Seat belt wearing detection method and apparatus based on region of interest, and device

Abstract

Disclosed in embodiments of the present invention are a seat belt wearing detection method and apparatus based on a region of interest, and a device. The method comprises: acquiring an image of a person in a vehicle; determining a preset inclined seat belt line on the basis of preset starting and ending points of a seat belt in the image of the person in the vehicle, and determining a first round point on a perpendicular bisector of the preset inclined seat belt line; taking the first round point as a circle center and the length between the first circle center and either of the preset starting and ending points as a radius to draw a first target circle; determining a target region of interest on the basis of the first target circle, the first circle center, and the preset starting and ending points; and inputting the target region of interest into a preset seat belt wearing classification model, and determining whether the person in the vehicle is wearing a seat belt. According to the method, the wearing condition of a seat belt can be detected on the basis of a region of interest, reducing the interference of non-regions of interest, improving detection accuracy, and the method has good adaptability.

Description

A safety belt wearing detection method, device and equipment based on a region of interest TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a safety belt wearing detection method, device and equipment based on a region of interest. BACKGROUND

[0002] In vehicle driving, wearing a safety belt can provide protection effectiveness for people in the vehicle in an emergency and reduce the risk of injury in an accident.

[0003] In the prior art, the wearing of a safety belt is usually only judged whether the safety belt is buckled. However, in actual application, some people simply clip the safety belt in the buckle position to evade wearing the safety belt. Therefore, the safety belt wearing detection method of the prior art will determine the above-mentioned situation as wearing the safety belt, resulting in low accuracy of safety belt wearing detection.

[0004] SUMMARY

[0005] The present application provides a safety belt wearing detection method, device and equipment based on a region of interest to improve the accuracy of safety belt wearing detection.

[0006] According to an aspect of the present application, a safety belt wearing detection method based on a region of interest is provided, which comprises:

[0007] Obtaining an image of a person in a vehicle;

[0008] Determining a diagonal safety belt preset line according to a preset start and end point of a seat belt in the image of the person in the vehicle, and determining a first circular point on a perpendicular line of the diagonal safety belt preset line;

[0009] Drawing a first target circle with the first circular point as the center and the length between the first circular point and the start point or the end point of the preset start and end point as the radius;

[0010] Determining a target region of interest according to the first target circle, the first circular point, and the preset start and end point;

[0011] Inputting the target region of interest into a preset safety belt wearing classification model to determine whether the person in the vehicle wears a safety belt.

[0012] Optionally, determining a target region of interest according to the first target circle, the first circular point, and the preset start and end point comprises:

[0013] Determining a first arc line composed of the preset start and end point in the first target circle;

[0014] The first region of interest formed by the oblique seat belt preset line and the first arc line is taken as a target region of interest.

[0015] A first sector region is determined in the first target circle according to the first circle point and the preset start and end point, and the first sector region is taken as a target region of interest.

[0016] Optionally, the target region of interest is determined according to the first target circle, the first circle center and the preset start and end point, and the target region of interest includes:

[0017] A second circle end point is determined on the horizontal seat belt preset line according to a preset end point of the seat belt in the image of the person in the vehicle.

[0018] A second target circle is drawn with the preset end point as a circle center and a length between the preset end point and the second circle end point as a radius.

[0019] The target region of interest is determined according to the first target circle, the first circle center, the preset start and end point, the second target circle and the second circle end point.

[0020] Optionally, the target region of interest is determined according to the first target circle, the first circle center, the preset start and end point, the second target circle and the second circle end point, and the target region of interest includes:

[0021] A first region of interest or a first sector region is determined according to the first target circle, the first circle center and the preset start and end point.

[0022] A second sector region is determined according to the second target circle, the preset end point, the second circle end point and an intersection point between the second target circle and the oblique seat belt preset line.

[0023] A second region of interest formed by the first region of interest or the first sector region and the second sector region is taken as a target region of interest.

