Method and apparatus for transmitting information to an emergency call center for a vehicle

Abstract

The present disclosure relates to a method and device for transmitting information to an emergency call center for a vehicle, an electronic device, and a storage medium, the method including: acquiring (11) video information of an occupant in a cabin in response to an emergency call being generated; detecting (12) a bloody state of the occupant in the cabin based on the video information; and transmitting (13) the bloody state to an emergency call center in response to the detection of the bloody state.

Description

[Technical Field]

[0001] This application claims priority to a Chinese patent application filed with the China Patent Office on August 31, 2021, bearing application number 202111016361.1 and entitled "Method and device for transmitting information to an emergency call center for a vehicle," the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the field of computers, and more particularly to a method and apparatus for transmitting information to an emergency call center for a vehicle, an electronic device, a computer program product, and a storage medium. [Background technology]

[0003] When a vehicle is involved in a traffic accident during road transport, if rescue personnel can quickly obtain information about the accident and provide rescue, the parties involved in the accident can be rescued quickly, which can reduce property loss and the number of casualties.

[0004] To allow rescue personnel to quickly obtain accident information, vehicles can be equipped with an in-vehicle emergency call (eCall) system. The eCall system is a typical application for internet-of-cars. Using technologies such as vehicle sensing, mobile communications, and satellite positioning, it quickly contacts a public rescue center after an accident occurs, automatically transmitting the vehicle's location and information to the rescue center, which then confirms the accident and rescues the injured. Summary of the Invention

[0005] The present disclosure provides a technical solution for information transmission.

[0006] According to one aspect of the present disclosure, Acquiring video information of passengers in the cabin in response to an emergency call; detecting a bleeding state of a passenger in the cabin based on the video information; In response to a bloody situation being detected, transmitting the bloody situation to an emergency call center.

[0007] In one possible embodiment, the step of detecting a bleeding state of a passenger in the cabin based on the video information includes: performing face detection and / or human body detection on the video information to find passengers in the cabin; and performing blood detection on the face and / or body surface of the occupant to determine whether the occupant is bloodied within the cabin.

[0008] In one possible embodiment, the step of detecting a bleeding state of a passenger in the cabin based on the video information includes: The method includes detecting whether or not the passenger is bleeding from blood color information and blood flow shape information based on the image information.

[0009] In one possible embodiment, the step of detecting a bleeding state of a passenger in the cabin based on the video information includes: detecting a body surface area of ​​a passenger in the cabin based on the image information; Dividing a body surface area of ​​the occupant into a plurality of detection areas; Detecting blood information for each of the detection areas and obtaining area detection results for each of the detection areas; and determining a bleeding state of the occupant based on the area detection results of each of the detection areas.

[0010] In one possible embodiment, detecting a body surface area of ​​the occupant in the cabin based on the image information includes detecting a face surface area of ​​the occupant in the cabin based on the image information; Dividing the body surface area of ​​the occupant into a plurality of detection areas includes dividing a face surface area of ​​the occupant into a plurality of detection areas.

[0011] In one possible embodiment, the step of detecting blood information for each of the detection areas and obtaining a region detection result for each of the detection areas includes: determining, for each detection region, a first confidence level that a blood flow condition exists in the detection region based on a shape and an area of ​​the blood flow in the detection region; Detecting the presence or absence of blood flow between adjacent detection regions; and increasing the reliability of the plurality of first detection regions and the second detection regions to a second reliability in response to detection that there is a blood flow contacting a first detection region and an adjacent second detection region among the detection regions, Determining the bleeding state of the occupant based on the area detection result of each of the detection areas includes: determining that there is bloodshed from the occupant if the first confidence level or the second confidence level exceeds a confidence threshold; and determining, based on the area of ​​blood flow in each of the detection regions, a severity of blood flow that is positively correlated with the sum of the areas of blood flow in each of the detection regions.

[0012] In one possible embodiment, the step of detecting a bleeding state of a passenger in the cabin based on the video information includes: detecting a body part of the bleeding person and a direction of the blood flow in response to detection of bleeding from the passenger in the cabin based on the image information; and determining the body part where the blood flow starts as the bleeding part based on the body part of the bleeding and the direction of the blood flow.

[0013] In one possible embodiment, the method comprises: Detecting a body posture of a passenger in the cabin based on the image information; The method further includes determining that the body posture of the passenger in the cabin is an abnormal body posture if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time.

[0014] In one possible embodiment, the method comprises: The method further includes determining that the occupant in the cabin has a fracture when it is determined that the body posture of the occupant in the cabin is a predetermined fracture posture.

[0015] In one possible embodiment, the method comprises: detecting a vital sign indicator of the occupant based on the video information, the vital sign indicator including at least one of a respiratory rate, a blood pressure, and a heart rate; and transmitting the vital signs indicator to an emergency call center.

[0016] In one possible embodiment, the method comprises: determining an injury level of the occupants in the cabin based on at least one of the detected bleeding status, vital sign indicators, and abnormal body posture of the occupants; and transmitting the injury rating to an emergency call center.

[0017] According to one aspect of the present disclosure, a video information acquisition unit that acquires video information of passengers in the cabin in response to an emergency call; a bleeding state detection unit that detects a bleeding state of a passenger in the cabin based on the image information; a bleeding situation transmitting unit configured to transmit the bleeding situation to the emergency call center in response to the detection of the bleeding situation.

[0018] In one possible embodiment, the blood situation detection unit comprises: an occupant detection subunit that performs face detection and / or human body detection on the video information to find occupants in the cabin; and a first bloody situation determination subunit for performing blood detection on the face and / or body surface of the occupant to determine the bloody situation of the occupant in the cabin.

[0019] In one possible embodiment, the blood-shedding condition detection unit detects whether or not the passenger is bleeding from blood color information and blood flow shape information based on the image information.

[0020] In one possible embodiment, the blood situation detection unit comprises: a body surface area detection subunit that detects a body surface area of ​​a passenger in the cabin based on the image information; a detection area dividing subunit that divides a body surface area of ​​the occupant into a plurality of detection areas; a region detection result determination subunit that detects blood information for each of the detection regions and obtains a region detection result for each of the detection regions; and a second blood-shedding state determination subunit that determines a blood-shedding state of the occupant based on the area detection result of each of the detection areas.

[0021] In one possible embodiment, the body surface area detection subunit detects a facial surface area of ​​a passenger in the cabin based on the video information; The detection area dividing subunit divides the facial surface area of ​​the occupant into a plurality of detection areas.

[0022] In one possible embodiment, the region detection result determination subunit determines, for each detection region, a first reliability that the detection region has a blood flow situation based on a shape and an area of ​​the blood flow in the detection region, detects whether or not there is a blood flow contacting each other between adjacent detection regions, and increases the reliability of the first detection region and the second detection region to a second reliability in response to detection of a blood flow contacting each other between a first detection region and an adjacent second detection region among the detection regions; The second blood-shedding situation determination subunit determines that there is bloodshed from the occupant if the first reliability or the second reliability exceeds a reliability threshold, and determines the severity of the bloodshed based on the area of ​​blood flow in each of the detection areas, which is positively correlated with the sum of the area of ​​blood flow in each of the detection areas.

