A seat belt wearing posture detection method, device, equipment and storage medium

Abstract

Embodiments of the present application disclose a safety belt wearing posture detection method, device, equipment and storage medium. The method comprises: acquiring an image of a person in a vehicle, and performing image segmentation on the image of the person in the vehicle to obtain a safety belt region in the image of the person in the vehicle; performing key point detection on the image of the person in the vehicle to obtain a key point region composed of key points; and determining whether the person in the vehicle wears a safety belt according to the safety belt region and the key point region; when it is determined that the person in the vehicle wears a safety belt, determining a first key point sub-region and a second key point sub-region formed by dividing the safety belt region in the key point region according to the safety belt region and the key point region; and determining whether the safety belt wearing posture of the person in the vehicle is correct according to the first key point sub-region and the second key point sub-region. The safety belt wearing situation is detected through the safety belt region and the key point region, so that the detection efficiency can be improved on the basis of ensuring the detection accuracy.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, device, and storage medium for detecting seat belt wearing posture. Background Technology

[0002] Wearing a seatbelt while driving can provide protection for occupants in emergency situations and reduce the risk of injury in an accident.

[0003] In current technology, seatbelt wearing checks typically only determine if the seatbelt is fastened, lacking assessment of the wearing posture. Incorrect seatbelt wearing posture can reduce its protective effect during an accident, increasing the risk of injury to the driver and passengers. Therefore, it is necessary to check seatbelt wearing posture. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for detecting seat belt wearing posture, thereby ensuring detection accuracy and improving detection efficiency.

[0005] According to one aspect of the present invention, a method for detecting seat belt wearing posture is provided, the method comprising:

[0006] Acquire images of occupants inside the vehicle, and perform image segmentation on the images to obtain the seatbelt area within the images of the occupants inside the vehicle;

[0007] Key point detection is performed on the image of the occupants in the vehicle to obtain a key point region composed of key points; and based on the seat belt region and the key point region, it is determined whether the occupants are wearing seat belts.

[0008] When determining that the occupants of the vehicle are wearing seat belts, a first key point sub-region and a second key point region are determined in the key point region by dividing the area through the seat belt region, based on the seat belt region and the key point region.

[0009] Based on the first key point sub-region and the second key point sub-region, determine whether the seat belt wearing posture of the occupants in the vehicle is correct.

[0010] Optionally, determining whether the seatbelt wearing posture of the vehicle occupants is correct based on the first key point sub-region and the second key point sub-region includes:

[0011] Based on the area values ​​of the first key point sub-region and the second key point sub-region, determine whether the seat belt wearing posture of the occupants in the vehicle is correct.

[0012] Optionally, determining whether the seatbelt wearing posture of the vehicle occupants is correct based on the area values ​​of the first key point sub-region and the second key point sub-region includes:

[0013] Based on the area values ​​of the first key point sub-region and the second key point sub-region, the area ratio between the first key point sub-region and the second key point sub-region;

[0014] When the area ratio is within a preset range, it is determined that the seat belt wearing posture of the occupants in the vehicle is correct;

[0015] Otherwise, it is determined that the seat belt wearing posture of the occupants in the vehicle is incorrect.

[0016] Optionally, the preset ratio range is the interval [0.5, 2].

[0017] Optionally, determining whether vehicle occupants are wearing seat belts based on the seat belt area and the key point area includes:

[0018] Based on the area values ​​of the seat belt area and the key point area, it is determined whether the occupants are wearing seat belts.

[0019] Optionally, determining whether vehicle occupants are wearing seat belts based on the area values ​​of the seat belt area and the key point area includes:

[0020] Based on the area values ​​of the seat belt area and the key point area, determine the area ratio of the seat belt area in the key point area;

[0021] When the area ratio is less than a preset ratio threshold, it is determined that the occupants of the vehicle are not wearing seat belts;

[0022] Otherwise, ensure that all occupants are wearing seatbelts.

[0023] Optionally, key point detection is performed on the image of the people inside the vehicle to obtain a key point region composed of key points, including:

[0024] The torso in the image of the person inside the vehicle is subjected to key point detection, including the neck, left shoulder, right shoulder, left thigh, and right thigh, to obtain a key point region in the shape of a pentagon composed of key points.

