CN110654314A - Deep learning-based automatic rearview mirror adjusting method and device - Google Patents
Deep learning-based automatic rearview mirror adjusting method and device Download PDFInfo
- Publication number
- CN110654314A CN110654314A CN201910943915.9A CN201910943915A CN110654314A CN 110654314 A CN110654314 A CN 110654314A CN 201910943915 A CN201910943915 A CN 201910943915A CN 110654314 A CN110654314 A CN 110654314A
- Authority
- CN
- China
- Prior art keywords
- rearview mirror
- deep learning
- eyes
- image
- driver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
- B60R1/02—Rear-view mirror arrangements
- B60R1/06—Rear-view mirror arrangements mounted on vehicle exterior
- B60R1/062—Rear-view mirror arrangements mounted on vehicle exterior with remote control for adjusting position
- B60R1/07—Rear-view mirror arrangements mounted on vehicle exterior with remote control for adjusting position by electrically powered actuators
Abstract
The embodiment of the invention provides a rearview mirror automatic adjusting method and device based on deep learning. The method comprises the following steps: acquiring an image including eyes of a driver and a distance from the eyes to a distance sensor; processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image; processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror; adjusting the rearview mirror according to the rotation angle and the eversion angle. The method and the device can quickly, accurately and smoothly adjust the position of the rearview mirror.
Description
Technical Field
The invention relates to the technical field of automobile industry, in particular to a rearview mirror automatic adjusting method and device based on deep learning.
Background
The rear view mirror is an important part of the vehicle. When the vehicle is traveling, the driver views the left and right sides and the rear of the vehicle through the rearview mirror.
The good rearview mirror angle is an important guarantee for the safe driving of the driver. When the vehicle changes lanes, turns or backs, the angle adjustment of the rearview mirror is directly related to the driving safety and the life safety of a driver.
The existing rearview mirror adjusting method is based on traditional image processing, and the angle of a rearview mirror is adjusted by acquiring the positions (up, down, left and right) of human eyes of a driver and the distances (front and back) of the human eyes of the driver and mapping the three-dimensional positions of the human eyes to the rearview mirror. However, this mapping is very complex and cannot be accurately represented by a simple mathematical model. And the existing rearview mirror adjusting method has insufficient conversion smoothness and accuracy.
Therefore, how to provide a rearview mirror adjusting method has been very important to solve the above technical problems in the prior art.
Disclosure of Invention
In view of the defects in the prior art, an embodiment of the present invention provides a method for automatically adjusting a rearview mirror based on deep learning, including:
acquiring an image including eyes of a driver and a distance from the eyes to a distance sensor;
processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image;
processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror;
adjusting the rearview mirror according to the rotation angle and the eversion angle.
Further, the method further comprises:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
Further, the method further comprises:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
Further, the deep learning network is a fully connected neural network.
On the other hand, the embodiment of the invention also provides a rearview mirror automatic adjusting device based on deep learning, which comprises:
the acquisition module is used for acquiring an image including eyes of a driver and the distance from the eyes to the distance sensor;
a coordinate module, configured to process the image using a convolutional neural network to obtain a planar coordinate of the human eye in the image;
the learning module is used for processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network so as to obtain the rotation angle and the eversion angle of the rearview mirror;
and the adjusting module is used for adjusting the rearview mirror according to the rotating angle and the everting angle.
Further, the obtaining module is further configured to:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
Further, the adjusting module is further configured to:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
Further, the deep learning network is a fully connected neural network.
On the other hand, an embodiment of the present invention further provides an electronic device, including:
at least one processor, at least one memory, a communication interface, and a bus; wherein the content of the first and second substances,
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, which calls the program instructions to perform the method as described above.
In another aspect, the embodiments of the present invention also provide a non-transitory computer-readable storage medium storing computer instructions, which cause the computer to execute the method described above.
