TWI459333B - An Attractive Force Detection Device and Its Method for Interactive Voice - Google Patents

Description

Interactive voice questioning driving attention detecting device and method thereof

The invention relates to a detecting device and a method thereof, in particular to an interactive voice questioning driving attention detecting device and a method thereof.

Issues such as road safety for driving and driving have gradually gained attention in recent years. Traffic safety accidents caused by improper operation of driving often occur, mainly due to fatigue caused by lack of driving sleep, excessive driving time without proper rest, or drunk driving. The spirit is dissipated, the concentration is not concentrated, etc., and the mental state of driving is not good, resulting in a car accident. In order to solve such problems, various technical solutions have been proposed. For example, Chinese Patent No. 200910310326.3, "Driving Monitoring Device and Method" mainly detects the driver's eye area and the hand placed on the steering wheel through image capture, and determines whether the driving hand is placed in the correct area on the steering wheel and Whether the eyes are open or closed due to fatigue.

US Patent No. 8,045,766, "Device, program, and method for determining sleepiness" provides another solution, mainly to capture the facial image of the driving, calculate the face through a specific algorithm, and discover the mental state of driving. When it is not good, use the gas device and the seat belt vibration device to wake up the drive, even through the brake controller.

The above technical means for detecting road safety problems and detecting the driving situation can be reasonably operated and have certain effects. However, it is not possible to quickly and accurately detect the concentration and mental state of driving.

In view of this, the present invention provides an interactive voice questioning driving attention detecting device and a method thereof, and the device monitoring, driving answering, and device determining are main monitoring processes. The device will present a voice prompt. After the driver hears the voice prompt, he must make corresponding head movements, such as blinking, turning the eyes, etc., shaking his head and other head movements, or opening the mouth of the mouth. Under normal conditions, driving can of course make the correct action, thereby determining the mental state of the driving and the concentration of attention. Compared with the conventional techniques, the present invention provides an interactive voice questioning driving attention detecting device and a method thereof, which are characterized by simple operation, fast execution, and the like.

The device for driving attention detection based on the interactive voice questioning provided by the invention mainly comprises an image capturing unit, a voice questioning unit and a safety determining unit. The image capturing unit can obtain the driving image, and the voice questioning unit can periodically or randomly issue a voice prompt, and the safety determining unit can detect the change of the driving image to determine whether the voice questioning instruction is met, and if the driving does not make a corresponding In the correct action of the voice prompt, the sound generating unit can selectively send a warning message to wake up the driving.

The invention also provides an interactive voice questioning method for driving attention detection, firstly, a voice questioning instruction is provided, then a driving image is obtained, and a change of the image is detected to determine whether the voice questioning instruction is met, and if the driving image is If the change does not meet the requirements of the voice questioning command, a warning message is sent to wake up the driver.

The object, technical contents and features of the present invention are described below in conjunction with the drawings.

Please refer to FIG. 1 for a schematic diagram of the device architecture of the present invention. The driving attention detecting device for interactive voice questioning according to the present invention mainly includes an image capturing unit 10, a processing unit 20, a sound generating unit 50, a communication unit 60, and a warning unit 70. The image capturing unit 10 is connected to the processing unit 20 to obtain a head image of the driving. The processing unit 20 includes at least a voice questioning unit 40 and a security determining unit 30. The voice questioning unit 40 can present a voice questioning command, and the security determining unit 40 performs arithmetic processing on the head image to determine the driving head, the face, and even the The image of the eye changes to detect the movement of the head, face and eyes of the driver.

