Method and device for correcting length of human body trunk in vehicle, vehicle and electronic equipment

Abstract

The invention discloses a method and device for correcting the trunk length of a human body in a vehicle, the vehicle and electronic equipment, and relates to the technical field of vehicle processing, and the method comprises the steps: recognizing image data of a target human body in a cabin, and obtaining a lower body region and a head region of the target human body; determining whether the head area falls into a preset adult stoop forward head area or not; under the condition that it is determined that the head area falls into a preset adult stoop forward head area, the comprehensive confidence degree of preset human body key points in the lower body area is calculated; and when it is determined that the comprehensive confidence coefficient is smaller than a preset confidence coefficient threshold value, correcting the in-vehicle human body trunk length of the target human body by using a trunk length correction coefficient. Compared with the prior art, according to the embodiment of the invention, by determining that the target human body enters the stoop forward-leaning posture and correcting the in-vehicle human body trunk length under the stoop forward-leaning posture, the recognition accuracy is improved when the in-vehicle human body trunk length of the human body is utilized to carry out auxiliary judgment on the human body attribute.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle processing technology, and in particular to a method and device for correcting the length of a human torso in a vehicle, a vehicle, and an electronic device. Background Art

[0002] In the related technology of judging the human attributes inside the cabin, the torso length of the human body inside the vehicle is projected by the camera inside the vehicle cabin, without correcting the torso length, and the torso length of the human body inside the vehicle is directly used to assist in judging the human attributes of the passenger.

[0003] When using the torso length of a human body in a car to assist in judging the human body's attributes, there is a difference between the torso length of a human body in a bent forward posture and the torso length of a human body in a normal sitting position. When an adult is in a bent forward posture, assisting in judging the adult's attributes may misidentify the adult as a child. Summary of the invention

[0004] The present disclosure provides a correction method and device for the length of a human torso in a vehicle, a vehicle, and an electronic device. The main purpose is to solve the problem that when the length of a human torso in a vehicle is used to assist in judging the attributes of a human body, the length of the human torso in a vehicle in a bent forward posture is different from the length of the human torso in a normal sitting posture. When an adult is in a bent forward posture, the auxiliary judgment of the adult's attributes may misidentify the adult as a child.

[0005] According to a first aspect of the present disclosure, a method for correcting the length of a human torso in a vehicle is provided, comprising:

[0006] Identify the image data of the target person in the cockpit to obtain the lower body area and the head area of ​​the target person;

[0007] Determine whether the head area falls within a preset adult bending forward head area;

[0008] When it is determined that the head area falls within the preset adult bending forward head area, calculating the comprehensive confidence of the preset human key points in the lower body area, wherein the comprehensive confidence is the visibility of the lower body area;

[0009] When it is determined that the comprehensive confidence is less than a preset confidence threshold, the torso length of the target human body in the vehicle is corrected using a torso length correction coefficient.

[0010] Optionally, the determining whether the head region falls within a preset adult bending forward head region includes:

[0011] Calling a preset human head detection algorithm to detect the image data and determine the head area of ​​the target human body;

[0012] The center coordinates of the head area are calculated, and based on the center coordinates, it is determined whether the head area falls within the preset adult bending forward head area.

[0013] Optionally, the calculating the comprehensive confidence of preset human body key points in the lower body region includes:

[0014] Calling a preset human body key point detection algorithm to detect the image data to determine whether there are preset human body key points;

[0015] On the premise of determining that the preset human body key points exist, the confidence of each preset human body key point is calculated respectively, and the comprehensive confidence of all the preset human body key points is calculated.

[0016] Optionally, before determining that the head region falls into the preset adult bending forward head region, the method includes:

[0017] Calling a preset human key point detection algorithm to determine the coordinates of the top of the head key point and the hip key point of the target human body in the image data;

[0018] The length of the torso of the person in the vehicle is calculated based on the coordinates of the key points on the top of the head and the key points on the hips.