[0023] In one possible embodiment, the blood situation detection unit comprises: a bleeding part detection subunit that detects a bleeding body part and a blood flow direction in response to detection of bleeding from a passenger in the cabin based on the image information; and a bleeding site detection subunit that determines the body site where the blood flow starts as the bleeding site based on the body site of the blood flow and the direction of the blood flow.

[0024] In one possible embodiment, the device comprises: a body posture detection unit that detects a body posture of a passenger in the cabin based on the image information; The system further includes an abnormal body posture determination unit that determines that the body posture of the passenger in the cabin is an abnormal body posture if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time.

[0025] In one possible embodiment, the device comprises: The vehicle further includes a fracture condition detection unit that determines that the occupant in the cabin has a fracture when it is determined that the body posture of the occupant in the cabin is a predetermined fracture posture.

[0026] In one possible embodiment, the device comprises: a vital sign indicator detection unit that detects a vital sign indicator including at least one of a respiratory rate, a blood pressure, and a heart rate of the occupant based on the video information; and a vital sign indicator sending unit for sending the vital sign indicator to an emergency call center.

[0027] In one possible embodiment, the device comprises: an injury level determination unit for determining an injury level of an occupant in the cabin based on at least one of the detected bleeding status, vital sign indicators, and abnormal body posture of the occupant; and an injury level sending unit for sending the injury level to an emergency call center.

[0028] According to one aspect of the present disclosure, there is provided an electronic device including a processor and a memory for storing instructions executable by the processor, the processor configured to call the instructions stored in the memory to perform the above method.

[0029] According to one aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the computer to implement the above method.

[0030] According to one aspect of the present disclosure, there is provided a computer program product including computer-readable code or a computer-readable non-volatile storage medium having computer-readable code recorded thereon, wherein when the computer-readable code is executed in a processor of an electronic device, the processor of the electronic device executes instructions for implementing the above-described method.

[0031] In an embodiment of the present disclosure, in response to an emergency call, video information of passengers in the cabin is acquired, and based on the video information, the bleeding status of the passengers in the cabin is detected. When the bleeding status is detected, the bleeding status is transmitted to an emergency call center. This allows the injury status of the passengers during the accident to be determined, so that the emergency call center can reasonably arrange rescue according to the injury status of the passengers during the accident. If the bleeding status is severe, the call center staff can shorten or omit inquiries, and urgently provide emergency rescue as soon as possible.

[0032] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and are not intended to limit the present disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments taken in conjunction with the drawings. [Brief explanation of the drawings]

[0033] The drawings incorporated herein as part of the present specification illustrate embodiments according to the present disclosure and, together with the specification, serve to explain the technical means of the present disclosure. [Figure 1] 1 shows a flowchart of an information transmission method according to an embodiment of the present disclosure. [Figure 2] 1 shows a block diagram of an information transmission device according to an embodiment of the present disclosure. [Figure 3] 1 shows a block diagram of an electronic device according to an embodiment of the present disclosure. [Figure 4] 1 shows a block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0034] Various exemplary embodiments, features, and aspects of the present disclosure will now be described in detail with reference to the drawings, in which like reference numerals indicate elements of the same or similar function, and in which various aspects of the embodiments are illustrated, but which are not necessarily drawn to scale unless otherwise specified.

[0035] The word "exemplary" as used herein means "serving as an example, instance, or illustration." Any embodiment described herein as "exemplary" should not be construed as preferred or advantageous over other embodiments.

[0036] The term "and / or" used herein merely describes a relationship between related objects and indicates that three relationships are possible. For example, A and / or B can indicate three cases: A is present only, both A and B are present, or B is present only. The term "at least one" used herein indicates any one of a plurality of elements or any combination of at least two of a plurality of elements. For example, including at least one of A, B, and C can indicate including any one or more elements selected from the set consisting of A, B, and C.

[0037] Furthermore, in order to better explain the present disclosure, many specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can be similarly implemented without some specific details. In some embodiments, detailed descriptions of methods, means, elements and circuits that are well known to those skilled in the art will be omitted in order to emphasize the gist of the present disclosure.

[0038] As explained in the Background Art section, emergency call services can shorten rescue times and reduce the mortality rate of rescuees in vehicle accidents. However, in related technologies, it is difficult to determine the extent of accident-related injuries after an accident occurs, and it is also impossible to identify casualties inside the vehicle. Therefore, when there are many emergency calls to a rescue center, the rescue center cannot arrange rescue in an efficient manner.

[0039] In an embodiment of the present disclosure, in response to an emergency call, video information of passengers in the cabin is acquired, and based on the video information, the bleeding status of the passengers in the cabin is detected. When the bleeding status is detected, the bleeding status is transmitted to an emergency call center. This allows the injury status of the passengers during the accident to be determined, so that the emergency call center can reasonably arrange rescue according to the injury status of the passengers during the accident. If the bleeding status is severe, the call center staff can shorten or omit inquiries, and urgently provide emergency rescue as soon as possible.

[0040] In one possible embodiment, the method may be performed by an intelligent driving control device installed in a vehicle. In another possible embodiment, the method may be performed by a terminal device, a server, or another processing device. The terminal device may be an in-vehicle device, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a wearable device, or the like. The in-vehicle device may be an in-vehicle infotainment or domain controller in the cabin of a vehicle, or an equipment host for performing an information transmission method in an advanced driving assistance system (ADAS), an occupant monitoring system (OMS), or a driver monitoring system (DMS). In some possible embodiments, the information transmission method may be implemented by a processor invoking computer-readable instructions stored in a memory. Steps of the transmission method may be performed by hardware or by a processor executing computer-executable code.

[0041] For convenience of explanation, in one or more embodiments of the present disclosure, the execution entity of the method for transmitting information to an emergency call center for a vehicle may be an on-board device of the vehicle. Hereinafter, an embodiment of the method will be described using an example in which the execution entity is an on-board device. The execution entity of the method being an on-board device is merely exemplary and should not be understood as limiting the method. FIG. 1 shows a flowchart of the method for transmitting information to an emergency call center for a vehicle according to an embodiment of the present disclosure. As shown in FIG. 1, the method for transmitting information to an emergency call center for a vehicle includes the following steps:

[0042] In step S11, in response to an emergency call, video information of passengers in the cabin is acquired.

[0043] Here, the video information is video information of passengers in the cabin of the vehicle, and the vehicle may be at least one of the following types of vehicles: a private car, a shared car, a car reserved online, a taxi, a truck, etc., but the present disclosure is not specifically limited to the type of vehicle.

[0044] The video information here may be video information of the area where the passengers are located in the cabin, and the video information may be collected by an on-board video collection device installed inside or outside the cabin of the vehicle. The on-board video collection device may be an on-board camera or a video collection device equipped with a camera. The camera may be a camera for collecting video information inside the vehicle or a camera for collecting video information outside the vehicle.