[0024] Optionally, the oblique seat belt preset line is determined according to the preset start and end point of the seat belt in the image of the person in the vehicle, and a first circle point is determined on a median line of the oblique seat belt preset line, and the target region of interest includes:

[0025] The first circle point is determined as a point on the median line of the oblique seat belt preset line and having a distance from the oblique seat belt preset line equal to half a length of the oblique seat belt preset line.

[0026] The second circle end point is determined on the horizontal seat belt preset line, and the target region of interest includes:

[0027] The intersection of the transverse safety belt preset line and the seat preset boundary vertical line is determined as a second circle end point.

[0028] Optionally, the method further comprises:

[0029] When it is determined that the occupant in the vehicle does not wear a safety belt, a safety belt wearing abnormality alarm is performed.

[0030] According to another aspect of the present application, there is provided a safety belt wearing detection device based on a region of interest, which comprises:

[0031] An occupant in-vehicle image acquisition module is configured to acquire an occupant in-vehicle image of a vehicle;

[0032] A first circle point determination module is configured to determine a diagonal safety belt preset line according to preset start and end points of a seat safety belt in the occupant in-vehicle image, and determine a first circle point on a mid-perpendicular line of the diagonal safety belt preset line;

[0033] A first target circle drawing module is configured to draw a first target circle with the first circle point as a center and a length between the first circle center and a start point or an end point in the preset start and end points as a radius;

[0034] A target region of interest determination module is configured to determine a target region of interest according to the first target circle, the first circle center, and the preset start and end points;

[0035] A safety belt wearing detection module is configured to input the target region of interest into a preset safety belt wearing classification model to determine whether an occupant in the vehicle wears a safety belt.

[0036] According to another aspect of the present application, there is provided an electronic device, which comprises:

[0037] at least one processor; and

[0038] a memory connected to the at least one processor in communication; wherein,

[0039] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the safety belt wearing detection method based on a region of interest according to any one of the embodiments of the present application.

[0040] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to implement the safety belt wearing detection method based on a region of interest according to any one of the embodiments of the present application when executed by the processor.

[0041] According to another aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of detecting seat belt wearing based on a region of interest according to any of the embodiments of the present application.

[0042] The technical scheme of the embodiment of the present application acquires the image of the person in the vehicle, determines the oblique seat belt preset line according to the preset start and end points of the seat belt in the image of the person in the vehicle, and determines the first circle point on the median line of the oblique seat belt preset line; draws the first target circle with the first circle point as the center and the length between the first circle point and the start point or the end point in the preset start and end points as the radius; determines the target region of interest according to the first target circle, the first circle point, and the preset start and end points; and inputs the target region of interest into the preset seat belt wearing classification model to determine whether the person in the vehicle wears the seat belt, thereby solving the problem of seat belt wearing detection, enabling the seat belt wearing situation to be detected based on the region of interest, reducing the interference of the non-region of interest, improving the detection accuracy, and having good adaptability.

[0043] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0045] Fig. 1 is a flowchart of a method for detecting seat belt wearing based on a region of interest according to an embodiment of the present application;

[0046] Fig. 2 is a schematic diagram of determining a target region of interest according to an embodiment of the present application;

[0047] Fig. 3 is a flowchart of a method for detecting seat belt wearing based on a region of interest according to an embodiment of the present application;

[0048] Fig. 4 is a schematic diagram of determining a target region of interest according to an embodiment of the present application;

[0049] Fig. 5 is a structural schematic diagram of a device for detecting seat belt wearing based on a region of interest according to an embodiment of the present application;

[0050] Fig. 6 is a structural schematic diagram of an electronic device implementing the method for detecting seat belt wearing based on a region of interest according to an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should belong to the protection scope of the present application.

[0052] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] Embodiment one

[0054] FIG. 1 is a flowchart of a safety belt wearing detection method based on a region of interest according to embodiment one of the present application. The present embodiment can be applied to detecting the safety belt wearing situation of a person in a vehicle. The method can be executed by a safety belt wearing detection device based on a region of interest. The safety belt wearing detection device based on a region of interest can be realized in the form of hardware and / or software. The safety belt wearing detection device based on a region of interest can be configured in an electronic device such as a vehicle controller or a vehicle processor, etc. As shown in FIG. 1, the method comprises:

[0055] Step 110, obtaining an in-vehicle person image of the vehicle.