[0019] Optionally, the correcting the in-vehicle human torso length of the target human body by using the torso length correction coefficient includes:

[0020] Determining the torso length correction coefficient based on a mapping relationship between the comprehensive confidence and the torso length of a human body in a normal sitting position in a vehicle;

[0021] The product of the torso length of the human body in the vehicle and the torso length correction coefficient is calculated to obtain the corrected torso length of the human body in the vehicle.

[0022] Optionally, calling a preset human key point detection algorithm to determine the coordinates of the top key points and the hip key points of the target human body in the image data includes:

[0023] If it is determined that the head area does not fall into the preset adult bending forward head area, calling the preset human key point detection algorithm to determine the coordinates of the top of the head key point and the coordinates of the crotch key point of the target human body in the image data;

[0024] If it is determined that the head area falls within the preset adult bending forward head area, and if it is determined that the comprehensive confidence is greater than or equal to the preset confidence threshold, the preset human key point detection algorithm is called to determine the coordinates of the top of the head key points and the coordinates of the hip key points of the target human body in the image data.

[0025] According to a second aspect of the present disclosure, a device for correcting the length of a human body in a vehicle is provided, comprising:

[0026] A recognition unit, used to recognize the image data of the target human body in the cabin, and obtain the lower body area and the head area of ​​the target human body;

[0027] A first determining unit is used to determine whether the head area falls within a preset head area for an adult bending forward;

[0028] A first calculation unit is used to calculate the comprehensive confidence of the preset human key points in the lower body region when it is determined that the head region falls into the preset adult bending forward head region, wherein the comprehensive confidence is the visibility of the lower body region;

[0029] The correction unit is used to correct the in-vehicle human torso length of the target human body using a torso length correction coefficient when it is determined that the comprehensive confidence is less than a preset confidence threshold.

[0030] Optionally, the first determining unit includes:

[0031] A first determination module is used to call a preset human head detection algorithm to detect the image data and determine the head area of ​​the target human body;

[0032] The second determination module is used to calculate the center coordinates of the head area, and determine whether the head area falls into the preset adult bending forward head area based on the center coordinates.

[0033] Optionally, the first computing unit includes:

[0034] A third determination module is used to call a preset human key point detection algorithm to detect the image data to determine whether there are preset human key points;

[0035] The first calculation module is used to calculate the confidence of each preset human body key point respectively and calculate the comprehensive confidence of all preset human body key points on the premise of determining the existence of the preset human body key points.

[0036] Optionally, before determining that the head area falls into the preset adult bending forward head area, the device includes:

[0037] A second determination unit is used to call a preset human key point detection algorithm to determine the coordinates of the top of the head key point and the coordinates of the crotch key point of the target human body in the image data;

[0038] The second calculation unit is used to calculate the length of the torso of the human body in the vehicle based on the coordinates of the key points on the top of the head and the coordinates of the key points on the hips.

[0039] Optionally, the correction unit includes:

[0040] A fourth determination module is used to determine the torso length correction coefficient based on the mapping relationship between the comprehensive confidence and the torso length of the human body in the vehicle in a normal sitting posture;

[0041] The second calculation module is used to calculate the product of the torso length of the human body in the vehicle and the torso length correction coefficient to obtain the corrected torso length of the human body in the vehicle.

[0042] Optionally, the second determining unit includes:

[0043] A fifth determination module is used to call the preset human key point detection algorithm to determine the coordinates of the top of the head key point and the coordinates of the crotch key point of the target human body in the image data when it is determined that the head area does not fall into the preset adult bending forward head area;

[0044] The fifth determination module is also used to call the preset human key point detection algorithm to determine the coordinates of the top of the head key points and the hip key points of the target human body in the image data when it is determined that the head area falls into the preset adult bending forward head area and the comprehensive confidence is greater than or equal to the preset confidence threshold.

[0045] According to a third aspect of the present disclosure, a vehicle is provided, comprising the device for correcting the length of a human torso in the vehicle as described in the second aspect above.