[0045] For example, the camera may include a DMS camera and / or an OMS camera used to collect video information inside the vehicle, or an ADAS camera used to collect video information outside the vehicle. It goes without saying that the in-vehicle video collection device may be a camera of another system or a separately arranged camera. In the embodiments of the present disclosure, the in-vehicle video collection device is not specifically limited.

[0046] The carrier of the image information here may be a two-dimensional image or video. For example, the image information may be a visible light image / video, an infrared light image / video, or a three-dimensional image composed of a point cloud scanned by a radar. Specific details can be determined according to the actual application, but the present disclosure is not limited thereto.

[0047] The communication connection established with the in-vehicle video collection device can acquire video information collected by the in-vehicle video collection device. In one example, the in-vehicle video collection device can transmit the collected video information to an in-vehicle controller or a remote server in real time via a bus or a wireless communication channel, and the in-vehicle controller or the remote server can receive the real-time video information via the bus or the wireless communication channel.

[0048] In step S12, the bleeding state of the passengers in the cabin is detected based on the image information.

[0049] Image processing techniques can be used to detect whether or not there is blood on the surface of the passenger's body, thereby detecting whether the passenger is bleeding. In one example, a neural network can be used to detect the blood on the passenger's body, or an object detection technique such as threshold processing can be used to detect blood in the image, thereby detecting the blood on the passenger in the cabin. Specific embodiments for detecting the blood on the passenger may be referred to in the possible embodiments provided in the present disclosure, and detailed descriptions thereof will be omitted here.

[0050] In step S13, in response to the detection of the bleeding condition, the bleeding condition is transmitted to an emergency call center.

[0051] There are various specific embodiments for transmitting the bloody state to the emergency call center, for example, whether or not a passenger in the cabin is bleeding may be transmitted, and if there is bleeding, more specific information about the bloody state, such as the specific location of the bleeding and the severity of the bleeding, may be transmitted.

[0052] This allows the bleeding situation to be transmitted to an emergency call center, which can determine whether the caller is bleeding or not, and if it determines that the caller is bleeding, can provide appropriate rescue measures, such as dispatching additional doctors with corresponding hemostatic supplies and blood transfusion supplies to deal with the bleeding situation.

[0053] In an embodiment of the present disclosure, in response to an emergency call, video information of passengers in the cabin is acquired, and based on the video information, the bleeding status of the passengers in the cabin is detected. When the bleeding status is detected, the bleeding status is transmitted to an emergency call center. This allows the injury status of the passengers during the accident to be determined, so that the emergency call center can reasonably arrange rescue according to the injury status of the passengers during the accident. If the bleeding status is severe, the call center staff can shorten or omit inquiries, and urgently provide emergency rescue as soon as possible.

[0054] In one possible embodiment, detecting a bloody state of an occupant in the cabin based on the video information includes performing face detection and / or body detection on the video information to locate an occupant in the cabin, and performing blood detection on the face and / or body surface of the occupant to determine a bloody state of an occupant in the cabin.

[0055] After acquiring image information about the inside of the cabin, human body detection and / or face detection is performed on the inside of the cabin based on the image information to obtain a human body detection result and / or face detection result for the inside of the cabin, and a detection result of a passenger in the cabin can be obtained based on the human body detection result and / or face detection result for the inside of the cabin. For example, the human body detection result and / or face detection result for the inside of the cabin can be used as the detection result of a passenger in the cabin. Furthermore, for example, the human body detection result and / or face detection result for the inside of the cabin can be processed to obtain the detection result of a passenger in the cabin.

[0056] In an embodiment of the present disclosure, human body detection and / or face detection are performed within the cabin to obtain a human body detection result and / or face detection result including position information of the human body and / or face within the cabin. For example, if one passenger is detected, the passenger detection result may include position information of the passenger. If multiple passengers are detected, the passenger detection result may include position information of each detected passenger.

[0057] The position information of the occupant can be indicated by the position information of the bounding box of the occupant. Then, blood detection of the occupant is performed in the image selected by this bounding box. Alternatively, the position information of the occupant can be indicated by the position information of a contour representing the boundary of the occupant. Then, blood detection of the occupant is performed in the image surrounded by the contour representing the boundary.

[0058] The location of the occupant's face can be obtained based on face detection, and if the face is detected, blood detection can be performed on the occupant's face to determine the bloody status of the occupant in the cabin. The location of the occupant's body can be obtained based on body detection, and if the human body is detected, blood detection can be performed on the occupant's body surface to determine the bloody status of the occupant in the cabin.

[0059] In an embodiment of the present disclosure, face detection and / or human body detection is performed on the video information to find passengers in the cabin, and blood detection is performed on the faces and / or body surfaces of the passengers to determine the bloody status of the passengers in the cabin. By performing face detection and / or human body detection on the video information and then performing blood detection on the faces and / or body surfaces of the passengers, it is possible to reduce the area of ​​the image on which blood detection is subsequently performed and improve detection efficiency, as well as reduce interference with blood detection from areas other than the passenger's body, thereby improving the accuracy of bloody status detection.

[0060] In a specific embodiment, blood may be detected from color information and shape information of blood flow. Therefore, in one possible embodiment, detecting whether a passenger in the cabin is bleeding based on the image information includes detecting whether the passenger is bleeding based on color information and shape information of blood flow based on the image information.

[0061] If a passenger is bleeding, the blood is often bright red. In computers, color is represented by defining color parameters in a color space, and the most common color space is the red-green-blue (RGB) color space. According to the color specification system established by the International Commission on Illumination (CIE), related technologies also include color spaces such as HSL, LMS, CMYK, CIE YUV, HSB (HSV), and YCbCr. There are various representation formats for color spaces, and different color spaces can have different characteristics, and color parameters of different color spaces can be converted between each other.

[0062] Based on the definitions of color parameters in different color spaces, the corresponding color parameters can be analyzed from the image information. When an image is stored in a computer, it is stored based on a default color space. In a computer, the default color space for most images is the RGB color space, which is divided into three color components: red (R), green (G), and blue (B), and each color component has a possible value range of 0 to 255. When reading the image information from a storage medium, the computer reads the image information using digital image processing technology to obtain the three-dimensional components of each pixel point in the image information in the default color space, i.e., the color parameters of the image information in the default color space.

[0063] Each pixel point has a color parameter, and different color parameters represent different colors, so the color of the pixel point can be identified based on the color parameter. Meanwhile, the color parameter for blood color may be a range. For example, using the RGB color space as an example, the range of blood color parameters may be (150,0,0) to (250,50,50). If the color of the pixel point falls within this range, it is determined to be blood color, and the bloody state is further verified based on the shape of the blood.

[0064] Alternatively, bloody situations may be detected using neural network technology. In image processing using neural network technology, image features are often extracted by performing a convolution operation on an image. This operation extracts pixel values ​​of the image, and blood color information is extracted as a high-dimensional feature. Based on this high-dimensional feature, the neural network can identify high-dimensional features related to blood color and further detect bloody situations.