[0056] In the embodiment of the present application, the in-vehicle personnel image can be an image of a driver or a passenger in the vehicle. The in-vehicle personnel image can include an image of an upper body and an abdominal region of the personnel. The in-vehicle personnel image can be captured by a camera, a video recorder or other photographing device. Specifically, to improve the accuracy of the seat belt wearing detection, a photographing device with a resolution greater than a preset resolution can be used to capture real-time images of the personnel in the vehicle. For example, if the seat belt wearing of the driver or the front passenger is to be detected, the photographing device can be installed at a position of an instrument panel or an A-pillar of the vehicle. If the seat belt wearing of the rear passengers is to be detected, the photographing device can be installed at a position of a B-pillar or an internal roof of the vehicle. The specific number of the photographing devices can be adjusted according to the actual seat belt wearing detection requirements.

[0057] To further improve the accuracy of the seat belt wearing detection in different environments, a photographing device with an adaptive exposure adjustment function can be used. The photographing device with the adaptive exposure adjustment function can obtain clear in-vehicle personnel images under different lighting conditions, such as sunlight, shade or night, thereby improving the accuracy of the seat belt wearing detection.

[0058] Before obtaining the in-vehicle personnel image for processing, the in-vehicle personnel image can also be preprocessed. The preprocessing operation includes but is not limited to image denoising, brightness adjustment and contrast enhancement. Through the image preprocessing operation, the image quality can be improved, and a more accurate visual basis can be provided for the seat belt wearing detection.

[0059] Step 120, determining a diagonal seat belt preset line according to the preset start and end points of the seat belt in the in-vehicle personnel image, and determining a first circle point on the median line of the diagonal seat belt preset line.

[0060] The preset start and end points of the seat belt can be the storage point and the buckle point of the seat belt, respectively. The line segment formed by the preset start and end points of the seat belt is the diagonal seat belt preset line. The first circle point can be determined on the median line of the diagonal seat belt preset line.

[0061] In an optional embodiment of the present application, to improve the reliability of the seat belt wearing detection, the first circle point is determined on the median line of the diagonal seat belt preset line, including: determining, on the median line of the diagonal seat belt preset line, a point with a distance from the diagonal seat belt preset line being half of the length of the diagonal seat belt preset line as the first circle point.

[0062] FIG. 2 is a schematic diagram of determining a target region of interest according to an embodiment of the present application. As shown in FIG. 2, the red line segment is the diagonal seat belt preset line, and the green line perpendicular to the diagonal seat belt preset line is the median line. The yellow point on the median line is the first circle point.

[0063] Step 130, drawing a first target circle with the first circle point as the center and the length between the first circle point and the start point or the end point in the preset start and end point as the radius.

[0064] Step 140, determining a target region of interest according to the first target circle, the first circle point, and the preset start and end point.

[0065] The target region of interest can be a region representing a safety belt wearing state. By performing image recognition on the target region of interest instead of performing image recognition on the image of the person in the vehicle, the interference of the background on the safety belt wearing detection can be eliminated, for example, the interference of light changes, driver clothes, and the like can be effectively reduced, the misjudgment rate can be reduced, and the stability and reliability of the detection result can be ensured.

[0066] In the embodiment of the application, the target region of interest can be a local region in the first target circle. Specifically, the target region of interest can be an overlapping region of a connecting line formed by the first circle point and the preset start and end point and the first target circle.

[0067] In the embodiment of the application, the target region of interest can be determined in various ways. For example, as shown in FIG. 2, a first region of interest or a first sector region can be determined according to the first target circle, the first circle point, and the preset start and end point, and the first region of interest or the first sector region can be taken as the target region of interest.

[0068] In an optional embodiment of the application, the target region of interest is determined according to the first target circle, the first circle point, and the preset start and end point, including: determining a first arc line formed by the preset start and end point in the first target circle; taking a first region of interest formed by the oblique safety belt preset line and the first arc line as the target region of interest; or determining a first sector region in the first target circle according to the first circle point and the preset start and end point, and taking the first sector region as the target region of interest.