[0046] According to a fourth aspect of the present disclosure, there is provided an electronic device, including:

[0047] at least one processor; and

[0048] a memory communicatively connected to the at least one processor; wherein,

[0049] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0050] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect.

[0051] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0052] The present disclosure provides a method and device for correcting the torso length of a human body in a vehicle, a vehicle, and an electronic device, which recognize the image data of a target human body in the cabin, obtain the lower body area and the head area of ​​the target human body; determine whether the head area falls into the preset adult bending forward head area; when it is determined that the head area falls into the preset adult bending forward head area, calculate the comprehensive confidence of the preset human key points in the lower body area; when it is determined that the comprehensive confidence is less than the preset confidence threshold, use the torso length correction coefficient to correct the torso length of the target human body in the vehicle. Compared with the related art, the embodiment of the present disclosure determines that the target human body enters a bending forward posture, and corrects the torso length of the human body in the vehicle in the bending forward posture, so that when the torso length of the human body in the vehicle is used to assist in judging the attributes of the human body, the recognition accuracy is improved.

[0053] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0055] Figure 1 A schematic flow chart of a method for correcting the length of a human torso in a vehicle provided by an embodiment of the present disclosure;

[0056] Figure 2 A schematic diagram of key points of a human body part provided by an embodiment of the present disclosure;

[0057] Figure 3 A schematic diagram of the head area of ​​an adult bending forward provided by an embodiment of the present disclosure;

[0058] Figure 4 A schematic diagram of a training process of a preset human head detection algorithm provided in an embodiment of the present disclosure;

[0059] Figure 5 A schematic diagram of a training process of a preset human key point detection algorithm provided in an embodiment of the present disclosure;

[0060] Figure 6 A flow chart of a method for calculating the length of a human body torso in a vehicle provided by an embodiment of the present disclosure;

[0061] Figure 7 A schematic diagram of the structure of a device for correcting the length of a human body torso in a vehicle provided by an embodiment of the present disclosure;

[0062] Figure 8 A schematic diagram of the structure of another device for correcting the length of a human body torso in a vehicle provided by an embodiment of the present disclosure;

[0063] Fig. 9 A schematic block diagram of an exemplary electronic device provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0064] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0065] The following describes a method and device for correcting the length of a human torso in a vehicle, a vehicle, and an electronic device according to an embodiment of the present disclosure with reference to the accompanying drawings.

[0066] Figure 1 A schematic flow chart of a method for correcting the length of a human torso in a vehicle provided in an embodiment of the present disclosure.

[0067] like Figure 1 As shown, the method is applied to a vehicle computer, and the method comprises the following steps:

[0068] Step 101 , identifying the image data of the target human body in the cabin to obtain the lower body area and the head area of ​​the target human body.

[0069] In order to better understand the key points of various parts of the human body, such as Figure 2 As shown, Figure 2A schematic diagram of key points of human body parts provided in an embodiment of the present application; in order to determine whether the target human body is in a bent forward posture, it is necessary to identify the image data of the target human body in the cockpit, and the vehicle computer collects the image data by calling the camera inside the cockpit of the vehicle, and transmits the image data to the vehicle computer. The embodiment of the present application does not limit the number and installation position of the cameras; the vehicle computer identifies the image data by calling a preset human head detection algorithm to obtain the head area of ​​the target human body, and identifies the image data by calling a preset human key point detection algorithm to obtain the lower body area of ​​the target human body; example, Figure 2 ①, ②, ③ and ④ are the external frame points of the human head, and the area surrounded by the external frame points of the human head is the head area. It is the key point of the waist, and the area below the key point of the waist is the lower body area.

[0070] Step 102, determining whether the head area falls within a preset adult bending forward head area.

