Wide area traffic surveillance using a multisensor tracking system

• US 5,696,503 A
• Filed: 07/23/1993
• Issued: 12/09/1997
• Est. Priority Date: 07/23/1993
• Status: Expired due to Fees

• Current Assignee: Condition Monitoring Systems Incorporated
• Original Assignee: Condition Monitoring Systems Incorporated
• Inventors: Nasburg, Robert E.
• Primary Examiner(s): Hofsass, Jeffery
• Assistant Examiner(s): Pope, Daryl C.
• Application Number:
  US08/096,769
• Time in Patent Office: 1,600 Days
• Field of Search: 340/933, 340/934, 340/992, 340/994, 364/436, 364/438
• US Class Current: 340/933
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions
• CPC Class Codes: G08G 1/07 Controlling traffic signals
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096741 where the source of the transmitted information selects which information to transmit to each vehicle
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G08G 1/20 Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles

Abstract

A wide area surveillance system for application to large road networks is described. The system employs smart sensors to identify plural individual vehicles in the network. These vehicles are tracked on an individual basis, and the system derives the behavior of the vehicle. Furthermore, the system derives traffic behavior on a local basis, across roadway links, and in sections of the network. Processing in the system is divided into multiple processing layers, with geographical separation of tasks.

Claims

1. A method of surveilling vehicles in a traffic network, the network defining plural discrete sections and plural discrete fields, the sections comprising plural fields, wherein at least two discrete sections cover discrete fields of view connected to one another by a roadway link, the method comprising:

(a) a vehicle detection and flow assessment step comprising;

(1) for a given vehicle in the network, sensing the vehicle in at least one field,

(2) determining the vehicle'"'"'s position within the fields, and

(3) characterizing the sensed vehicle based upon predefined attributes and assigning a unique identifier to the vehicle;

(b) a local tracking and flow assessment step comprising;

(1) for a given vehicle from those sensed in the vehicle detection and flow assessment step, the vehicle having been determined to be in a first particular field, at a particular position, and having a unique identifier, tracking the vehicle through the field,

(2) estimating the time required for the vehicle to travel from the first field to a second field, and

(3) associating the identifier of the vehicle with the detection of the vehicle in the second field, the vehicle having been detected in the second field in the vehicle detection and flow assessment step;

(4) characterizing the flow of all sensed vehicles within a given field; and

(c) an area wide flow characterization step comprising;

(1) estimating a state of traffic flow over a section of the network,

(2) detecting flow disruptions based upon the state of traffic flow, and

(3) characterizing flow over the section.

2. A method of surveilling a vehicle having a fingerprint in a wide area traffic network comprising:

detecting a vehicle'"'"'s entry into the network at a location in the network with a passive sensor;

identifying the vehicle'"'"'s fingerprint;

tracking the vehicle'"'"'s flow through the network by comparing vehicle fingerprints at various times and at non-contiguous locations using a plurality of sensors wherein at least two of said sensors have non-overlapping fields of view; and

generating a correlation matrix of selected vehicle origination locations in the network and selected vehicle destination locations in the network.

3. A sensor system comprising a plurality of fingerprinting sensors, each said sensor defining a field and a local traffic processor coupled to the sensor, the sensor when activated providing raw signals to the local traffic processor, the raw signals including fingerprints of vehicles within the field, the vehicles each having a position, the local traffic processor when activated distinguishing the fingerprints, characterizing each sensed vehicle based upon predefined attributes within its fingerprint, and determining the position of each sensed vehicle within the field, wherein at least two of said plurality of sensors have non-overlapping fields of view.

4. A sensor system as set forth in claim 3, wherein the sensor comprises a video camera.

5. A traffic surveillance system comprising:

a plurality of sensor systems, the sensor systems having non-overlapping fields of view, each said sensor system comprising a fingerprinting sensor defining a field and a local traffic processor coupled to the sensor, the sensor when activated providing raw signals to the local traffic processor, the raw signals including fingerprints of vehicles within the field, the vehicles each having a position, the local traffic processor when activated distinguishing individual vehicles based upon their respective fingerprints, reducing the fingerprints to characterizations of predefined attributes, and determining the position of each distinguished vehicle within the field; and

a wide area traffic flow processor coupled to the local traffic processors, the wide area traffic flow processor adapted to track movement of a vehicle through a given sensor'"'"'s field and from the given sensor'"'"'s field of view into a non-overlapping field of view of a second sensor, through correlation of characterized attributes and determined locations where one location is at least 200 feet from another location.