[0065] Since the color of the passenger's clothing, accessories, and other items attached to the passenger may be similar to the color of blood, the presence or absence of bleeding in the passenger can be detected from the shape of the blood flow, which can be obtained based on the shape of the actual blood flow in the image.

[0066] Blood detection is achieved using a deep neural network. The neural network for blood detection may be, for example, an attention-based Seq2Seq model, a Tensorflow model, or the like. The neural network may be a trained network, or may be trained with an image dataset containing bloody occupants in the image content based on the characteristics of the video information containing blood from the occupants. By marking bloody areas in the image dataset and training the neural network, the accuracy of the blood detection by the neural network can be improved, allowing for accurate detection of blood on the occupants' faces and / or skin.

[0067] In an embodiment of the present disclosure, based on the image information, the presence or absence of bleeding of the passenger is detected from blood color information and blood flow shape information, thereby making it possible to accurately detect the bleeding status of the passenger in the cabin.

[0068] In one possible embodiment, detecting the bleeding status of a passenger in the cabin based on the image information includes detecting a body surface area of ​​the passenger in the cabin based on the image information, dividing the body surface area of ​​the passenger into a plurality of detection areas, detecting blood information for each detection area to obtain area detection results for each of the detection areas, and determining the bleeding status of the passenger based on the area detection results for each of the detection areas.

[0069] Based on the video information, the body surface region of the passenger in the cabin can be detected. The body surface region may be represented by coordinates in the image and divided into a plurality of detection regions. There are various specific forms for dividing the detection region, and for example, the body surface region can be divided using a mesh. In this division form, exposed parts of the body surface (e.g., the face, neck, etc.) can be divided into meshes of equal area. Furthermore, the body surface region can be divided according to the human body parts on the body surface, such as dividing the arms as one detection region, the chest as one detection region, and the abdomen as one detection region. When dividing the body surface region according to the human body parts, human body keypoint detection is performed on the human body to obtain keypoints for identifying the human body parts, and the body surface region can be divided based on the keypoints to obtain a plurality of detection regions. Furthermore, although there are various forms for dividing the body surface region, the present disclosure is not limited thereto.

[0070] After obtaining the multiple detection regions, blood information can be detected for each detection region. For specific examples of detecting blood information, please refer to possible embodiments provided in this disclosure. For example, blood can be detected based on the color and shape of blood flow, or by a trained neural network, but detailed descriptions thereof will be omitted here.

[0071] After detecting blood information for each detection area, a region detection result for each detection area can be obtained. The region detection result may indicate the presence or absence of blood. If the region detection result indicates the presence of blood, the area of ​​blood and the position information of the blood flow in the detection area can be further detected.

[0072] Then, based on the region detection results of each detection region, weighted fusion can be performed on the region detection results of each detection region to determine the bloody state of the occupant. Alternatively, the region detection results can be combined to determine the reliability of blood from the occupant and the severity of the blood. For specific details, please refer to possible embodiments provided in the present disclosure, and detailed descriptions will be omitted here.

[0073] In an embodiment of the present disclosure, the body surface area of ​​a passenger in a cabin is detected based on image information, the body surface area of ​​the passenger is divided into a plurality of detection areas, blood information is detected for each detection area, and a detection result for each detection area is obtained. As a result, the bleeding status of the passenger is determined based on the detection result for each detection area, thereby improving the detection accuracy of the bleeding status.

[0074] In one possible embodiment, detecting the body surface area of ​​the occupant in the cabin based on the image information includes detecting the facial surface area of ​​the occupant in the cabin based on the image information, and dividing the body surface area of ​​the occupant into a plurality of detection areas includes dividing the facial surface area of ​​the occupant into a plurality of detection areas.

[0075] Based on the video information, a facial surface area of ​​a passenger in the cabin can be detected, and the facial surface area may be represented by coordinates in the image. The facial surface area is divided into multiple detection areas. There are various specific ways to divide the facial surface area, and for example, the facial surface area can be divided using a mesh. The mesh may have the same area. This allows the facial surface area to be divided using meshes of the same area. Furthermore, the facial surface area can be divided according to facial surface regions, such as dividing the forehead as one detection region, dividing each side of the nose as one detection region, and dividing the mouth and the area below it as one detection region. When dividing the facial surface area according to facial regions, facial keypoint detection is performed on the facial surface to obtain keypoints for identifying facial regions, and the facial surface area can be divided based on the keypoints to obtain multiple detection regions. There are various ways to divide the facial surface area, but the present disclosure is not limited thereto.

[0076] In an embodiment of the present disclosure, the facial surface area of ​​a passenger in the cabin is detected based on video information, and the facial surface area of ​​the passenger is divided into multiple detection areas. Based on the area detection results of each detection area, the bloody state of the passenger's face is determined, thereby improving the accuracy of detecting the bloody state.

[0077] In one possible embodiment, detecting blood information for each detection area and obtaining area detection results for each detection area includes: determining, for each detection area, a first reliability that a bloody state exists in the detection area based on the shape and area of ​​the blood flow in the detection area; detecting whether or not there is a blood flow contacting each other between adjacent detection areas; and increasing the reliability of the first detection areas and the second detection area to a second reliability in response to detecting whether there is a blood flow contacting each other between a first detection area and an adjacent second detection area among the detection areas; and determining the bloody state of the occupant based on the area detection results for each of the detection areas includes determining that there is blood from the occupant if the first reliability or the second reliability exceeds a reliability threshold; and determining the severity of the bloody state, which is positively correlated with the sum of the areas of the blood flow in each of the detection areas, based on the area of ​​the blood flow in each of the detection areas.

[0078] When detecting blood flow from video information using image processing technology, it can be considered a binary classification that determines whether a pixel point in an image represents blood flow or not, and can be realized using deep learning image segmentation technology. This allows the positions of pixel points representing blood flow in the detection area to be obtained, and when multiple pixel points classified as blood flow are connected, they form a blood flow area, i.e., a single blood flow shape can be formed. On the other hand, the area of ​​blood flow can be the area of ​​multiple pixel points classified as blood flow in the image, or it can be converted into the actual area of ​​the occupant's body surface.

[0079] A first confidence level that a blood flow condition exists can be determined for each detection region based on the shape and area of ​​the blood flow in each detection region. Specifically, this can be determined using a neural network. The first confidence level represents the confidence level that a blood flow condition exists in a single detection region. The first confidence level is positively correlated with the area of ​​the blood flow in that region; that is, the larger the area, the higher the first confidence level. The closer the shape of the blood flow in the detection region is to the actual shape of the blood flow, the higher the first confidence level.

[0080] After obtaining the first reliability for each detection area, the presence or absence of blood flow between the detection areas can be further detected. Specifically, the detection can be performed based on the position of blood detected in each detection area. The position of blood in each detection area may be a position in the video information. If the positions of blood are adjacent in the video information, it can be detected that there is blood flow between the detection areas.

