Technical feasibility

PART B: VALORISATION PLAN

SECTION I: Testing

 

1

Has the R & D result been tested?

YES

X

NO

 

The following question is replied according to the reply in question 1

 

 

 

If yes

 

1a

In what mode has the result been tested?•             Prototype•             Pilot Application

•             Alpha/BETA testing

 

A prototype of automatic video surveillance system is installed in the Artificial Vision and Real-Time Systems advanced laboratory of theUniversityofUdine. The software, continuously developed and tested, is installed on a workstation of the laboratory. The workstation is attached to at least 3 video cameras mounted on the roof of the building at approximately12 metersfrom the ground.  Two cameras are (pan-tilt-zoom) while the third is static and with a wide-angle lens. The testing is performed by observing the activities of the nearby parking lot. By observing the activities of the entities involved (persons, vehicles, etc.) the system can be trained to distinguish between normal and anomalous behavior. The system is not dedicated for parking lots only. It can be applied to any area that needs surveillance. The system is being tested also under varying weather and illumination conditions.
1b. Please describe and discuss the testing results
Note: Explain testing process and its results in brief
The testing that is currently underway is primarily meant to verify the effectiveness of the algorithms developed so far in real-world conditions.  In this sense the system is being tested in rather difficult conditions (outdoors, many entities in scene) where occlusions, changing weather and illumination conditions, reflections, to mention only the most severe, can give raise to many false alarms and missed alarms. The testing is performed by having the system analyze a given video sequence which has been previously labeled by a human operator. The system analyzes the video stream an tries to detect the anomalous patterns that need to be recognized and for which it was trained in advance. The output of the system is compared to the ground truth provided by the human operator.Results have shown up to now a good performance of the system. The main issues are related to extreme conditions such as sudden illumination changes and severe occlusions. The current development is geared to improve the performance also under these conditions. The current performance figures report 10% false alarms and 5% missed alarms. The performance is overall good given the prototypical state of the software.

 

If no:

 

1c

Describe what type of testing does the R&D result need?
Note: According to the type of R&D Result – product, service, software, etc.
 
1d. What is the time needed for testing?
Note: Define time in terms of working days
1e. What is the cost needed for testing?
Note: Assessment of costs in terms of value class

 

SECTION 2: Current Stage of Development

 

2a

To what extent does the development team have technical resources for supporting the production of a new product[1]? (Researchers, human resources, hardware, etc. )
Note: Describe whether the R&D result is a result of collective effort and developers could be available for technical advice if the product is to be produced.
The founding members of Avires comprise 1 full professor, 2 assistant professors and 1 post-doc fellow in Computer Science.The Avires team has specific experience in the development of advanced surveillance systems. In particular, knowledge is available in the context of sensor calibration techniques, scene modeling and understanding, application dependent databases, real-time audio-video streaming. Specific methods for performance evaluation of surveillance systems have been studied.As members of the Artificial Vision and Real-Time Systems lab the team has participated in the development of the prototypical surveillance systems installed at the sanitary landfill test-site of the Athena European project (remote surveillance of teleoperated vehicles in a risky environment). The AVIRES Lab has developed image processing software of different prototypical surveillance projects with SOCIETA’ AUTOVIE VENETE S.p.A (Italy) for surveillance of tollgates and motorway overpasses. At the present moment, the AVIRES Lab is active in the field of the video/based surveillance systems for transport environments (unattended highway areas, unattended tunnels and bridge) and for security public environments (metro line and railway stations and airports).

The team has decades of experience in the field of computer vision and specifically video surveillance. The team regularly publishes scientific papers in refereed international journals and conferences.

 

2b

What are the technical issues that need to be tackled for full deployment, if needed?
Note: Reply might refer to technical processes, testing, further development, etc
The algorithms need a final engineering phase to increase the robustness of the software and its usability. The user interface needs also to be revisited and simplified.Also, software deployment for market production require extensive testing on different platforms.An in-depth survey of existing cameras may be required to test compatibility issues.

One year of work of two full-time programmers is estimated.

 

2c

What additional technical resources are needed for the production of this new product?
Note: Reply might refer to machinery, or software licenses,
Since foresees the take care of the development of the software but not its actual installation and set-up at the customers’ premises (along with necessary supporting gear, i.e. laying of cables, installing supports for cameras, camera placement, electric connections, etc.), final installation procedures (outdoor installations in public places) need to be further investigated and possible liaisons with CCTV installers may be required.

 

 

2d

Overall assessment of the current stage of technical development.
Note:
An automatic surveillance system prototype is currently being tested at the Artificial Vision and Real-Time System laboratory of theuniversityofUdine. The software aims to assist a human operator in the tedious chore of detecting rare anomalous events  in an environment where normal activities are continuously undergoing (i.e. a parking lot, a factory, etc.). The software has a wide spectrum of applicability in all the situations where security needs to be enforced to protect the  safety of people or to defend property. Current performances are good but the software requires final engineering and extensive testing. Collaborations for final installations may be required.

SECTION 3: Deployment

3a

Define the demands for large scale production in terms of
  • Materials
N/A. Avires aims at developing only software. No significant material requirements are envisaged. Physical installation will be given in outsourcing to Closed Circuit Television (CCTV )installers.
  • technologies, tools, machineries
The deployment of a functioning system requires a workstation where to install the software, placement of cameras in the areas to be monitored , electric connections and wiring. This phase will be given in outsourcing to CCTV installers.
  • Staff effort
The deployment of the system requires expert CCTV installers that can perform all the electric connections and wiring necessary to connect the camera sto the workstation where the sofwtare is running.  This phase will be given in outsourcing to CCTV installers.
Note:

SECTION 4: Overall Assessment

 

1

What is you overall assessment of the technical feasibility of the research result?
Note:
Given the acknowledge scientific expertise of the team in the field of computer vision and video surveillance and the performances of the existing prototype, the software is very likely to be feasible. In addition, the team is not aiming to perform directly the final installation of the product, leaving this phase to expert CCTV installers. Thus no additional expertise or materials/tools are needed. The expected final engineering an testing phase of the system to hit the market is expected to last one year and the the effort of two full-time programmers is foreseen.

 

 

 

KEYWORDS QUANTITATIVE ASSESSMENT (0-5).

Please encircle as appropriate.

 

Adequacy of testing activity undertaken so far 1 2 3 x 5
Adequacy and availability of technical resources of the development team 1 2 3 x 5
Current development stage 1 2 3 x 5
Overall technical feasibility 1 2 3 4 x

 

 

 

 

Bookmark the permalink. Follow any comments here with the RSS feed for this post. Post a comment or leave a trackback: Trackback URL.

Post a Comment

You must be logged in to post a comment.

Request a proposal

Valorisation Plan Authors

Related Documents

There in no related documents

Visit the other applications of the INTERVALUE Platform: R&D Repository | IP Agreements

© 2009-2010 INTERVALUE Project