Adaptive mobile image acquisition device, identity recognition method, system and apparatus

Abstract

The embodiment of the present specification provides an image acquisition device and an identity recognition method, which can generate translation instructions and rotation instructions for the image acquisition device through receiving measurement information determined by the vehicle-mounted radar, and control the mechanism based on the instructions after the image acquisition device receives the instructions, and realize movement through gear transmission, adjust the position of the image acquisition device, so that the image acquisition device can match the height and orientation of the pedestrian when collecting the image of the pedestrian. In the above process, the combination of the vehicle-mounted radar and the adaptive image acquisition device can generate movement instructions of the image acquisition device according to the corresponding measurement information of the pedestrian, so that the image acquisition device can adapt to the height and orientation of the pedestrian, improve the accuracy of identity recognition, and there is no need for the pedestrian to adjust the posture to adapt to the position of the image acquisition device, thereby improving the user experience.

Description

TECHNICAL FIELD

[0001] The present specification relates to the technical field of human-computer interaction, and in particular, to an image acquisition device with adaptive movement, an identity recognition method, system and device. BACKGROUND

[0002] With the development of vehicle intelligence, people are gradually saying goodbye to the traditional starting mode based on the vehicle key. Through the keyless starting technology, users can no longer worry about the problem of being unable to enter the vehicle due to the loss or damage of the vehicle key. Through keyless starting, users no longer rely on traditional keys and can enter the vehicle through fingerprint unlocking or terminal unlocking.

[0003] With the maturity of face recognition technology, keyless starting based on face recognition technology has become a more and more popular way. On the one hand, face recognition technology is more intelligent and more accurate in identity verification, and only allows specific users to unlock the vehicle, which can further improve the safety of vehicle use. On the other hand, face recognition technology can free the user's hands and only need to swipe the face to unlock the vehicle, which can further improve the convenience of vehicle use. Therefore, face recognition technology is recognized by more and more users due to its safety, accuracy and effectiveness.

[0004] However, in actual use, due to the limited range of images collected by the image acquisition device mounted on the vehicle, the accuracy of face recognition is low in some cases. For example, users of different heights may have different recognition accuracy when unlocking their faces, and need to bend down or stand on their toes to accurately identify. For example, for users from different directions, the accuracy of face unlocking is also quite different, and users need to face the image acquisition device as much as possible to accurately identify.

[0005] Therefore, in order to improve user experience and avoid the problem that users need to actively adjust to improve face recognition accuracy, the image acquisition device needs to be improved. SUMMARY

[0006] Therefore, in order to improve user experience and avoid the problem that users need to actively adjust to improve face recognition accuracy, the image acquisition device needs to be improved.

[0007] To achieve the above purpose, the technical solutions of one or more embodiments of the present specification are as follows:

[0008] According to a first aspect of an embodiment of the present specification, an image acquisition device with adaptive movement is provided, comprising:

[0009] The image acquisition device is installed in a vehicle body structure of the vehicle, and a rack and a ring gear are installed on the vehicle body structure;

[0010] The control module is configured to receive a movement instruction generated by a processor of the vehicle based on a reflection signal received by a vehicle-mounted radar, and send the image to the processor of the vehicle for identity recognition. The reflection signal is generated by an obstacle in the environment around the vehicle reflecting a radar signal. The movement instruction includes a translation instruction and a rotation instruction.

[0011] In response to the translation instruction, the first mechanism is controlled to perform an extension action to engage the first gear with the rack, the second mechanism is controlled to perform a contraction action to disengage the second gear from the ring gear, and the image acquisition device is driven to translate along the length direction of the rack by driving the first gear. In response to the rotation instruction, the first mechanism is controlled to perform a contraction action to disengage the first gear from the rack, the second mechanism is controlled to perform an extension action to engage the second gear with the ring gear, and the image acquisition device is driven to rotate around the center of the ring gear by driving the second gear. The first mechanism and the second mechanism are respectively fixedly connected with the image acquisition device, the first mechanism is fixedly connected with the first gear, and the second mechanism is fixedly connected with the second gear.

[0012] According to a second aspect of the embodiments of the present specification, a vehicle is provided, which includes the image acquisition device described above.

[0013] According to a third aspect of the embodiments of the present specification, an identity recognition method is provided, which is applied to a vehicle carrying at least one self-adaptive image acquisition device. The method includes:

[0014] The reflection signal received by the vehicle-mounted radar is acquired, and the reflection signal is analyzed and processed to determine measurement information corresponding to a pedestrian in the environment around the vehicle. The reflection signal is generated by an obstacle in the environment around the vehicle reflecting a radar signal. The measurement information at least includes an outline of the pedestrian and a reflection area.

