System and method for creating environmental model for intelligent intersection functions
An intelligent intersection method includes receiving raw sensor data from a sensors mounted relative to a street intersection. The received raw sensor data is fused to create at least one object sensed by the sensors. An object list is created or updated with information pertaining to created object, the object list serving as an environmental model. One or more intelligent intersection functions is subsequently performed based in part upon the environmental model. The method may further include determining whether the created object is associated with first data defining a topology of at least one of a plurality of lanes, a crosswalk or a sidewalk corresponding to the intersection. Upon an affirmative determination that the created object is associated with the first data, the method classifies the created object as a vehicle or a pedestrian for use as an attribute of the created object in the object list.
1 . A method of controlling an intelligent intersection system, the method comprising:
receiving image data of a street intersection;
generating based on the image data a first topology of a plurality of lanes in the street intersection and a second topology of at least one crosswalk or at least one sidewalk associated with the street intersection;
determining whether the object is disposed within the first topology or the second topology based on a position of the object; and
classifying the object as a vehicle based on determining the object is disposed within the first topology and a pedestrian based on determining the object is disposed within the second topology;
and
performing an intelligent intersection function based on classifying the object as the vehicle or the pedestrian model.
2 . The method of claim 1 , wherein determining whether the object is disposed within the first topology or the second topology comprises:
detecting the object, by a plurality of radar sensors;
fusing radar data of radar reflections from the object received by the plurality of radar sensors;
determining the position of the object based on a result of fusing the radar reflections; and
determining whether the position of the object is disposed within the first topology or the second topology.
3 . The method of claim 2 , further comprising storing the object in an object list that is an environmental model of the intelligent infrastructure system,
wherein performing the intelligent infrastructure function comprises performing the intelligent intersection function based on the object list.
4 . The method of claim 3 , wherein the object list comprises an attribute of the object associated with the object.
5 . The method of claim 4 , wherein the attribute of the object comprises a classification of the object as the vehicle or a classification of the object as the pedestrian.
6 . The method of claim 5 , wherein the attribute of the object comprises at least one of a size of the object, a position of the object, a velocity of the object, and a heading of the object.
7 . The method of claim 6 , wherein the fusing comprises providing raw sensor data of the plurality of radar sensors to one of an extended Kalman filter, a particle filter, a Bayesian network, or a convolutional neural network to create the object.
8 . An intelligent intersection system comprising:
a processing unit; and
memory coupled to the processing unit, the memory storing program code having instructions which, when executed by the processing unit, cause the processing unit to perform a method comprising:
receiving image data of a street intersection;
generating based on the image data a first topology of a plurality of lanes in the street intersection and a second topology of at least one crosswalk or at least one sidewalk associated with the street intersection;
determining whether the object is disposed within the first topology or the second topology based on a position of the object; and
classifying the object as a vehicle based on determining the object is disposed within the first topology and a pedestrian based on determining the object is disposed within the second topology; and
performing an intelligent intersection function based on classifying the object as the vehicle or the pedestrian.
9 . The intelligent intersection system of claim 8 , wherein determining whether the object is disposed within the first topology or the second topology comprises:
detecting the object, by a plurality of radar sensors;
fusing radar data of radar reflections from the object received by the plurality of radar sensors;
determining the position of the object based on a result of fusing the radar reflections; and
determining whether the position of the object is disposed within the first topology or the second topology.
10 . The intelligent intersection system of claim 9 , wherein the method further comprises storing the object in an object list that is an environmental model of the intelligent infrastructure system,
wherein performing the intelligent infrastructure function comprises performing the intelligent intersection function based on the object list.
11 . The intelligent intersection system of claim 10 , wherein the object list comprises an attribute of the object associated with the object.
12 . The intelligent intersection system of claim 11 , wherein the attribute of the object comprises a classification of the object as the vehicle or a classification of the object as the pedestrian.
13 . The intelligent intersection system of claim 12 , wherein the attribute of the object comprises at least one of a size of the object, a position of the object, a velocity of the object, and a heading of the object.
14 . The intelligent intersection system of claim 13 , wherein the fusing comprises providing raw sensor data of the plurality of radar sensors to one of an extended Kalman filter, a particle filter, a Bayesian network, or a convolutional neural network to create the object.