The voice questioning command issued by the voice questioning unit 40 may be a voice prompt that can be heard by the driver, and the sound is generated by the sound generating unit 50. There are many changes to the voice prompts, such as: first look at the left and then right command, first look at the next command, first look at the next command, circle command, or blink command. After driving to hear the voice question command provided by the voice questioning unit 40, or the voice prompt, the corresponding action must be made, such as blinking a specific number of times, looking at the left and right eyes, or according to a voice question command, the entire head is turned to the left. Or move to the right, nod your head, smile, open your mouth, and so on. The above voice prompts are subject to various changes, and the above are merely examples and are not intended to limit the scope of the invention. Then, the security judging unit 30 will detect continuous image changes of driving and determine whether the requirements of the voice questioning instruction are met. If the image change of the driving does not meet the requirements of the voice questioning command, a warning message is sent, for example, the sound is generated by the sound generating unit 50, the blinking light is emitted through the warning unit 70 such as the LED light, or the communication unit can be selectively used. 60 warning messages are transmitted back to the traffic control center to remind the driver of the state of attention. This design is a very effective driving state return mechanism for the mass transit industry to ensure the safety of passengers and cargo.

Regarding the driving attention detecting device for interactive voice questioning provided by the present invention, please refer to FIG. 4, FIG. 6 and FIG. 7 to explain the actual use situation. The device body 100 of the present invention can be selectively placed in front of the driver's seat, preferably above the instrument panel, as shown in FIG. The device body 100 is internally equipped with the aforementioned processing unit 20 and other electronic components required for operation. The camera 101 can capture images of driving, and the sound generating unit 102 is configured to issue a voice questioning command and a voice prompt. After the driver hears the voice prompt from the sound generating unit 102, the corresponding action should be made. For example, the voice prompt is: "Please look at the left and then look right", then as shown in Fig. 6 and Fig. 7, the driving should be Look to the left first, then look to the right. When the driver makes the correct action, it means that the driver is in a state of waking, and the concentration has a certain concentration. On the other hand, if the driver does not make the correct action, a warning message is issued, such as a warning sound by the sound generating unit 102 to wake up the driving.

The method for detecting the attention of the interactive voice questioning of the present invention will be described in detail with reference to FIG. 2, FIG. 3A, and FIG. 3B. First, the device issues a voice question command (S101), and the voice question command can send a voice prompt through the sound generating unit. The voice prompt has multiple possibilities, such as first reading the left and then right reading, first looking at the next command, and then looking at the first. Look at commands, loop commands, and more. Then, a head image of the driving is obtained (S102). The image processing is performed on the head image to generate an eye search area (S103), and an eye image of the driving is obtained (S104). Referring to FIG. 5 and step S104, after acquiring the head image 200 for driving, the image digit processing is performed within the range of the head image 200, and an eye search area 201 is defined, and the eye search area is defined. An eye image 202 is found within 201. In addition, the foregoing steps S102 to S104 are optional steps, and the related art can directly obtain the eye image without first obtaining the head image and then analyzing and obtaining the eye image.

After the step S104, as shown in FIG. 3A, the change of the eye image is detected, the eye feature is obtained (S105), and the change of the eye image is determined whether the voice request command is met (S106), if the driver has Make the correct action corresponding to the voice question command, such as the voice question command and the voice prompt to inform the driver to make: first left and right, and the driver also makes the action of looking at the left and then right eye, then you can end the investigation. The process of measuring judgment. On the other hand, if the driver does not make a correct action based on the voice question command, the device will issue a warning message (S107) to wake up the driver.

In addition to detecting the rotation of the driving eye, it is also possible to detect the movement of the head of the driving to determine. Referring to FIG. 2 and FIG. 3B, after step S102, step S201 may be selectively performed to perform image digital processing on the head image (S201), and the image digital processing at this time may further enhance the image, such as Enhance the contrast value, brightness and other values of the image to help find the edges of the features in the image. Then, detecting the change of the head image, obtaining the head feature (S202), and detecting whether the voice questioning instruction is met (S203), as in the foregoing method flow, the driving is made according to the content of the voice questioning instruction and the voice prompt. The correct action, then the process of detecting and judging ends. Otherwise, a warning message (S204) is issued to wake up the driving.