[0025] According to another aspect of the present invention, a seatbelt wearing posture detection device is provided, the device comprising:

[0026] The seat belt area determination module is used to acquire images of occupants inside the vehicle and perform image segmentation on the images of occupants inside the vehicle to obtain the seat belt area in the images of occupants inside the vehicle.

[0027] The seatbelt wearing detection module is used to perform key point detection on the image of the occupants in the vehicle to obtain a key point region composed of key points; and to determine whether the occupants are wearing seatbelts based on the seatbelt region and the key point region.

[0028] The key point sub-region determination module is used to determine, when it is determined that the occupant is wearing a seat belt, a first key point sub-region and a second key point region formed by dividing the key point region through the seat belt region, based on the seat belt region and the key point region.

[0029] The seatbelt wearing posture detection module is used to determine whether the seatbelt wearing posture of the occupants in the vehicle is correct based on the first key point sub-region and the second key point sub-region.

[0030] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0031] At least one processor; and

[0032] A memory communicatively connected to the at least one processor; wherein,

[0033] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the seat belt wearing posture detection method according to any embodiment of the present invention.

[0034] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the seat belt wearing posture detection method according to any embodiment of the present invention.

[0035] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the seatbelt wearing posture detection method according to any embodiment of the present invention.

[0036] The technical solution of this invention acquires an image of a person inside a vehicle and performs image segmentation to obtain a seat belt region within the image. It then performs key point detection on the image to obtain a key point region composed of key points. Based on the seat belt region and the key point region, it determines whether the person inside the vehicle is wearing a seat belt. When determining that the person is wearing a seat belt, it determines a first key point sub-region and a second key point sub-region within the key point region, formed by dividing the area based on the seat belt region. Based on the first and second key point regions, it determines whether the person's seat belt wearing posture is correct. This solves the problem of seat belt wearing posture detection. By detecting seat belt wearing status through the seat belt region and the key point region, it improves detection efficiency while ensuring detection accuracy.

[0037] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a flowchart of a seatbelt wearing posture detection method according to Embodiment 1 of the present invention;

[0040] Figure 2 This is a schematic diagram of seat belt segmentation and key point detection according to Embodiment 1 of the present invention;

[0041] Figure 3 This is a schematic diagram of a key point sub-region provided in Embodiment 1 of the present invention;

[0042] Figure 4 This is a flowchart of a seatbelt wearing posture detection method according to Embodiment 2 of the present invention;

[0043] Figure 5 This is a schematic diagram of the structure of a seat belt wearing posture detection device according to Embodiment 3 of the present invention;

[0044] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the seat belt wearing posture detection method of the present invention. Detailed Implementation

[0045] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0046] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0047] Example 1

[0048] Figure 1 This is a flowchart of a seatbelt wearing posture detection method according to Embodiment 1 of the present invention. This embodiment is applicable to detecting the seatbelt wearing posture of occupants in a vehicle. The method can be executed by a seatbelt wearing posture detection device, which can be implemented in hardware and / or software. This seatbelt wearing posture detection device can be configured in electronic devices such as vehicle controllers or vehicle processors. Figure 1 As shown, the method includes:

[0049] Step 110: Obtain images of people inside the vehicle and perform image segmentation on the images to obtain the seat belt area in the images of people inside the vehicle.

[0050] In this embodiment of the invention, the in-vehicle occupant image can be an image of the driver or passenger inside the vehicle. The in-vehicle occupant image may include images of the upper body and abdominal area of ​​the occupant. The in-vehicle occupant image can be captured by a camera, video recorder, or other imaging device. Specifically, to improve the accuracy of seatbelt wearing detection, an imaging device with a resolution greater than a preset value can be used to capture real-time images of occupants inside the vehicle. For example, if detecting the seatbelt wearing status of the driver or front passenger, the imaging device can be installed on the vehicle's dashboard or A-pillar. If detecting the seatbelt wearing status of rear-seat occupants, the imaging device can be installed on the B-pillar or interior roof. The specific number of imaging devices can be adjusted according to the actual seatbelt wearing detection requirements.