[0071] In order to better understand the head area of ​​a pre-set adult bending forward, Figure 3 As shown, Figure 3 A schematic diagram of the head area of ​​an adult bending forward provided in an embodiment of the present application; the positions of the head area of ​​the target human body in a normal sitting posture and a bending forward posture are different, and the position of the head area in the normal sitting posture is much higher than the position of the head area in the bending forward posture. Therefore, by determining whether the head area falls into the preset adult bending forward head area, it can be roughly judged whether the target human body is in the bending forward posture, wherein the preset adult bending forward head area is the average area of ​​the adult bending forward head obtained by collecting a large amount of image data of adults in the cabin in the bending forward posture and analyzing the image data. The embodiment of the present application does not limit the method for obtaining and the value of the preset adult bending forward head area.

[0072] Step 103, when it is determined that the head area falls into the preset adult bending forward head area, calculate the comprehensive confidence of the preset human body key points in the lower body area, wherein the comprehensive confidence is the visibility of the lower body area.

[0073] Please continue reading Figure 2, it is not enough to determine that the target human body is in a bent forward posture just by the head area falling into the preset adult bending forward head area, because the height of children is much shorter than that of adults, and the head area of ​​children in a normal sitting position may fall into the preset adult bending forward head area. For example, the preset adult bending forward head area is 50 cm to 60 cm, and the position of the child's head area in a normal sitting position is 55 cm; when the target human body is in the bent forward posture, the visibility of the preset lower body key points will be reduced due to the occlusion of the upper body, wherein the preset lower body key points include but are not limited to the waist key point, the left crotch key point, the lower crotch key point, the right crotch key point, the left knee key point and the right knee key point, for example, Figure 2 middle The key point of the waist. It is the key point of the left crotch. It is the key point of the lower crotch. It is the key point of the right crotch. is the left knee key point, Right knee key point, but it should be clear that this statement is not intended to limit the number and position of the preset lower body key points; when it is determined that the head area falls into the preset adult bending forward head area, the confidence of the preset lower body key points is calculated respectively by the preset human body key point detection algorithm, and the confidence of the preset lower body key points is added to obtain the comprehensive confidence of the preset human body key points, wherein the higher the comprehensive confidence, the higher the visibility of the preset lower body key points, and the lower the comprehensive confidence, the lower the visibility of the preset lower body key points.

[0074] Step 104: When it is determined that the comprehensive confidence is less than a preset confidence threshold, the torso length of the target person in the vehicle is corrected using a torso length correction coefficient.

[0075] Since the torso length of an adult in a car in a bent-over leaning forward posture is shorter than that of an adult in a normal sitting posture, it is possible that the torso length of an adult in a car in a bent-over leaning forward posture is equivalent to that of a child in a normal sitting posture. When the torso length of a human in a car is used to assist in judging the attributes of the human body, the adult may be mistakenly identified as a child. Therefore, when it is determined that the comprehensive confidence is less than a preset confidence threshold, the torso length correction coefficient is used to correct the torso length of the target human in the car, wherein the preset confidence threshold is a large amount of image data collected from adults in the cabin in a bent-over leaning forward posture, and the image data is analyzed to obtain an average comprehensive confidence of the adult in a bent-over posture. The torso length correction coefficient is a dynamic value. The lower the comprehensive confidence, the higher the torso length correction coefficient. The preset confidence threshold and the torso length correction coefficient are not limited in the embodiment of the present application.

[0076] The method for correcting the torso length of a human body in a vehicle provided by the present disclosure identifies the image data of a target human body in a cockpit, obtains the lower body area and the head area of ​​the target human body; determines whether the head area falls into the preset adult bending forward head area; when it is determined that the head area falls into the preset adult bending forward head area, calculates the comprehensive confidence of the preset human key points in the lower body area; when it is determined that the comprehensive confidence is less than the preset confidence threshold, uses the torso length correction coefficient to correct the torso length of the target human body in the vehicle. Compared with the related art, the embodiment of the present disclosure determines that the target human body enters a bending forward posture, and corrects the torso length of the human body in the vehicle in the bending forward posture, so that when the torso length of the human body in the vehicle is used to assist in judging the attributes of the human body, the recognition accuracy is improved.