[0081] The presence of tangent blood flows between the detection areas indicates that the occupant's blood flow area is larger than the area of ​​blood flow in a single detection area, and therefore the reliability of the occupant's blood flow should be further increased. Therefore, in response to detecting tangent blood flows between a first detection area and an adjacent second detection area among the detection areas, the reliability of the plurality of first detection areas and the second detection area is increased to a second reliability, thereby increasing the reliability of the presence of blood flow in the first detection area and the second detection area.

[0082] For example, if the first reliability of the first detection region and the second detection region are 0.6 and 0.7, respectively, and it is detected that there is a blood flow between the first detection region and the second detection region, the reliability of the first detection region and the second detection region can be increased to 0.7 and 0.8, respectively, to obtain the second reliability. Note that the specific increase in the first reliability can be determined according to actual needs, and is not specifically limited in the present disclosure.

[0083] The reliability may represent the reliability of the presence of blood from the occupant, so a reliability threshold may be preset, and if the first reliability or the second reliability exceeds the reliability threshold, it may be determined that the occupant is bleeding. The reliability threshold may be determined according to actual needs, and the present disclosure is not specifically limited thereto.

[0084] Furthermore, since a larger area of ​​blood flow indicates a higher severity of blood flow, in one possible embodiment, the severity of blood flow can be determined based on the area of ​​blood flow in each detection region, which is positively correlated with the sum of the areas of blood flow in each of the detection regions.

[0085] In an embodiment of the present disclosure, for each detection area, a first reliability level of the presence of blood in the detection area is determined based on the shape and area of ​​the blood flow in the detection area. The presence or absence of blood flow between adjacent detection areas is detected. If a blood flow between a first detection area and an adjacent second detection area is detected, the reliability levels of the first detection area and the second detection area are increased to a second reliability level. If the first reliability level or the second reliability level exceeds a reliability threshold, it is determined that the occupant is bleeding. This improves the accuracy of detecting blood. Furthermore, by determining the severity of the blood flow based on the area of ​​the blood flow in each detection area and transmitting the severity of the blood flow to an emergency call center, the emergency call center can timely determine the severity of the bleeding of the emergency caller, rationally arrange for rescue, and provide appropriate rescue.

[0086] In one possible embodiment, detecting a bleeding state of a passenger in the cabin based on the image information includes detecting the body part from which the blood is flowing and the direction of the blood flow in response to detecting the presence of bleeding from a passenger in the cabin based on the image information, and determining the body part from which the blood flow starts as the bleeding part based on the body part from which the blood is flowing and the direction of the blood flow.

[0087] By detecting the human body key points, it is possible to identify the body part on the occupant's body surface, and therefore the body part where the blood is located. In addition, because blood has fluidity, blood may flow from one part to multiple parts of the body after leaving the other part. This allows the direction of the blood flow to be further detected, and based on the direction of the blood flow, the body part where the blood flow starts can be determined as the bleeding part.

[0088] The blood flow direction can be detected based on multiple video frames of the video information. Blood detection is performed in the multiple video frames, and the direction in which the blood flow gradually increases can be detected based on the blood flow in the multiple video frames, and this direction can be determined as the blood flow direction.

[0089] In an embodiment of the present disclosure, when bleeding from a passenger in the cabin is detected based on the video information, the body part of the bleeding and the direction of the blood flow are detected, and the body part from which the blood flow starts is determined as the bleeding part based on the body part of the bleeding and the direction of the blood flow. This allows the bleeding part to be accurately identified and the bleeding part to be transmitted to an emergency call center as a bleeding situation, so that the emergency call center can identify the bleeding part of the person making the emergency call, understand the severity of the bleeding based on the bleeding part, rationally arrange for rescue, and provide appropriate rescue.

[0090] In one possible embodiment, the method further includes detecting a body posture of an occupant in the cabin based on the image information, and determining that the body posture of the occupant in the cabin is an abnormal body posture if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time.

[0091] In an embodiment of the present disclosure, the body posture of an occupant in a cabin can be detected based on video information. Exemplarily, the body posture of the occupant can be detected using image recognition technology. In detecting the body posture, the body posture can be detected by detecting human body key points. In one example of this embodiment, a plurality of human body key points to be detected are set in advance. For example, a human body skeleton is set to include 17 key points each representing a part of the human body. By detecting these 17 key points, the positional relationships between each part of the human body can be obtained based on the positional relationships between these 17 key points. The positional relationships between each part of the human body are a specific form of representing the body posture.

[0092] In one example of this embodiment, video information is input to a backbone network, and the backbone network performs feature extraction on the video information to obtain a feature map. Based on the feature map, the positions of key points on the human body are detected to obtain the human body posture. The backbone network can be, but is not limited to, a network such as ResNet or MobileNet.

[0093] After detecting the body posture of the passenger in the cabin, it can be determined whether the body posture is a preset abnormal body posture. If it is determined that the body posture is a preset abnormal body posture, it can be determined that the passenger in the cabin has an abnormal health condition. The preset abnormal body postures include at least one of "body leaning to one side," "head tilted downward," and "face facing upward." Since the passenger's body posture can reflect the passenger's physical health condition to a certain extent, if a passenger is injured after an accident, they often cannot maintain a straight body posture and adopt abnormal postures such as leaning to one side, tilting their head downward, or lying on their back. These body postures can accurately indicate that the passenger's current health condition is abnormal.

[0094] Therefore, these abnormal body postures are set in advance, and after detecting the body posture of the occupant in the cabin, it is determined whether the body condition of the occupant in the cabin is the predetermined abnormal body posture, and if it is determined that the body posture is the predetermined abnormal body posture, it can be determined that the health condition of the occupant in the cabin is abnormal.

[0095] In addition, in order to improve the accuracy of detecting abnormal conditions, if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time, it can be determined that the body posture of the occupant in the cabin is an abnormal body posture.

[0096] In an embodiment of the present disclosure, the body posture of the passenger in the cabin is detected based on the video information, and if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time, the body posture of the passenger in the cabin is determined to be an abnormal body posture, thereby accurately determining the abnormal condition of the passenger and accurately determining the degree of injury of the passenger and transmitting it to an emergency call center, so that the emergency call center can prioritize rescue of passengers with severe injuries.

[0097] In one possible embodiment, the method further includes determining that an occupant in the cabin has a fracture if the body posture of the occupant in the cabin is determined to be a predetermined fracture posture.

[0098] If an occupant has a fracture, their body posture will clearly differ from a normal body posture. For example, if a part of the occupant other than the joints is bent, it can be determined that the occupant has a fracture. For example, if a part of the occupant other than the arm joint is bent, it can be determined that the occupant's arm is broken. Also, for example, if a part of the occupant other than the foot joint is bent, it can be determined that the occupant's leg is broken.

[0099] In one possible embodiment, the method further includes detecting vital sign indicators, including at least one of a respiratory rate, a blood pressure, and a heart rate of the occupant, based on the video information, and transmitting the vital sign indicators to an emergency call center.