[0051] To further improve the accuracy of seatbelt wearing posture detection in different environments, a camera with adaptive exposure adjustment can be used. This adaptive exposure adjustment allows the camera to capture clear images of occupants under various lighting conditions, such as sunlight, shadows, or nighttime, thereby improving the accuracy of seatbelt wearing posture detection.

[0052] Before performing image segmentation on the images of occupants inside the vehicle, preprocessing operations can be performed. These preprocessing operations include, but are not limited to, image denoising, brightness adjustment, and contrast enhancement. Image preprocessing improves image quality, providing a more accurate visual basis for seatbelt wearing posture detection.

[0053] Image segmentation of an image of occupants inside a vehicle can be achieved by separating the seatbelt from the background. Specifically, image segmentation can involve identifying a diagonal region of the seatbelt within the image of the occupants. For example, Figure 2 This is a schematic diagram of seat belt segmentation and key point detection according to Embodiment 1 of the present invention. Figure 2 As shown, the green safety belt area is the diagonal safety belt area obtained by image segmentation.

[0054] In this embodiment of the invention, the image segmentation method is not specifically limited. For example, the seat belt can be segmented from the image using a deep learning model or traditional image processing methods. For instance, the seat belt region can be segmented by training a semantic segmentation model such as HRNet. The segmentation accuracy of the seat belt region can be at the pixel level. Image segmentation using a deep learning model can consider various body types, improving the accuracy of seat belt segmentation and thus enhancing the applicability and robustness of seat belt wearing posture detection.

[0055] Before training the semantic segmentation model, images of occupants inside the vehicle can be collected and annotated to generate training samples for the semantic segmentation model. Image annotation can involve labeling the diagonal seatbelt region and the background in the occupant image. For example, the diagonal seatbelt region and the background can be labeled as 1 and 0, respectively. In this embodiment of the invention, image annotation can employ advanced image processing or deep learning techniques to accurately segment and identify the diagonally worn seatbelt and the background. Seatbelt region segmentation provides a basis for determining the seatbelt wearing status and the correctness of the posture.

[0056] In some specific applications, image segmentation of images of people inside a vehicle can be performed by segmenting the lateral seat belt region in addition to the segmentation of the diagonal seat belt region.

[0057] Step 120: Perform key point detection on the image of the people inside the vehicle to obtain the key point region composed of key points; and determine whether the people inside the vehicle are wearing seat belts based on the seat belt region and the key point region.

[0058] Keypoint detection can be implemented using a keypoint detection model. For example, a keypoint detection model could be CenterNet. Keypoints include, but are not limited to, the neck, left shoulder, right shoulder, left thigh, and right thigh of an occupant inside the vehicle. Figure 2 As shown, the area enclosed by the yellow line is the critical point region. Obtaining the critical point region through critical point detection provides a basis for seat belt wearing posture detection, improving the accuracy of seat belt wearing posture detection.

[0059] Before performing keypoint detection, images of occupants inside the vehicle can be acquired and annotated to generate training samples for the keypoint detection model. Image annotation involves marking key points of the occupants in the images, such as the neck, left shoulder, right shoulder, left thigh, and right thigh. In this embodiment of the invention, advanced keypoint detection technology can be employed through image annotation to accurately detect key points of the occupants and determine keypoint regions. Keypoint detection provides a basis for determining the seatbelt wearing status and the correctness of posture.

[0060] Specifically, in an optional embodiment of the present invention, key point detection is performed on the image of people inside the vehicle to obtain a key point region composed of key points. This includes: performing key point detection on the torso of the people inside the vehicle image, including the neck, left shoulder, right shoulder, left thigh, and right thigh, to obtain a key point region composed of key points in a pentagonal shape. Figure 2 The key point area shown can describe the body posture of the people inside the vehicle.

