WO2013170882A1

WO2013170882A1 - Collaborative vehicle detection of objects with a predictive distribution

Info

Publication number: WO2013170882A1
Application number: PCT/EP2012/059004
Authority: WO
Inventors: Marcus Nyberg; Cristian Norlin; Peter Gomez
Original assignee: Telefonaktiebolaget L M Ericsson (Publ)
Priority date: 2012-05-15
Filing date: 2012-05-15
Publication date: 2013-11-21

Abstract

A system for providing information to vehicles includes a receiver for receiving data from a plurality of vehicles including vehicle data and data from sensors associated with the vehicles, a first processor for evaluating contents of the received data to determine an appropriate storage medium for storing the received data, a first storage medium for storing the vehicle data, a second storage medium for storing the sensor data, a second processor for analyzing data from the first and second storage media to create trace data and for identifying recipients of the trace data and a transmitter for transmitting the trace data to the identified recipients wherein the identified recipients are a subset of the plurality of vehicles.

Description

Collaborative Vehicle Detection Of Objects

With A Predictive Distribution

TECHNICAL FIELD

The invention is related to information systems and more particularly to systems and methods for providing predictive event information to vehicles.

BACKGROUND

There exist methods for vehicles (like cars) to detect objects in their vicinity. Various sensors are used to recognize events such as road or weather conditions in a vehicle's vicinity. Objects can also be detected using, for example, infrared night vision and distance meters. Recognition of objects such as wildlife of different shapes and sizes is also taking place as they are about to wander into the path of a vehicle. This is often combined with different pre-crash systems and an action taken by the vehicle such as braking.

Other methods include using sensors to detect information such as accident information and weather conditions (i.e. precipitation, temperatures, etc.) which is then broadcast to vehicles in the vicinity of the affected areas. Information can be communicated between vehicles to relay information about upcoming traffic patterns.

There also exist the so-called "road trains" which enable cars to communicate with other cars in the immediate area and maintain a safe and constant distance from the cars in front of them. This is especially desirable when travelling longer distances in order to increase safety and save energy (fuel).

Other methods include using sensors to detect information such as accident information and weather conditions (i.e. precipitation, temperatures, etc.) which is then broadcast to vehicles in the vicinity of the affected areas. Information can be communicated between vehicles to relay information about upcoming traffic patterns. There also exist the so-called "road trains" which enable cars to communicate with other cars in the immediate area and maintain a safe and constant distance from the cars in front of them. This is especially desirable when travelling longer distances in order to increase safety and save energy (fuel).

Existing solutions focus on direct communication of information between vehicles based on the occurrence of a certain event or the registration of sensor information. This means that even though these systems help the drivers, the time span between when the sensors register something and when the driver receives a warning/message is relatively short - the driver has little time to react. Ideally, the time span should be long enough for the driver to be able to prepare and take appropriate actions before entering the location that might be dangerous. Current solutions for recognizing objects present the information when and where an object is noticed or when an incident occurs, and thereby lacks the ability to predict or project potential future events. These solutions do not always provide vehicles and users with adequate time to avoid problem; stated another way, they are often reactive rather than proactive.

Mechanisms for complementing and improving existing notification systems, therefore, are highly desirable.

SUMMARY

It should be emphasized that the terms "comprises" and "comprising", when used in this specification, are taken to specify the presence of stated features, integers, steps or components; but the use of these terms does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof.

In accordance with an exemplary embodiment, a network node is disclosed. The node comprises: a receiving means for receiving data from a plurality of vehicles including at least one of vehicle data and sensor data from sensors associated with the vehicles, a processor for processing the received data, a memory for storing the received data and a transmitting means for transmitting the processed data. The processor stores vehicle data in a first data base and sensor data in a second data base, projects object or event data based on analyzing the received data, identifies recipients for the projected object or event data and transmits the projected object or event data to the identified recipients.

In accordance with another exemplary embodiment, a method for providing projected object or event data to recipient vehicles is disclosed. The method comprises: receiving data from a plurality of vehicles including at least one of vehicle data and sensor data from sensors associated with the vehicles, evaluating contents of the received data, storing the received data in at least one of two databases based on the evaluation, analyzing the received data to determine projected object or event data, identifying recipient vehicles of the projected object or event data and transmitting the projected object or event data to the identified recipient vehicles.

