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

Patent metadata

Field	Value
Publication number	US-10453337-B2
Application number	US-201514750584-A
Country	US
Kind code	B2
Filing date	Jun 25, 2015
Priority date	Jun 25, 2015
Publication date	Oct 22, 2019
Grant date	Oct 22, 2019

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.

First claim

What is claimed is:

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

Assignees

• Here Global Bv

Inventors

• Anastassov Anton
• Linder Eric
• Stenneth Leon Oliver

Classifications

• G01C21/3694

  Output thereof on a road map · CPC title

• G08G1/0133 Primary

  for classifying traffic situation · CPC title

• G06N20/00

  Machine learning · CPC title

• G01C21/3602

  Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title

• G01C21/3492

  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 title