CN111976593A - Voice prompt method, device, equipment and storage medium for vehicle external object - Google Patents
Voice prompt method, device, equipment and storage medium for vehicle external object Download PDFInfo
- Publication number
- CN111976593A CN111976593A CN202010849882.4A CN202010849882A CN111976593A CN 111976593 A CN111976593 A CN 111976593A CN 202010849882 A CN202010849882 A CN 202010849882A CN 111976593 A CN111976593 A CN 111976593A
- Authority
- CN
- China
- Prior art keywords
- prompt
- vehicle
- image
- candidate
- voice
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000007613 environmental effect Effects 0.000 claims description 18
- 238000013145 classification model Methods 0.000 claims description 16
- 238000002372 labelling Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 abstract description 8
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000009413 insulation Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 235000000391 Lepidium draba Nutrition 0.000 description 1
- 241000949477 Toona ciliata Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q5/00—Arrangement or adaptation of acoustic signal devices
- B60Q5/005—Arrangement or adaptation of acoustic signal devices automatically actuated
- B60Q5/006—Arrangement or adaptation of acoustic signal devices automatically actuated indicating risk of collision between vehicles or with pedestrians
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a voice prompt method, a voice prompt device, voice prompt equipment and a storage medium for an object outside a vehicle. The method comprises the following steps: identifying at least one alternative prompt object in real time in front of the vehicle, and acquiring object attribute information of each alternative prompt object; determining the distance between each candidate prompt object and the vehicle; if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object; and carrying out voice broadcast on the customized prompt words in the environment outside the vehicle. The method can carry out targeted voice prompt on the target candidate prompt object outside the vehicle, is easy to be perceived by the target candidate prompt object, is not easy to be shielded by a noise reduction algorithm of the noise reduction earphone, cannot become artificial noise, and can ensure the safety of other road users.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent automobiles, in particular to a method, a device, equipment and a storage medium for prompting an object outside a vehicle by voice.
Background
When the vehicle is running, the vehicle may not be easily perceived by other road users due to the low noise, and thus a traffic accident may occur. For example, when the electric vehicle is running at a low speed, other road users may not be able to detect the approach of the vehicle in time through sound, and there is a traffic safety problem.
In the prior art, buzzers are generally adopted to prompt other road users so as to reduce traffic accidents. However, when the sound outside the vehicle is mixed, the sound of the buzzer is not easy to be detected in time; moreover, for a road user wearing the noise reduction earphone, the sound of the buzzer is easily shielded by the noise reduction algorithm of the noise reduction earphone, so that the problem of traffic safety exists. If the aim of prompting is achieved by simply controlling the volume of the buzzer, the sound of the buzzer is easy to become artificial noise, and the overall negative effect on the road noise is caused.
Disclosure of Invention
The embodiment of the invention provides a voice prompt method, a voice prompt device, voice prompt equipment and a storage medium for an object outside a vehicle, which can be used for carrying out voice prompt on the object outside the vehicle in a targeted manner and ensuring the driving safety of the object outside the vehicle.
In a first aspect, an embodiment of the present invention provides a method for voice prompting an object outside a vehicle, where the method includes:
identifying at least one alternative prompt object in front of the vehicle in real time, and acquiring object attribute information of each alternative prompt object;
determining the distance between each alternative prompt object and the vehicle;
if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object;
and carrying out voice broadcast on the customized prompt words in the environment outside the vehicle.
In a second aspect, an embodiment of the present invention further provides a device for prompting an object outside a vehicle by voice, where the device includes:
the system comprises an alternative prompt object identification module/object attribute information acquisition module, a prompt object recognition module and a prompt object attribute information acquisition module, wherein the alternative prompt object identification module/object attribute information acquisition module is used for identifying at least one alternative prompt object in front of a vehicle in real time and acquiring object attribute information of each alternative prompt object;
the distance determining module is used for determining the distance between each candidate prompting object and the vehicle;
the customized prompt language generating module is used for generating a customized prompt language corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance;
and the voice broadcasting module is used for carrying out voice broadcasting on the customized prompt words in the environment outside the vehicle.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method for voice prompting an off-board object, as described in any embodiment of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for voice prompting an object outside a vehicle according to any embodiment of the present invention.
According to the technical scheme of the embodiment of the invention, at least one alternative prompt object is identified in real time in front of the vehicle, and object attribute information of each alternative prompt object is obtained; determining the distance between each candidate prompt object and the vehicle; if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object; carry out voice broadcast to the customization suggestion in the car external environment, difficult quilt is perceived when having solved among the prior art and adopting bee calling organ to indicate, is easily fallen the algorithm of making an uproar and shields, can't ensure other road user driving safety's problem, realized can pertinence carry out voice prompt to different target alternative suggestion objects, and be difficult for being fallen the earphone and shield of making an uproar to ensure other road user driving safety's effect.
Drawings
FIG. 1 is a flow chart of a method for voice prompting an object outside a vehicle according to an embodiment of the present invention;
FIG. 2 is a flowchart of a voice prompt method for an object outside a vehicle according to a second embodiment of the present invention;
FIG. 3 is a flowchart of a method for voice prompting an object outside a vehicle according to a third embodiment of the present invention;
FIG. 4 is a flowchart of a method for voice prompting an object outside a vehicle according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a voice prompt device for an object outside a vehicle according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for prompting a vehicle-external object with voice according to an embodiment of the present invention, where this embodiment is applicable to a situation where a vehicle performs voice prompt on other road users during road driving, and the method may be implemented by a device for prompting a vehicle-external object with voice, where the device may be implemented by software and/or hardware, and the device may be integrated in a processor or a controller of the vehicle, as shown in fig. 1, where the method specifically includes:
and 110, identifying at least one candidate prompt object in front of the vehicle in real time, and acquiring object attribute information of each candidate prompt object.