In accordance with a further embodiment, a system for providing information to vehicles is disclosed. The system comprises: a receiver for receiving data from a plurality of vehicles including vehicle data and data from sensors associated with the vehicles, a first processor for evaluating contents of the received data to determine an appropriate storage medium for storing the received data, a first storage medium for storing the vehicle data, a second storage medium for storing the sensor data, a second processor for analyzing data from the first and second storage media to create trace data and for identifying recipients of the trace data and a transmitter for transmitting the trace data to the identified recipients wherein the identified recipients are a subset of the plurality of vehicles.

Several advantages may be realized by exemplary embodiments. Information from cars (and other vehicles) equipped with various sensors to detect objects, conditions and events along a road is collected in a collaborative manner and is utilized to project potential problems to other vehicles. Changes in sensor registered information is projected to determine how situations may develop over time and together with the prediction of future paths of vehicles, exemplary embodiments describe how a proactive time-shifted location- based tele-presence can be achieved instead of existing reactive object-recognition systems.

BRIEF DESCRIPTION OF THE DRAWINGS

The objects and advantages of the invention will be understood by reading the following detailed description in conjunction with the drawings in which:

FIG. 1 illustrates a vehicle equipped with sensors in accordance with exemplary embodiments;

FIGs. 2(A) and 2(B) illustrate time lapse scenarios of road conditions in accordance with exemplary embodiments;

FIG. 3 illustrates a selection scenario for determining recipients of trace data in accordance with exemplary embodiments;

FIG. 4 illustrates a system in accordance with exemplary embodiments;

FIG. 5 illustrates a network node in accordance with exemplary embodiments; and

FIG. 6 illustrates a method in accordance with exemplary embodiments.

DETAILED DESCRIPTION

The various features of the invention will now be described with reference to the figures, in which like parts are identified with the same reference characters or numerals.

The various aspects of the invention will now be described in greater detail in connection with a number of exemplary embodiments. To facilitate an understanding of the invention, many aspects of the invention are described in terms of sequences of actions to be performed by elements of a computer system or other hardware capable of executing programmed instructions. It will be recognized that in each of the embodiments, the various actions could be performed by specialized circuits (e.g., analog and/or discrete logic gates interconnected to perform a specialized function), by one or more processors programmed with a suitable set of instructions, or by a combination of both. The term "circuitry configured to" perform one or more described actions is used herein to refer to any such embodiment (i.e., one or more specialized circuits and/or one or more programmed processors).

Moreover, the invention can additionally be considered to be embodied entirely within any form of computer readable carrier, such as solid-state memory, magnetic disk, or optical disk containing an appropriate set of computer instructions that would cause a processor to carry out the techniques described herein. Thus, the various aspects of the invention may be embodied in many different forms, and all such forms are contemplated to be within the scope of the invention. For each of the various aspects of the invention, any such form of embodiments as described above may be referred to herein as "logic configured to" perform a described action, or alternatively as "logic that" performs a described action.

Cellular system can be used to transmit information between the vehicles and the traffic control system. Information on speed, distance, directions, diversions and traffic jams as well as images from road cameras can be obtained and presented to users of advanced mobile devices by apps ("applications").

When vehicle travels along a predefined path (road) there are lots of objects along the road that could be registered. These objects may not be an immediate danger for a particular vehicle, i.e. they don't motivate any further reactions within the vehicle such as emergency braking, displays of warning messages, or similar action, but they may still be very valuable for drivers of other vehicles to know about them. Today there is thus a missed opportunity for "crowdsourcing" sensor data from many vehicles in order to be able to analyze the data and to generate more accurate information about objects, their behavior, and other parameters, and to distribute this to other vehicles. This predictive information can be very valuable before arriving to a critical location and before a situation (such as approaching a part of the road where there is an animal nearby) occurs.

Sensor systems used for monitoring certain events often compare values to known thresholds in order to decide if the situation is normal or in a dangerous state. There are situations when these threshold values are impossible to know beforehand for example, when gathering sensor data from cars travelling along roads with all the objects that may appear.

