CN209879530U - Depth vision vehicle-mounted monitoring device - Google Patents
Depth vision vehicle-mounted monitoring device Download PDFInfo
- Publication number
- CN209879530U CN209879530U CN201921176334.9U CN201921176334U CN209879530U CN 209879530 U CN209879530 U CN 209879530U CN 201921176334 U CN201921176334 U CN 201921176334U CN 209879530 U CN209879530 U CN 209879530U
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- depth
- image
- monitoring device
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model relates to an on-vehicle monitoring devices of degree of depth vision, a serial communication port, include: the device comprises a 3D image acquisition assembly, an image processing module, a positioning module, an audio module, a communication module, a power supply module and an outer cover shell; the 3D image acquisition assembly is used for acquiring a three-dimensional measurement image and depth information of a shot object; the image processing module is used for processing the image and depth information of the measured object acquired by the 3D image acquisition assembly; the audio module is used for inputting and outputting voice; the positioning module is used for acquiring the geographical position information of the vehicle; the communication module is used for receiving and sending data; the power supply module is used for supplying power to other modules in the device; the 3D image acquisition assembly, the image processing module, the audio module, the positioning module, the communication module and the power supply module are installed in the outer cover shell. The utility model discloses a 3D structured light gets strong and makes up for the weak point with the TOF technique, has accurate discernment, real-time identification, stabilizes the efficient advantage.
Description
Technical Field
The invention relates to the technical field of automobile control, in particular to a depth vision vehicle-mounted monitoring device.
Background
With the technical development of intelligent driving of automobiles, computer machine vision technology, image processing technology and the like are applied in the field of automobile control, and are particularly applied more in the field of safe driving of automobiles. In recent years, with the rapid increase of automobile reserves in China, traffic accidents are in a rapid growth trend, main factors causing the traffic accidents include fatigue driving, drunk driving, drug driving, physical and emotional factors of drivers, and meanwhile, death events caused by the fact that people or infants in a vehicle are locked in the vehicle occur frequently, so that serious damage is brought to the life and property safety of people.
By utilizing a machine vision technology, particularly a 3D vision technology, through three-dimensional measurement shooting with proper precision, more correct object segmentation, three-dimensional data model reconstruction and intelligent vision recognition and analysis are realized. However, the existing machine vision technology mainly includes a monocular vision technology, a binocular vision technology and a TOF (time of flight) technology, and the single technical scheme has defects in use scenes and functions. Therefore, aiming at the interior of the vehicle based on the machine vision technology, the device capable of realizing the visual intelligent control on the environment inside the driver and the passenger of the vehicle and the interior of the vehicle is very necessary, and the monitoring on the aspects of the vehicle control safety and the environment is favorably realized.
Disclosure of Invention
In view of this, the invention aims to provide a depth vision vehicle-mounted monitoring device, which integrates 3D structured light and TOF technologies to make up for deficiencies, so as to realize intelligent identification of biological information, physical conditions, emotional conditions and driving environments of drivers and passengers in a vehicle and acquisition of corresponding three-dimensional information, and has the advantages of accurate identification, real-time identification, stability and high efficiency.
In order to achieve the purpose, the invention provides the following technical scheme: a depth vision in-vehicle monitoring device, comprising: the device comprises a 3D image acquisition assembly, an image processing module, a positioning module, an audio module, a communication module, a power supply module and an outer cover shell; the 3D image acquisition assembly is used for acquiring a three-dimensional measurement image and depth information of a shot object; the image processing module is used for processing the image and depth information of the measured object acquired by the 3D image acquisition assembly; the audio module is used for inputting and outputting voice; the positioning module is used for acquiring the geographical position information of the vehicle; the communication module is used for receiving and sending data; the power supply module is used for supplying power to other modules in the device; the 3D image acquisition assembly, the image processing module, the audio module, the positioning module, the communication module and the power supply module are installed in the outer cover shell.
Further, the 3D image acquisition assembly comprises a 3D structured optical camera and a TOF depth sensing camera, and the working distance of the 3D image acquisition assembly is within a range of + y to + x to-y =2500 mm and + z to + x to-z =2500 mm based on the three-dimensional coordinates of the interior space of the vehicle.
Further, the 3D structure light camera comprises an infrared lens, a floodlight induction element and a dot matrix projector and is used for acquiring information such as human face three-dimensional images, human body temperature and action expressions.
Furthermore, the TOF deep sensing camera comprises a distance sensor, an infrared lens, a floodlight sensing element, a dot matrix projector and a flash memory, and is used for acquiring accurate contour and depth information of the human face and three-dimensional image information of the environment in the vehicle.
Further, the CPU of the image processing module adopts one of the high-pass cellon processors 600 to 800 series.
Furthermore, the positioning module adopts one of a Beidou satellite or a GPS positioning module.
