Models for stop sign database creation
An improved system and method of determining presence of stop signs at intersection based on multiple types of data including ground truth data, telemetry data, and/or trip stills gathered from vehicle devices. The data may be analyzed and aggregated by one or more models and/or neural networks to develop a prediction regarding presence of stop signs at individual intersections.
1 . A method performed by a computing system having one or more hardware computer processors and one or more non-transitory computer readable storage device storing software instructions executable by the computing system, the method comprising:
accessing map data including a plurality of hexagon-shaped regions each associated with a geographic area;
accessing a plurality of telemetry data points from a plurality of vehicles, wherein each of the telemetry data points indicates at least a speed of a vehicle associated with a geographic location;
for individual telemetry data points, associating the telemetry data point to a corresponding hexagon-shaped region; and
for individual hexagon-shaped regions:
evaluating a machine learning algorithm, based at least on the telemetry data points associated with the hexagon-shaped region, to determine a characteristic of the hexagon-shaped region;
if the characteristic of the hexagon-shaped region meets a first criteria, updating the map data associated with the hexagon-shaped region with a first indication; and
if the characteristic of the hexagon-shaped region does not meet the criteria, updating the map data associated with the hexagon-shaped region with a second indication;
providing the map data to a navigation application associated with a vehicle, wherein the map data is usable in detection of safety events that are customized based on which of the first or second indication is associated with a current hexagon shaped-region where the vehicle is positioned.
2 . The method of claim 1 , wherein the map data is stored in a network-accessible location that is accessible by each of a plurality of vehicle devices.
3 . The method of claim 1 , wherein the map data is usable by a vehicle device attached to a first vehicle.
4 . The method of claim 3 , wherein the vehicle device includes one or more of a video sensor, audio sensor, accelerometer, or global positioning system (GPS).
5 . The method of claim 4 , wherein the vehicle device includes communication circuitry configured to transmit data to, and receive data from, a backend server.
6 . The method of claim 5 , wherein the geographic location of telemetry data points includes a latitude and longitude coordinate.
7 . The method of claim 5 , wherein individual telemetry data points each include one or more of a bearing, direction, timestamp, or vehicle ID.
8 . A computing system comprising:
a hardware computer processor;
a non-transitory computer readable medium having software instructions stored thereon, the software instructions executable by the hardware computer processor to cause the computing system to perform operations comprising:
accessing map data including a plurality of hexagon-shaped regions each associated with a geographic area;
accessing a plurality of telemetry data points from a plurality of vehicles, wherein each of the telemetry data points indicates at least a speed of a vehicle associated with a geographic location;
for individual telemetry data points, associating the telemetry data point to a corresponding hexagon-shaped region; and
for individual hexagon-shaped regions:
evaluating a machine learning algorithm, based at least on the telemetry data points associated with the hexagon-shaped region, to determine a characteristic of the hexagon-shaped region;
if the characteristic of the hexagon-shaped region meets a criteria, updating the map data associated with the hexagon-shaped region with a first indication; and
if the characteristic of the hexagon-shaped region does not meet the criteria, updating the map data associated with the hexagon-shaped region with a second indication;
providing the map data to a navigation application associated with a vehicle, wherein the map data is usable in detection of safety events that are customized based on which of the first or second indication is associated with a current hexagon shaped-region where the vehicle is positioned.
9 . The computing system of claim 8 , wherein the map data is stored in a network-accessible location that is accessible by each of a plurality of vehicle devices.
10 . The computing system of claim 8 , wherein the map data is usable by a vehicle device attached to a first vehicle.
11 . The computing system of claim 10 , wherein the vehicle device includes one or more of a video sensor, audio sensor, accelerometer, or global positioning system (GPS).
12 . The computing system of claim 11 , wherein the vehicle device includes communication circuitry configured to transmit data to, and receive data from, a backend server.
13 . The computing system of claim 12 , wherein the geographic location of telemetry data points includes a latitude and longitude coordinate.
14 . The computing system of claim 12 , wherein individual telemetry data points each include one or more of a bearing, direction, timestamp, or vehicle ID.