The front of the vehicle can be provided with a camera device to collect the video stream of the road in front of the vehicle in real time. For example, a camera is installed in front of the interior of the vehicle, and an image in front of the vehicle can be acquired at a rate of 30 frames per second. Each frame of image in the video stream may be taken as an image in front of the vehicle, and the alternative prompt object included in the image in front of the vehicle may be identified. The alternative prompting object can be other road users besides the vehicle. For example, the candidate cueing object may be a pedestrian, an automobile, a non-automobile vehicle, a pet, or the like outside the vehicle. Herein, the non-automotive vehicle means a tool for carrying a person or cargo, but does not include an automobile. For example, the non-automotive vehicle may be a bicycle, a motorcycle, an electric vehicle, or a scooter, among others. The method for identifying the alternative prompt object can be an image recognition algorithm, a deep learning recognition algorithm or a machine learning recognition algorithm.
The object attribute information of the candidate presentation object may be attribute information included in the candidate presentation object. The object attribute information may be obtained by identifying and acquiring the candidate prompt object. The identification method can be an image identification algorithm, a deep learning identification algorithm or a machine learning identification algorithm and the like. Different alternate prompt objects may have the same or different object attribute information. The object property information may include one or more items of information.
For example, the object attribute information of the pedestrian may include age information, height information, gender information, clothes color information, hair style information, quantity information, and the like. As another example, the object attribute information of the automobile may include vehicle type information, body color information, license plate number information, and the like. For another example, the object attribute information of the non-automobile vehicle may include the type information of the non-automobile vehicle and the object attribute information of the vehicle member. The attribute information of the vehicle member may be the same as or similar to the object attribute information of the pedestrian. Also for example, the object attribute information of the pet may include category information of the pet, color information of the pet, object attribute information of pedestrians near the pet, and the like.
And step 120, determining the distance between each candidate prompt object and the vehicle.
The distance between the candidate prompt object and the vehicle can be determined in various ways. For example, for a vehicle mounted with the distance detection device, the distance between the candidate presentation object and the vehicle may be detected by the distance detection device. The distance detection device may be a millimeter wave, a laser radar, a vision sensor, or the like. Alternatively, the distance between the candidate presentation object and the vehicle may be determined by specifying the position information of the candidate presentation object in the image in front of the vehicle and converting the coordinates of the position in the image and the actual position. Alternatively, the distance between the candidate prompt object and the vehicle may be determined by information fusion through the distance information acquired by the distance detection device and the position of the candidate prompt object in the image in front of the vehicle, so that the determination of the position and the distance of the candidate prompt object can be more accurate.
In order to accurately determine the distance between the candidate prompting object and the vehicle even for a vehicle without a distance detection device, in an embodiment of the present invention, optionally, determining the distance between each candidate prompting object and the vehicle includes: acquiring an image in front of the vehicle in real time, carrying out image recognition on the image in front of the vehicle, and determining the position information of each candidate prompt object in the image in front of the vehicle; and determining the distance between each candidate prompting object and the vehicle according to the conversion relation between the preset image depth of field and the actual distance and the position information.
The position of the candidate prompting object in the image in front of the vehicle can be determined through image recognition, for example, the minimum unit occupied by the candidate prompting object in the image in front of the vehicle can be determined first. The minimum unit may be determined in the following manner: and covering the alternative prompt object through the rectangle, and determining the rectangle as the minimum unit of the alternative prompt object when the alternative prompt object just can be covered by the rectangle.
For example, a coordinate system with a horizontal axis and a vertical axis may be established with the bottom center of the vehicle front image as the origin. The coordinates of the four vertices of the minimum unit of the candidate prompt object can be determined under this coordinate system. If the candidate prompt object is on the left part of the origin, the lower right corner of the minimum unit of the candidate prompt object can be determined as the point closest to the vehicle; if the candidate prompt object is on the right side of the origin, the lower left corner of the minimum unit of the candidate prompt object can be determined to be the point closest to the vehicle. In this coordinate system, the abscissa (x, y) of the closest point of the candidate guidance object to the vehicle may be determined as the position information of the candidate guidance object in the image in front of the vehicle.
The conversion relation between the preset image depth of field and the actual distance can be determined according to the position of a camera installed on the vehicle and the model of the camera. The conversion relationship between the depth of field of the image and the actual distance may be a linear relationship, and the specific conversion relationship may be obtained in advance through an experiment. For example, a conversion relationship D between an abscissa x of the candidate presentation object in a vehicle front image acquired by a camera mounted in the vehicle and a horizontal axis distance D of the candidate presentation object from the vehicle in practice, where F represents a functional relationship, may be determined experimentally as F (x). Through an experimental mode, a conversion relation L between a vertical coordinate y of the candidate prompting object in a vehicle front image acquired by a camera installed in the vehicle and a vertical axis distance L of the candidate prompting object from the vehicle in practice is determined to be f (y), wherein f represents a functional relation. The distance in the lateral direction between the candidate presentation object and the vehicle can be determined from the position information (x, y) of the candidate presentation object and the conversion relationships D (f), (x) and L (f), (y).
It should be noted that the vertical axis distance L may refer to a distance from the candidate cue object to the vehicle head. The horizontal axis distance D may be a vertical distance from the candidate cueing object to the central axis of the vehicle.
When the candidate presentation object is a pet, the person near the pet may be further specified, and the object attribute information of the person near the pet may be used as one item of object attribute information of the pet. For example, the person near the pet may be determined in such a manner that the distance between the center point of the minimum unit of the pet and the center point of the minimum unit of the person is smaller than a set value in the images of consecutive frames (for example, 60 frames), and the person may be determined as the person near the pet.