6. A traffic surveillance system as set forth in claim 5, wherein the sensor comprises a video camera.

7. A traffic surveillance system as set forth in claim 5, wherein the wide area traffic processor is further programmed to characterize flow within each sensor'"'"'s field, associate vehicles from one sensor to another, compute travel time between predefined points for a particular vehicle identified by two or more local traffic processors, and estimate average link time between sensors.

8. A traffic surveillance system as set forth in claim 5, the wide area traffic flow processor further programmed to estimate flow over sections of a roadway within the fields of the sensors.

9. A traffic surveillance system for surveilling vehicles in a traffic network, the traffic network defining plural discrete, widely spaced-apart sections and plural discrete fields, the sections comprising plural fields, the traffic surveillance system comprising:

(a) a vehicle detection and flow assessment layer comprising;

(1) a plurality of fingerprinting sensors each having a range of at least one field and,

(2) a plurality of local traffic processors each coupled to at least one of the sensors and adapted to determine vehicle positions within the range of the sensors, uniquely characterize sensed vehicles based upon predefined attributes, and assign a unique identifier to each sensed vehicle;

(b) a local tracking and flow assessment layer coupled to the vehicle detection and flow assessment layer and comprising;

(1) means for tracking vehicles sensed by the vehicle detection and flow assessment layer through the fields in which the vehicles were sensed,

(2) means for correlating vehicle identifiers produced in different local traffic processors,

(3) means for estimating vehicle travel time between fields, and

(4) means for characterizing the flow of all sensed vehicles within a given field;

(c) an area wide flow characterization layer comprising;

(1) means for estimating traffic flow over a given section of the network,

(2) means for detecting flow disruptions based upon the traffic flow, and

(3) means for characterizing flow over the given section.

10. A traffic surveillance system comprising:

a plurality of sensor systems, where at least two of said sensor systems are separated from one another by a roadway link, the sensor systems each comprising a fingerprinting sensor defining a field and a local traffic processor coupled to the sensor, the sensor when activated providing raw signals to the local traffic processor, the raw signals including fingerprints of vehicles within the field, the vehicles each having a position, the local traffic processor when activated uniquely distinguishing individual vehicles based upon their respective fingerprints, reducing the fingerprints to characterizations of predefined attributes, and determining the position of each distinguished vehicle within the field; and

a wide area traffic flow processor coupled to the local traffic processors, the wide area traffic flow processor comprising a programmed computer having a program and thereby operable to associate vehicles from a first sensor to a second sensor having a non-overlapping field of view with the first sensor, and connected to said first sensor via a roadway link, and compute travel time between predefined points for a particular vehicle identified by two or more local traffic processors.

11. A traffic surveillance system comprising:

a plurality of sensor systems, the sensor systems each comprising a fingerprinting sensor observing a field and a local traffic processor coupled to the sensor, the sensor when activated providing raw signals to the local traffic processor, the raw signals including fingerprints of vehicles within the field, the vehicles each having a position, the local traffic processor when activated distinguishing individual vehicles based upon their respective fingerprints, reducing the fingerprints to characterizations of predefined attributes, and determining the position of each distinguished vehicle within the field; and

a wide area traffic flow processor coupled to the local traffic processors, the wide area traffic flow processor comprising a programmed computer having a program and thereby operable to associate vehicles from a first sensor observing a first field of view to a second sensor observing a second field of view, said second field of view being non-overlapping with said first field of view, and estimate average travel time between sensors.

12. A sensor system comprising a first passive, fixed sensor having a first field and a first local traffic processor coupled to the first sensor, the first sensor when activated providing raw signals to the first local traffic processor, the raw signals including fingerprints of vehicles within the first field, the vehicles each having a position, the first local traffic processor when activated distinguishing the fingerprints, characterizing each sensed vehicle based upon predefined attributes within its fingerprint, and determining the position of each sensed vehicle within the first field, and a second passive, fixed sensor having a second field and a second local traffic processor coupled to the second sensor, the second sensor when activated providing raw signals to the second local traffic processor, the raw signals including fingerprints of vehicles within the second field, the vehicles each having a position, the second local traffic processor when activated distinguishing the fingerprints, characterizing each sensed vehicle based upon predefined attributes within its fingerprint, and determining the position of each sensed vehicle within the second field, wherein said first field and said second field are non-overlapping.