[0069] As shown in FIG. 2, the first arc line can be an orange arc line. Specifically, the first arc line is a short arc line close to the direction of the horizontal safety belt region on the first target circle from the preset start point (safety belt storage point) to the preset end point (safety belt buckle point). For example, in the main driver seat as shown in FIG. 2, the first arc line can be a short arc line close to the lower right in the first target circle and formed by the preset start and end point, that is, the orange arc line. For another example, in the co-driver seat, the first arc line can be a short arc line close to the lower left in the first target circle and formed by the preset start and end point. The length of the first arc line is close to the length when the safety belt is correctly worn.

[0070] The first region of interest can be a closed region formed by the diagonal seat belt preset line and the first arc line. For example, the first region of interest can be the blue region shown in FIG. 2. The first sector region can be a closed region formed by the connection line between the first dot and the preset start and end points, and the first arc line. For example, the first sector region can be the blue region and the purple region shown in FIG. 2.

[0071] In the embodiments of the present application, the first region of interest or the first sector region is used as the target region of interest for image recognition, which can eliminate the interference of the background on the seat belt wearing detection to a certain extent, reduce the misjudgment rate, and ensure the stability and reliability of the detection result. The first region of interest can represent the seat belt wearing state more than the first sector region, and the first region of interest is smaller. Therefore, the first region of interest is used as the target region of interest for image recognition, which has higher recognition reliability and accuracy than the first sector region for image recognition, smaller data processing amount in image recognition, and higher recognition efficiency.

[0072] Step 150: inputting the target region of interest into a preset seat belt wearing classification model to determine whether the person in the vehicle wears a seat belt.

[0073] The preset seat belt wearing classification model can be a classification model designed based on a convolutional neural network. For example, the main structural unit of the preset seat belt wearing classification model is a 3*3 convolutional layer, which realizes down-sampling processing when the step is 2, the feature map size is halved, and the efficient transmission and gradient propagation of information between different layers are realized through residual connection; finally, the feature map is average-pooled and sent to a fully connected layer to obtain a two-dimensional output, which respectively represents the classification probabilities of wearing a seat belt and not wearing a seat belt. The sum of the classification probabilities of wearing a seat belt and not wearing a seat belt is 1. If the probability of wearing a seat belt is less than the probability of not wearing a seat belt, it indicates that the person in the vehicle does not wear a seat belt; otherwise, it indicates that the person in the vehicle wears a seat belt.

[0074] In the embodiments of the present application, the preset seat belt wearing classification model can be generated by training using sample data such as the target region of interest. The sample data can be a kind of labeled data, that is, whether to wear a seat belt can be labeled.

[0075] The above seat belt wearing detection method is not limited to the detection of seat belt wearing in any vehicle or any position in the vehicle, and has high adaptability.

[0076] On the basis of the above-mentioned embodiments, optionally, the method further comprises: when it is determined that the person in the vehicle does not wear a safety belt, performing safety belt wearing abnormality alarm. The abnormality alarm can be audio and / or visual prompt alarm. In the embodiments of the application, the abnormality alarm can be a real-time feedback mechanism, thereby accurately and timely prompting the person in the vehicle to wear a safety belt and ensuring driving safety.

[0077] The technical scheme of the embodiment comprises: acquiring a person-in-vehicle image of a vehicle; determining a diagonal safety belt preset line according to a preset start and end point of a seat safety belt in the person-in-vehicle image, and determining a first circle point on a midline of the diagonal safety belt preset line; drawing a first target circle with the first circle point as a center and a length between the first center and a start point or an end point of the preset start and end point as a radius; determining a target region of interest according to the first target circle, the first circle center and the preset start and end point; and inputting the target region of interest into a preset safety belt wearing classification model to determine whether the person in the vehicle wears a safety belt. The technical scheme solves the detection problem of safety belt wearing, can detect the safety belt wearing condition based on the region of interest, reduces the interference of non-regions of interest on detection, improves detection accuracy, and has good adaptability.