When the candidate prompt object is a non-automobile carrier, a carrier member of the non-automobile carrier can be further determined, and the object attribute information of the carrier member is used as the object attribute information of the non-automobile carrier. Wherein, the carrier member is a person using a non-automobile carrier. For example, the carrier member may be determined in such a way that when the distance between the center point of the minimum unit of the person and the center point of the minimum unit of the non-automotive carrier in the images of consecutive frames (for example, 60 frames) is less than the diagonal length of the minimum unit of the person, the carrier member of the artificial non-automotive carrier may be determined.
And step 130, if the distance between the target candidate prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object.
The distance between the target candidate presenting object and the vehicle may be a closest linear distance between the target candidate presenting object and the vehicle, or may be a horizontal axis distance D and a vertical axis distance L between the target candidate presenting object and the vehicle. In determining whether the distance between the target candidate presentation object and the vehicle is within the safe distance range, the body width W of the vehicle may be considered. For example, when the vehicle width W of the vehicle is large, the lateral distance candidate presentation object of the vehicle needs to be within the safety range by making the lateral distance value of the lateral axis larger.
For example, whether the distance D between the target candidate prompting object and the horizontal axis of the vehicle and the distance L between the target candidate prompting object and the vertical axis of the vehicle are both within the safe range may be respectively determined, and whether prompting for the candidate prompting object is required may be determined. For example, when the distance D of the horizontal axis is greater than 2 meters and the distance L of the vertical axis is greater than 5 meters, it is determined that the distance between the target candidate prompt object and the vehicle is greater than the safe distance; otherwise, determining that the distance between the target candidate prompting object and the vehicle is smaller than or equal to the safe distance.
The customized prompt is generated for the target candidate prompt object, and may be dedicated to prompt the target candidate prompt object. The customized prompt language may include the target candidate prompt object and object attribute information of the target candidate prompt object. The customized prompt language can also comprise the relative position information of the target prompt object and the vehicle. The target candidate prompt object can accurately acquire the prompt information by customizing the prompt, and the customized prompt is the prompt voice with object attribute information, is completely different from noise-like sound of a buzzer, is not easily shielded by a noise reduction algorithm, and has more effectiveness.
For example, a pedestrian may create a pattern similar to "a woman wearing pink clothing in front, please drive to the side, and a car behind please pay attention to safety". For another example, the pet may be a prompt to the owner of the pet, and may generate a message similar to "women carrying a white cat on the left side in front, bothersome to keep your pet, and please pay attention to safety when going to the car at the back". As another example, a model YY white like "the front license plate XXX is generated for a car, and the rear license plate is a car that is paying attention to driving safety". Also for example, for a bicycle may be generated similar to "a woman riding a bicycle with a white top on the front right, going to the side in trouble, asking you to pay attention to the safety behind", etc.
In order to standardize the generation of the customized prompt, and quickly fuse the target candidate prompt object and the object attribute information of the target candidate prompt object, in an optional implementation manner of the embodiment of the present invention, the generating of the customized prompt corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object includes: determining a corresponding voice prompt template according to the target alternative prompt object; and generating the object attribute information of the target candidate prompt object into a customized prompt corresponding to the target candidate prompt object according to the voice prompt template.
The voice prompt template is a template for normalizing information such as a target candidate prompt object, object attribute information of the target candidate prompt object, and a position of the target candidate prompt object relative to the vehicle, and generating a customized prompt. The voice prompt template may correspond to the target candidate prompt object, that is, there may be a plurality of voice prompt templates, and the voice templates of the target candidate prompt objects may be the same or different. For example, different voice prompt templates may be determined according to the category of the target candidate prompt object.
For example, a voice prompt template a may be used for pedestrians, and the voice prompt template a may be "men/women/boys/girls with X side front Y color clothing, please drive side by side, and get a car back to pay attention to safety". The voice prompt template B can be adopted for pets, and the voice prompt template B can be "man/woman/boy/girl carrying Y color Z (pet species) on the front X side, bothersome to pay attention to your pet, and please pay attention to safety when going to a car later". The automobile can adopt a voice prompt template C, and the voice prompt template C can be a model of Y color YY with the license plate number XXX in the front and the automobile coming from the rear please pay attention to the driving safety. The voice prompt template D can be adopted for non-automobile vehicles, and the voice prompt template D can be 'front X-side Y-color bicycle/motorcycle/electric vehicle/scooter man/woman/boy/girl, which is troublesome to drive by side and requires a user to pay attention to safety when the vehicle comes from the back'.
When the object attribute information of the target candidate prompt object is acquired, the target candidate topic, namely the type of the object, the object attribute information and the position relative to the vehicle, can be added to the voice prompt template to generate a customized prompt language corresponding to the target candidate prompt object. The process from the voice prompt template To the customized prompt can be realized by using Text-To-Speech (TTS) technology.
And 140, carrying out voice broadcasting on the customized prompt words in the environment outside the vehicle.
Wherein the vehicle may be equipped with a player for playing a customized alert, such as a horn. The installation position of player can be in the vehicle outside, can guarantee that the customization suggestion broadcast is clear, can not receive the sound insulation performance influence of vehicle, leads to the interior customization suggestion of car to report sound very big, and the outside sound of vehicle is very little. When the voice broadcasting of the customized prompt words is carried out, the orientation of the player can be adjusted, so that the voice broadcasting of the customized prompt words is more targeted. For example, when the target candidate cue object is on the left front side of the vehicle, the player may be oriented toward the left front side. For another example, when the target candidate cue object is on the right front side of the vehicle, the player may be oriented toward the right front side. For another example, when the target candidate cue object is directly in front of the vehicle, the player may be directed directly in front.