[0015] The height of the pedestrian is determined according to the outline, a translation instruction for a target image acquisition device is generated based on the height, and the translation instruction is sent to the target image acquisition device to make the target image acquisition device move to a position adaptive to the height of the pedestrian by translation.

[0016] determine a direction of the face of the pedestrian according to the reflection area, generate a rotation instruction for the target image acquisition device based on the direction, and send the rotation instruction to the target image acquisition device to enable the target image acquisition device to move to a position that is adapted to the direction of the face of the pedestrian through rotation;

[0017] acquire a face image of the pedestrian captured by the target image acquisition device, perform identity recognition based on the face image, determine whether the pedestrian is a target user, and execute a preset vehicle control instruction if the pedestrian is the target user.

[0018] According to a fourth aspect of the embodiments of the present specification, an identity recognition system is provided, which is applied to a vehicle, and the system comprises:

[0019] at least one self-adaptive mobile image acquisition device, configured to track a pedestrian in a surrounding environment of the vehicle and acquire a face image of the pedestrian;

[0020] a vehicle-mounted radar, configured to receive a reflection signal, which is generated by reflecting a radar signal by an obstacle in the surrounding environment of the vehicle;

[0021] a processor of the vehicle, configured to:

[0022] perform analysis processing on the reflection signal to determine measurement information corresponding to the pedestrian in the surrounding environment of the vehicle, wherein the measurement information at least comprises an outline of the pedestrian and a reflection area;

[0023] determine a height of the pedestrian according to the outline, generate a translation instruction for a target image acquisition device based on the height, and send the translation instruction to the target image acquisition device to enable the target image acquisition device to move to a position that is adapted to the height of the pedestrian through translation;

[0024] determine a direction of the face of the pedestrian according to the reflection area, generate a rotation instruction for the target image acquisition device based on the direction, and send the rotation instruction to the target image acquisition device to enable the target image acquisition device to move to a position that is adapted to the direction of the face of the pedestrian through rotation;

[0025] acquire a face image of the pedestrian captured by the target image acquisition device, perform identity recognition based on the face image, determine whether the pedestrian is a target user, and execute a preset vehicle control instruction if the pedestrian is the target user.

[0026] According to a fifth aspect of the embodiments of the present specification, an identity recognition device is provided, which is applied to a vehicle, and the vehicle is provided with at least one self-adaptive mobile image acquisition device, and the device comprises:

[0027] The analysis module acquires a reflected signal received by the vehicle-mounted radar, and performs analysis processing on the reflected signal to determine measurement information corresponding to a pedestrian in the environment around the vehicle; wherein the reflected signal is generated by reflecting a radar signal by an obstacle in the environment around the vehicle; and the measurement information at least includes an outline of the pedestrian, and a reflection area;

[0028] The translation instruction generation module determines a height of the pedestrian according to the outline, generates a translation instruction for a target image acquisition device based on the height, and sends the translation instruction to the target image acquisition device, so that the target image acquisition device moves to a position suitable for the height of the pedestrian by translation.

[0029] The rotation instruction generation module determines an orientation of a face of the pedestrian according to the reflection area, generates a rotation instruction for the target image acquisition device based on the orientation, and sends the rotation instruction to the target image acquisition device, so that the target image acquisition device moves to a position suitable for the orientation of the face of the pedestrian by rotation.

[0030] The identity recognition module acquires a face image of the pedestrian collected by the target image acquisition device, and performs identity recognition based on the face image to determine whether the pedestrian is a target user; if yes, a preset vehicle control instruction is executed.

[0031] According to a sixth aspect of the embodiments of the present specification, an electronic device is provided, which includes a communication interface, a processor, a memory and a bus, the communication interface, the processor and the memory are connected with each other through the bus;

[0032] The memory stores machine readable instructions, and the processor executes the above method by calling the machine readable instructions.

[0033] According to a seventh aspect of the embodiments of the present specification, a machine readable storage medium is provided, which stores machine readable instructions, and the machine readable instructions realize the above method when called and executed by a processor.

[0034] The technical solutions provided by the embodiments of the present specification can include the following beneficial effects:

[0035] By the above technical solution, the translation instructions and rotation instructions for the adaptively moving image acquisition device are generated by receiving the measurement information determined by the vehicle-mounted radar. After the image acquisition device receives the instructions, the mechanism is controlled based on the instructions, and the movement is realized through the gear transmission to adjust the position of the image acquisition device, so that the image acquisition device can match the height and orientation of the pedestrian when collecting the image of the pedestrian. In the above process, by combining the vehicle-mounted radar with the adaptively moving image acquisition device, the movement instructions of the image acquisition device can be generated according to the measurement information corresponding to the pedestrian, so that the image acquisition device can adapt to the height and orientation of the pedestrian, improve the accuracy of identity recognition, and the user experience is improved without the need for the pedestrian to adjust the posture to adapt to the position of the image acquisition device. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 A schematic diagram of an adaptively moving image acquisition device is provided for an exemplary embodiment of the present specification;