[0100] Vital sign indicators are detected based on vital sign sensing information collected by a vital sign sensor. For example, let's assume that the vital sign sensor is a millimeter-wave radar. The principle of monitoring respiratory rate and heart rate using millimeter-wave radar is to emit electromagnetic waves with the radar and detect the frequency of the echo signal to detect the respiratory rate and heart rate of the passenger. In this example, the vital sign sensing information is the echo signal of the millimeter-wave radar. Millimeter-wave radar can detect minute vibrations and movements of the human body by measuring changes in the phase of the echo signal. In one example, heart rate and respiratory rate can be detected by detecting the amplitude of the thoracic cavity.

[0101] After detecting the vital sign indicators, the vital sign indicators can be transmitted to an emergency call center, so that the emergency call center can reasonably arrange rescue and accurately rescue the passengers.

[0102] In one possible embodiment, the method further includes determining an injury level of the occupants in the cabin based on at least one of the detected bleeding status of the occupants, vital sign indicators, and abnormal body posture, and transmitting the injury level to an emergency call center.

[0103] The injury grade indicates the severity of the passenger's injuries, and is divided into grades 0 to 10, with the higher the grade, the more severe the injuries. Grade 0 indicates that the passenger was not injured.

[0104] The injury grade may be one or more types. For example, one injury grade may comprehensively represent the severity of the bleeding condition, abnormal body posture, vital sign indicators, etc. of the passenger, or multiple grades may be used, such as a preset bleeding grade, fracture grade, vital sign weakening grade, etc., to represent the severity of the passenger's injury.

[0105] The blood loss grade can be determined based on the area and location of the blood loss. The area of ​​blood loss is positively correlated with the blood loss grade, and the blood loss grade increases when the blood loss is in a location that is important to the human body, such as the head or abdomen. The fracture grade is positively correlated with the degree of curvature of the human skeleton and the number of fractured bones, and the blood loss grade increases when the fracture is in a location that is important to the human body, such as the head. The vital sign weakness grade is negatively correlated with vital sign indicators, and the lower the respiratory rate, blood pressure, and heart rate, the higher the vital sign weakness grade.

[0106] If a single injury grade comprehensively represents the severity of the occupant's bleeding, abnormal body posture, and vital sign indicators, the grades of the occupant's bleeding, abnormal body posture, and vital sign indicators can be weighted to obtain a single overall injury grade, or the injury grade can be determined based on the most severe of the occupant's bleeding, abnormal body posture, and vital sign indicators.

[0107] In an embodiment of the present disclosure, the injury level of the passengers in the cabin is determined based on at least one of the detected bleeding status, vital sign indicators, and abnormal body posture of the passengers, and the injury level is transmitted to an emergency call center, so that the emergency call center can prioritize rescue of passengers with higher injury levels according to the injury level, reduce or omit inquiries, provide faster rescue, and reduce personal and property losses.

[0108] An application scenario of an embodiment of the present disclosure will be described below. In this application scenario, when an emergency call is made after an accident, video information of the passengers in the cabin is acquired. If it is detected that the passengers in the cabin are not obviously bleeding and are in a normal posture, it is determined that the casualties are minor. Upon receiving the emergency call, the call center briefly confirms the situation with the passengers in the vehicle and then determines that no additional rescue is necessary.

[0109] Another application scenario of the embodiment of the present disclosure will be described below. In this application scenario, when an emergency call is made after an accident, video information of the passengers in the cabin is acquired. If it is detected that the passengers in the cabin are bleeding profusely from the skin of their bodies, their limbs are motionless, and they are not breathing well, it is determined that the injury level is high and the injury level is transmitted to an emergency call center. The emergency call center directly dispatches an ambulance to the accident scene, and emergency call center staff communicate with the passengers in the vehicle to further understand the specific situation.

[0110] It is understood that the above method embodiments mentioned in this disclosure can be combined with each other to form embodiments as long as they do not violate the principles and logic. Due to space limitations, detailed descriptions are omitted in this disclosure. Those skilled in the art will understand that the specific execution order of each step in the above method according to a specific embodiment is determined by its function and possible underlying logic.

[0111] The present disclosure also provides a vehicle-based information transmission device to an emergency call center, an electronic device, a computer-readable storage medium, and a program, all of which are used to realize any of the information transmission methods provided in the present disclosure. For the corresponding technical means and explanations, please refer to the corresponding descriptions of the methods, and detailed explanations will be omitted.

[0112] 2 shows a block diagram of an information transmitting device according to an embodiment of the present disclosure. As shown in FIG. 2, the device 20 includes: an image information acquisition unit 21 that acquires image information of passengers in the cabin in response to an emergency call; a bleeding state detection unit (22) for detecting bleeding states of passengers in the cabin based on the image information; and a bleeding situation sending unit 23 for sending the bleeding situation to an emergency call center in response to the detection of the bleeding situation.

[0113] In one possible embodiment, the blood situation detection unit comprises: an occupant detection subunit that performs face detection and / or human body detection on the video information to find occupants in the cabin; and a first bloody situation determination subunit for performing blood detection on the face and / or body surface of the occupant to determine the bloody situation of the occupant in the cabin.

[0114] In one possible embodiment, the blood-shedding condition detection unit detects whether or not the passenger is bleeding from blood color information and blood flow shape information based on the image information.

[0115] In one possible embodiment, the blood situation detection unit comprises: a body surface area detection subunit that detects a body surface area of ​​a passenger in the cabin based on the image information; a detection area dividing subunit that divides a body surface area of ​​the occupant into a plurality of detection areas; a region detection result determination subunit that detects blood information for each of the detection regions and obtains a region detection result for each of the detection regions; and a second blood-shedding state determination subunit that determines a blood-shedding state of the occupant based on the area detection result of each of the detection areas.

[0116] In one possible embodiment, the body surface area detection subunit detects a facial surface area of ​​a passenger in the cabin based on the video information; The detection area dividing subunit divides the facial surface area of ​​the occupant into a plurality of detection areas.

[0117] In one possible embodiment, the region detection result determination subunit determines, for each detection region, a first reliability that the detection region has a blood flow situation based on a shape and an area of ​​the blood flow in the detection region; detects whether or not there is a blood flow contacting each other between adjacent detection regions; and increases the reliability of the plurality of first detection regions and the second detection region to a second reliability in response to detection of a blood flow contacting each other between a first detection region and an adjacent second detection region among the detection regions; The second blood-shedding situation determination subunit determines that there is bloodshed from the occupant if the first reliability or the second reliability exceeds a reliability threshold, and determines the severity of the bloodshed based on the area of ​​blood flow in each of the detection areas, which is positively correlated with the sum of the area of ​​blood flow in each of the detection areas.