[0061] Determining whether vehicle occupants are wearing seat belts can be based on the seat belt area and key point area, which can involve judging the position and / or proportion of the seat belt area within the key point area. For example, if the position of the seat belt area within the key point area meets preset position conditions, and / or if the proportion of the seat belt area within the key point area meets preset proportion conditions, it can be determined that the vehicle occupants are wearing seat belts. Otherwise, it is determined that the vehicle occupants are not wearing seat belts.

[0062] In an optional embodiment of the present invention, determining whether the occupants are wearing seat belts based on the seat belt area and the key point area includes: determining whether the occupants are wearing seat belts based on the area values ​​of the seat belt area and the key point area.

[0063] The inventors discovered that in practical applications, when a person wears a seatbelt correctly, the seatbelt typically covers a certain area of ​​the person's body. However, when a person does not wear a seatbelt correctly, the area of ​​the person's body may not be covered by the seatbelt, or the coverage area may be small. Based on the above considerations, in this embodiment of the invention, whether the occupant is wearing a seatbelt can be determined by the area value between the seatbelt area and the key point area. For example, if the ratio or difference between the areas of the seatbelt area and the key point area meets a corresponding preset area condition, it can be determined that the occupant is wearing a seatbelt. Otherwise, it is determined that the occupant is not wearing a seatbelt.

[0064] Furthermore, in an optional embodiment of the present invention, determining whether the occupants are wearing seat belts based on the area values ​​of the seat belt area and the critical point area includes: determining the area ratio of the seat belt area in the critical point area based on the area values ​​of the seat belt area and the critical point area; when the area ratio is less than a preset ratio threshold, determining that the occupants are not wearing seat belts; otherwise, determining that the occupants are wearing seat belts.

[0065] The preset percentage threshold can be any value within the range [15%, 30%]. Optionally, the preset percentage threshold is 20%. The technical solution of this invention determines whether a person is wearing a seatbelt by the percentage of the seatbelt area within the pentagon of the person's body, thus conveniently and accurately detecting whether a person is wearing a seatbelt.

[0066] It should be noted that, to improve the accuracy of seatbelt wearing detection, when using area ratio for detection, the ratio is the ratio of the area of ​​the seatbelt region within the critical point area to the area of ​​the critical point area. Seatbelt areas outside the critical point area are not included in the area ratio calculation. The calculation method for the area value is not specifically limited in this embodiment of the invention.

[0067] Step 130: When determining that the occupants are wearing seat belts, determine the first critical point sub-region and the second critical point sub-region in the critical point region by dividing the area through the seat belt region, based on the seat belt area and the critical point area.

[0068] Figure 3 This is a schematic diagram of a key point sub-region provided according to Embodiment 1 of the present invention. For example... Figure 3 As shown, the seat belt area can divide the critical point area into two parts, which are respectively defined as the first critical point sub-area and the second critical point sub-area.

[0069] Step 140: Determine whether the seat belt wearing posture of the occupants is correct based on the first key point area and the second key point area.

[0070] The inventors' research on actual seatbelt wearing revealed that when a person wears a seatbelt correctly, the seatbelt smoothly covers the person's body, and the first and second critical point sub-regions defined by the seatbelt meet certain balance conditions. In this invention, the correctness of the seatbelt wearing posture can be determined based on the relationship between the first and second critical point regions. For example, the correctness of the seatbelt wearing posture can be determined by whether one or more of the area ratio, perimeter, or shape of the first and second critical point regions meet the corresponding balance conditions.

[0071] The technical solution of this embodiment acquires images of occupants inside the vehicle and performs image segmentation to obtain the seat belt region within the occupant image; it then performs key point detection on the occupant image to obtain a key point region composed of key points; based on the seat belt region and the key point region, it determines whether the occupants are wearing seat belts; when determining whether the occupants are wearing seat belts, it determines a first key point sub-region and a second key point sub-region within the key point region, formed by dividing the seat belt region, based on the seat belt region and the key point region; based on the first key point region and the second key point region, it determines whether the occupants' seat belt wearing posture is correct. This solves the problem of seat belt wearing posture detection. By detecting seat belt wearing status through the seat belt region and the key point region, it can improve detection efficiency while ensuring detection accuracy.