13. A traffic surveillance system for surveying a wide area of traffic, said system comprising:

(a) a first video sensor system, said first video sensor system having a range of at least a first field of view, and being able to detect and identify a given vehicle present in said first field of view, and transmit a first signal concerning said given vehicle;

(b) a second video sensor system, said second video sensor system having a range of at least a second field of view and being able to detect and identify said given vehicle present in said second field of view and transmit a second signal concerning said given vehicle wherein a roadway link connects said first video sensor system with said second video sensor system; and

(c) a wide area flow processor capable of receiving said first signal and said second signal and recognizing and tracking movement of said given vehicle from said first video sensor system'"'"'s field of view through said second video sensor system'"'"'s field of view.

14. A traffic surveillance system as set forth in claim 13, wherein said first video sensor system determines a first position of said given vehicle in said first field of view and said second video sensor system determines a second position of said given vehicle in said second field of view.

15. A traffic surveillance system as set forth in claim 13, wherein said second field of view is non-contiguous with said first field of view.

16. A traffic surveillance system as set forth in claim 15, wherein said second field of view is located at a distance of greater than 200 feet from said first field of view.

17. A traffic surveillance system as set forth in claim 15, wherein said second field of view is located at a distance of greater than one fourth mile from said first field of view.

18. A traffic surveillance system as set forth in claim 13, wherein said first video sensor system comprises:

(a) a first video sensor capable of sensing characteristics of said given vehicle, said characteristics being adequate to identify said given vehicle, and providing a first data signal containing therein characterizing data concerning said given vehicle; and

(b) a first traffic processor coupled to said first video sensor, said first traffic processor receiving said first data signal and distinguishing said given vehicle from other vehicles based on said first data signal.

19. A traffic surveillance system as set forth in claim 18, wherein said first video sensor comprises a video camera.

20. A traffic surveillance system as set forth in claim 13, wherein said wide area flow processor utilizes a predictor algorithm to predict a future location for said given vehicle and uses location information concerning said given vehicle to correct said predictor algorithm.

21. A traffic surveillance system as set forth in claim 13, wherein said wide area of traffic comprises a traffic network of greater than one half mile in length.

22. A traffic surveillance system as set forth in claim 13, wherein said wide area of traffic comprises a traffic network of up to 50 miles in length.

23. A traffic surveillance system for surveying a wide area of traffic, said system comprising:

(a) a first sensor system, said first sensor system having a range of at least a first field, and being able to detect and identify a given vehicle present in said first field, and transmit a first signal concerning said given vehicle;

(b) a second sensor system, said second sensor system having a range of at least a second field and being able to detect and identify said given vehicle present in said second field and transmit a second signal concerning said given vehicle wherein a roadway link connects said first sensor system with said second sensor system; and

(c) a wide area flow processor capable of receiving said first signal and said second signal and recognizing and tracking movement of said given vehicle from said first sensor system'"'"'s field through said second sensor system'"'"'s field.

24. A traffic surveillance system as set forth in claim 23, wherein said first sensor comprises an image processor, said image processor performing automated license plate reading.

25. A traffic surveillance system for surveying a wide area of traffic, said wide area of traffic comprising a traffic network of greater than one half mile in length, said traffic surveillance system comprising:

(a) a first video sensor system, said first video sensor system having a range of at least a first field of view, and being able to detect and uniquely identify a given vehicle present in said first field of view, and transmit a first signal concerning said given vehicle, and said first video sensor system determining a first position of said given vehicle in said first field of view, and wherein said first video sensor system comprises;

(i) a first video sensor capable of sensing characteristics of said given vehicle, said characteristics being adequate to uniquely identify said vehicle, and providing a first data signal containing therein characterizing data concerning said given vehicle; and

(ii) a first traffic processor coupled to said first video sensor, said first traffic processor receiving said first data signal and uniquely distinguishing said given vehicle from other vehicles based on said first data signal;

(b) a second video sensor system, said second video sensor system having a range of at least a second field of view, said first field of view being non-contiguous with said second field of view, and said second video sensor system being able to detect and uniquely identify said given vehicle present in said second field of view and transmit a second signal concerning said given vehicle, and said second video sensor system determining a second position of said given vehicle in said second field of view wherein a roadway link connects said first video sensor system with said second video sensor system; and

(c) a wide area flow processor capable of receiving said first signal and said second signal and recognizing and tracking movement of said given vehicle from said first video sensor system'"'"'s field of view through said second video sensor system'"'"'s field of view.