[0078] Embodiment two

[0079] Fig. 3 is a flowchart of a safety belt wearing detection method based on a region of interest according to an embodiment two of the application. The embodiment is a further refinement of the above-mentioned technical scheme, and the technical scheme in the embodiment can be combined with each optional scheme in one or more of the above-mentioned embodiments.

[0080] Specifically, in an optional embodiment of the application, determining a target region of interest according to the first target circle, the first circle center and the preset start and end point comprises: determining a horizontal safety belt preset line according to a preset end point of the seat safety belt in the person-in-vehicle image, and determining a second circle end point on the horizontal safety belt preset line; drawing a second target circle with the preset end point as a center and a length between the preset end point and the second circle end point as a radius; and determining the target region of interest according to the first target circle, the first circle center, the preset start and end point, the second target circle and the second circle end point.

[0081] As shown in Fig. 3, the method comprises:

[0082] Step 310: acquiring a person-in-vehicle image of a vehicle.

[0083] Step 320: determining a diagonal safety belt preset line according to a preset start and end point of a seat safety belt in the person-in-vehicle image, and determining a first circle point on a midline of the diagonal safety belt preset line.

[0084] Step 330, draw a first target circle with the first circle center as the center and the length between the first circle center and the starting point or the ending point in the preset starting and ending points as the radius.

[0085] Step 340, determine a horizontal seat belt preset line according to the preset ending point of the seat belt in the image of the person in the vehicle, and determine a second circle endpoint on the horizontal seat belt preset line.

[0086] Among them, according to the direction of the seat belt, the horizontal seat belt preset line is obtained by extending horizontally from the preset ending point of the seat belt. For example, when detecting the seat belt wearing of the driver, the horizontal seat belt preset line can be obtained by extending horizontally to the right from the preset ending point of the seat belt. Or, when detecting the seat belt wearing of the co-driver, the horizontal seat belt preset line can be obtained by extending horizontally to the left from the preset ending point of the seat belt. The second circle endpoint can be selected on the horizontal seat belt preset line. For example, the second circle endpoint can be determined at a certain distance from the preset ending point on the horizontal seat belt preset line. For example, the distance from the preset ending point to the shoulder position of the person in the vehicle close to the preset starting point can be taken as a reference distance. The second circle endpoint can be determined at the reference distance interval along the horizontal seat belt direction on the horizontal seat belt preset line from the preset ending point.

[0087] In an optional embodiment of the embodiment of the present application, the second circle endpoint on the horizontal seat belt preset line comprises: determining the intersection of the horizontal seat belt preset line and the seat preset boundary vertical line as the second circle endpoint.

[0088] Fig. 4 is a schematic diagram of determining a target region of interest according to the second embodiment of the present application. As shown in Fig. 4, the blue horizontal line is the horizontal seat belt preset line, and the green point on the horizontal seat belt preset line is the second circle endpoint. As shown in Fig. 4, when detecting the seat belt wearing of the driver seat, the seat preset boundary vertical line can be the right side door inner boundary vertical line, that is, the second circle endpoint can be the intersection of the horizontal seat belt and the right side door. When detecting the seat belt wearing of the co-driver seat, the seat preset boundary vertical line can be the left side door inner boundary vertical line, that is, the second circle endpoint can be the intersection of the horizontal seat belt and the left side door. When detecting the seat belt wearing of the middle position of the rear row, the second circle endpoint can be the intersection of the horizontal seat belt and the seat preset boundary vertical line in the vertical direction of the seat belt preset starting point. When detecting the seat belt wearing of other positions of the rear row, the determination method of the second circle endpoint can refer to the driver seat and the co-driver seat, which will not be described here.

[0089] Step 350, draw a second target circle with the preset ending point as the center and the length between the preset ending point and the second circle endpoint as the radius.

[0090] Step 360, determining a target region of interest according to the first target circle, the first circle center, the preset start and end point, the second target circle, and the second circle end point.

[0091] The target region of interest can be determined according to the first target circle, the first circle center, and the preset start and end point, or the first region of interest or the first fan-shaped region.