[0072] Example 2

[0073] Figure 4 This is a flowchart of a seat belt wearing posture detection method according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0074] Specifically, in an optional embodiment of the present invention, determining whether the seat belt wearing posture of the occupants is correct based on the first key point sub-region and the second key point sub-region includes: determining whether the seat belt wearing posture of the occupants is correct based on the area values ​​of the first key point sub-region and the second key point sub-region.

[0075] like Figure 4 As shown, the method includes:

[0076] Step 210: Obtain images of people inside the vehicle and perform image segmentation on the images of people inside the vehicle to obtain the seat belt area in the images of people inside the vehicle.

[0077] Step 220: Perform key point detection on the image of people inside the vehicle to obtain the key point region composed of key points.

[0078] In an optional embodiment of the present invention, key point detection is performed on the image of the person inside the vehicle to obtain a key point region composed of key points, including: key point detection of the torso in the image of the person inside the vehicle, including the neck, left shoulder, right shoulder, left thigh, and right thigh, to obtain a key point region composed of key points in a pentagonal shape.

[0079] Step 230: Determine whether the occupants are wearing seat belts based on the seat belt area and key point area.

[0080] In an optional embodiment of the present invention, determining whether the occupants are wearing seat belts based on the seat belt area and the key point area includes: determining whether the occupants are wearing seat belts based on the area values ​​of the seat belt area and the key point area.

[0081] In an optional embodiment of the present invention, determining whether the occupants are wearing seat belts based on the area values ​​of the seat belt area and the critical point area includes: determining the area ratio of the seat belt area in the critical point area based on the area values ​​of the seat belt area and the critical point area; when the area ratio is less than a preset ratio threshold, determining that the occupants are not wearing seat belts; otherwise, determining that the occupants are wearing seat belts.

[0082] Optional, the preset percentage threshold is 20%.

[0083] Step 240: When determining that the occupants are wearing seat belts, determine the first critical point sub-region and the second critical point sub-region in the critical point region by dividing the area through the seat belt region, based on the seat belt region and the critical point region.

[0084] Step 250: Determine whether the seat belt wearing posture of the occupants is correct based on the area values ​​of the first key point sub-region and the second key point sub-region.

[0085] To ensure the accuracy of seatbelt wearing posture detection, the area values ​​of the first and second key point regions can be used to determine whether the occupant's seatbelt wearing posture is correct. There are several ways to determine the correctness of the seatbelt wearing posture using the area values ​​of the first and second key point regions. For example, the ratio or difference between the areas of the first and second key point regions can be used to determine whether the occupant's seatbelt wearing posture is correct.

[0086] In an optional embodiment of the present invention, determining whether the seat belt wearing posture of the occupants is correct based on the area values ​​of the first key point region and the second key point region includes: determining the area ratio between the first key point region and the second key point region based on the area values ​​of the first key point region and the second key point region; determining that the seat belt wearing posture of the occupants is correct when the area ratio is within a preset ratio range; otherwise, determining that the seat belt wearing posture of the occupants is incorrect.

[0087] In their practical research, the inventors discovered that the ideal condition for wearing a seatbelt is that the areas of the first critical point region and the second critical point region are relatively uniform, that is, the ratio of their areas is close to 1:1. Incorrect seatbelt wearing, such as when the seatbelt is loose, hung behind the shoulder, or other incorrect wearing methods, will cause a shift in the area ratio between the first and second critical point regions. For example, if the seatbelt is concentrated too much at the top or too much at the bottom, it may lead to an imbalance in the area ratio. Therefore, in this embodiment of the invention, a preset ratio range can be set according to the above conditions.

[0088] Considering the influence of various factors on seat belt wearing, such as different body types of people, in order to ensure the accuracy of seat belt wearing posture detection, in an optional embodiment of the present invention, the preset ratio range is [0.5, 2].

[0089] Specifically, in practical applications, if the ratio of the smaller area value to the larger area value in the first critical point sub-region and the second critical point sub-region is less than 0.5, the seat belt wearing posture is determined to be incorrect; otherwise, the seat belt wearing posture is determined to be correct.