[0077] As a refinement of step 102, when determining whether the head region falls within the preset adult bending forward head region, since the head region is a range region, not an accurate coordinate value, the center point of the head region needs to be used to replace the head region, for example, Figure 2 The intersection of the straight line formed by ① and ④ and the straight line formed by ② and ③ is the center of the head area; it can be implemented in but not limited to the following way: calling a preset human head detection algorithm, detecting the image data, determining the circumscribed frame coordinates of the head area of ​​the target human body, determining the center of the head area through the intersection of the straight lines formed by the coordinates of the pairwise symmetrical circumscribed frame points, and calculating the center coordinates of the head area, and determining whether the head area falls into the preset adult bending forward head area by comparing the center coordinates with the range coordinates of the preset adult bending forward head area. However, it should be clear that this statement is not intended to limit the method of determining whether the head area falls into the preset adult bending forward head area.

[0078] In order to better understand the preset human head detection algorithm, Figure 4 As shown, Figure 4 A schematic diagram of a training process of a preset human head detection algorithm provided in an embodiment of the present application; inside a cockpit, a large amount of diverse image data is collected, and for each image data, the coordinate information of the human body external frame, the coordinate information of the head external frame, and the coordinate position information of the human body key points inside each external frame are annotated to obtain labeled image data, and a first deep learning network algorithm for detecting the coordinates of the human head external frame is constructed, wherein the first deep learning network algorithm is composed of a first backbone network algorithm for detecting the coordinates of the human head external frame, a first shoulder network algorithm, and a first head network algorithm, and the labeled image data is pre-processed and put into the first deep learning network algorithm for training to obtain the preset human head detection algorithm, and the coordinates of the human body external frame and the head external frame are output.

[0079] As a refinement of step 103, when calculating the comprehensive confidence of the preset human key points in the lower body area, the comprehensive confidence is composed of the sum of the confidences of each preset human key point. Therefore, it is necessary to calculate the confidence of each preset human key point, which can be achieved by but not limited to the following methods: calling a preset human key point detection algorithm, detecting the image data, obtaining the coordinate values ​​of each preset human key point, and calculating the confidence of each preset human key point respectively through the coordinate values ​​of each preset human key point, and summing the confidences of each preset human key point to obtain the comprehensive confidence of all preset human key points.

[0080] In order to better understand the preset human key point detection algorithm, Figure 5 As shown, Figure 5 A schematic diagram of a training process of a preset human key point detection algorithm provided in an embodiment of the present application; by building a second deep learning network algorithm for detecting human key point coordinates, wherein the second deep learning network algorithm is composed of a second backbone network algorithm for detecting human key point coordinates, a second shoulder network algorithm and a second head network algorithm, multiple human bodies in the labeled image data are extracted and separated to obtain image data of a single human body, and the image data of the single human body is preprocessed and placed in the second deep learning network algorithm for training to obtain the preset human key point detection algorithm, and output the human key point coordinates and the confidence of the human key points.

[0081] In practical applications, before determining that the head area falls into the preset adult bending forward head area, it is necessary to calculate the torso length of the target person in the vehicle, so as to correct the torso length of the target person in the vehicle when determining that the target person enters the bending forward posture; Figure 6 A flow chart of a method for calculating the length of a human body torso in a vehicle provided by an embodiment of the present disclosure includes:

[0082] Step 201, calling a preset human key point detection algorithm to determine the coordinates of the top of the head key points and the coordinates of the hip key points of the target human body in the image data.

[0083] Please continue reading Figure 2 The torso length of the human body in the car is the length of the upper body of the human body, which is roughly the straight-line distance from the top of the head to the hips. The torso length of the human body in the car is often used to assist in judging the attributes of the human body. Therefore, it is necessary to obtain the coordinates of the key points on the top of the head and the key points on the hips of the target human body. The image data is identified by calling a preset human key point detection algorithm to obtain the coordinates of the key points on the top of the head and the key points on the hips.