According to exemplary embodiments, systems and methods are disclosed that utilize sensor data to predict events. The sensor data can be captured or collected by vehicles equipped with various types of sensors. Sensors can detect objects such as a fallen tree, or livestock near the road; they can also detect events such as temperature, rain, etc. The captured data is communicated to a network location for assessment and analysis. The analysis can be utilized to predict the development of the sensor data over time. The predictions or developments (which could be referred to as "traces") are distributed to other vehicles (referred to as "recipient" vehicles) that are likely to be affected by the data as it develops over time. The sensor registration of many units/vehicles is leveraged to alert recipient vehicles about potential objects, situations or events at a much earlier time than when the recipient vehicles' own sensors may register the objects, situations and events.

The term "trace" data may be thought of as the data that results from analyzing and/or processing of sensor data representing sensing of an object, an event or a situation. A trace can also be viewed as sensor data that has been enriched by the analysis performed on it by the processor at the node. The distributed data does not necessarily assume that a certain situation is wrong or dangerous. A trace is identified that is deemed to be valuable for distribution to specific vehicles. The specific vehicles may be those that are likely to be affected by the object, situation or event as determined by the analysis. The distribution need not necessarily be to all vehicles.

Sensor data is received continuously from vehicles. The received data is analyzed to identify patterns. The patterns can be utilized to predict future evolution of a particular object, situation or event. This is beneficial when trying to understand how certain conditions can lead to or evolve toward future problems. In order to distribute information to appropriate vehicles, a system according to exemplary embodiments tracks information about various vehicles. The information includes, but is not limited to, vehicle location, direction of travel of the vehicle, speed of the vehicle, etc.

A vehicle, such as vehicle 100 of FIG. 1, can be equipped with various sensors 110 that can, inter alia, register objects or events along a path or road on which the vehicle is travelling as illustrated in FIG. 1. An object can include wildlife such as a bear or a deer or can be a fallen tree obstructing the road for example. An event can include a weather condition such as rain, snow, etc. Some examples of sensors include high-definition (HD) video cameras, infrared cameras, heat-sensitive cameras, distance sensors, temperature sensors, engine sensors, accelerometers, detailed speedometers, GPS components, etc.

A vehicle can present the information from the sensors to the operator of the vehicle via one of many output types 120. Some examples of the output types include a transparent augmented layer on the windscreen, on a personal device, through a built-in car information system, ambient light, audio feedback and tactile feedback such as stiffening of the steering wheel for example. Vehicles can transmit vehicle data such as vehicle location, speed and direction of travel. Vehicle can also transmit sensor data such a type of object, event or situation detected by the sensor as well as the time and location of the detection of such object, event or situation. Vehicles can receive trace data. The vehicles can interpret objects recognized by sensors as well as present traces to drivers in various formats. A mobile communication device 130 of the driver can also be used to gather, send, receive and present data. For example, when the device 130 is brought into the vehicle 100, the device 130 can connect to the built-in equipment of the vehicle 100 in order to both complement the data that is being gathered by the vehicle's sensors and to also function as an output device. Personalized settings and driving history can also be made available for vehicles that are shared by multiple drivers.

An exemplary embodiment is described with reference to the time lapse scenarios illustrated in FIGs. 2(A) and 2(B). At a first instant in time (Tl) as illustrated FIG. 2(A), a first vehicle 210 is travelling on a road and an object 200 is in the vicinity of vehicle 210. Sensors associated with vehicle 210 detect object 200 and transmit the object location to a network node 250. Vehicle 210 can also transmit its (i.e. vehicle's) identification, location, speed and direction of travel. If equipped with appropriate sensors, vehicle 210 can also identify object 200 along with a time of detection of the object by the sensors and a location of the object and transmit this information to node 250.

A second vehicle 220 may also be travelling along this road in the same direction and behind (by 2 km in this example) vehicle 210. Vehicle 220 transmits its identification, location, speed and direction of travel to node 250. Vehicle 220 may not be equipped with sensors or its sensors may not have detected any objects, events, situations, etc. Network node 250 may process the received information from each of these vehicles. In this exemplary situation, the information on object 200 from vehicle 210 may be distributed to vehicle 220 to warn or advise caution to the operator of vehicle 220 about potential danger from object 200 (i.e. a trace is created from data received from vehicle 210 and submitted to vehicle 220). The information distributed to vehicle 220 can be viewed as a projected event as node 250 projects future evolution of the object into a potential event or situation of concern for vehicle 220.