Further, the audio module includes a speaker for outputting voice and a microphone for inputting audio.
Further, the communication module comprises one or more of GSM, wifi/Bluetooth, Zigbee, NB-IoT, 2G, 3G, 4G and 5G networks.
Furthermore, the power supply voltage of the power supply module is 5V-12V.
The invention has the beneficial effects that: compared with the prior art, the technical scheme of the invention integrates and applies the 3D vision technology of 3D structured light and TOF (time of flight technology), the 3D image acquisition assembly comprises a 3D structured light camera and a TOF (time of flight) deep sensing camera, and the 3D structured light technology has good balance performance in face recognition, biological information, recognition precision, resolution and low light expression and is used for acquiring the face recognition and biological information recognition of a driver, including information such as human body temperature and action expression; the advantages of long TOF working distance, low light expression, real-time and rapid environment depth calculation and 3D modeling are utilized to obtain accurate face contour of a driver and three-dimensional image information of an environment in a vehicle. The purpose of monitoring the driving activities in the vehicle can be realized by means of continuous data acquisition of the camera and algorithm processing, for example, whether the driver is drowsy or not and the pupil expansion degree of the driver can be detected by tracking the staring direction, the eye opening degree and the head position of the driver, and whether the driver drinks or uses medicines or not can be judged. Meanwhile, through scanning the interior of the whole vehicle, including the passengers in the back row, the biological information of the passengers in the back row can be acquired, and if the facial expressions of the passengers are painful or uncomfortable, the situations such as infants left intentionally and separately occur, and an alarm is triggered so as to be processed in time.
According to the technical scheme, the positioning module, such as a Beidou satellite or GPS positioning module, is applied, a series of driving behavior data of a driver, such as acceleration, deceleration, parking, turning and the like, can be collected, and other data, such as driving habits, a time schedule, emotion of the driver, comfort of the environment in the vehicle and the like, of the driver can be known through algorithm processing.
The technical scheme of the invention integrates 3D structured light and TOF technology, makes up for deficiencies to realize intelligent identification of biological information, physical conditions, emotional conditions and driving environment of drivers and passengers in the vehicle and acquisition of corresponding three-dimensional information, and has the advantages of accurate identification, real-time identification, stability and high efficiency.
Drawings
FIG. 1 is a schematic diagram of the structural principle of the present invention;
FIG. 2 is a schematic diagram of the 3D image capture assembly of the present invention;
FIG. 3 is a schematic three-dimensional coordinate diagram of the in-vehicle monitoring range of the present invention;
FIG. 4 is a schematic view of the installation position of the depth vision vehicle-mounted monitoring device in the vehicle;
in the figure: 1. depth vision vehicle-mounted monitoring device, 2, the reflector, 3, front windshield, 11, 3D image acquisition subassembly, 12, image processing module, 13, orientation module, 14, audio frequency module, 15, communication module, 16, power module, 17, dustcoat casing, 111, 3D structure light camera, 112, TOF deep sensation camera, f1, infrared lens, f2, floodlight inductive element, f3, dot matrix projector, f4, distance sensor, f5, flash memory.
Detailed Description
The invention is further described with reference to the following figures and examples.
The embodiment of the invention is as follows: a depth vision in-vehicle monitoring device 1, comprising: the system comprises a 3D image acquisition assembly 11, an image processing module 12, a positioning module 13, an audio module 14, a communication module 15, a power supply module 16 and an outer cover shell 17; the 3D image acquisition assembly 11 is used for acquiring a three-dimensional measurement image and depth information of a shot object; the image processing module 12 is configured to process the image and depth information of the measured object acquired by the 3D image acquisition component 11; the audio module 14 is used for inputting and outputting voice; the positioning module 13 is used for acquiring the geographical position information of the vehicle; the communication module 15 is used for receiving and transmitting data; the power supply module 16 is used for supplying power to other modules in the device; the 3D image acquisition assembly 11, the image processing module 12, the audio module 14, the positioning module 13, the communication module 15 and the power supply module 16 are installed in the housing shell 17.
To be further described, the 3D image capturing assembly 11 includes a 3D structured light camera 111 and a TOF depth sensing camera 112, and the working distance thereof is within a range of + y to + x to-y =2500 mm and + z to + x to-z =2500 mm based on the three-dimensional coordinates of the vehicle interior space, that is: the working distance in the direction of the vehicle height + y to + x to-y is 2500 mm, and the working distance in the direction of the vehicle width + z to + x to-z is 2500 mm.
The 3D structured light camera 111 includes an infrared lens f1, a floodlight sensing element f2, and a dot matrix projector f3, and is configured to obtain a three-dimensional image of a human face, a human body temperature, an action expression, and other information.
