| Network
of Excellence |
CARiMan |
The
Internet Portal for Computer Aided Risk Management |
Responsible: NTUA, UC3M, BUW,
IPSI,
SAE , ETRA
Assistance: DUTH, PRO,
UoO, all
partners
The main goal of this JPA is to: “Ensure traffic safety by improving
the reliability of traffic signaling infrastructure”. Safety critical traffic signalling infrastructure
components account for a large number of traffic jams, delays and accidents.
These occur despite the extensive, and very costly, maintenance effort required
under national safety regulations. One example is the periodical on-site visual
inspections of traffic signalling required in several member state safety
regulations. Furthermore, visual inspections in the field performed while normal
traffic operation is maintained is one of the reasons for the large number of
accidents involving maintenance personnel at work in the field.
A structured technique to come up with maintenance strategies based on
the awareness of the nature and causes of malfunctions is called Reliability
Centred Maintenance (RCM). The underlying technique in the total methodology is
known as Failure Mode, Effects and Criticality Analysis (FMECA). This concept
identifies: a)why a failure can occur, b) how it occurs and c) the consequences
of the failure. The application of the RCM to total traffic signalling
infrastructure gives the JPA a total innovative approach. The RCM analysis will
be developed, implemented and evaluated on all various types of traffic
signalling devices This sector of traffic signalling infrastructure chosen gives
the greatest potential for improvement in safety and traffic delays. However the
techniques to be developed can be applied the other aspects of traffic
signalling infrastructure. Trials and evaluations will take place in every
participating traffic company.
The most feature of a computer vision system for vehicle safety is to detect
pedestrians in a road and alert the driver for a crash. Apart from the
detection of pedestrians, object
detection system should be also accomplished. This way, stacks of woods,
leaves, obstacles or other objects that prevent the secure and secure traffic of
vehicle are localized. Furthermore, detection of humans or animals that may be
cause accidents is within the framework of the Cariman proposal. Motion-based
algorithms, object tracking methods and classification methods can be applied
toward this direction. Traffic signs
can easily be overlooked by a driver, causing the driver to e.g. drive too fast.
Thus, a system should be able to recognise the most important signs, display
them on the dashboard and possibly warn the driver if he miss to follow them. Activity
recognition aims at identifying the events or movements of specific meaning.
Example include, recognition flying birds,
fire, detection of heavily raining or a unusual situations that may cause
accident. Activity recognition is performed by analyzing the characteristics of
a motion of a scene using appropriate models.
| Network
of Excellence |
CARiMan |
The
Internet Portal for Computer Aided Risk Management |