A processor at node 250 can process the received data utilizing, for example, algorithms directed to data analysis, pattern recognition and mapping, recommendation systems, deviation analysis, etc. If node 250 concludes that the received information represents a potential concern or danger to vehicle 220, it will create a trace. Node 250 forwards the trace data to vehicle 220 that is predicted or expected to arrive at a location at which object 200 was detected or registered. The trace can be formatted in many forms depending on the capabilities of the receiving vehicles.

At a subsequent time (T2) as illustrated in FIG. 2(B), vehicle 220 may be close to and detect object 200. Vehicle 220 transmits the object location as well as continue to transmit its (i.e. vehicle's) identification, location, speed and direction of travel to node 250. Object 200 is a little further away from the road at this time (than in FIG. 2(A)). Node 250 can interpret this as object 200 moving away from the road. The information on object 200 may be distributed to a third vehicle 230 that is travelling along the same road in the same direction and behind (by 2 km in this example) vehicle 220 and is also expected to be in the vicinity of object 200.

In this example, each vehicle (i.e. vehicle 210 in FIG. 2(A) and vehicle 220 in FIG. 2(B)) near object 200 detects and reports the object location to node 250. Node 250 (after analyzing the data) provides the object information (i.e. trace) to other vehicles that are likely to encounter object 200 (i.e. vehicle 220 in FIG. 2(A) and vehicle 230 in FIG. 2(B)).

Vehicle 220, for example, receives object data from node 250 in FIG. 2(A) and transmits object data to node 250 in FIG. 2(B). In exemplary embodiment, therefore, vehicles 210, 220 and 230 work in a collaborative manner to proactive ly provide information. On a road with many vehicles that travel back and forth, exemplary embodiments utilize the sensor data from all vehicles in order to validate, update and improve the trace information. In this manner, trends over time or object changes can be detected and future events or object location can be predicted. Information about an object that is received over time from multiple vehicles may be used to predict direction of movement of the object (i.e. either toward the road or away from the road for example). Similarly, event data such as increasing or decreasing temperature or precipitation or fog can be used to predict future conditions.

While new sensor data may be used to improve the traces, old information deemed obsolete can be removed after a pre-determined period of time. The determination to designate traces as obsolete may be based on a weighted function of their age and the amount of overriding sensor data. Thus, irrelevant traces are gradually removed.

Many vehicles may be travelling along a particular road (i.e. more than the three vehicles illustrated in FIGs. 2(A) and 2(B)). The trace data on potential dangers or situations to avoid is distributed, however, only to those vehicles that are likely to be affected or likely to encounter the potential danger. This is accomplished by keeping track of location, direction and speed of vehicles and that of objects, events, etc. A user or vehicle's historical driving or travel patterns can also be accessed to assist in predicting future paths.

Exemplary methods for determining relevant recipients are illustrated with reference to FIG. 3. Vehicle 310 detects object 300 and transmits this data to a network node 350 for processing. Network node 350 evaluates the location, direction of travel, speed and if available, driving history of each of vehicles 320, 330 and 340 to determine which of these vehicles can receive the trace about object 300.

Network node 350 predicts that vehicle 320 will be in the vicinity of object 300 as it is travelling toward object and historical information may indicate that it turns right at the junction of the two roads. Similarly, vehicle 340 may also be predicted to be in the vicinity of object 300 based on direction of travel and historical information which may indicate it continues along the road to the left (i.e. not turn right at the junction). Since vehicle 330 is travelling away from object 300 (i.e. to the right), network node 350 can predict that vehicle 330 will not be in the vicinity of object 300. Based on this information, trace data on object 300 is distributed to vehicles 320 and 340. Trace data is not distributed to vehicle 330.

A system in accordance with exemplary embodiments is described with reference to FIG. 4. System 400 includes a network node 420 for receiving vehicle data and sensor data from sensors of a vehicle if the vehicle is equipped with sensors. A vehicle can be a car, a bus or a truck equipped with a set of connected devices including, for example, personal devices, sensors, and output terminals. Depending on the capabilities for interpreting objects recognized by the sensors, the sensor data sent to the system can have different formats.

In system 400 of FIG. 4, five vehicles 411-415 are illustrated. Vehicles 411-413 are equipped with sensors while vehicles 414 and 415 are not equipped with sensors in this particular example. The sensors can be integrated with the vehicles or can be integrated within a mobile communication device of a user or driver of a vehicle. The sensors within a mobile device of a user can be associated with the vehicle being driven by the driver or in which the user is a passenger.