While the present invention has been described in its preferred embodiments, the present invention is not intended to limit the scope of the present invention, and the invention may be modified and modified without departing from the spirit and scope of the invention. The scope of protection is subject to the definition of the scope of the patent application attached.

10. . . Image capture unit

20. . . Processing unit

30. . . Safety judgment unit

40. . . Voice questioning unit

50. . . Sound generating unit

60. . . Communication unit

70. . . Warning unit

100. . . Device body

101. . . camera

102. . . Sound generating unit

200. . . Head image

201. . . Eye search area

202. . . Eye image

S101. . . Issue a voice question command

S102. . . Get the head image of driving

S103. . . Perform image digital processing on the head image to generate an eye search area

S104. . . Get the eye image of driving

S105. . . Detect changes in eye images

S106. . . Whether it meets the requirements of the voice questioning instruction

S107. . . Send a warning message

S201. . . Image digital processing of the head image

S202. . . Detect changes in head image

S203. . . Whether it meets the requirements of the voice questioning instruction

S204. . . Send a warning message

1 is a schematic diagram of the device architecture of the present invention.

2 is a schematic flow chart of the method of the present invention.

3A is a schematic flow chart of a splicing method of the present invention.

3B is a schematic flow chart of another continuation method of the present invention.

Figure 4 is a schematic view of the use of the present invention.

Figure 5 is a schematic diagram of the image taking operation of the present invention.

Figure 6 is a schematic view of the driving use of the present invention.

Figure 7 is a schematic view of another driving use of the present invention.

10. . . Image capture unit

20. . . Processing unit

30. . . Safety judgment unit

40. . . Voice questioning unit

50. . . Sound generating unit

60. . . Communication unit

70. . . Warning unit

Claims (8)

An interactive voice questioning driving attention detecting device includes: an image capturing unit for obtaining an image of driving; and a processing unit connected to the image capturing unit, comprising: a voice questioning unit For presenting a voice questioning command, the voice questioning command is to send a voice prompt through a sound generating unit; and a security determining unit is connected to the image capturing unit and the voice questioning unit to detect the image. Change to determine whether it meets the requirements of the voice questioning instruction. The driving attention detecting device of the interactive voice questioning method of claim 1, further comprising a sound generating unit that issues a warning message if the change of the image does not meet the requirement of the voice questioning instruction. For example, the interactive voice questioning driving attention detecting device described in claim 2, wherein detecting the change of the image and determining whether the voice questioning instruction is met is determined whether the driving is based on the voice prompt. The corresponding action. The driving attention detecting device of the interactive voice questioning method described in claim 2, wherein the voice prompt is selected from the group consisting of first looking at the left and then looking at the right command, first reading the command and then reading the command. Next, look at one of the combination of command, a circle command, a blink command, a shake command, a one-point command, a smile command, and a shut-up command. An interactive voice questioning method for driving attention detection includes the following steps: proposing a voice questioning instruction, the voice questioning instruction is sent by a voice questioning unit, and the voice questioning unit is located in a processing unit, and the The voice questioning command can send a voice prompt through a sound generating unit; obtain an image of driving; detect the change of the image, and determine whether the voice questioning instruction is met. Requesting; and if the change in the image does not meet the requirements of the voice questioning instruction, a warning message is issued. The method for driving attention detection according to the interactive voice question described in claim 5, wherein the time of the voice questioning instruction is issued periodically or randomly. The method for driving attention detection according to the interactive voice question described in claim 5, wherein the detecting the change of the image to determine whether the requirement of the voice questioning instruction is met, whether the driving is based on the voice prompt Make the appropriate action. The method for driving attention detection according to the interactive voice question described in claim 5, wherein the voice prompt is selected from the group consisting of a first look at the left and a right command, a first look at the command, and a first command. Look at the command, a circle command, a blink command, a shake command, a nod command, a smile command, and a shut-up command.