[0118] In one possible embodiment, the blood situation detection unit comprises: a bleeding part detection subunit that detects a bleeding body part and a blood flow direction in response to detection of bleeding from a passenger in the cabin based on the image information; and a bleeding site detection subunit that determines the body site where the blood flow starts as the bleeding site based on the body site of the blood flow and the direction of the blood flow.

[0119] In one possible embodiment, the device comprises: a body posture detection unit that detects a body posture of a passenger in the cabin based on the image information; The system further includes an abnormal body posture determination unit that determines that the body posture of the passenger in the cabin is an abnormal body posture if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time.

[0120] In one possible embodiment, the device comprises: The vehicle further includes a fracture condition detection unit that determines that the occupant in the cabin has a fracture when it is determined that the body posture of the occupant in the cabin is a predetermined fracture posture.

[0121] In one possible embodiment, the device comprises: a vital sign indicator detection unit that detects a vital sign indicator including at least one of a respiratory rate, a blood pressure, and a heart rate of the occupant based on the video information; and a vital sign indicator sending unit for sending the vital sign indicator to an emergency call center.

[0122] In one possible embodiment, the device comprises: an injury level determination unit for determining an injury level of an occupant in the cabin based on at least one of the detected bleeding status, vital sign indicators, and abnormal body posture of the occupant; and an injury level sending unit for sending the injury level to an emergency call center.

[0123] In some embodiments, the functions or modules possessed by the apparatus according to the embodiments of the present disclosure can be used to perform the methods described in the above-mentioned method embodiments, and for the specific realization and technical effects thereof, reference can be made to the descriptions of the above-mentioned method embodiments, and detailed descriptions will be omitted here for the sake of brevity.

[0124] An embodiment of the present disclosure further provides a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions, when executed by a processor, causing the computer to implement the above method. The computer-readable storage medium may be a computer-readable volatile storage medium or a computer-readable non-volatile storage medium.

[0125] An embodiment of the present disclosure further provides an electronic device including a processor and a memory for storing instructions executable by the processor, the processor configured to invoke the instructions stored in the memory to perform the above method.

[0126] An embodiment of the present disclosure further provides a computer program product including computer-readable code or a computer-readable non-volatile storage medium having computer-readable code recorded thereon, wherein when the computer-readable code is executed in a processor of an electronic device, the processor of the electronic device performs the above-described method.

[0127] The electronic device may be provided as a terminal, a server or other form of device.

[0128] 3 illustrates a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0129] Referring to FIG. 3 , electronic device 800 may include one or more of a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0130] The processing component 802 typically controls the overall operation of the electronic device 800, such as operations related to display, phone calls, data communication, camera operation, and recording operation. The processing component 802 may include one or more processors 820 that execute instructions to perform all or some of the steps of the above-described methods. The processing component 802 may also include one or more modules for interaction with other components. For example, the processing component 802 may include a multimedia module for interaction with the multimedia component 808.

[0131] The memory 804 is configured to store various types of data to support operation on the electronic device 800. These data include, by way of example, instructions for any application programs or methods operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 may be implemented by various types of volatile or non-volatile storage devices, such as, for example, static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks, or combinations thereof.

[0132] The power component 806 provides power to each component of the electronic device 800. The power component 806 may include a power management system, one or more power sources, and other components related to power generation, management, and distribution for the electronic device 800.

[0133] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, it may be implemented as a touch screen that receives input signals from a user. The touch panel may include one or more touch sensors to detect touches, slides, and gestures on the touch panel. The touch sensors may detect not only the boundaries of a touch or slide operation, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a photography mode or an image capture mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may have a fixed optical lens system or a fixed focal length and optical zoom capability.

[0134] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 may include a microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, or a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0135] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include, but are not limited to, a home button, volume buttons, a start button, and a lock button.

[0136] The sensor component 814 includes one or more sensors for evaluating the status of various aspects of the electronic device 800. For example, the sensor component 814 can detect the on / off state of the electronic device 800, the relative positioning of components such as the display and keypad of the electronic device 800, changes in the position of the electronic device 800 or certain components of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and temperature changes of the electronic device 800. The sensor component 814 may also include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor component 814 may further include an optical sensor for use in imaging applications, such as a complementary metal-oxide semiconductor (CMOS) or charge-coupled device (CCD) image sensor. In some embodiments, the sensor component 814 may further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0137] The communication component 816 is configured to realize wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as a wireless network (WiFi), a second-generation mobile communication system (2G), a third-generation mobile communication system (3G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be realized by radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0138] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processors (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements that may be used to perform the methods described above.

[0139] In an exemplary embodiment, a non-volatile computer-readable storage medium, such as a memory 804, is further provided that includes computer program instructions that, when executed by the processor 820 of the electronic device 800, can cause the above-described method to be performed.

[0140] FIG. 4 illustrates a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server. Referring to FIG. 4, the electronic device 1900 includes a processing component 1922 including one or more processors, and memory resources, such as memory 1932, for storing instructions executable by the processing component 1922, such as an application program. The application program stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. The processing component 1922 is configured to perform the above-described method by executing the instructions.

[0141] The electronic device 1900 may further include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as a Microsoft server operating system (Windows Server®), a graphical user interface-based operating system developed by Apple Inc. (Mac OS X®), a multitasking, multiuser operating system (Unix®), a free and open-source Unix-like operating system (Linux®), an open-source Unix-like operating system (FreeBSD®), or the like.

[0142] In an exemplary embodiment, a non-volatile computer-readable storage medium, such as a memory 1932, is further provided that includes computer program instructions that, when executed by the processing component 1922 of the electronic device 1900, can cause the above-described methods to be performed.

[0143] The present disclosure may be a system, a method, and / or a computer program product, which may include a computer-readable storage medium having computer-readable program instructions for causing a processor to implement aspects of the present disclosure.

[0144] A computer-readable storage medium may be a tangible device capable of storing and storing instructions for use in an instruction-executing device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. Further specific examples (non-exhaustive list) of computer-readable storage media include portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanically encoded devices such as punch cards or slot-in protrusion structures on which instructions are stored, and any suitable combination of the above. As used herein, a computer-readable storage medium is not to be construed as a momentary signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagated through a waveguide or other transmission medium (e.g., pulsed light passing through a fiber optic cable), or an electrical signal transmitted over an electrical wire.

[0145] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium into each computing / processing device, or may be downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface within each computing / processing device receives the computer-readable program instructions from the network and transfers the computer-readable program instructions for storage in a computer-readable storage medium within each computing / processing device.

[0146] Computer program instructions for carrying out the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine language instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or target code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, and common procedural programming languages ​​such as "C" or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. When remote computers are involved, the remote computers may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, the state information of the computer-readable program instructions may be used to personalize electronic circuitry, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), to execute the computer-readable program instructions to implement aspects of the present disclosure.