[0084] Step 202, calculating the torso length of the person in the vehicle based on the coordinates of the top of the head key points and the coordinates of the hip key points.

[0085] By connecting the straight line between the coordinates of the key points on the top of the head and the coordinates of the key points on the hips and calculating the straight line distance, the torso length of the human body in the vehicle is obtained, so that the torso length of the human body in the vehicle can be used to assist in judging the attributes of the human body. If it is determined that the target human body is in a bent forward posture, the torso length of the human body in the vehicle needs to be corrected.

[0086] As a refinement of step 104, when the torso length of the target human body in the vehicle is corrected using the torso length correction coefficient, the degree of bending forward of the target human body is different, and the degree of correction of the torso length of the human body in the vehicle is also different. Therefore, in order to accurately correct the torso length of the human body in the vehicle, it can be achieved by but not limited to the following methods: based on the mapping relationship between the comprehensive confidence and the torso length of the human body in the vehicle in a normal sitting position, the higher the degree of bending forward of the target human body, the lower the visibility of the key points of the lower body of the target human body, and the lower the comprehensive confidence. Therefore, there is a mapping relationship between the comprehensive confidence and the torso length of the human body in the vehicle in a normal sitting position. Based on the mapping relationship, the torso length correction coefficient is dynamically adjusted. When the torso length correction coefficient is determined, the product of the torso length of the human body in the vehicle and the torso length correction coefficient is calculated to obtain the corrected torso length of the human body in the vehicle.

[0087] Related to the above embodiment, when calling the preset human key point detection algorithm to determine the coordinates of the top key points of the target human body and the coordinates of the key points of the hips in the image data, the target human body may be in a normal sitting posture in addition to being in a bent forward posture, and the target human body is a child and is in a normal sitting posture; if it is determined that the head area does not fall into the preset adult bent forward head area, it is determined that the target human body is in a normal sitting posture, and at this time it is also necessary to determine the coordinates of the top key points of the target human body and the coordinates of the key points of the hips in the image data, and calculate The torso length of the target person in the car, but the torso length of the target person in the car is not corrected; if it is determined that the head area falls into the preset adult bending forward head area, and it is determined that the comprehensive confidence is greater than or equal to the preset confidence threshold, then the target person is determined to be a child and is in a normal sitting posture. At this time, it is also necessary to determine the coordinates of the key points on the top of the head and the key points on the hips of the target person in the image data, and calculate the torso length of the target person in the car, but the torso length of the target person in the car is not corrected.

[0088] In summary, the embodiments of the present disclosure can achieve the following effects:

[0089] 1. The disclosed embodiment determines that the target human body enters a bent forward posture, and corrects the torso length of the human body in the vehicle in the bent forward posture, so that the recognition accuracy is improved when the torso length of the human body in the vehicle is used to assist in judging the human attributes.

[0090] 2. The disclosed embodiment successfully identifies the target human body's bent forward posture inside the cabin, separates it from other postures and performs special processing, thereby greatly reducing the false detection of adults being identified as children in the bent forward posture, and greatly improving the accuracy of human attribute judgment results inside the cabin.

[0091] Corresponding to the above-mentioned method for correcting the length of a human torso in a vehicle, the present invention further provides a device for correcting the length of a human torso in a vehicle. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, details not disclosed in the device embodiment can be referred to the above-mentioned method embodiment, and will not be described in detail in the present invention.

[0092] Figure 7 A schematic diagram of a device for correcting the length of a human torso in a vehicle provided by an embodiment of the present disclosure, as shown in FIG. Figure 7 As shown, including:

[0093] The recognition unit 31 is used to recognize the image data of the target human body in the cabin to obtain the lower body area and the head area of ​​the target human body;

[0094] A first determining unit 32 is used to determine whether the head area falls into a preset head area for an adult bending forward;

[0095] A first calculation unit 33 is used to calculate the comprehensive confidence of the preset human key points in the lower body region when it is determined that the head region falls into the preset adult bending forward head region, wherein the comprehensive confidence is the visibility of the lower body region;

[0096] The correction unit 34 is used to correct the in-vehicle human torso length of the target human body using a torso length correction coefficient when it is determined that the comprehensive confidence is less than a preset confidence threshold.

