Method and apparatus for providing safety levels estimate for a travel link based on signage information

• US 10,453,337 B2
• Filed: 06/25/2015
• Issued: 10/22/2019
• Est. Priority Date: 06/25/2015
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Anastassov, Anton, Linder, Eric, Stenneth, Leon Oliver
• Primary Examiner(s): Lin, Abby Y
• Assistant Examiner(s): Williams, Kelly D
• Application Number:
  US14/750,584
• Publication Number:
  US 20160379485A1
• Time in Patent Office: 1,580 Days
• Field of Search: None
• CPC Class Codes: G01C 21/3415 Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
• CPC Class Codes: G01C 21/3492 employing speed data or traffic data, e.g. real-time or historical traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01C 21/3694 Output thereof on a road map
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0116 from roadside infrastructure, e.g. beacons
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/065 by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
• CPC Class Codes: G08G 1/096716 where the received information does not generate an automatic action on the vehicle control
• CPC Class Codes: G08G 1/096758 where no selection takes place on the transmitted or the received information
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G08G 1/096816 where the complete route is transmitted to the vehicle at once
• CPC Class Codes: G08G 1/096844 where the complete route is dynamically recomputed based on new data
• CPC Class Codes: G08G 1/096866 where the complete route is shown to the driver
• CPC Class Codes: G08G 1/0969 having a display in the form of a map
• CPC Class Codes: G09B 29/007 using computer methods

Abstract

An approach is provided for determining safety levels for one or more locations based, at least in part, on signage information. The approach involves determining signage information associated with at least one location. The approach also involves causing, at least in part, a creation of at least one predictor model based, at least in part, on the signage information and one or more attributes associated with the at least one location. The approach also involves causing, at least in part, a classification of the at least one location, one or more other locations, or a combination thereof according to one or more safety levels using, at least in part, the at least one predictor model.

Claims

1. A method comprising:

acquiring signage information, by way of at least one sensor and at least one of the following;

a map, a database and cloud, the signage information associated with at least one location, the signage information including a presence of one or more signs in the at least one location, one or more characteristics of the one or more signs, one or more locations of the one or more signs, or a combination thereof, and wherein the one or more signs include, at least in part, one or more physical signs, one or more virtual signs, or a combination thereof, and wherein the one or more signs include, at least in part, a combination of one or more traffic signs and one or more non-traffic signs;

creating at least one predictor model based, at least in part, on the signage information and one or more attributes associated with the at least one location, wherein the one or more attributes associated with the at least one location include, at least in part, a traffic volume attribute;

classifying the at least one location, one or more other locations, or a combination thereof according to one or more safety levels using, at least in part, the at least one predictor model; and

using normalized probe density data as a proxy for the traffic volume attribute,

wherein the normalized probe density data is derived from probe data that has been filtered, the probe data includes more than one of historical safety information, speed information, and timestamp information, for one or more vehicles in at least one road link associated with the at least one location, and

wherein the filtered probe data has been map-matched with historical accident data.

2. The method of claim 1, further comprising:

determining the historical safety information for the at least one location, wherein the historical safety information includes, at least in part, historical accident information for the at least one location; and

training the at least one predictor model based, at least in part, on the historical safety information.

3. The method of claim 2, further comprising:

labeling the at least one location according to the one or more safety levels using the historical safety information,

wherein the training of the at least one predictor model is based, at least in part, on the labeling.

4. The method of claim 3, further comprising:

processing of the historical safety information to determine a number of accidents, a number of accidents per length of road segment, a number of accidents per unit of time, or a combination thereof,

wherein the labeling of the at least one location is based, at least in part, on the number of accidents, the number of accidents per length of road segment, the number of accidents per unit of time, or a combination thereof.

5. The method of claim 1, further comprising at least one of the following:

ranking the at least one location, the one or more other locations, or a combination thereof based, at least in part, on the one or more safety levels;

presenting at least one map encompassing the at least one location, the one or more other locations, or a combination thereof that is coded to show the one or more safety levels;

presenting one or more notifications based, at least in part, on the one or more safety levels; and

calculating at least one navigation route to avoid one or more areas based, at least in part, on the one or more safety levels.

6. The method of claim 1, wherein (a) the creation of the at least one predictor model;

(b) the classification of the at least one location, one or more other locations, or a combination thereof;

or (c) a combination thereof is performed with respect to an individual user, a group of users, or a combination thereof.

7. The method of claim 1, wherein the signage information includes, at least in part, an absence of the one or more signs in the at least one location, a detectability of the one or more signs, or a combination thereof.

8. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

acquiring signage information, by way of at least one sensor and at least one of the following;

a map, a database and cloud, the signage information associated with at least one location and the signage information including a presence of one or more signs in the at least one location, one or more characteristics of the one or more signs, one or more locations of the one or more signs, or a combination thereof, and wherein the one or more signs include, at least in part, a combination of one or more traffic signs and one or more non-traffic signs;

creating at least one predictor model based, at least in part, on the signage information and one or more attributes associated with the at least one location, wherein the one or more attributes associated with the at least one location include, at least in part, a traffic volume attribute;

classifying the at least one location, one or more other locations, or a combination thereof according to one or more safety levels using, at least in part, the at least one predictor model; and

using normalized probe density data as a proxy for the traffic volume attribute,

wherein the normalized probe density data is derived from probe data that has been filtered, the probe data includes more than one of historical safety information, speed information, and timestamp information, for one or more vehicles in at least one road link associated with the at least one location, and

wherein the filtered probe data has been map-matched with historical accident data.

9. The apparatus of claim 8, wherein the one or more signs include, at least in part, one or more physical signs, one or more virtual signs, or a combination thereof.

10. The apparatus of claim 8, wherein the apparatus is further caused to:

determine the historical safety information for the at least one location, wherein the historical safety information includes, at least in part, historical accident information for the at least one location; and

train the at least one predictor model based, at least in part, on the historical safety information.

11. The apparatus of claim 10, wherein the apparatus is further caused to:

label the at least one location according to the one or more safety levels using the historical safety information,

wherein the training of the at least one predictor model is based, at least in part, on the labeling.

12. A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:

acquiring signage information, by way of at least one sensor and at least one of the following;

a map, a database and cloud, the signage information associated with at least one location and the signage information including a presence of one or more signs in the at least one location, one or more characteristics of the one or more signs, one or more locations of the one or more signs, or a combination thereof, and wherein the one or more signs include, at least in part, a combination of one or more traffic signs and one or more non-traffic signs;

creating at least one predictor model based, at least in part, on the signage information and one or more attributes associated with the at least one location, wherein the one or more attributes associated with the at least one location include, at least in part, a traffic volume attribute;

classifying the at least one location, one or more other locations, or a combination thereof according to one or more safety levels using, at least in part, the at least one predictor model; and

using normalized probe density data as a proxy for the traffic volume attribute,

wherein the normalized probe density data is derived from probe data that has been filtered, the probe data includes more than one of historical safety information, speed information, and timestamp information, for one or more vehicles in at least one road link associated with the at least one location, and

wherein the filtered probe data has been map-matched with historical accident data.