According to the technical scheme of the embodiment, at least one candidate prompt object is identified in real time in front of the vehicle, and object attribute information of each candidate prompt object is acquired; determining the distance between each candidate prompt object and the vehicle; if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object; carry out voice broadcast to the customization suggestion in the car external environment, difficult quilt is perceived when having solved among the prior art and adopting bee calling organ to indicate, is easily fallen the algorithm of making an uproar and shields, can't ensure other road user driving safety's problem, realized can pertinence carry out voice prompt to different target alternative suggestion objects, and be difficult for being fallen the earphone and shield of making an uproar to ensure other road user driving safety's effect.
Example two
Fig. 2 is a flowchart of a voice prompt method for an object outside a vehicle according to a second embodiment of the present invention, which is a further refinement of the foregoing technical solution, and the technical solution in this embodiment may be combined with various alternatives in one or more of the foregoing embodiments. As shown in fig. 2, the method includes:
and step 210, identifying at least one candidate prompt object in front of the vehicle in real time, and acquiring object attribute information of each candidate prompt object.
And step 220, determining the distance between each candidate prompting object and the vehicle.
And step 230, if the distance between the target candidate prompt object and the vehicle is determined to be less than or equal to the safe distance, generating a customized prompt corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object.
And step 240, acquiring environmental noise information in the environment outside the vehicle within a set time interval.
The manner of acquiring the environmental noise information may be implemented by a noise acquisition device external to the vehicle, for example, a microphone may be disposed outside the vehicle. To ensure the validity of the voice prompt, the set time interval may be 1 second.
Illustratively, the ambient noise in the environment outside the vehicle can be acquired in real time through an external microphone, and the average value N of the amplitude of the ambient noise within 1 second is counted as the ambient noise information.
And step 250, determining voice prompt volume according to the environmental noise information and the distance between the target alternative prompt object and the vehicle, and carrying out voice broadcast on the customized prompt according to the voice prompt volume.
And when the average value N of the environmental noise amplitude is larger, the required voice prompt volume is larger. The larger the distance between the target candidate prompt object and the vehicle is, the larger the required voice prompt volume is. Therefore, the positive correlation function relationship can be adopted to establish the relational expression of the environmental noise information, the distance and the voice prompt volume. In the present embodiment, the expression can be given by
Calculating voice prompt volume, wherein A is voice prompt volume, N is the average value of the ambient noise amplitude within 1 second, D is the distance between the target candidate prompt object and the vehicle along the horizontal axis, L is the distance between the target candidate prompt object and the vehicle along the vertical axis,
and prompting the distance between the object and the vehicle for the target candidate, wherein alpha is a coefficient. α can be determined by the formula β ═ 20lg (a/N), where lg (·) represents a logarithmic function, and β can be a constant greater than or equal to 50 in decibels in order to ensure the clarity of the customized prompts in voice announcement.
In this embodiment, the voice prompt volume of the customized prompt may be adjusted in real time according to the ambient noise information in the vehicle exterior environment and the distance between the target candidate prompt object and the vehicle. The voice prompt sound measuring tool can be guaranteed to be pointed, the situation that the customized prompt sound cannot be heard by the target alternative prompt object due to the fact that the voice prompt volume is too large to form noise or too small can be avoided, and the voice broadcast of the customized prompt sound can be accurate and effective.
In order to further improve the effectiveness of the voice prompt volume, in an optional implementation manner of the embodiment of the present invention, determining the voice prompt volume according to the environmental noise information and the distance between the target candidate prompt object and the vehicle includes: and determining the voice prompt volume according to the environmental noise information, the target alternative prompt object and the distance between the target alternative prompt object and the vehicle.
Wherein, when the target alternative prompt objects are different, the voice prompt volume can be differentThe same is true. For example, automobiles generally have some sound insulation, while pedestrians and vehicle members other than automobile vehicles generally do not have sound insulation. Therefore, for the case that the target candidate prompt object is a car, the target candidate prompt object can be determined according to
On the basis of the calculated voice volume, the volume is increased appropriately. Alternatively, the increase ratio of the voice volume may be 30% to 50%. According to the survey results, the higher the model price of the automobile is, the better the sound insulation effect is. Therefore, the specific increase rate of the voice volume can be determined according to the automobile model. The method has the advantages that the approximate price sequencing of automobiles of different models can be obtained in advance, the sound insulation effect sequencing is determined, the increase proportion of the voice volume is determined specifically, and people in the automobiles can be guaranteed to obtain the customized prompt words accurately.
According to the technical scheme of the embodiment, environmental noise information in the environment outside the vehicle in a set time interval is acquired; the voice prompt volume is determined according to the environmental noise information and the distance between the target alternative prompt object and the vehicle, and the customized prompt is subjected to voice broadcast according to the voice prompt volume, so that the problem that the prompt volume is fixed or randomly and irregularly adjusted when a buzzer is adopted for prompting in the prior art is solved, and the voice prompt volume can be accurately determined according to the environmental noise information and the distance between the target alternative prompt object and the vehicle; the effectiveness of voice prompt is ensured, and the condition that the target candidate prompt object cannot hear the customized prompt language due to the fact that the voice prompt volume is too large to form noise or too small can be avoided.
EXAMPLE III
Fig. 3 is a flowchart of a voice prompt method for an object outside a vehicle according to a third embodiment of the present invention, which is a further refinement of the foregoing technical solution, and the technical solution in this embodiment may be combined with various alternatives in one or more of the foregoing embodiments. As shown in fig. 3, the method includes:
and 310, acquiring an image in front of the vehicle in real time, performing first image recognition on the image in front of the vehicle, and determining a candidate prompt object contained in the image in front of the vehicle.
In an optional implementation manner of the embodiment of the present invention, the candidate prompt object includes at least one of the following items: pedestrian, automotive and non-automotive vehicles.
The first image recognition may be recognition of a candidate prompt object type, for example, an image recognition algorithm using a deep neural network large classifier. Pedestrian, automobile, and non-automobile vehicles included in the image in front of the vehicle may be determined from the first image recognition.
