surveillance community the VIRAT Video Dataset, which is a new large-scale surveillance video dataset designed to assess the performance of event recognition algorithms in realistic scenes. Exemplary video clips along with annotations and diverse event statistics will be showcased during the demo. The dataset includes videos collected from both stationary ground cameras and moving aerial vehicles. We expect the dataset to further research in continuous visual event recognition(CVER), where the goal is to both recognize an event and to localize the corresponding space-time volume from large continuous video. This is far more closely aligned with real-world video surveillance analytics needs than the current research which aims to classify a pre-clipped video segment of a single event. Accurate CVER would have immediate and far reaching impact in domains including surveillance, video-guided human behavior research, assistive technology, and video archive analysis.
Smart Resource-Aware Multi-Sensor Network
Alpen-Adria Universität Klagenfurt, Eye-Tech, infoFACTORYAbstract
At the ”Industrial Surveillance Day” we demonstrate the current state of the Smart Resource-Aware Multi-Sensor Network project (SRSnet). In this demonstration we focus on user interface and the multimedia data warehouse which stores detected simple and complex events as well as multimedia data such as images and short audio/video sequences. We show real data generated during a prototype deployment of our network in the Nationalpark Hohe Tauern in Austria. From the data that is gathered and processed within the sensor network, SRSnet filters events that are relevant to users and inserts them into the data warehouse via a web service interface. Via a convenient interface, users can query for specific events in the data warehouse.
Construction Site Monitoring from Highly-Overlapping MAV images
Siemens CTAbstract
We present a concept for automatic construction site monitoring by taking into account 4D information (3D over time), that is acquired from highly-overlapping digital aerial images. On the one hand today’s maturity of flying micro aerial vehicles (MAVs) enables a low-cost and an efficient image acquisition of high-quality data that maps construction sites entirely from many varying viewpoints. On the other hand, due to low-noise sensors and high redundancy in the image data, recent developments in 3D reconstruction workflows have benefited the automatic computation of accurate and dense 3D scene information. Having both an inexpensive high-quality image acquisition and an efficient 3D analysis workflow enables monitoring, documentation and visualization of observed sites over time with short intervals. Relating acquired 4D site observations, composed of color, texture, geometry over time, largely supports automated methods toward full scene understanding, the acquisition of both the change and the construction site’s progress.
OUTLIER – Online Learning and Visualization of Unusual Events
Graz University of Technology, Johanneum Research, Siemens CTAbstract
Unusual event detection, i.e., identifying (previously unseen) rare/critical events, has become one of the major challenges in visual surveillance. The main solution for this problem is to describe local or global normalness and to report events that do not fit to the estimated models. The majority of existing approaches, however, is limited to a single description (e.g., appearance or motion) and/or builds on inflexible (unsupervised) learning techniques, both clearly degrading the practical applicability. To overcome these limitations, we demonstrate a system that, on the one hand is capable of extracting and modeling several representations in parallel and, on the other hand, allows for user interaction within a continuous learning setup. Novel yet intuitive concepts of result visualization and user interaction will be presented that allow for exploiting the underlying data.*
Intelligent Crossing Sensor and Vehicle Detector
SLR EngineeringAbstract
The aim of the iCS system is to detect and record footages of possibly hazardous situations on a pedestrian crossing and/or conduct real-time traffic surveillance. Videos recorded by cameras could be used for enforcement purposes or as evidence in case of an accident. Information about the traffic could be used for statistic purposes and thus help to improve road infrastructure planning and traffic flow. The system contains two Smart Cameras. The first one detects pedestrians which are on or close to the pedestrian crossing, the second one detects and tracks vehicles approaching the the crossing, additionally the vehicle's numberplate is detected and recognized. Based on vehicle's position, direction and velocity and pedestrian's position the system decides if the situation is hazardous or not. If so both cameras start to record beginning with several seconds before the decision (using an image ring buffer).
VTrack: Video Analytics for automatic video-surveillance
TechnoAware, University of GenovaAbstract
TechnoAware research and develops technologies and solutions for ambient intelligence. Established in 2003 TechnoAware was born from the experiences and competencies of the ISIP40 research group of the University of Genova. This research group is studying and implementing video analytics algorithms since 1985 and is considered nowadays one of the major actors in this filed worldwide. Entirely made up by researchers and experts in the video analytics field, TechnoAware main principles are: proprietary technologies (highly customizable and modular solutions), scientific competencies (high quality level and performances), continuous research and technological innovation (cutting edge products).
Pedestrian sensing for increased traffic safety and efficiency at signalized intersections
TraficonAbstract
The control of signalized intersection plays an important role in the safety and efficiency of urban traffic. The last decades a lot of resources were spent on ITS for the detection of vehicles at traffic lights. Today not only the efficiency of traffic is of interest but also the safety of pedestrians is becoming a priority. To respond to this need two new traffic video sensors are proposed specifically designed for the detection of pedestrians in an urban setting.
Level of Service Classification for Smart Cameras
Alpen-Adria Universität Klagenfurt, ASFINAGAbstract
At the Industrial Surveillance Day, ASFINAG and the Alpen Adria Universitt Klagenfurt (in particular the Institute of Information Technology and the Institute of Networked and Embedded Systems) demonstrate a show case of their video-based level of service (LOS) classification for smart cameras. This LOS classification system has been developed in a joint Lakeside Labs project in Klagenfurt, Austria. It is part of a case study which aims at improving the quality of traffic messages for the two particular traffic situations level-of-service (LOS) and weather-related road conditions (WRRC) on two dedicated test tracks on Austrian motorways. Using a live connection to a smart camera at one of these test tracks, we plan to show a live demonstration for visual speed estimation and LOS classification. This demo is coordinated with our partner SLR Engineering, which provided the smart cameras for the case study.
- 12:00 — 14:00
- Business Lunch with ISD Exhibitors and IMGS-TA1 members
- 14:00 — 15:00
- Keynote lecture
Josef Birchbauer (more...) - 15:00 — 16:00
- ISD Oral Session: Traffic Monitoring
Traffic video detection: a manufacturers' point of view
Wouter Favoreel (Traficon) details...
A high-way operator's view on automated video surveillance
Nikolaus Viertl (ASFINAG) details...
- 16:00 — 16:15
- Coffee Break
- 16:15 — 17:30
- Panel discussion: Industry vs. User Perspective?
Enormous market potential has been foreseen for automated video surveillance, but we notice today that most of the surveillance systems are still CCTV. What are the reasons despite the considerable R&D and business efforts of the past?
Is there a fundamental lack of understanding the user's problems or are these problems today unsolvable with the current understanding in Computer Vision?
Panel:
- Wouter Favoreel, R&D Director, Traficon
- Nikolaus Viertl, Project Manager, ASFINAG
- Stuart Rankin, Technology Officer, Home Office
- Csaba Beleznai, Senior Scientist, AIT Austrian Insitute of Technology
Moderation: Oliver Sidla, SLR Engineering
- 17:30
- Drinks & Farewell
