Real-Time Multiclass Driver Action Recognition Using Random Forests
US-2015098609-A1 · Apr 9, 2015 · US
US9972184B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9972184-B2 |
| Application number | US-201414339652-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 24, 2014 |
| Priority date | Jul 24, 2014 |
| Publication date | May 15, 2018 |
| Grant date | May 15, 2018 |
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.
The present disclosure generally relates to systems and methods for monitoring a vehicle operator and for monitoring the environment of a vehicle operator. In particularly, the present disclosure relates to systems and methods for determining a physical position of an operator within a vehicle and for determining environmental conditions surrounding the vehicle operator. The systems may include at least one of: an image sensor, an infrared sensor, an ultrasonic sensor, a microphone or a combination or sub-combination thereof. The methods may determine a position and/or an orientation of a vehicle operator's head, arms, hands, legs, feet, etc., a combination thereof or a sub-combination thereof. The methods may generate a warning when a position of the vehicle operator is inappropriate, such as when the vehicle operator has not looked in front of the vehicle for an extended period of time when the vehicle is travelling forward, when the vehicle operator is looking at a cellular telephone, when the vehicle operator has been looking downward for an extended period of time, etc.
Opening claim text (preview).
What is claimed is: 1. A computer implemented method for generating data representative of a position of at least a portion of a vehicle driver within an interior of a vehicle and data representative of an operating environment within the vehicle, the method comprising: acquiring, from one or more data sources, model data, wherein the model data is representative of a model of at least a portion of the interior of the vehicle including at least a portion of a model vehicle operator; acquiring, from two or more position sensors, vehicle driver position data, wherein a first one of the two or more position sensors is a pressure transducer located within a vehicle driver-side seat, wherein a position of the vehicle driver within the vehicle driver-side seat is inferred from shifting weight on the vehicle driver-side seat, wherein a second one of the two or more position sensors is used to generate a three-dimensional model of a vehicle driver within the interior of the vehicle, and wherein the vehicle driver position data is representative of the position of at least the portion of the vehicle driver within the interior of the vehicle; comparing, using one or more processors, the vehicle driver position data with the model data; and determining, using one or more processors, a difference between the vehicle driver position data and the model data based on the comparison of the vehicle driver position data with the model data to detect a vehicle driver position. 2. The method of claim 1 , further comprising: generating at least one of: a warning to the vehicle driver that a position of at least a portion of the vehicle driver has deviated from a position of at least a portion of the model vehicle operator and an advisory to the vehicle driver how to correct a deviation of a position of at least a portion of the vehicle driver has deviated from a position of at least a portion of the model vehicle operator. 3. The method of claim 1 , wherein the vehicle driver position data is acquired from at least one of: an infrared sensor, an ultrasonic sensor, or an image sensor. 4. The method of claim 1 , wherein the vehicle driver position data includes information that is representative of at least one of: a gaze direction of the vehicle driver, an in-car gesture of the vehicle driver, a position of the vehicle driver's head, an orientation of the vehicle driver's head, a position of at least one of the vehicle driver's hands, an orientation of at least one of the vehicle driver's hands, a position of at least one of the vehicle driver's feet or an item within at least one of the vehicle driver's hands. 5. The method of claim 4 , wherein the vehicle driver position data includes a time stamp and the information is tracked over time. 6. The method of claim 1 , further comprising: acquiring, from one or more audio sensors, audio data, wherein the audio data is representative of sound within the interior of the vehicle. 7. The method of claim 6 , wherein the audio data is indicative of a volume of the sound. 8. A system for generating data representative of a position of at least a portion of a vehicle driver within an interior of a vehicle and data representative of an operating environment within the vehicle using one or more processors, the system comprising: a model data acquisition module stored on a memory that, when executed by a processor, causes the processor to acquire model data, wherein the model data is representative of a model of at least a portion of the interior of the vehicle including at least a portion of a model vehicle operator; a position data acquisition module stored on a memory that, when executed by a processor, causes the processor to acquire position data from at least two position sensors, wherein a first one of the at least two position sensors is a pressure transducer located within a vehicle driver-side seat, wherein a position of the vehicle driver within the vehicle driver-side seat is inferred from shifting weight on the vehicle driver-side seat, wherein a second one of the at least two position sensors is used to generate a three-dimensional model of a vehicle driver within the interior of the vehicle, and wherein the position data is representative of the position of at least the portion of the vehicle driver within the interior of the vehicle; a comparison module stored on a memory that, when executed by a processor, causes the processor to compare the position data with the model data; and a determination module stored on a memory that, when executed by a processor, causes the processor to determine differences between a vehicle driver position and a model vehicle operator position based on the comparison of the position data with the model data to detect a vehicle driver position associated with a vehicle accident. 9. The system of claim 8 , further comprising: a data transmission module stored on a memory that, when executed by a processor, causes the processor to transmit the position data to a remote server. 10. The system of claim 9 , wherein the position data includes a time stamp and the information is tracked over time. 11. The system of claim 9 , wherein the model data acquisition module and the comparison module are executed by a processor within the remote server. 12. The system of claim 8 , wherein the position data includes information that is representative of at least one of: a gaze direction of the vehicle driver, an in-car gesture of the vehicle driver, a position of the vehicle driver's head, an orientation of the vehicle driver's head, a position of at least one of the vehicle driver's hands, an orientation of at least one of the vehicle driver's hands, a position of at least one of the vehicle driver's feet or an item within at least one of the vehicle driver's hands. 13. The system of claim 8 , further comprising: an audio data acquisition module stored on a memory that, when executed by a processor, causes the processor to acquire audio data, wherein the audio data is representative of sound within the interior of the vehicle. 14. A non-transitory, computer-readable medium storing instructions that when executed by a process of a computer system cause the computer system to generate data representative of a position of at least a portion of a vehicle driver within an interior of a vehicle and data representative of an operating environment within the vehicle, the instructions comprising: a model data acquisition module that, when executed by a processor, causes the processor to acquire model data, wherein the model data is representative of a model of at least a portion of the interior of the vehicle including at least a portion of a model vehicle operator; a position data acquisition module that, when executed by a processor, causes the processor to acquire position data from at least two position sensors, wherein a first one of the at least two position sensors is a pressure transducer located within a vehicle driver-side seat, wherein a position of the vehicle driver within the vehicle driver-side seat is inferred from shifting weight on the vehicle driver-side seat, wherein a second one of the at least two position sensors is used to generate a three-dimensional model of a vehicle driver within the interior of the vehicle, and wherein the position data is representative of the position of at least the portion of the vehicle driver within the interior of the vehicle; a comparison module that, when executed by a processor, causes the processor to compare the position data with the model data; and a determination module that, when executed by a processor, causes the processor to determin
Alarms for ensuring the safety of persons · CPC title
for occupant comfort {, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel} · CPC title
indicating a condition of sleep, e.g. anti-dozing alarms · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.