In an optional implementation manner of the embodiment of the present invention, performing first image recognition on an image in front of a vehicle, and determining a candidate prompt object included in the image in front of the vehicle includes: inputting the image in front of the vehicle into a first classification model, and acquiring a first labeling result image of the image in front of the vehicle output by the first classification model, wherein the first labeling result image is labeled with: the candidate prompt object recognition area and the candidate prompt object recognized in the candidate prompt object recognition area.
The first classification model may be a deep neural network large classifier, and the deep neural network large classifier may be used to identify the category of the candidate prompt object. The alternate cueing object identification area may be an area for identifying an alternate cueing object. For example, the candidate hint object identification area may be the smallest box containing the candidate hint object, which may be understood as the smallest unit described above.
When the type of the candidate prompt object is identified through the first classification model, the candidate prompt object identification area can be marked in the image in front of the vehicle, the candidate prompt object identification area is identified, and the candidate prompt object is determined. One or more candidate presentation object recognition areas may exist in the same vehicle front image, and the target candidate presentation object may be recognized for each recognition area. Through the division of the identification area, the identification can be more accurate, and the information interference outside the identification area can be avoided.
And step 320, performing second image recognition on the image in front of the vehicle according to the recognized candidate prompt objects, and determining object attribute information of each candidate prompt object contained in the image in front of the vehicle.
The second image recognition may be recognition of object attribute information of each candidate prompt object. The second image recognition may be a deep neural network small classifier. The second image recognition of different alternate prompt objects may be different. For example, the second image recognition of each alternate cued object may each include color recognition, and the second image recognition of the alternate cued object relating to the person may include identification of age and gender. The second image recognition involving the candidate cueing object of the vehicle may comprise vehicle type number recognition or the like.
In an optional implementation manner of the embodiment of the present invention, performing second image recognition on the image in front of the vehicle according to the recognized candidate guidance object, and determining object attribute information of each candidate guidance object included in the image in front of the vehicle includes: inputting the first labeling result image into a second classification model, and acquiring a second labeling result image of the vehicle front image output by the second classification model, wherein the second labeling result image is marked with: and object attribute information respectively corresponding to the candidate prompt objects in each candidate prompt object identification area.
Wherein the second classification model may be a deep neural network mini-classifier. When the second classification model is used for identifying the object attribute information of the candidate prompt object, the object attribute information of the candidate prompt object identification area can be identified by using a deep neural network small classifier corresponding to the candidate prompt object.
In an optional implementation manner of the embodiment of the present invention, the object attribute information corresponding to the pedestrian includes at least one of: age information, gender information, and clothing color information; the object attribute information corresponding to the car includes at least one of: vehicle type information and vehicle body color information; the object attribute information corresponding to the non-automobile vehicle includes at least one item of information of a vehicle member of the non-automobile vehicle: age information, gender information, and clothing color information.
The age information may be rough data, and may be data for classifying people and children. The gender information may be male or female, or may be uncertain. The garment color information may include a top color and/or a bottom color. The vehicle type information may be model information of the vehicle, such as a brand of the vehicle and a model of the vehicle. The body color may be white, black, gray, blue, red, yellow, or the like.
In addition, for the non-automobile vehicle, the type of the non-automobile vehicle, such as a bicycle, a motorcycle, an electric vehicle, or a scooter, can be directly recognized during the first image recognition. Alternatively, only the non-vehicle may be recognized at the time of the first image recognition, and the specific type may be determined at the time of the second image recognition.
And step 330, determining the distance between each candidate prompt object and the vehicle.
And 340, if the distance between the target candidate prompt object and the vehicle is determined to be less than or equal to the safe distance, generating a customized prompt corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object.
And 350, performing voice broadcasting on the customized prompt words in the environment outside the vehicle.
According to the technical scheme of the embodiment, the standby prompt object contained in the image in front of the vehicle is determined by acquiring the image in front of the vehicle in real time and performing first image recognition on the image in front of the vehicle; according to the alternative prompt objects obtained through recognition, second image recognition is carried out on the images in front of the vehicle, object attribute information of all the alternative prompt objects contained in the images in front of the vehicle is determined, the problems that in the prior art, prompting is not targeted through a buzzer, the prompting is not easy to perceive, the prompting is easy to shield through a noise reduction algorithm, and the driving safety of other road users cannot be guaranteed are solved, the types of the alternative prompt objects and the corresponding object attribute information can be accurately determined, further, targeted prompting can be carried out, the shielding is not easy to shield through noise reduction earphones, and therefore the driving safety of other road users is guaranteed.
Fig. 4 is a flowchart of a voice prompt method for an object outside a vehicle according to a third embodiment of the present invention, and as shown in fig. 4, a using process according to the third embodiment of the present invention is as follows: during the driving process of the vehicle, the video stream of the road in front is collected through the camera, and auxiliary collection can be carried out by combining a vision sensor, millimeter waves or a laser radar and the like. Ambient noise information outside the vehicle may be collected by an external microphone. For each frame of image in front of the vehicle in the video stream, candidate prompt objects such as pedestrians, pets, vehicles and non-automobiles can be identified by using an image identification algorithm, and specific object attribute information is identified for each kind of candidate prompt objects. Unique identification information can be allocated to each alternative prompt object, an object database is established, and the types of the alternative prompt objects and corresponding object attribute information are stored. The distance between the candidate prompting object and the vehicle can be calculated through a conversion relation between the preset image depth and the actual distance. Or, information fusion can be performed by combining multi-mode visual information of millimeter waves or laser radars, and the distance between the candidate prompt object and the vehicle is determined. If the alternative prompt object is in the coverage range of the vehicle driving path and the distance is less than or equal to the safe distance, the customized prompt language can be generated according to the object attribute information of the alternative prompt object and the voice prompt template. And calculating voice prompt volume according to the distance between the candidate prompt object and the vehicle, the object attribute information and the ambient noise information. And broadcasting the customized prompt words according to the voice prompt volume.