Network node 420 can include a plurality of functional modules or components for communicating, processing and storing data. Network node 420, for example, includes a communication interface 421 for receiving data from vehicles 411-415. A processing module 422 (Processing Module 1) can analyze the received data and forward it to an appropriate storage location such as one of databases 423 and 424. Information received from any of the vehicles 411-415 includes location, speed, direction of travel, etc. This information is stored in database 424. Information received from some of the vehicles (such as 411-413) can also include sensor data that is stored in database 423. That is, vehicle data including location, speed, direction of travel, etc. is stored in database 424 and sensor data such as identity and location of object or event is stored in database 423. If a vehicle transmits vehicle and sensor data, then the vehicle data is stored in database 424 and the sensor data from that vehicle is stored in database 423.

Network node 420 can also include a second processing module 425 (Processing Module 2). Module 425 continuously aggregates and analyzes the sensor information to generate trace data. Module 425 can analyze vehicle location, direction and speed to project or predict the vehicle path. Module 425 can also project or predict future events based on the analysis and identify recipient vehicles for receiving the trace data. Trace data is distributed via a transmitting module 427.

The trace data that is distributed can be stored in trace database 426 for a predetermined period of time. Threshold values for the trace data can also be stored in database 426. The threshold values include, for example, how close a vehicle has to be to an existing or future event (such as object 405) before the trace data is distributed to that vehicle.

Vehicles 411-415 of FIG. 4 continuously transmit data to the network node regardless of whether the sensory systems within the vehicles have detected any objects. The type of information and the frequency at which the information is transmitted can differ based on the vehicle. In one scenario, vehicles 414 and 415 are not equipped with sensors in which case they do not transmit any sensor data. Alternatively, vehicles 414 and 415 can be equipped with sensors that may not have encountered or detected any objects - in this case also, these vehicles do not have any sensor data to be transmitted to the node. If a vehicle transmits only location and speed, the information is fairly "thin" (not very large in terms of bytes of data) and only needs to be transmitted at a lower frequency than if sensor data is included. Sensors within vehicles 411-413, on the other hand, may detect objects and the data to be transmitted includes both vehicle and sensor data. The frequency for this type of transmission may be higher (as high as the network bandwidth can facilitate for example).

Module 425 analyzes incoming sensor data (from database 423) by comparing it with information about vehicles in relevant areas (from database 424) for example. Module 425 can utilize various algorithms to aggregate the data (such as machine learning and case-based reasoning) and store calculations and predictions as traces in trace database 426. Using the information in these databases (i.e. 423, 424 and 426) as well as information from other sources or services 428, data analysis and recommendation algorithms can be applied.

Information from other services can include public service announcements, weather alerts, public event information such as parades, concerts, etc. Module 425 then produces a "decision" on whether the information is to be treated as a trace. If so, the severity or potential danger from the trace can be determined. A determination can also be made as to whether other existing trace information is to be updated. A determination can be made as to whether the trace information is to be distributed. The (recipient) vehicles to which the trace information is to be distributed are also identified.

The trace information that is distributed varies between recipient vehicles based, for example, on their (i.e. the vehicles') location relative to the object. Vehicles on a side of the road closer to the object may receive different information than vehicles on a side of the road farther from the object. It can also differ based on direction of travel of the vehicle - vehicles travelling in one direction receive different information than vehicles travelling in a second direction. It can also differ based on capabilities of the vehicle. One vehicle can receive trace information in an audio mode and another vehicle can receive trace information via a tactile feedback of the steering wheel for example. The trace information can also provide instructions to the users of the vehicles on how to react to an object or to a potentially dangerous event.

Processing modules 422 and 425 can be separate modules or the functions of each of them can be integrated into one processing module. The databases 423, 424 and 428 can be separate databases or they can all be combined into one database.

Vehicles can have different levels of functionality and intelligence based, at least partly, on the type of sensors that are associated with them. Accordingly, network node 420 of system 400 is capable of handling various detail levels in the sensor data and object description as input from the vehicles.

The functionality of network node 420 in system 400 of FIG. 4 is illustrated as numerical sequence 1, 2/2*, 3 and 4**.