[0092] For example, the second fan-shaped region can be determined according to the second target circle and the second circle end point, and the overlapping region of the second fan-shaped region and the first region of interest or the first fan-shaped region can be used as the target region of interest. The second target circle and the second circle end point can further reduce the region of interest determined according to the first target circle, the first circle center, and the preset start and end point, thereby further avoiding the influence of the background on the safety belt wearing detection and improving the detection accuracy.

[0093] In an optional embodiment of the present application, the target region of interest is determined according to the first target circle, the first circle center, the preset start and end point, the second target circle, and the second circle end point, including: determining the first region of interest or the first fan-shaped region according to the first target circle, the first circle center, and the preset start and end point; determining the second fan-shaped region according to the second target circle, the preset end point, the second circle end point, and the intersection of the second target circle and the diagonal safety belt preset line; and taking the second region of interest formed by the overlapping of the first region of interest or the first fan-shaped region and the second fan-shaped region as the target region of interest.

[0094] The first region of interest or the first fan-shaped region is determined according to the first target circle, the first circle center, and the preset start and end point, including: determining a first arc line formed by the preset start and end point in the first target circle; taking the first region of interest formed by the diagonal safety belt preset line and the first arc line as the target region of interest; or determining the first fan-shaped region in the first target circle according to the first circle point and the preset start and end point, and taking the first fan-shaped region as the target region of interest.

[0095] In the present application, the second fan-shaped region is a closed region formed by the connection line of the preset end point and the second circle end point, the diagonal safety belt preset line, and the second target circle. The second fan-shaped region can represent the safety belt wearing condition. As shown in FIG. 4, the second fan-shaped region can be a closed region formed by the red diagonal safety belt preset line, the blue transverse safety belt preset line, and the second target circle (purple arc line).

[0096] As shown in FIG. 4, the first region of interest or the first sector region, and the second region of interest formed by the overlap of the second sector region, can be a yellow region.

[0097] The target region of interest determined in the above manner can best represent the seat belt wearing condition, and avoid the influence of the existence of the seat belt in the first region of interest or the first sector region on the seat belt wearing detection due to the suspension of the seat belt even if it is not worn. The second region of interest can effectively filter the area above the shoulders of the vehicle occupant, reduce the misclassification probability, and make the target region of interest more targeted.

[0098] Step 370: inputting the target region of interest into a preset seat belt wearing classification model to determine whether the vehicle occupant wears a seat belt.

[0099] Step 380: when it is determined that the vehicle occupant does not wear a seat belt, performing a seat belt wearing abnormality alarm.

[0100] The technical scheme of the embodiment of the present application comprises the following steps: obtaining a vehicle occupant image of a vehicle; determining a diagonal seat belt preset line according to a preset start and end point of a seat belt in the vehicle occupant image, and determining a first circular point on the perpendicular bisector of the diagonal seat belt preset line; drawing a first target circle with the first circular point as the center and the length between the first circular point and the start point or the end point of the preset start and end point as the radius; determining a horizontal seat belt preset line according to the preset end point of the seat belt in the vehicle occupant image, and determining a second circular end point on the horizontal seat belt preset line; drawing a second target circle with the preset end point as the center and the length between the preset end point and the second circular end point as the radius; determining a target region of interest according to the first target circle, the first circular point, the preset start and end point, the second target circle, and the second circular end point; determining a target region of interest according to the first target circle, the first circular point, the preset start and end point, the second target circle, and the second circular end point; when it is determined that the vehicle occupant does not wear a seat belt, performing a seat belt wearing abnormality alarm, thereby solving the problem of seat belt wearing detection, and enabling the seat belt wearing condition to be detected based on the region of interest, reducing the interference of non-interest regions on detection, improving detection accuracy, and having good adaptability; the driver can be prompted to adjust in time when the driver does not wear a seat belt, thereby improving driving safety; and the development and application of intelligent driving technology are promoted, and support is provided for future intelligent traffic construction.

[0101] In the technical scheme of the embodiment of the present application, the acquisition, storage, and application of user personal information (such as the vehicle occupant image) comply with relevant legal regulations and do not violate public order and good customs.