Example four
Fig. 5 is a schematic structural diagram of a voice prompt device for an object outside a vehicle according to a fourth embodiment of the present invention. With reference to fig. 5, the apparatus comprises: a candidate prompt object recognition module/object attribute information acquisition module 510, a distance determination module 520, a customized prompt generation module 530 and a voice broadcast module 540.
The candidate prompt object identification module/object attribute information acquisition module 510 is configured to identify at least one candidate prompt object in front of the vehicle in real time and acquire object attribute information of each candidate prompt object;
a distance determining module 520, configured to determine a distance between each candidate prompt object and the vehicle;
a customized prompt generating module 530, configured to generate a customized prompt corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object if it is determined that the distance between the target candidate prompt object and the vehicle is less than or equal to the safe distance;
and the voice broadcasting module 540 is used for performing voice broadcasting on the customized prompt in the environment outside the vehicle.
Optionally, the apparatus further comprises:
and the environmental noise information acquisition module is used for acquiring environmental noise information in the environment outside the vehicle within a set time interval.
Optionally, the voice broadcast module 540 includes:
the voice prompt volume determining unit is used for determining voice prompt volume according to the environmental noise information and the distance between the target candidate prompt object and the vehicle;
and the voice broadcasting unit is used for carrying out voice broadcasting on the customized prompt words according to the voice prompt volume.
Optionally, the voice prompt volume determining unit includes:
and the voice prompt volume determining subunit is used for determining the voice prompt volume according to the environmental noise information, the target alternative prompt object and the distance between the target alternative prompt object and the vehicle.
Optionally, the candidate prompt object identifying module/object attribute information obtaining module 510 includes:
the candidate prompt object determining unit is used for acquiring an image in front of the vehicle in real time, performing first image recognition on the image in front of the vehicle and determining a candidate prompt object contained in the image in front of the vehicle;
and an object attribute information determination unit configured to perform second image recognition on the vehicle front image based on the recognized candidate presentation objects, and determine object attribute information of each candidate presentation object included in the vehicle front image.
Optionally, the candidate prompt object determining unit is specifically configured to:
inputting the image in front of the vehicle into a first classification model, and acquiring a first labeling result image of the image in front of the vehicle output by the first classification model, wherein the first labeling result image is labeled with: the candidate prompt object recognition area and the candidate prompt object recognized in the candidate prompt object recognition area.
Optionally, the object attribute information determining unit is specifically configured to:
inputting the first labeling result image into a second classification model, and acquiring a second labeling result image of the vehicle front image output by the second classification model, wherein the second labeling result image is marked with: and object attribute information respectively corresponding to the candidate prompt objects in each candidate prompt object identification area.
Optionally, the candidate prompt object includes at least one of: pedestrian, automotive and non-automotive vehicles;
the object attribute information corresponding to the pedestrian includes at least one of: age information, gender information, and clothing color information;
the object attribute information corresponding to the car includes at least one of: vehicle type information and vehicle body color information;
the object attribute information corresponding to the non-automobile vehicle includes at least one item of information of a vehicle member of the non-automobile vehicle: age information, gender information, and clothing color information.
Optionally, the distance determining module 520 includes:
the position information determining unit is used for acquiring an image in front of the vehicle in real time, carrying out image recognition on the image in front of the vehicle and determining the position information of each candidate prompt object in the image in front of the vehicle;
and the distance determining unit is used for determining the distance between each candidate prompting object and the vehicle according to the conversion relation between the preset image depth of field and the actual distance and the position information.
Optionally, the customized hint generating module 530 includes:
the voice prompt template determining unit is used for determining a corresponding voice prompt template according to the target candidate prompt object;
and the customized prompt language generating unit is used for generating the customized prompt language corresponding to the target candidate prompt object according to the object attribute information of the target candidate prompt object and the voice prompt template.
The voice prompt device for the vehicle-exterior object provided by the embodiment of the invention can execute the voice prompt method for the vehicle-exterior object provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 6 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention, and as shown in fig. 6, the computer device includes:
one or more processors 610, one processor 610 being exemplified in fig. 6;
a memory 620;
the apparatus may further include: an input device 630 and an output device 640.
The processor 610, the memory 620, the input device 630 and the output device 640 of the apparatus may be connected by a bus or other means, and fig. 6 illustrates the example of connection by a bus.
The memory 620, as a non-transitory computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a method for voice prompting an off-board object according to an embodiment of the present invention (for example, the candidate prompt object recognition module/object attribute information acquisition module 510, the distance determination module 520, the customized prompt generation module 530, and the voice broadcast module 540 shown in fig. 5). The processor 610 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 620, namely, implements a voice prompt method for an object outside a vehicle according to the above method embodiment, namely:
identifying at least one alternative prompt object in front of the vehicle in real time, and acquiring object attribute information of each alternative prompt object;
determining the distance between each alternative prompt object and the vehicle;
if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object;
and carrying out voice broadcast on the customized prompt words in the environment outside the vehicle.
The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 620 optionally includes memory located remotely from processor 610, which may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 630 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus. The output device 640 may include a display device such as a display screen.
EXAMPLE six
The sixth embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for voice prompting an object outside a vehicle, according to the sixth embodiment of the present invention:
identifying at least one alternative prompt object in front of the vehicle in real time, and acquiring object attribute information of each alternative prompt object;
determining the distance between each alternative prompt object and the vehicle;
if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object;
and carrying out voice broadcast on the customized prompt words in the environment outside the vehicle.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (14)
1. A voice prompt method for an object outside a vehicle is characterized by comprising the following steps:
identifying at least one alternative prompt object in front of the vehicle in real time, and acquiring object attribute information of each alternative prompt object;
determining the distance between each alternative prompt object and the vehicle;
if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance, generating a customized prompt corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object;
and carrying out voice broadcast on the customized prompt words in the environment outside the vehicle.