A network node in accordance with exemplary embodiment is described with reference to FIG. 5. Network node 500 can include, inter alia, a reception interface 510, a processor 520, computer readable medium in the form of memory 530 and transmission interface 540 all of which may be interconnected via bus 340. Network node 500 may be somewhat similar to network node 420 of FIG. 4. Interfaces 510 and 540 may be similar to interfaces 421 and 427. Processor 520 may be similar to modules 422 and 425. Memory 530 may be similar to databases 423, 424, 426 and 428. Interfaces 510 and 540 can be a modem for receiving and transmitting information respectively. Processor 520 can be a generic processor such as those found in computing devices.

Reception interface 510 can receive data from a plurality of vehicles (including sensor data from sensor equipped vehicles) as described above. The received data is stored in memory 530. Processor 520 analyzes the vehicle and sensor data to determine trace data and identify recipient vehicles for the trace data. Trace data can also be stored in memory 530. The trace data is distributed via transmitting interface 520. Memory 530 can include a plurality of databases as described above.

A method in accordance with exemplary embodiments is described with reference to FIG. 6. Data is received from a plurality of sources such as vehicles at 610. The data includes vehicle information such as location, speed, etc. If the vehicle includes sensors, then the received information can also include sensor data. The contents of the received data are evaluated at 620 to determine whether only vehicle information (i.e. speed, location, etc.) is included or if sensor data is also included. The received data can be stored in one of two databases at 630. Vehicle information is stored in one database and sensor data is stored in a second database. The received data is analyzed to project objects or events at 640.

An event as a generic term can also be used to describe either the presence of an object or the occurrence of a potentially dangerous or inconvenient condition such as water, ice, etc. The analysis can include analysis or evaluation of the received data. The received data can be compared to pre-stored object (location) or event data to detect trends for example. The pre-stored data may have been received earlier from the same location or it could be information received from other services such as a public service announcement related to weather for example. Projection or prediction may include identifying a potential condition that drivers should be aware of. A number of recipients for receiving the projected data may be identified at 650. The prediction or projection may be transmitted at 660 to relevant recipient vehicles as described above with reference to FIG. 4.

In one embodiment, in order for the processor 520 to be able to perform the steps illustrated in FIG. 6, memory 530 comprises a computer program (CP) 535 with computer program modules which when run by the processor 520 causes the network node 500 to perform all or some of the steps illustrated in FIG. 6. While the description above has focused on vehicles gathering data, exemplary embodiments may be equally applicable in other situations such as when fire fighters and emergency personnel may collaborate at one location.

Other examples could be related to the registration of traces that last for a longer period of time such as, for example, boats equipped with an intelligent sonar system that may be used to collaboratively map the bottom of a body of water. When vehicles, people and sensors pass by the same location and detect objects, the objects can be registered with a system that uses the data to build on previously gathered or received information.

Several advantages may be realized by exemplary embodiments as described. Cars (and other vehicles) are increasingly being equipped with various sensors and cameras to detect objects along a road. Exemplary embodiments provide a mechanism to better utilize information gathered in a collaborative manner from many different vehicles travelling along the same road.

With a collaborative approach, a central system can generate valuable knowledge based on the registrations made by a large number of vehicles and then distribute potential problem indications to relevant recipients.

Another advantage is the ability to predict changes in sensor registered information and determine how situations may develop over time. Together with the prediction of future paths of vehicles, exemplary embodiments describe how a proactive time-shifted location- based tele-presence can be achieved instead of existing reactive object-recognition systems.

The invention has been described with reference to particular embodiments.

However, it will be readily apparent to those skilled in the art that it is possible to embody the invention in specific forms other than those of the embodiment described above. The described embodiments are merely illustrative and should not be considered restrictive in any way. The scope of the invention is given by the appended claims, rather than the preceding description, and all variations and equivalents which fall within the range of the claims are intended to be embraced therein.

Claims

WHAT IS CLAIMED IS:

1. A network node (500) comprising:

a receiving means (510) for receiving data from a plurality of vehicles including at least one of vehicle data and sensor data from sensors associated with the vehicles;

a processor (520) for processing the received data;

a memory (530) for storing the received data; and

a transmitting means (540) for transmitting the processed data wherein the processing by the processor further comprises:

storing vehicle data in a first data base and sensor data in a second data base; projecting object or event data based on analyzing the received data;

identifying recipients for the projected object or event data; and

transmitting the projected object or event data to the identified recipients.