[0102] Embodiment three

[0103] Fig. 5 is a structural schematic diagram of a seat belt wearing detection device based on a region of interest according to Embodiment Three of the present application. As shown in Fig. 5, the device comprises an in-vehicle personnel image acquisition module 510, a first circle point determination module 520, a first target circle drawing module 530, a target region of interest determination module 540, and a seat belt wearing detection module 550. Wherein:

[0104] The in-vehicle personnel image acquisition module 510 is configured to acquire an in-vehicle personnel image of a vehicle.

[0105] The first circle point determination module 520 is configured to determine a diagonal seat belt preset line according to a preset start and end point of a seat belt in the in-vehicle personnel image, and determine a first circle point on a perpendicular line of the diagonal seat belt preset line.

[0106] The first target circle drawing module 530 is configured to draw a first target circle with the first circle point as the center and a length between the first circle point and a start point or an end point of the preset start and end point as the radius.

[0107] The target region of interest determination module 540 is configured to determine a target region of interest according to the first target circle, the first circle point, and the preset start and end point.

[0108] The seat belt wearing detection module 550 is configured to input the target region of interest into a preset seat belt wearing classification model to determine whether the in-vehicle personnel wears a seat belt.

[0109] Optionally, the target region of interest determination module 540 comprises:

[0110] A first arc line determination unit is configured to determine a first arc line composed of the preset start and end point in the first target circle.

[0111] A target region of interest determination unit is configured to take a first region of interest composed of the diagonal seat belt preset line and the first arc line as the target region of interest; or

[0112] A first fan-shaped region determination unit is configured to determine a first fan-shaped region in the first target circle according to the first circle point and the preset start and end point, and take the first fan-shaped region as the target region of interest.

[0113] Optionally, the target region of interest determination module 540 comprises:

[0114] A second circle point determination unit is configured to determine a horizontal seat belt preset line according to a preset end point of the seat belt in the in-vehicle personnel image, and determine a second circle point on the horizontal seat belt preset line.

[0115] A second target circle drawing unit is configured to draw a second target circle with the preset end point as the center and a length between the preset end point and the second circle point as the radius.

[0116] A target region of interest determination unit is configured to determine a target region of interest according to the first target circle, the first circle center, the preset start and end points, the second target circle, and the second circle end point.

[0117] Optionally, the target region of interest determination unit is specifically configured to:

[0118] determine a first region of interest or a first sector region according to the first target circle, the first circle center, and the preset start and end points;

[0119] determine a second sector region according to the second target circle, the preset end point, the second circle end point, and the intersection of the second target circle and the diagonal safety belt preset line;

[0120] determine a second region of interest by overlapping the first region of interest or the first sector region and the second sector region, and take the second region of interest as the target region of interest.

[0121] Optionally, the first circle point determination module 520 comprises:

[0122] A first circle point determination unit is configured to determine a point with a distance of half the length of the diagonal safety belt preset line from the diagonal safety belt preset line as the first circle point on the perpendicular bisector of the diagonal safety belt preset line.

[0123] Optionally, the second circle end point determination unit comprises:

[0124] A second circle end point determination subunit is configured to determine the intersection of the transverse safety belt preset line and the seat preset boundary perpendicular line as the second circle end point.

[0125] Optionally, the device further comprises:

[0126] An abnormality alarm module is configured to perform safety belt wearing abnormality alarm when it is determined that the person in the vehicle is not wearing a safety belt.

[0127] The safety belt wearing detection device based on the region of interest provided in the embodiments of the present application can perform the safety belt wearing detection method based on the region of interest provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0128] Embodiment Four

[0129] FIG. 6 shows a structural diagram of an electronic device 10 that can be used to implement embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0130] As shown in FIG. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0132] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the region-of-interest based safety belt wearing detection method.

[0133] In some embodiments, the region-of-interest based seat belt wearing detection method can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, parts or all of the computer program can be loaded and / or installed onto electronic device 10 via, e.g., ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the region-of-interest based seat belt wearing detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the region-of-interest based seat belt wearing detection method by other any suitable means, e.g., by way of firmware.