[0097] The present disclosure provides a correction device for the torso length of a human body in a vehicle, which identifies the image data of a target human body in the cabin, obtains the lower body area and the head area of ​​the target human body; determines whether the head area falls into the preset adult bending forward head area; when it is determined that the head area falls into the preset adult bending forward head area, calculates the comprehensive confidence of the preset human key points in the lower body area; when it is determined that the comprehensive confidence is less than the preset confidence threshold, uses the torso length correction coefficient to correct the torso length of the target human body in the vehicle. Compared with the related art, the embodiment of the present disclosure determines that the target human body enters a bending forward posture, and corrects the torso length of the human body in the vehicle in the bending forward posture, so that when the torso length of the human body in the vehicle is used to assist in judging the attributes of the human body, the recognition accuracy is improved.

[0098] Furthermore, in a possible implementation of this embodiment, Figure 8 As shown, the first determining unit 32 includes:

[0099] The first determination module 321 is used to call a preset human head detection algorithm to detect the image data and determine the head area of ​​the target human body;

[0100] The second determination module 322 is used to calculate the center coordinates of the head area, and determine whether the head area falls into the preset adult bending forward head area based on the center coordinates.

[0101] Furthermore, in a possible implementation of this embodiment, Figure 8 As shown, the first calculation unit 33 includes:

[0102] The third determination module 331 is used to call a preset human key point detection algorithm to detect the image data to determine whether there are preset human key points;

[0103] The first calculation module 332 is used to calculate the confidence of each preset human body key point respectively, and calculate the comprehensive confidence of all preset human body key points, on the premise of determining that the preset human body key points exist.

[0104] Furthermore, in a possible implementation of this embodiment, Figure 8 As shown, before determining that the head area falls into the preset adult bending forward head area, the device includes:

[0105] The second determination unit 35 is used to call a preset human key point detection algorithm to determine the coordinates of the top of the head key point and the coordinates of the crotch key point of the target human body in the image data;

[0106] The second calculation unit 36 ​​is used to calculate the length of the torso of the person in the vehicle based on the coordinates of the key points on the top of the head and the coordinates of the key points on the hips.

[0107] Furthermore, in a possible implementation of this embodiment, Figure 8 As shown, the correction unit 34 includes:

[0108] A fourth determination module 341 is used to determine the torso length correction coefficient based on the mapping relationship between the comprehensive confidence and the torso length of the human body in the vehicle in a normal sitting posture;

[0109] The second calculation module 342 is used to calculate the product of the torso length of the human body in the vehicle and the torso length correction coefficient to obtain the corrected torso length of the human body in the vehicle.

[0110] Furthermore, in a possible implementation of this embodiment, Figure 8 As shown, the second determining unit 35 includes:

[0111] The fifth determination module 351 is used to call the preset human key point detection algorithm to determine the coordinates of the top of the head key points and the coordinates of the hip key points of the target human body in the image data when it is determined that the head area does not fall into the preset adult bending forward head area.

[0112] The fifth determination module 351 is also used to call the preset human key point detection algorithm to determine the coordinates of the top of the head key points and the hip key points of the target human body in the image data when it is determined that the head area falls into the preset adult bending forward head area and the comprehensive confidence is greater than or equal to the preset confidence threshold.

[0113] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and the principle is the same, which is not limited in this embodiment.

[0114] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0115] Fig. 9 A schematic block diagram of an example electronic device 400 that can be used to implement an embodiment of the present disclosure 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 processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0116] like Fig. 9 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 402 or a computer program loaded from a storage unit 408 to a RAM (Random Access Memory) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O (Input / Output) interface 405 is also connected to the bus 404.

