Machine learning based driver assistance
US-2020005060-A1 · Jan 2, 2020 · US
US10853622B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10853622-B2 |
| Application number | US-201916430528-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jun 4, 2019 |
| Priority date | Jun 8, 2018 |
| Publication date | Dec 1, 2020 |
| Grant date | Dec 1, 2020 |
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 driver monitoring device 1 comprises an imaging device 2 capturing an image of a face of a driver of a vehicle to generate an image, a face detecting part 31 detecting the face from the image, a face orientation estimating part 32 estimating a face orientation of the driver, and a cause judging part 33 judging a cause for the face not being detected. The face detecting part detects the face by extracting feature points of the face from the image. When the detection state of the face changes from “detected” to “not detected”, the cause judging part judges that the cause is an eating or drinking action of the driver if in a predetermined number of images until the detection state changes from “detected” to “not detected”, the face orientation is a front and the feature points at a lower region of the face are not extracted.
Opening claim text (preview).
The invention claimed is: 1. A driver monitoring device comprising an imaging device capturing an image of a face of a driver of a vehicle to generate an image, a face detecting part configured to detect the face from the image, a face orientation estimating part configured to estimate a face orientation of the driver based on the image if the face is detected by the face detecting part, and a cause judging part configured to judge a cause for the face not being detected if the face is not detected by the face detecting part, wherein the face detecting part is configured to detect the face by extracting feature points of the face from the image, and when the detection state of the face changes from “detected” to “not detected”, the cause judging part is configured to judge that the cause is an eating or drinking action of the driver if in a predetermined number of images until the detection state changes from “detected” to “not detected”, the face orientation estimated by the face orientation estimating part is a front and the feature points at a lower region of the face are not extracted by the face detecting part. 2. The driver monitoring device according to claim 1 , further comprising a warning part configured to issue a warning to the driver, wherein the warning part is configured to suppress a warning to the driver if it is judged that the cause is an eating or drinking action of the driver compared to if it is judged that the cause is something other than an eating or drinking action of the driver. 3. The driver monitoring device according to claim 2 , wherein the warning part is configured to issue a warning to the driver if a state in which the state of detection of the face is not detected continues for a threshold time, and the warning part is configured to extend the threshold time if it is judged that the cause is an eating or drinking action of the driver compared to if it is judged that the cause is something other than an eating or drinking action of the driver. 4. A driver monitoring device comprising an imaging device capturing an image of a face of a driver of a vehicle to generate an image, and a control device configured to detect the face from the image, estimate a face orientation of the driver based on the image if detecting the face, and judge a cause for the face not being detected if the face is not detected, wherein the control device is configured to detect the face by extracting feature points of the face from the image, and when the detection state of the face changes from “detected” to “not detected”, the control device is configured to judge that the cause is an eating or drinking action of the driver if in a predetermined number of images until the detection state changes from “detected” to “not detected”, the face orientation is a front and the feature points at a lower region of the face are not extracted.
Mounting of pick-up tubes, electronic image sensors, deviation or focusing coils · CPC title
adapted for image acquisition of a particular organ or body part (A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062) · CPC title
Recognising the driver's state or behaviour, e.g. attention or drowsiness · CPC title
Detection; Localisation; Normalisation · CPC title
Feature extraction; Face representation · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.