According to the method and the device for automatically adjusting the rearview mirror based on deep learning, provided by the embodiment of the invention, the convolutional neural network and the deep learning network are adopted to carry out reasoning and conversion on the mapping relation between the positions of the human eyes and the angles of the rearview mirror, so that the position of the rearview mirror can be quickly, accurately and smoothly adjusted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a deep learning-based automatic rearview mirror adjustment method according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of an automatic adjusting device for a rearview mirror based on deep learning according to an embodiment of the invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flowchart of an automatic adjusting method for a deep learning-based rearview mirror according to an embodiment of the present invention, and referring to fig. 1, the automatic adjusting method for a deep learning-based rearview mirror includes:
s1, acquiring an image including eyes of the driver and the distance between the eyes and the distance sensor;
it should be noted that the execution subject of the method may be a computer, such as a PC, a desktop, a notebook, a pad, an embedded computer, and so on.
Wherein, the computer can obtain the image including driver's eyes through the image acquisition device.
In one embodiment, the image acquisition device adopts an infrared camera with a supplementary light, and the infrared camera is suitable for use in both day and night scenes. Because the infrared camera with the supplementary lighting is insensitive to the intensity of light, the collected image can be ensured to have higher definition, and the identification is convenient.
Of course, in other embodiments, for example, a high-definition camera may also be used as the image acquisition device, which is not limited in the embodiments of the present invention.
It should be noted that, after the image acquisition device acquires the image including the eyes of the driver, it first screens the acquired image. For example, if the captured image includes only one eye of the driver (the instantaneous head of the driver moving suddenly at the moment of capturing the head image), the image capturing device will not upload the image to the computer, but will re-capture a new image until the captured image includes clear eyes of the driver.
It can be understood that the image acquisition device can be installed at any position in front of the driver, and only the requirement that the image acquisition device can acquire the facial image of the driver is met. In one embodiment, the image capturing device is mounted directly forward and above the driver's seat.
In one embodiment, the distance sensor is mounted at a position directly forward and upward of the driver's seat. In another embodiment, the distance sensor and the image acquisition device are integrated so that the distance sensor and the image acquisition device are installed at the same position. Of course, the distance sensor can be installed at any position in front of the driver, and only the requirement that the distance sensor can obtain the distance from the eyes of the driver to the distance sensor is required to be met.
Optionally, a binocular camera may also be used to simultaneously acquire the image of the eyes of the driver and the distance of the eyes from the binocular camera.
S2, processing the image by using a convolutional neural network to acquire plane coordinates of the human eyes in the image;
in one embodiment, the convolutional neural network is a surrounding frame and the positions of both eyes of the detected face in the image through an MTCNN face detection network. The embodiment of the invention uses the middle positions of the two eyes as the positions of the human eyes.
It should be noted that, by adopting the convolutional neural network, good real-time performance can be provided on the premise of ensuring accuracy, and the convolutional neural network can be planted and used in various mobile terminals.
In some embodiments, in order to accurately find the position of the human eye through the convolutional neural network, CelebA, FDDB, MegaFace, and LFW public data sets, as well as images collected in conjunction with the driving environment in the vehicle, may be trained as training data sets.
S3, processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror;
in one embodiment, the deep learning network is a fully-connected neural network, which is a 3-layer fully-connected layer small network.
In this embodiment, the input is the plane coordinates and the distance of the human eye to the distance sensor, and the output is the rotation angle and the valgus angle of the rearview mirror.
It should be noted that, by adopting the fully-connected neural network, good real-time performance can be provided on the premise of ensuring accuracy, and the method can be used for planting in various mobile terminals.
S4, adjusting the rearview mirror according to the rotation angle and the eversion angle.
After the rotation angle and the eversion angle of the rearview mirror are obtained, the rearview mirror can be adjusted to rotate and/or evert to the corresponding angles, so that the optimal vision is provided for the driver.
According to the automatic rearview mirror adjusting method based on deep learning, the convolutional neural network and the deep learning network are adopted to carry out reasoning and conversion on the mapping relation between the positions of the human eyes and the angles of the rearview mirrors, so that the positions of the rearview mirrors can be adjusted quickly, accurately and smoothly.