[0117] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a correction method for the length of a human torso in a vehicle. For example, in some embodiments, the correction method for the length of a human torso in a vehicle may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method described above may be executed. Alternatively, in other embodiments, the computing unit 401 may be configured to execute the aforementioned method for correcting the length of the human torso in a vehicle by any other appropriate means (eg, by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0121] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only-Memory) or a flash memory, an optical fiber, a CD-ROM (Compact Dis sc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0124] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may 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 difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0125] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0126] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for correcting the length of a human body torso in a vehicle, characterized in that: include: Identify the image data of the target person in the cockpit to obtain the lower body area and the head area of ​​the target person; Determine whether the head area falls within a preset adult bending forward head area; When it is determined that the head area falls within the preset adult bending forward head area, calculating the comprehensive confidence of the preset human key points in the lower body area, wherein the comprehensive confidence is the visibility of the lower body area; When it is determined that the comprehensive confidence is less than a preset confidence threshold, the torso length of the target human body in the vehicle is corrected using a torso length correction coefficient.

2. The method according to claim 1, characterized in that: The step of determining whether the head region falls within a preset adult bending forward head region comprises: Calling a preset human head detection algorithm to detect the image data and determine the head area of ​​the target human body; The center coordinates of the head area are calculated, and based on the center coordinates, it is determined whether the head area falls within the preset adult bending forward head area.

3. The method according to claim 2, characterized in that The calculating of the comprehensive confidence of the preset human body key points in the lower body region comprises: Calling a preset human body key point detection algorithm to detect the image data to determine whether there are preset human body key points; On the premise of determining that the preset human body key points exist, the confidence of each preset human body key point is calculated respectively, and the comprehensive confidence of all the preset human body key points is calculated.

4. The method according to claim 1, characterized in that: Before determining that the head area falls into the preset adult bending forward head area, the method includes: Calling a preset human key point detection algorithm to determine the coordinates of the top of the head key point and the hip key point of the target human body in the image data; The length of the torso of the person in the vehicle is calculated based on the coordinates of the key points on the top of the head and the key points on the hips.

5. The method according to claim 4, characterized in that The method of correcting the torso length of the target human body in the vehicle by using the torso length correction coefficient comprises: Determining the torso length correction coefficient based on a mapping relationship between the comprehensive confidence and the torso length of a human body in a normal sitting position in a vehicle; The product of the torso length of the human body in the vehicle and the torso length correction coefficient is calculated to obtain the corrected torso length of the human body in the vehicle.

6. The method according to claim 4, characterized in that The calling of a preset human key point detection algorithm to determine the coordinates of the top key points and the crotch key points of the target human body in the image data includes: If it is determined that the head area does not fall into the preset adult bending forward head area, calling the preset human key point detection algorithm to determine the coordinates of the top of the head key point and the coordinates of the crotch key point of the target human body in the image data; If it is determined that the head area falls within the preset adult bending forward head area, and if it is determined that the comprehensive confidence is greater than or equal to the preset confidence threshold, the preset human key point detection algorithm is called to determine the coordinates of the top of the head key points and the coordinates of the hip key points of the target human body in the image data.

7. A device for correcting the length of a human body in a vehicle, characterized in that: include: A recognition unit, used to recognize the image data of the target human body in the cabin, and obtain the lower body area and the head area of ​​the target human body; A first determining unit is used to determine whether the head area falls within a preset head area for an adult bending forward; A first calculation unit is used to calculate the comprehensive confidence of the preset human key points in the lower body region when it is determined that the head region falls into the preset adult bending forward head region, wherein the comprehensive confidence is the visibility of the lower body region; The correction unit is used to correct the in-vehicle human torso length of the target human body using a torso length correction coefficient when it is determined that the comprehensive confidence is less than a preset confidence threshold.

8. A vehicle, characterized in that: The vehicle comprises the device for correcting the length of the torso of a human body in the vehicle as claimed in claim 8.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

11. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images