Methods of providing insurance savings based upon telematics and insurance incentives
US-10475127-B1 · Nov 12, 2019 · US
US10913461B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10913461-B2 |
| Application number | US-201916428332-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 31, 2019 |
| Priority date | Mar 6, 2017 |
| Publication date | Feb 9, 2021 |
| Grant date | Feb 9, 2021 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A driving behavior determining method, apparatus, and device, and a storage medium are provided. The method includes obtaining, by a computing device, a driving video of a target vehicle. A content of the driving video includes a road and a neighboring vehicle of the target vehicle, and the neighboring vehicle includes at least one of a front vehicle in front of the target vehicle and a rear vehicle at a rear of the target vehicle. The method also includes: obtaining, by the computing device, vehicle running information that comprises a running status of the target vehicle; and determining, by the computing device, whether a dangerous driving behavior exists according to the driving video and the vehicle running information corresponding to a same time period. The dangerous driving behavior is a driving behavior having an accident risk.
Opening claim text (preview).
What is claimed is: 1. A driving behavior determining method, comprising: obtaining, by a computing device, a driving video of a target vehicle, a content of the driving video comprising a road and a neighboring vehicle of the target vehicle, the neighboring vehicle comprising at least one of a front vehicle in front of the target vehicle and a rear vehicle at a rear of the target vehicle; obtaining, by the computing device, vehicle running information that comprises steering information of the target vehicle, the steering information including status of a turn signal light; recognizing the driving video to obtain a driving video recognition result, the driving video recognition result comprising lane information and vehicle distance information; and determining, by the computing device, whether a dangerous driving behavior exists according to the driving video recognition result and the vehicle running information corresponding to a same time period, the dangerous driving behavior being a driving behavior having an accident risk, including departing from a lane without turning on the turn signal light. 2. The method according to claim 1 , wherein the driving video recognition result further comprises relative speed information, wherein the lane information comprises a lane in which the target vehicle is located, the vehicle distance information comprises at least one of a distance to the front vehicle or a distance to the rear vehicle, and the relative speed information comprises at least one of a speed relative to the front vehicle or a speed relative to the rear vehicle. 3. The method according to claim 2 , wherein the recognizing the driving video to obtain a driving video recognition result comprises at least one of: recognizing a lane line comprised in the driving video, and determining the lane information according to the lane line; recognizing an image location of the neighboring vehicle in the driving video, and determining the vehicle distance information according to the image location and a preset distance scale, the preset distance scale comprising mapping relationships between image locations in the driving video and actual distances; or recognizing an image location of the neighboring vehicle in the driving video, and determining the relative speed information according to a change of the image location. 4. The method according to claim 1 , wherein after the determining whether the dangerous driving behavior exists according to the driving video recognition result and the vehicle running information, the method further comprises: determining a danger level of the dangerous driving behavior; calculating update data according to a frequency of occurrence of the dangerous driving behavior, the danger level, and a weight corresponding to the dangerous driving behavior; and updating driving behavior data corresponding to the target vehicle based on the update data. 5. The method according to claim 4 , wherein the determining a danger level of the dangerous driving behavior comprises: determining the danger level according to a current speed comprised in the vehicle running information and a traffic flow, when the dangerous driving behavior is departing from a lane without turning on the turn signal light; or determining the danger level according to the current speed and a current vehicle distance, when the dangerous driving behavior is keeping an excessively short distance between vehicles or applying emergency braking, wherein the current speed has a positive correlation with the danger level, the traffic flow has a positive correlation with the danger level, and the current vehicle distance has a negative correlation with the danger level. 6. The method according to claim 1 , wherein the determining whether the dangerous driving behavior exists according to the driving video recognition result and the vehicle running information comprises: determining that a first dangerous driving behavior exists in response to detecting that the lane information changes, a distance to the front vehicle is less than a first threshold based on the vehicle distance information, and no turn signal light has been turned on based on the steering information. 7. The method according to claim 1 , wherein the driving video recognition result further comprises relative speed information, and the vehicle running information comprises a current speed; and the determining whether the dangerous driving behavior exists according to the driving video recognition result and the vehicle running information comprises: determining a safe braking distance corresponding to the current speed, and determining that a second dangerous driving behavior exists in response to detecting that the distance to the front vehicle is less than the safe braking distance based on the vehicle distance information and detecting that the current speed is greater than a speed of the front vehicle the relative speed information, the second dangerous driving behavior being a driving behavior of keeping an excessively short distance between vehicles. 8. The method according to claim 1 , wherein the vehicle running information comprises a current acceleration; and the determining whether the dangerous driving behavior exists according to the driving video recognition result and the vehicle running information comprises: determining that a third dangerous driving behavior exists in response to detecting that a distance to the front vehicle is greater than a second threshold and a distance to the rear vehicle is less than a third threshold based on the vehicle distance information, and detecting that the target vehicle is braking based on the current acceleration, the third dangerous driving behavior being a driving behavior of applying emergency braking. 9. A driving behavior determining apparatus, comprising: a memory; and a processor coupled to the memory and configured to perform: obtaining a driving video of a target vehicle, a content of the driving video comprising a road and a neighboring vehicle of the target vehicle, the neighboring vehicle comprising at least one of a front vehicle in front of the target vehicle and a rear vehicle at a rear of the target vehicle; obtaining vehicle running information that comprises steering information of the target vehicle, the steering information including status of a turn signal light; recognizing the driving video to obtain a driving video recognition result, the driving video recognition result comprising lane information and vehicle distance information; and determining whether a dangerous driving behavior exists according to the driving video recognition result and the vehicle running information corresponding to a same time period, the dangerous driving behavior being a driving behavior having an accident risk, including departing from a lane without turning on the turn signal light. 10. The apparatus according to claim 9 , wherein the driving video recognition result further comprises relative speed information; wherein the lane information comprises a lane in which the target vehicle is located, the vehicle distance information comprises at least one of a distance to the front vehicle or a distance to the rear vehicle, and the relative speed information comprises at least one of a speed relative to the front vehicle or a speed relative to the rear vehicle. 11. The apparatus according to claim 10 , wherein the recognizing the driving video to obtain a driving video recognition result comprises at least one of: recognizing a lane line comprised in the driving video, and determining the lane information according to the lane line; recognizing an image lo
Gains, weighting coefficients or weighting functions · CPC title
Relative longitudinal speed · CPC title
Longitudinal distance · CPC title
related to ambient conditions · CPC title
Processor details or data handling, e.g. memory registers or chip architecture · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.