The TOF deep sensing camera 112 comprises a distance sensor f4, an infrared lens f1, a floodlight sensing element f2, a dot matrix projector f3 and a flash memory f5 and is used for acquiring accurate contour and depth information of a human face and three-dimensional image information of an environment in a vehicle.
The CPU of the image processing module 12 employs one of the high pass cellon processors 600 to 800 series.
The positioning module 13 adopts one of a Beidou satellite or a GPS positioning module.
The audio module 14 includes a speaker for outputting voice and a microphone for inputting audio.
The communication module 15 includes one or more of GSM, wifi/bluetooth, Zigbee, NB-IoT, 2G, 3G, 4G, and 5G networks.
The power supply voltage of the power supply module 16 is 5V-12V.
Further, the invention integrates 3D structured light and TOF technology to make up for deficiencies, so as to realize intelligent identification of biological information, physical conditions, emotional conditions and driving environment of drivers and passengers in the vehicle and acquisition of corresponding three-dimensional information, and has the advantages of accurate identification, real-time identification, stability and high efficiency.
The 3D structured light adopts invisible infrared laser with a specific wavelength as a light source, the emitted light is projected on an object through a certain code, the distortion of a returned code pattern is obtained through an algorithm to obtain the position and depth information of the object, the three-dimensional structure of the shot object is obtained through an optical means, and the information is used more deeply, so that the three-dimensional. However, the detection effective distance of the 3D structured light technology is short, the technology is easily interfered by external environment light, and the accuracy of face recognition is reduced rapidly along with the increase of the distance.
The TOF technology is characterized in that light pulses are continuously transmitted to an observed object, then the sensor is used for receiving light returned from the object, the distance of a target object is obtained by detecting the flight time of the light pulses, the TOF working distance is long, the light performance is low, the environment depth calculation is real-time and rapid, and the 3D modeling has the advantages. The effective distance of TOF detection is longer, the depth calculation accuracy is not reduced along with the increase of the distance, but the resolution ratio is poorer, and the edge accuracy is low.
Referring to fig. 3 and 4, the depth vision vehicle-mounted monitoring device 1 is marked according to three-dimensional coordinates by combining the size of the general internal space of the existing vehicle, is arranged on the upper part of a reflector 2 of a front windshield 3 of the vehicle, and collects image information to the interior of the vehicle. The 3D structured light camera 111 uses invisible infrared laser with a specific wavelength as a light source, and uses the speckle structured light emitted from the dot-matrix projector f3 to project the speckle structured light on the face of a driver or a front passenger through a certain code, and obtains the position and depth information of the face by the image processing module 12 calculating the distortion of the returned code pattern through an algorithm. The TOF depth-sensing camera 112 continuously transmits light pulses, then receives light returning from the face of a person by using a distance sensor f4, and finally obtains the distance of a target object by detecting the flight (round trip) time of the light pulses, so that the accurate contour of the face of the person and a three-dimensional image in a vehicle can be accurately obtained.
Compared with the prior art, the technical scheme of the invention integrates and applies the 3D vision technology of 3D structured light and TOF (time of flight of light), has good balance performance in face recognition, biological information, recognition precision, resolution and low light expression by utilizing the 3D structured light technology, and is used for acquiring the face recognition and biological information recognition of a driver, including information such as human body temperature, action expression and the like; the advantages of long TOF working distance, low light expression, real-time and rapid environment depth calculation and 3D modeling are utilized to obtain accurate face contour of a driver and three-dimensional image information of an environment in a vehicle. The purpose of monitoring the driving activities in the vehicle can be realized by means of continuous data acquisition of the camera and algorithm processing, for example, whether the driver is drowsy or not and the pupil expansion degree of the driver can be detected by tracking the staring direction, the eye opening degree and the head position of the driver, and whether the driver drinks or uses medicines or not can be judged. Meanwhile, through scanning the interior of the whole vehicle, including the passengers in the back row, the biological information of the passengers in the back row can be acquired, and if the facial expressions of the passengers are painful or uncomfortable, the situations such as infants left intentionally and separately occur, and an alarm is triggered so as to be processed in time.
According to the technical scheme, the positioning module 13 such as a Beidou satellite or GPS positioning module is used for collecting a series of driving behavior data of a driver such as acceleration, deceleration, parking and turning, and other data such as driving habits, a time schedule, driver emotion and in-vehicle environment comfort level are known through algorithm processing, so that the driving comfort experience is improved.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express the specific embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (9)
1. A depth vision vehicle-mounted monitoring device, comprising: the device comprises a 3D image acquisition assembly, an image processing module, a positioning module, an audio module, a communication module, a power supply module and an outer cover shell; the 3D image acquisition assembly is used for acquiring a three-dimensional measurement image and depth information of a shot object; the image processing module is used for processing the image and depth information of the measured object acquired by the 3D image acquisition assembly; the audio module is used for inputting and outputting voice; the positioning module is used for acquiring the geographical position information of the vehicle; the communication module is used for receiving and sending data; the power supply module is used for supplying power to other modules in the device; the 3D image acquisition assembly, the image processing module, the audio module, the positioning module, the communication module and the power supply module are installed in the outer cover shell.
2. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the 3D image acquisition assembly comprises a 3D structure optical camera and a TOF depth sensing camera, and the working distance of the 3D image acquisition assembly is in the range of + y to + x to-y =2500 mm and + z to + x to-z =2500 mm by taking the three-dimensional coordinates of the internal space of the vehicle as a reference.
3. The depth vision vehicle-mounted monitoring device of claim 2, wherein: the 3D structure light camera comprises an infrared lens, a floodlight induction element and a dot matrix projector and is used for acquiring information such as human face three-dimensional images, human body temperature and action expressions.
4. The depth vision vehicle-mounted monitoring device of claim 2, wherein: the TOF deep sensing camera comprises a distance sensor, an infrared lens, a floodlight sensing element, a dot matrix projector and a flash memory and is used for acquiring accurate contour and depth information of a human face and three-dimensional image information of an environment in a vehicle.
5. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the CPU of the image processing module adopts one of the high-pass CellON processors 600 to 800 series.
6. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the positioning module adopts one of a Beidou satellite or a GPS positioning module.
7. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the audio module includes a speaker for outputting voice and a microphone for inputting audio.
8. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the communication module comprises one or more of GSM, wifi/Bluetooth, Zigbee, NB-IoT, 2G, 3G, 4G and 5G networks.
9. The depth vision vehicle-mounted monitoring device of claim 1, wherein: the power supply voltage of the power supply module is 5V-12V.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921176334.9U CN209879530U (en) | 2019-07-25 | 2019-07-25 | Depth vision vehicle-mounted monitoring device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201921176334.9U CN209879530U (en) | 2019-07-25 | 2019-07-25 | Depth vision vehicle-mounted monitoring device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN209879530U true CN209879530U (en) | 2019-12-31 |
Family
ID=68949379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201921176334.9U Expired - Fee Related CN209879530U (en) | 2019-07-25 | 2019-07-25 | Depth vision vehicle-mounted monitoring device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN209879530U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538970A (en) * | 2020-07-08 | 2020-08-14 | 德能森智能科技（成都）有限公司 | Cloud platform system based on intelligent Internet of things |
-
2019
- 2019-07-25 CN CN201921176334.9U patent/CN209879530U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111538970A (en) * | 2020-07-08 | 2020-08-14 | 德能森智能科技（成都）有限公司 | Cloud platform system based on intelligent Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9180887B2 (en) | Driver identification based on face data | |
| CN106585629B (en) | A kind of control method for vehicle and device | |
| US10078966B2 (en) | Warning method outside vehicle, driver assistance apparatus for executing method thereof and vehicle having the same | |
| CN110651313A (en) | Control device and control method | |
| CN101242523B (en) | Field watch apparatus | |
| EP2596746B1 (en) | Pupil detection device and pupil detection method | |
| US10349032B2 (en) | Vehicle occupant head positioning system | |
| WO2020029444A1 (en) | Method and system for detecting attention of driver while driving | |
| CN104786933A (en) | Panoramic image driving auxiliary device and panoramic image driving auxiliary method | |
| US9892329B2 (en) | Animal type determination device | |
| CN115768671A (en) | Motion sickness detection system for autonomous vehicles | |
| JP6693489B2 (en) | Information processing device, driver monitoring system, information processing method, and information processing program | |
| WO2020145093A1 (en) | Display controller, display device, display system, mobile object, image generation method, and carrier means | |
| CN209879530U (en) | Depth vision vehicle-mounted monitoring device | |
| JP2019088522A (en) | Information processing apparatus, driver monitoring system, information processing method, and information processing program | |
| CN112307802A (en) | Depth vision vehicle-mounted monitoring device | |
| US11903647B2 (en) | Gaze detector, method for controlling gaze detector, method for detecting corneal reflection image position, and storage medium | |
| CN113276821B (en) | Driver state estimating device | |
| CN113276822B (en) | Driver state estimating device | |
| WO2014162654A1 (en) | Monitoring system | |
| WO2018170538A1 (en) | System and method of capturing true gaze position data | |
| JP2021077134A (en) | Vehicle control device and driver state determination method | |
| JP2021077135A (en) | Vehicle control device and driver state determination method | |
| CN112565724B (en) | Image projection method and system | |
| US20220381913A1 (en) | Distance measurement sensor, signal processing method, and distance measurement module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191231 Termination date: 20200725 |