[0090] Based on the above embodiments, optionally, the method further includes: issuing a seatbelt wearing abnormality alarm when a seatbelt is not worn or the seatbelt wearing posture is incorrect. The abnormality alarm can be an audio and / or visual cue alarm. In this embodiment of the invention, the abnormality alarm can be a real-time feedback mechanism, thereby accurately and promptly prompting vehicle occupants to wear the seatbelt in the correct posture, ensuring driving safety.

[0091] The technical solution of this invention acquires an image of a person inside a vehicle and performs image segmentation to obtain a seat belt region within the image. Key point detection is then performed on the image to obtain a key point region composed of key points. Based on the seat belt region and the key point region, it is determined whether the person inside the vehicle is wearing a seat belt. When determining whether the person is wearing a seat belt, a first key point sub-region and a second key point sub-region are determined within the key point region, formed by dividing the seat belt region. Based on the area values ​​of the first and second key point regions, it is determined whether the person's seat belt wearing posture is correct. This solves the problem of seat belt wearing posture detection. By detecting seat belt wearing status through the seat belt region and the key point region, a comprehensive judgment of seat belt wearing status can be achieved, improving detection efficiency while ensuring detection accuracy. It also reduces the possibility of false positives and false negatives, and can promptly detect incorrect seat belt wearing postures.

[0092] In the technical solutions of this invention, the acquisition, storage, and application of user personal information (such as images of people inside the vehicle) comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0093] Example 3

[0094] Figure 5 This is a structural schematic diagram of a seatbelt wearing posture detection device according to Embodiment 3 of the present invention. Figure 5 As shown, the device includes: a seatbelt area determination module 510, a seatbelt wearing detection module 520, a key point sub-area determination module 530, and a seatbelt wearing posture detection module 540. Wherein:

[0095] The seat belt area determination module 510 is used to acquire images of occupants inside the vehicle and perform image segmentation on the images of occupants inside the vehicle to obtain the seat belt area in the images of occupants inside the vehicle.

[0096] The seat belt wearing detection module 520 is used to perform key point detection on images of people inside the vehicle to obtain a key point region composed of key points; and to determine whether people inside the vehicle are wearing seat belts based on the seat belt region and the key point region.

[0097] The key point sub-region determination module 530 is used to determine, when determining that the occupants are wearing seat belts, the first key point sub-region and the second key point region formed by dividing the key point region through the seat belt region, based on the seat belt region and the key point region.

[0098] The seatbelt wearing posture detection module 540 is used to determine whether the seatbelt wearing posture of the occupants in the vehicle is correct based on the first key point sub-region and the second key point sub-region.

[0099] Optional, the seatbelt wearing posture detection module 540 includes:

[0100] The seatbelt wearing posture detection unit is used to determine whether the seatbelt wearing posture of the occupants in the vehicle is correct based on the area values ​​of the first key point sub-region and the second key point sub-region.

[0101] Optional, the seatbelt wearing posture detection unit includes:

[0102] The area ratio determination sub-unit is used to determine the area ratio between the first key point sub-region and the second key point sub-region based on the area values ​​of the first key point sub-region and the second key point sub-region.

[0103] The seatbelt wearing posture detection subunit is used to determine that the seatbelt wearing posture of the occupants is correct when the area ratio is within a preset range; otherwise, it is determined that the seatbelt wearing posture of the occupants is incorrect.

[0104] Optionally, the preset ratio range is [0.5, 2].

[0105] Optional, the seatbelt wearing detection module 520 includes:

[0106] The seatbelt wearing detection unit is used to determine whether the occupants are wearing seatbelts based on the area values ​​of the seatbelt area and the key point area.

[0107] Optional, the seatbelt wearing detection unit includes:

[0108] The area proportion determination sub-unit is used to determine the area proportion of the seat belt area in the critical point area based on the area values ​​of the seat belt area and the critical point area.

[0109] The seatbelt wearing detection subunit is used to determine that the occupants are not wearing seatbelts when the area ratio is less than a preset ratio threshold; otherwise, it determines that the occupants are wearing seatbelts.