Further, the method further comprises:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
It will be appreciated that when the driver is seated in the driver's seat (and an image including the eyes of the driver may be acquired) this is indicative of the driver needing to use the vehicle, and therefore the driver can conveniently use the mirror by controlling the mirror to be in the open state at this time.
When the driver leaves the driver seat (at the moment, images including the eyes of the driver cannot be acquired), the situation that the driver does not need to use the vehicle temporarily is indicated, and the rearview mirror can be controlled to be in a closed state, so that the rearview mirror is protected and is prevented from being damaged due to collision of other objects (such as other vehicles).
Further, the method further comprises:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
When the position of the mirror changes suddenly, for example in the event of a collision, resulting in a change in the angle of rotation and/or the angle of eversion of the mirror, the mirror can be readjusted to the adjusted rear position, so that it returns to the position providing the best view at the first time, thus protecting the driver and the vehicle.
On the other hand, the embodiment of the invention also provides a deep learning-based automatic rearview mirror adjusting device, as shown in fig. 2, the device includes an acquisition module 1, a coordinate module 2, a learning module 3, and an adjusting module 4.
The acquisition module 1 is used for acquiring an image including eyes of a driver and a distance between the eyes and a distance sensor.
It should be noted that, after the acquiring module 1 acquires the image including the eyes of the driver, it first filters the acquired image. For example, if the captured image includes only one eye of the driver (the instantaneous head of the driver moving suddenly at the moment of capturing the head image), the image capturing device will not upload the image to the computer, but will re-capture a new image until the captured image includes clear eyes of the driver.
The coordinate module 2 is used for processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image;
in one embodiment, the convolutional neural network is a surrounding frame and the positions of both eyes of the detected face in the image through an MTCNN face detection network. The embodiment of the invention uses the middle positions of the two eyes as the positions of the human eyes.
It should be noted that, by adopting the convolutional neural network, good real-time performance can be provided on the premise of ensuring accuracy, and the convolutional neural network can be planted and used in various mobile terminals.
In some embodiments, in order to accurately find the position of the human eye through the convolutional neural network, CelebA, FDDB, MegaFace, and LFW public data sets, as well as images collected in conjunction with the driving environment in the vehicle, may be trained as training data sets.
The learning module 3 is used for processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network so as to obtain the rotation angle and the eversion angle of the rearview mirror;
in one embodiment, the deep learning network is a fully-connected neural network, which is a 3-layer fully-connected layer small network.
In this embodiment, the input is the plane coordinates and the distance of the human eye to the distance sensor, and the output is the rotation angle and the valgus angle of the rearview mirror.
It should be noted that, by adopting the fully-connected neural network, good real-time performance can be provided on the premise of ensuring accuracy, and the method can be used for planting in various mobile terminals.
The adjusting module 4 is used for adjusting the rearview mirror according to the rotation angle and the eversion angle.
After the rotation angle and the eversion angle of the rearview mirror are obtained, the rearview mirror can be adjusted to rotate and/or evert to the corresponding angles, so that the optimal vision is provided for the driver.
According to the automatic rearview mirror adjusting device based on deep learning, the convolutional neural network and the deep learning network are adopted to carry out reasoning and conversion on the mapping relation between the positions of the human eyes and the angles of the rearview mirrors, so that the positions of the rearview mirrors can be adjusted quickly, accurately and smoothly.
Further, the obtaining module 1 is further configured to:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
It will be appreciated that when the driver is seated in the driver's seat (and an image including the eyes of the driver may be acquired) this is indicative of the driver needing to use the vehicle, and therefore the driver can conveniently use the mirror by controlling the mirror to be in the open state at this time.
When the driver leaves the driver seat (at the moment, images including the eyes of the driver cannot be acquired), the situation that the driver does not need to use the vehicle temporarily is indicated, and the rearview mirror can be controlled to be in a closed state, so that the rearview mirror is protected and is prevented from being damaged due to collision of other objects (such as other vehicles).