2. The network node of claim 1 , wherein the processor is further for analyzing the received data by detecting patterns associated with objects or events within the received data.

3. The network node of claim 1, wherein the processor is further for transmitting to vehicles within a potential impact zone of the projected object or event.

4. The network node of claim 1 , wherein the storing of the vehicle data in the first database comprises storing a location, a speed and a direction of travel of the vehicle.

5. The network node of claim 4, wherein the storing of the sensor data in the second database includes storing a location of the object or event detected by a sensor and a time of detection of the object or event.

6. The network node of claim 5, further comprising:

a third database for storing object data and event data from other sources including a public service entity.

7. The network node of claim 1 , wherein the processor comprises at least two processing elements.

8. The network node of claim 7, wherein a first of the two processing elements is for determining contents of the received data and for storing the received data in one of the two databases based on the determination.

9. The network node of claim 8, wherein a second of the two processing elements is for projecting object or event data.

10. The network node of claim 8, wherein a second of the two processing elements is for identifying recipient vehicles for the projected object or event data.

11. The network node of claim 10, wherein the second processing element is further for transmitting the projected object or event data via the transmitting means.

12. A method (600) for providing projected object or event data to recipient vehicles, the method comprising:

receiving data from a plurality of vehicles (610) including at least one of vehicle data and sensor data from sensors associated with the vehicles;

evaluating contents of the received data (620);

storing the received data in at least one of two databases based on the evaluation

(630);

analyzing the received data to determine projected object or event data (640);

identifying recipient vehicles of the projected object or event data (650); and transmitting the projected object or event data to the identified recipient vehicles

(660).

13. The method of claim 12, wherein the recipients of the projected object or event data are a subset of the plurality of vehicles.

14. The method of claim 12, wherein the step of analyzing further comprises detecting a trend in a movement of an object over a period of time based on location information of the object received from the plurality of vehicles.

15. The method of claim 12, wherein the step of analyzing further comprises detecting a trend in event data.

16. The method of claim 15, wherein the event data corresponds to weather conditions and the trend represents an increase or a decrease in at least one of temperature, precipitation and humidity.

17. The method of claim 12, wherein the identification of a recipient vehicle comprises identifying vehicles within a pre-determined distance of a location of a projected event or object.

18. The method of claim 17, further comprising determining if the identified vehicles are travelling toward the location of the projected event or object.

19. The method of claim 12, wherein the vehicle data comprises a location, a speed and a direction of travel of the vehicle, the vehicle data being stored in a first one of the at least two databases.

20. The method of claim 12, wherein sensor data comprises an identification and a time of detection of an object or event by the sensor, the sensor data being stored in a second one of the two databases.

21. The method of claim 12, wherein the step of analyzing further comprises applying a set of rules stored in a third database to the received data.

22. The method of claim 12, wherein the sensor data includes data from at least one of a high-definition video camera, an infrared camera, a heat-sensitive camera, a distance sensor, a temperature sensor, an engine sensor, an accelerometer and a detailed speedometer.

23. The method of claim 22, wherein object and event data in the received sensor data corresponds to potential hazards to the recipient vehicles.

24. A system (400) for providing information to vehicles comprising:

a receiver (421) for receiving data from a plurality of vehicles including vehicle data and data from sensors associated with the vehicles;

a first processor (422) for evaluating contents of the received data to determine an appropriate storage medium for storing the received data;

a first storage medium (424) for storing the vehicle data;

a second storage medium (423) for storing the sensor data;

a second processor (425) for analyzing data from the first and second storage media to create trace data and for identifying recipients of the trace data; and

a transmitter (427) for transmitting the trace data to the identified recipients wherein the identified recipients are a subset of the plurality of vehicles.

25. The system of claim 24, further comprising:

a third storage medium (428) for storing information from sources other than the vehicles; and

a fourth storage medium (427) for storing trace data transmitted to the recipients.

26. The system of claim 24, wherein the received vehicle data includes an identification, a location, a rate of travel and a direction of travel of the vehicle.

27. The system of claim 24, wherein the received vehicle sensor data includes object or event data detected by the sensors.

28. The system of claim 27, wherein the object data includes a location and a time of detection of the object. The system of claim 28, wherein the object is an animal.

The system of claim 27, wherein the event data is weather related data.