2. The method of claim 1, further comprising: acquiring environmental noise information in an environment outside the vehicle within a set time interval;
the voice announcement of the customized prompt language in the environment outside the vehicle comprises the following steps:
and determining voice prompt volume according to the environmental noise information and the distance between the target alternative prompt object and the vehicle, and carrying out voice broadcast on the customized prompt according to the voice prompt volume.
3. The method of claim 2, wherein determining a voice prompt volume based on the ambient noise information and the distance between the target candidate prompt object and the vehicle comprises:
and determining voice prompt volume according to the environmental noise information, the target alternative prompt object and the distance between the target alternative prompt object and the vehicle.
4. The method of claim 1, wherein identifying at least one candidate cueing object in front of the vehicle in real-time and obtaining object attribute information for each candidate cueing object comprises:
acquiring an image in front of a vehicle in real time, performing first image recognition on the image in front of the vehicle, and determining an alternative prompt object contained in the image in front of the vehicle;
and performing second image recognition on the image in front of the vehicle according to the recognized candidate prompting objects, and determining object attribute information of each candidate prompting object contained in the image in front of the vehicle.
5. The method of claim 4, wherein identifying at least one alternate cueing object in front of the vehicle in real-time and obtaining object attribute information for each of the alternate cueing objects comprises:
the method for performing first image recognition on the image in front of the vehicle and determining the candidate prompt object contained in the image in front of the vehicle comprises the following steps:
inputting the image in front of the vehicle into a first classification model, and acquiring a first labeling result image of the image in front of the vehicle output by the first classification model, wherein the first labeling result image is labeled with: the alternative prompt object recognition area and the alternative prompt object recognized in the alternative prompt object recognition area;
according to the candidate prompt objects obtained by recognition, performing second image recognition on the image in front of the vehicle, and determining object attribute information of each candidate prompt object contained in the image in front of the vehicle, wherein the second image recognition comprises the following steps:
inputting the first labeling result image into a second classification model, and acquiring a second labeling result image of the vehicle front image output by the second classification model, wherein the second labeling result image is labeled with: and object attribute information respectively corresponding to the candidate prompt objects in each candidate prompt object identification area.
6. The method of claim 4 or 5, wherein the alternative prompt object comprises at least one of: pedestrian, automotive and non-automotive vehicles;
the object attribute information corresponding to the pedestrian includes at least one of: age information, gender information, and clothing color information;
the object attribute information corresponding to the car includes at least one of: vehicle type information and vehicle body color information;
the object attribute information corresponding to the non-automobile vehicle comprises at least one item of information of vehicle members of the non-automobile vehicle, wherein the item of information comprises: age information, gender information, and clothing color information.
7. The method of claim 1, wherein determining the distance between each candidate cueing object and the vehicle comprises:
acquiring an image in front of a vehicle in real time, performing image recognition on the image in front of the vehicle, and determining position information of each candidate prompt object in the image in front of the vehicle;
and determining the distance between each candidate prompting object and the vehicle according to a preset conversion relation between the depth of field of the image and the actual distance and the position information.
8. The method of claim 1, wherein generating a customized prompt corresponding to the target candidate prompt object based on the object attribute information of the target candidate prompt object comprises:
determining a corresponding voice prompt template according to the target alternative prompt object;
and generating the object attribute information of the target candidate prompt object into a customized prompt corresponding to the target candidate prompt object according to the voice prompt template.
9. A voice guidance device for an object outside a vehicle, comprising:
the system comprises an alternative prompt object identification module/object attribute information acquisition module, a prompt object recognition module and a prompt object attribute information acquisition module, wherein the alternative prompt object identification module/object attribute information acquisition module is used for identifying at least one alternative prompt object in front of a vehicle in real time and acquiring object attribute information of each alternative prompt object;
the distance determining module is used for determining the distance between each candidate prompting object and the vehicle;
the customized prompt language generating module is used for generating a customized prompt language corresponding to the target alternative prompt object according to the object attribute information of the target alternative prompt object if the distance between the target alternative prompt object and the vehicle is determined to be smaller than or equal to the safe distance;
and the voice broadcasting module is used for carrying out voice broadcasting on the customized prompt words in the environment outside the vehicle.
10. The apparatus of claim 9, further comprising:
the environment noise information acquisition module is used for acquiring environment noise information in the environment outside the vehicle within a set time interval;
the voice broadcast module includes:
the voice prompt volume determining unit is used for determining voice prompt volume according to the environmental noise information and the distance between the target candidate prompt object and the vehicle;
and the voice broadcasting unit is used for carrying out voice broadcasting on the customized prompt words according to the voice prompt volume.
11. The apparatus according to claim 9, wherein the candidate prompt object identification module/object attribute information obtaining module comprises:
the candidate prompt object determining unit is used for acquiring an image in front of a vehicle in real time, performing first image recognition on the image in front of the vehicle and determining a candidate prompt object contained in the image in front of the vehicle;
and an object attribute information determination unit configured to perform second image recognition on the vehicle front image based on the recognized candidate presentation objects, and determine object attribute information of each of the candidate presentation objects included in the vehicle front image.
12. The apparatus of claim 9, wherein the distance determining module comprises:
the position information determining unit is used for acquiring an image in front of a vehicle in real time, performing image recognition on the image in front of the vehicle, and determining position information of each candidate prompt object in the image in front of the vehicle;
and the distance determining unit is used for determining the distance between each candidate prompting object and the vehicle according to a conversion relation between the preset image depth of field and the actual distance and the position information.
13. A computer device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of voice prompting an off-board object as recited in any of claims 1-8.