Further, the adjusting module 4 is further configured to:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
When the position of the mirror changes suddenly, for example in the event of a collision, resulting in a change in the angle of rotation and/or the angle of eversion of the mirror, the mirror can be readjusted to the adjusted rear position, so that it returns to the position providing the best view at the first time, thus protecting the driver and the vehicle.
On the other hand, an embodiment of the present invention further provides an electronic device, as shown in fig. 3. The electronic device may include: a Processor (Processor)410, a Communication Interface (Communication Interface)420, a Memory (Memory)430 and a Communication Bus (Bus)440, wherein the Processor 410, the Communication Interface 420 and the Memory 430 are configured to communicate with each other via the Communication Bus 440. The processor 410 may call a computer program stored on the memory 430 and executable on the processor 410 to perform the deep learning based automatic rearview mirror adjustment method provided by the above embodiments, for example, including:
acquiring an image including eyes of a driver and a distance from the eyes to a distance sensor; processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image; processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror; adjusting the rearview mirror according to the rotation angle and the eversion angle.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to, when executed by a processor, perform the deep learning based rearview mirror automatic adjustment method provided in the foregoing embodiments, for example, the method includes:
acquiring an image including eyes of a driver and a distance from the eyes to a distance sensor; processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image; processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror; adjusting the rearview mirror according to the rotation angle and the eversion angle.
The above-described embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the technical scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A rearview mirror automatic adjustment method based on deep learning is characterized by comprising the following steps:
acquiring an image including eyes of a driver and a distance from the eyes to a distance sensor;
processing the image by using a convolutional neural network to acquire plane coordinates of the human eye in the image;
processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network to obtain the rotation angle and the eversion angle of the rearview mirror;
adjusting the rearview mirror according to the rotation angle and the eversion angle.
2. The deep learning based rearview mirror automatic adjustment method according to claim 1, further comprising:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
3. The deep learning based rearview mirror automatic adjustment method according to claim 2, further comprising:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
4. The deep learning based rearview mirror automatic adjustment method according to any one of claims 1-3, wherein the deep learning network is a fully connected neural network.
5. The utility model provides a rear-view mirror automatic regulating apparatus based on degree of depth study which characterized in that includes:
the acquisition module is used for acquiring an image including eyes of a driver and the distance from the eyes to the distance sensor;
a coordinate module, configured to process the image using a convolutional neural network to obtain a planar coordinate of the human eye in the image;
the learning module is used for processing the plane coordinates and the distance from the human eyes to the distance sensor by using a deep learning network so as to obtain the rotation angle and the eversion angle of the rearview mirror;
and the adjusting module is used for adjusting the rearview mirror according to the rotating angle and the everting angle.
6. The deep learning based rearview mirror automatic adjusting device according to claim 5, wherein the obtaining module is further configured to:
and after the image comprising the eyes of the driver is acquired, the rearview mirror is in an open state.
7. The deep learning based rearview mirror automatic adjustment device according to claim 6, wherein the adjustment module is further configured to:
recording the adjusted rear position of the rearview mirror;
and if the position of the rearview mirror is detected to be changed suddenly, the rearview mirror is restored to the adjusted position.
8. The automatic rearview mirror adjusting device based on deep learning as claimed in any one of claims 5-7, wherein the deep learning network is a fully connected neural network.
9. An electronic device, comprising:
at least one processor, at least one memory, a communication interface, and a bus; wherein the content of the first and second substances,
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, wherein the processor invokes the program instructions to perform the method of any of claims 1 to 4.
10. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943915.9A CN110654314A (en) | 2019-09-30 | 2019-09-30 | Deep learning-based automatic rearview mirror adjusting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943915.9A CN110654314A (en) | 2019-09-30 | 2019-09-30 | Deep learning-based automatic rearview mirror adjusting method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110654314A true CN110654314A (en) | 2020-01-07 |
Family
ID=69038458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910943915.9A Pending CN110654314A (en) | 2019-09-30 | 2019-09-30 | Deep learning-based automatic rearview mirror adjusting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110654314A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113276777A (en) * | 2021-06-21 | 2021-08-20 | 南京信息工程大学无锡研究院 | Control method, device, equipment and medium for exterior rearview mirror |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203093899U (en) * | 2012-12-06 | 2013-07-31 | 长安大学 | Device for automatically folding and unfolding rearview mirror of car based on single chip microcomputer |
| CN203739761U (en) * | 2013-12-25 | 2014-07-30 | 长安大学 | Anti-collision bus rearview mirror |
| CN105769120A (en) * | 2016-01-27 | 2016-07-20 | 深圳地平线机器人科技有限公司 | Fatigue driving detection method and device |
| CN107031510A (en) * | 2016-12-29 | 2017-08-11 | 宁波吉利汽车研究开发有限公司 | A kind of outside rear-view mirror system for regulating angle |
| CN107564363A (en) * | 2017-09-05 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for driving model switching |
-
2019
- 2019-09-30 CN CN201910943915.9A patent/CN110654314A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203093899U (en) * | 2012-12-06 | 2013-07-31 | 长安大学 | Device for automatically folding and unfolding rearview mirror of car based on single chip microcomputer |
| CN203739761U (en) * | 2013-12-25 | 2014-07-30 | 长安大学 | Anti-collision bus rearview mirror |
| CN105769120A (en) * | 2016-01-27 | 2016-07-20 | 深圳地平线机器人科技有限公司 | Fatigue driving detection method and device |
| CN107031510A (en) * | 2016-12-29 | 2017-08-11 | 宁波吉利汽车研究开发有限公司 | A kind of outside rear-view mirror system for regulating angle |
| CN107564363A (en) * | 2017-09-05 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for driving model switching |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113276777A (en) * | 2021-06-21 | 2021-08-20 | 南京信息工程大学无锡研究院 | Control method, device, equipment and medium for exterior rearview mirror |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10021932B2 (en) | Helmet system and methods | |
| US8958599B1 (en) | Input method and system based on ambient glints | |
| US6927694B1 (en) | Algorithm for monitoring head/eye motion for driver alertness with one camera | |
| US20220301218A1 (en) | Head pose estimation from local eye region | |
| CN104570347B (en) | Head-mounted display device and imaging method thereof | |
| WO2020231401A1 (en) | A neural network for head pose and gaze estimation using photorealistic synthetic data | |
| DE102013206739A1 (en) | Method for determining whether an occupant of a vehicle notices relevant objects in the vicinity of the vehicle | |
| CN110826369A (en) | Driver attention detection method and system during driving | |
| CN108711407B (en) | Display effect adjusting method, adjusting device, display equipment and storage medium | |
| WO2022126419A1 (en) | Rear-view mirror control method and related device | |
| CN111062292A (en) | Fatigue driving detection device and method | |
| JP2018090170A (en) | Head-up display system | |
| CN114022565A (en) | Alignment method and alignment device for display equipment and vehicle-mounted display system | |
| JP2022502757A (en) | Driver attention state estimation | |
| CN102043942A (en) | Visual direction judging method, image processing method, image processing device and display device | |
| CN113978366A (en) | Intelligent electronic rearview mirror system based on human eye attention and implementation method | |
| CN113325586A (en) | Head-mounted device, display control method and display control device | |
| CN113376840A (en) | Image display position adjusting method and device and storage medium | |
| CN110654314A (en) | Deep learning-based automatic rearview mirror adjusting method and device | |
| US20230174074A1 (en) | In-cabin safety sensor installed in vehicle and method of providing service platform thereof | |
| Badgujar et al. | Driver gaze tracking and eyes off the road detection | |
| CN114022514A (en) | Real-time sight line inference method integrating head posture and eyeball tracking | |
| CN115649094B (en) | Intelligent control method for driving position, domain controller and related device | |
| KR20210148497A (en) | Camera Apparatus Installing at a Car for Detecting Drowsy Driving and Careless Driving and Method thereof | |
| FR3097515A1 (en) | System for adapting at least one human-machine interface of a vehicle according to a physical impairment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200107 |