[0134] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0135] Computer programs used to implement the processes of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program running on the processor implements the functions / operations specified in the flowcharts and / or the block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as part of a standalone software package, or entirely on a remote machine or server.

[0136] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, 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.

[0137] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0138] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0139] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0140] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0141] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A region of interest based seat belt wearing detection method, characterized in that, The method comprises the following steps: acquiring an in-vehicle personnel image of a vehicle; determining a diagonal seat belt preset line according to a preset start and end point of a seat belt in the in-vehicle personnel image, and determining a first circle point on a midline of the diagonal seat belt preset line; drawing a first target circle with the first circle point as the center and a length between the first circle point and a start point or an end point of the preset start and end point as the radius; determining a target region of interest according to the first target circle, the first circle point, and the preset start and end point; inputting the target region of interest into a preset seat belt wearing classification model to determine whether the in-vehicle personnel wears a seat belt.

2. The method of claim 1, wherein, The method for determining the target region of interest according to the first target circle, the first circle point, and the preset start and end point comprises the following steps: determining a first arc line constituted by the preset start and end point in the first target circle; taking a first region of interest constituted by the diagonal seat belt preset line and the first arc line as the target region of interest; or determining a first sector region in the first target circle according to the first circle point and the preset start and end point, and taking the first sector region as the target region of interest.

3. The method of claim 1, wherein, The method for determining the target region of interest according to the first target circle, the first circle point, and the preset start and end point comprises the following steps: determining a horizontal seat belt preset line according to a preset end point of a seat belt in the in-vehicle personnel image, and determining a second circle end point on the horizontal seat belt preset line; drawing a second target circle with the preset end point as the center and a length between the preset end point and the second circle end point as the radius; determining the target region of interest according to the first target circle, the first circle point, the preset start and end point, the second target circle, and the second circle end point.

4. The method of claim 3, wherein, The method for determining the target region of interest according to the first target circle, the first circle point, the preset start and end point, the second target circle, and the second circle end point comprises the following steps: determining a first region of interest or a first sector region according to the first target circle, the first circle point, and the preset start and end point; determining a second sector region according to a second target circle, the preset end point, the second circle end point, and an intersection point of the second target circle and the diagonal seat belt preset line; taking a second region of interest constituted by overlapping the first region of interest or the first sector region and the second sector region as the target region of interest.

5. The method according to claim 3, wherein the method for determining the diagonal seat belt preset line according to the preset start and end point of the seat belt in the in-vehicle personnel image and determining the first circle point on the midline of the diagonal seat belt preset line comprises the following steps: determining a point with a distance of half the length of the diagonal seat belt preset line from the diagonal seat belt preset line as the first circle point on the midline of the diagonal seat belt preset line; the method for determining the second circle end point on the horizontal seat belt preset line comprises the following steps: determining the intersection point of the horizontal seat belt preset line and the seat preset boundary perpendicular line as the second circle end point.

6. The method of claim 1, wherein, The method further comprises the following steps: when it is determined that the in-vehicle personnel does not wear a seat belt, performing a seat belt wearing abnormality alarm.

7. A region of interest based seat belt wearing detection apparatus characterized by, The method comprises the following steps: An in-vehicle personnel image acquisition module is configured to acquire an in-vehicle personnel image of a vehicle. A first circle point determination module is configured to determine a diagonal seat belt preset line according to a preset start and end point of a seat belt in the in-vehicle personnel image, and determine a first circle point on a perpendicular bisector of the diagonal seat belt preset line. A first target circle drawing module is configured to draw a first target circle with the first circle point as a center and a length between the first circle point and a start point or an end point of the preset start and end point as a radius. A target region of interest determination module is configured to determine a target region of interest according to the first target circle, the first circle point, and the preset start and end point. A seat belt wearing detection module is configured to input the target region of interest into a preset seat belt wearing classification model to determine whether an in-vehicle personnel wears a seat belt.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the region of interest based seat belt wearing detection method in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the region of interest based seat belt wearing detection method in any one of claims 1-6 when executed by the processor.

10. A computer program product comprising a computer program which, when executed by a processor, implements the region of interest based seat belt wearing detection method according to any one of claims 1-6.

Images