14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out a method for voice prompting of an object external to a vehicle according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010849882.4A CN111976593A (en) | 2020-08-21 | 2020-08-21 | Voice prompt method, device, equipment and storage medium for vehicle external object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010849882.4A CN111976593A (en) | 2020-08-21 | 2020-08-21 | Voice prompt method, device, equipment and storage medium for vehicle external object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111976593A true CN111976593A (en) | 2020-11-24 |
Family
ID=73443916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010849882.4A Pending CN111976593A (en) | 2020-08-21 | 2020-08-21 | Voice prompt method, device, equipment and storage medium for vehicle external object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111976593A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113002421A (en) * | 2021-04-25 | 2021-06-22 | 广州小鹏汽车科技有限公司 | Vehicle exterior safety prompting method and device |
| CN114162042A (en) * | 2021-12-31 | 2022-03-11 | 江苏理工学院 | Self-adaptive vehicle horn developed based on BP neural network |
| CN114973652A (en) * | 2022-04-22 | 2022-08-30 | 岚图汽车科技有限公司 | Visual blind area reminding method and system, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206841295U (en) * | 2017-02-28 | 2018-01-05 | 江苏金坛汽车工业有限公司 | A kind of horn volume control system and automobile for reminding pedestrian |
| CN108256401A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | A kind of method and device for obtaining objective attribute target attribute Feature Semantics |
| CN109740517A (en) * | 2018-12-29 | 2019-05-10 | 上海依图网络科技有限公司 | A kind of method and device of determining object to be identified |
| CN109795407A (en) * | 2017-11-17 | 2019-05-24 | 成都配天智能技术有限公司 | A kind of method, apparatus and vehicle of vehicle intelligent prompting |
| CN110329144A (en) * | 2019-03-30 | 2019-10-15 | 惠州德赛信息科技有限公司 | A kind of Vehicular intelligent whistle method |
| JP2020098629A (en) * | 2020-02-12 | 2020-06-25 | 株式会社東芝 | Object detection method |
-
2020
- 2020-08-21 CN CN202010849882.4A patent/CN111976593A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256401A (en) * | 2016-12-29 | 2018-07-06 | 杭州海康威视数字技术股份有限公司 | A kind of method and device for obtaining objective attribute target attribute Feature Semantics |
| CN206841295U (en) * | 2017-02-28 | 2018-01-05 | 江苏金坛汽车工业有限公司 | A kind of horn volume control system and automobile for reminding pedestrian |
| CN109795407A (en) * | 2017-11-17 | 2019-05-24 | 成都配天智能技术有限公司 | A kind of method, apparatus and vehicle of vehicle intelligent prompting |
| CN109740517A (en) * | 2018-12-29 | 2019-05-10 | 上海依图网络科技有限公司 | A kind of method and device of determining object to be identified |
| CN110329144A (en) * | 2019-03-30 | 2019-10-15 | 惠州德赛信息科技有限公司 | A kind of Vehicular intelligent whistle method |
| JP2020098629A (en) * | 2020-02-12 | 2020-06-25 | 株式会社東芝 | Object detection method |
Non-Patent Citations (1)
| Title |
|---|
| 李长云: "智能感知技术及在电气工程中的应用", 电子科技大学出版社, pages: 222 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113002421A (en) * | 2021-04-25 | 2021-06-22 | 广州小鹏汽车科技有限公司 | Vehicle exterior safety prompting method and device |
| CN114162042A (en) * | 2021-12-31 | 2022-03-11 | 江苏理工学院 | Self-adaptive vehicle horn developed based on BP neural network |
| CN114973652A (en) * | 2022-04-22 | 2022-08-30 | 岚图汽车科技有限公司 | Visual blind area reminding method and system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111976593A (en) | Voice prompt method, device, equipment and storage medium for vehicle external object | |
| US7792328B2 (en) | Warning a vehicle operator of unsafe operation behavior based on a 3D captured image stream | |
| CN108226854B (en) | Apparatus and method for providing visual information of rear vehicle | |
| CN109795407B (en) | Vehicle-mounted intelligent reminding method and device and vehicle | |
| JP2018107759A (en) | Image processing device, image processing method, and image processing system | |
| CN113597617A (en) | Display method, display device, display equipment and vehicle | |
| CN113205088B (en) | Obstacle image presentation method, electronic device, and computer-readable medium | |
| CN115312061A (en) | Voice question-answer method and device in driving scene and vehicle-mounted terminal | |
| CN111985373A (en) | Safety early warning method and device based on traffic intersection identification and electronic equipment | |
| CN112699802A (en) | Driver micro-expression detection device and method | |
| CN112699862B (en) | Image data processing method, device, equipment and storage medium | |
| Meng et al. | Application and development of AI technology in automobile intelligent cockpit | |
| CN113352989A (en) | Intelligent driving safety auxiliary method, product, equipment and medium | |
| CN113619483A (en) | Reminding method for vehicle, corresponding reminding device and vehicle | |
| CN116872840A (en) | Vehicle anti-collision early warning method and device, vehicle and storage medium | |
| CN110727269A (en) | Vehicle control method and related product | |
| CN112758089A (en) | Voice reminding method, advanced driving assistance system and computer storage medium | |
| CN114332798A (en) | Processing method and related device for network car booking environment information | |
| CN110139205B (en) | Method and device for auxiliary information presentation | |
| CN109987024A (en) | Parking assisting system and method based on audio azimuth information | |
| KR20220122832A (en) | Apparatus and method for riding notification of mobility on demand | |
| CN109977753B (en) | Early warning method and vehicle | |
| JP2020103702A (en) | Information processing device and program | |
| US20230290137A1 (en) | Information processing apparatus, information processing method, and program | |
| Gabrielli et al. | An advanced multimodal driver-assistance prototype for emergency-vehicle detection |
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 |
Application publication date: 20201124 |