Pedestrian right of way monitoring and reporting system and method

• US 9,824,277 B2
• Filed: 08/23/2016
• Issued: 11/21/2017
• Est. Priority Date: 04/19/2013
• Status: Active Grant

• Current Assignee: Polaris Sensor Technologies, Inc
• Original Assignee: Polaris Sensor Technologies, Inc
• Inventors: Edmondson, Richard P., Hanks, Jonathan B.
• Primary Examiner(s): Cunningham, Gregory F
• Application Number:
  US15/244,712
• Publication Number:
  US 20160364614A1
• Time in Patent Office: 455 Days
• Field of Search: 382103
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 20/49 Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats

Abstract

A system and method for monitoring vehicle traffic and collecting data indicative of pedestrian right of way violations by vehicles is provided. The system comprises memory and logic for monitoring traffic intersections and recording evidence indicating that vehicles have violated pedestrian right of way. Two sensor modalities collecting video data and radar data of the intersection under observation are employed in one embodiment of the system. The violation evidence can be accessed remotely by a traffic official for issuing of traffic citations.

Claims

1. A system, comprising:

memory; and

logic configured to receive and store in the memory radar data and video data indicative of possible pedestrians and vehicles in an area under observation,

the logic further configured to segment and classify the radar and video data and correlate classified radar objects with classified video objects to identify correlated objects of interest, wherein the logic configured to correlate classified radar objects with classified video objects comprises logic configured to search classified video objects for correlating classified radar objects, record a likeness of the modalities for a property, and determine a likelihood of correlation between the modalities,

the logic further configured to track the correlated objects to identify tracked pedestrians and vehicles,

the logic further configured to receive and store in the memory traffic rules data indicative of pedestrian right of way traffic laws for the area under observation,

the logic further configured to process the tracked pedestrians and vehicles with the traffic rules data to generate and store in the memory data indicative of alleged vehicle pedestrian right of way violations.

2. The system of claim 1, wherein the logic configured to determine the likelihood of correlation between the modalities is further configured to compute a temporal likeness score for each correlated object.

3. The system of claim 2, wherein the logic configured to determine the likelihood of correlation of the modalities is further configured to assign a confidence value for each object based upon the temporal likeness score.

4. The system of claim 1, wherein the logic is further configured to receive and store in the memory traffic signal state data indicative of the state of a vehicle traffic signal corresponding to activity of the tracked radar and video objects.

5. The system of claim 2, the traffic signal state data further comprises data indicative of the state of a pedestrian crosswalk signal.

6. The system of claim 1, wherein the area under observation includes one or more pedestrian crosswalks.

7. A method of recording evidence of suspected pedestrian right of way violations by vehicles, the method, comprising:

receiving raw video data from one or more video cameras collecting video data of an area under observation;

processing the raw video data to form packetized video data;

spatially segmenting the packetized video data and classifying video objects of interest;

receiving raw radar data from one or more radar sensors collecting radar data of the area under observation;

spatially segmenting the raw radar data and classifying radar objects of interest;

correlating the radar and video objects of interest, wherein the correlating step comprises

searching classified video objects for correlating classified radar objects,

recording a likeness of the modalities for a property, and

determining a likelihood of correlation between the modalities;

tracking the correlated objects of interest;

receiving traffic rules data indicative of pedestrian right of way traffic laws;

applying the traffic rules data to the correlated objects of interest and recording alleged violation data.

8. The method of claim 7, wherein the correlating step comprising determining a likelihood of correlation between the modalities further comprises computing a temporal likeness score for each correlated object.

9. The method of claim 8, wherein the correlating step comprising determining a likelihood of correlation between the modalities further comprises assigning a confidence value for each object based upon the temporal likeness score.

10. The method of claim 7, further comprising receiving traffic signal state data from a vehicle traffic signal and processing the traffic signal state data with the traffic rules to record alleged violation data.

11. The method of claim 10, wherein the traffic signal state data comprises data indicative of the state of a vehicle traffic signal.

12. The method of claim 11, wherein the traffic signal state data further comprises data indicative of the state of a pedestrian crosswalk signal.

13. The method of claim 7, further comprising remotely accessing the alleged violation data and generating traffic citations.

14. A method of recording evidence of suspected pedestrian right of way violations by vehicles, the method, comprising:

receiving raw video data from one or more video cameras collecting video data of an area under observation;

processing the raw video data to form packetized video data;

spatially segmenting the packetized video data and classifying video objects of interest;

receiving raw radar data from one or more radar sensors collecting radar data of the area under observation;

spatially segmenting the raw radar data and classifying radar objects of interest;

correlating the radar and video objects of interest,

tracking the correlated objects of interest, wherein the tracking step comprises predicting position data of prior known objects, updating position data for prior known objects based upon current observed objects, adding position data for new objects, and discarding position data for stale objects;

receiving traffic rules data indicative of pedestrian right of way traffic laws;

applying the traffic rules data to the correlated objects of interest and recording alleged violation data.

15. The method of claim 14, further comprising remotely accessing the alleged violation data and generating traffic citations.

16. The method of claim 14, wherein the tracking step of predicting position data of prior known objects comprises predicting state vectors of prior observed objects.

17. The method of claim 16, wherein the tracking step of updating position data for prior known objects based upon current observed objects comprises updating state vectors for prior known objects based upon current state vectors.

18. The method of claim 17, wherein the tracking step of adding position data for new objects comprises adding state vectors for new objects.

19. The method of claim 18, wherein the tracking step of discarding position data for stale objects comprises discarding state vectors for objects that have not been observed over a plurality of sets of data over time.