[0147] Although various aspects of the present disclosure have been described herein with reference to flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure, it should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0148] These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus such that, when executed by the processor of the computer or other programmable data processing apparatus, the instructions cause the apparatus to perform the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may be stored on a computer-readable storage medium to cause the computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, a computer-readable storage medium having instructions stored thereon includes an article of manufacture having instructions that implement each aspect of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0149] The computer-readable program instructions may be loaded into a computer, other programmable data processing apparatus, or other device and cause the computer, other programmable data processing apparatus, or other device to perform a series of operational steps, thereby creating a computer-implementable process. In this manner, the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0150] The flowcharts and block diagrams in the drawings illustrate possible system architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of instructions, which may include one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions depicted in the blocks may be implemented out of the order depicted in the drawings. For example, two consecutive blocks may be executed substantially in parallel, or may be executed in reverse order depending on the functionality. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0151] The computer program product may be tangibly realized in hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium. In another alternative embodiment, the computer program product is embodied as a software product, such as a Software Development Kit (SDK).

[0152] Although the embodiments of the present disclosure have been described above, the above description is merely illustrative and not exhaustive, and is not limited to the disclosed embodiments. Various modifications and alterations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms chosen in this specification are intended to appropriately interpret the principles, practical applications, or improvements to existing technology of the embodiments, or to allow other skilled in the art to understand the embodiments disclosed herein.

Claims

1. Acquiring video information of passengers in the cabin in response to an emergency call; detecting a bleeding state of a passenger in the cabin based on the video information; responsive to a blood-shedding condition being detected, transmitting the blood-shedding condition to an emergency call center; The above-mentioned detecting a bleeding state of a passenger in the cabin based on the image information includes: detecting a body surface area of ​​a passenger in the cabin based on the image information; Dividing a body surface area of ​​the occupant into a plurality of detection areas; Detecting blood information for each of the detection areas and obtaining area detection results for each of the detection areas; determining a bloody state of the occupant based on the area detection results of each of the detection areas; The above-described detecting blood information for each of the detection areas and obtaining area detection results for each of the detection areas includes: determining, for each detection region, a first confidence level that the detection region has a blood flow condition based on a shape and an area of ​​the blood flow in the detection region; Detecting the presence or absence of blood flow between adjacent detection regions; and increasing the reliability of the plurality of first detection regions and the second detection regions to a second reliability in response to detection that there is a blood flow contacting a first detection region and an adjacent second detection region among the detection regions, Determining the bleeding state of the occupant based on the area detection result of each of the detection areas includes: determining that there is bloodshed from the occupant if the first confidence level or the second confidence level exceeds a confidence threshold; and determining a severity of blood flow based on the area of ​​blood flow in each of the detection regions, the severity of blood flow being positively correlated with the sum of the areas of blood flow in each of the detection regions.

10. A method for transmitting information to an emergency call center for a vehicle, comprising:

2. The above-mentioned detecting a bleeding state of a passenger in the cabin based on the image information includes: performing face detection and / or human body detection on the video information to find passengers in the cabin; and performing blood detection on the face and / or body surface of the passenger to determine whether the passenger is bloodied within the cabin.

2. The method for transmitting information to an emergency call center for a vehicle according to claim 1.

3. The above-mentioned detecting a bleeding state of a passenger in the cabin based on the image information includes: and detecting whether or not the passenger is bleeding from blood color information and blood flow shape information based on the image information.

3. The method for transmitting information to an emergency call center for a vehicle according to claim 1 or 2.

4. the detecting of a body surface area of ​​the occupant in the cabin based on the image information includes detecting a face surface area of ​​the occupant in the cabin based on the image information; The dividing the body surface area of ​​the occupant into a plurality of detection areas includes dividing a face surface area of ​​the occupant into a plurality of detection areas.

2. The method for transmitting information to an emergency call center for a vehicle according to claim 1.

5. The above-mentioned detecting a bleeding state of a passenger in the cabin based on the image information includes: detecting a body part of the bleeding person and a direction of the blood flow in response to detection of bleeding from the passenger in the cabin based on the image information; determining the body part where the blood flow starts as the bleeding part based on the body part of the blood flow and the direction of the blood flow.

5. The method for transmitting information to an emergency call center for a vehicle according to claim 1.

6. Detecting a body posture of the occupant in the cabin based on the video information, and determining that the body posture of the occupant in the cabin is an abnormal body posture if the body posture is a predetermined abnormal body posture and the duration of the abnormal body posture exceeds a predetermined time; Detecting vital sign indicators, including at least one of a respiratory rate, a blood pressure, and a heart rate, of the passenger based on the video information, and transmitting the vital sign indicators to an emergency call center; determining an injury level of the passenger in the cabin based on at least one of the detected bleeding status of the passenger, the vital sign indicator, and the abnormal body posture of the passenger, and transmitting the injury level to an emergency call center.

6. The method for transmitting information to an emergency call center for a vehicle according to claim 1.

7. a video information acquisition unit that acquires video information of passengers in the cabin in response to an emergency call; a bleeding state detection unit that detects a bleeding state of a passenger in the cabin based on the image information; a bleeding situation transmitting unit configured to transmit the bleeding situation to an emergency call center in response to detection of the bleeding situation, The bleeding state detection unit that detects a bleeding state of a passenger in the cabin based on the image information includes: detecting a body surface area of ​​a passenger in the cabin based on the image information; Dividing a body surface area of ​​the occupant into a plurality of detection areas; Detecting blood information for each of the detection areas and obtaining area detection results for each of the detection areas; determining a bloody state of the occupant based on the area detection results of each of the detection areas; The above-described detecting blood information for each of the detection areas and obtaining area detection results for each of the detection areas includes: determining, for each detection region, a first confidence level that the detection region has a blood flow condition based on a shape and an area of ​​the blood flow in the detection region; Detecting the presence or absence of blood flow between adjacent detection regions; and increasing the reliability of the plurality of first detection regions and the second detection regions to a second reliability in response to detection that there is a blood flow contacting a first detection region and an adjacent second detection region among the detection regions, Determining the bleeding state of the occupant based on the area detection result of each of the detection areas includes: determining that there is bloodshed from the occupant if the first confidence level or the second confidence level exceeds a confidence threshold; and determining a severity of blood flow based on the area of ​​blood flow in each of the detection regions, the severity of blood flow being positively correlated with the sum of the areas of blood flow in each of the detection regions.

1. A vehicle-mounted information transmission device for transmitting information to an emergency call center.

8. a processor; a memory for storing instructions executable by the processor; The processor is configured to invoke instructions stored in the memory to perform the method for transmitting information to an emergency call center for a vehicle according to any one of claims 1 to 6. An electronic device characterized by:

9. A computer-readable storage medium having stored thereon computer program instructions, which, when executed by a processor, implements the method for transmitting information to an emergency call center for a vehicle according to any one of claims 1 to 6. A computer-readable storage medium comprising:

10. The method includes computer-readable code or a computer-readable non-volatile storage medium having computer-readable code recorded thereon, and when the computer-readable code is executed in a processor of an electronic device, the processor of the electronic device executes instructions for implementing the method for transmitting information to an emergency call center for a vehicle according to any one of claims 1 to 6.

1. A computer program product comprising:

Images