[0110] Optional, the seatbelt wearing detection module 520 includes:

[0111] The key point region determination unit is used to detect key points in the torso of the person inside the vehicle, including the neck, left shoulder, right shoulder, left thigh, and right thigh, and obtain a key point region composed of key points in a pentagonal shape.

[0112] The seat belt wearing posture detection device provided in this embodiment of the invention can execute the seat belt wearing posture detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0113] Example 4

[0114] Figure 6A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0115] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0117] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of 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 suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the seatbelt wearing posture detection method.

[0118] In some embodiments, the seatbelt wearing posture detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the seatbelt wearing posture detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the seatbelt wearing posture detection method by any other suitable means (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0122] To provide interaction with a user, the systems and techniques described herein 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).

[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0124] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. 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 substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting seatbelt wearing posture, characterized in that, include: Acquire images of occupants inside the vehicle, and perform image segmentation on the images to obtain the seatbelt area within the images of the occupants inside the vehicle; Key point detection is performed on the image of the people inside the vehicle to obtain a key point region composed of key points; Based on the seat belt area and the key point area, it is determined whether the occupants are wearing seat belts; When determining that the occupants are wearing seat belts, a first key point sub-region and a second key point region are determined in the key point region by dividing the area through the seat belt region, based on the seat belt region and the key point region. Based on the area values ​​of the first key point sub-region and the second key point sub-region, determine the area ratio between the first key point sub-region and the second key point sub-region; When the area ratio is within a preset range, it is determined that the seat belt wearing posture of the occupants in the vehicle is correct; Otherwise, it is determined that the seat belt wearing posture of the occupants in the vehicle is incorrect; The preset ratio range is [0.5, 2].

2. The method according to claim 1, characterized in that, Determining whether vehicle occupants are wearing seat belts based on the seat belt area and the key point area includes: Based on the area values ​​of the seat belt area and the key point area, it is determined whether the occupants are wearing seat belts.

3. The method according to claim 2, characterized in that, Determining whether vehicle occupants are wearing seat belts based on the area values ​​of the seat belt area and the key point area includes: Based on the area values ​​of the seat belt area and the key point area, determine the area ratio of the seat belt area in the key point area; When the area ratio is less than a preset ratio threshold, it is determined that the occupants of the vehicle are not wearing seat belts; Otherwise, ensure that all occupants are wearing seatbelts.

4. The method according to claim 1, characterized in that, Keypoint detection is performed on the image of the people inside the vehicle to obtain a keypoint region composed of keypoints, including: The torso in the image of the person inside the vehicle is subjected to key point detection, including the neck, left shoulder, right shoulder, left thigh, and right thigh, to obtain a key point region in the shape of a pentagon composed of key points.

5. A seatbelt wearing posture detection device, characterized in that, include: The seat belt area determination module is used to acquire images of occupants inside the vehicle and perform image segmentation on the images of occupants inside the vehicle to obtain the seat belt area in the images of occupants inside the vehicle. The seatbelt wearing detection module is used to perform key point detection on the image of the occupants in the vehicle to obtain a key point region composed of key points; Based on the seat belt area and the key point area, it is determined whether the occupants are wearing seat belts; The key point sub-region determination module is used to determine, when it is determined that the occupant is wearing a seat belt, a first key point sub-region and a second key point region formed by dividing the key point region through the seat belt region, based on the seat belt region and the key point region. The seatbelt wearing posture detection module is used to determine whether the seatbelt wearing posture of the occupant in the vehicle is correct based on the first key point sub-region and the second key point sub-region. The seatbelt wearing posture detection module includes: The area ratio determination subunit is used to determine the area ratio between the first key point sub-region and the second key point sub-region based on the area values ​​of the first key point sub-region and the second key point sub-region. The seatbelt wearing posture detection subunit is used to determine that the seatbelt wearing posture of the occupant is correct when the area ratio is within a preset ratio range; otherwise, it is determined that the seatbelt wearing posture of the occupant is incorrect. The preset ratio range is [0.5, 2].

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the seat belt wearing posture detection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the seatbelt wearing posture detection method according to any one of claims 1-4.

Images