[0037] Figure 2 A flowchart of an identity recognition method is provided for an exemplary embodiment of the present specification;

[0038] Figure 3 A schematic diagram of an orientation is provided for an exemplary embodiment of the present specification;

[0039] Figure 4 A schematic diagram of an identity recognition method is provided for an exemplary embodiment of the present specification;

[0040] Figure 5 An architecture diagram of an identity recognition system is provided for an exemplary embodiment of the present specification;

[0041] Figure 6 A structural schematic diagram of an electronic device in which an identity recognition apparatus is provided for an exemplary embodiment of the present specification;

[0042] Figure 7 A block diagram of an identity recognition apparatus is provided for an exemplary embodiment of the present specification. DETAILED DESCRIPTION

[0043] The exemplary embodiments will be described in detail herein with reference to the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Instead, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of the present specification as detailed in the appended claims.

[0044] It should be noted that the steps of the respective methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the steps included in the methods thereof can be more or less than described in this specification. Furthermore, a single step described in this specification can be broken down into multiple steps in other embodiments; and multiple steps described in this specification can be combined into a single step in other embodiments.

[0045] It is worth emphasizing that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0046] Therefore, the present specification provides a self-adaptive mobile image acquisition device, which cooperates with the vehicle-mounted radar, generates translation instructions and rotation instructions for the image acquisition device based on the reflection signals received by the radar, to realize the active adaptation of the image acquisition device to the pedestrian, thereby improving the user experience and increasing the identity recognition accuracy.

[0047] In implementation, at least one self-adaptive mobile image acquisition device can be carried on the vehicle.

[0048] The self-adaptive mobile image acquisition device can include an acquisition module and a control module. The acquisition module can be used to acquire images of the environment around the vehicle. The control module can be used to receive the movement instructions generated by the processor of the vehicle based on the reflection signals received by the vehicle-mounted radar, and send the images to the processor of the vehicle for identity recognition.

[0049] Firstly, the vehicle can obtain the reflection signals received by the vehicle-mounted radar, and analyze and process the reflection signals to determine the measurement information corresponding to the pedestrian in the environment around the vehicle.

[0050] For example, the vehicle-mounted radar can receive reflection signals generated by reflecting radar signals by obstacles in the environment around the vehicle. The vehicle can analyze and process the obtained reflection signals to obtain the contour corresponding to the pedestrian in the environment around the vehicle, and the reflection area.

[0051] Then, the vehicle can determine the height of the pedestrian according to the contour, and generate translation instructions for the target image acquisition device based on the height. The vehicle can determine the orientation of the face of the pedestrian according to the reflection area, and generate rotation instructions for the target image acquisition device based on the orientation.

[0052] For example, the height of the pedestrian can be determined according to the contour, and a translation instruction for the target image collection device can be generated according to a height difference between a current height of the target image collection device and the height of the pedestrian; the orientation of the face of the pedestrian can be determined according to the reflection area, and a rotation instruction for the target image collection device can be generated according to an angle difference between a current orientation of the target image collection device and the orientation of the face of the pedestrian.

[0053] Subsequently, the translation instruction can be sent to the target image collection device, so that the target image collection device moves to a position suitable for the height of the pedestrian by translation; and the rotation instruction can be sent to the target image collection device, so that the target image collection device moves to a position suitable for the orientation of the face of the pedestrian by rotation.

[0054] Correspondingly, the image collection device can control the first mechanism to perform an extension action to make the first gear engage with the rack, control the second mechanism to perform a contraction action to make the second gear disengage from the gear ring, and drive the first gear to drive the image collection device to translate along the length direction of the rack.

[0055] For example, the target image collection device can control the first mechanism to perform an extension action to make the first gear engage with the rack, control the second mechanism to perform a contraction action to make the second gear disengage from the gear ring, and drive the first gear to drive the image collection device to translate along the length direction of the rack, according to the distance, speed and direction of translation in the received translation instruction.

[0056] Correspondingly, the image collection device can control the first mechanism to perform a contraction action to make the first gear disengage from the rack, control the second mechanism to perform an extension action to make the second gear engage with the gear ring, and drive the second gear to drive the image collection device to rotate with the center of the gear ring as the center.

[0057] For example, the target image collection device can control the first mechanism to perform a contraction action to make the first gear disengage from the rack, control the second mechanism to perform an extension action to make the second gear engage with the gear ring, and drive the second gear to drive the image collection device to rotate with the center of the gear ring as the center, according to the angle, speed and direction of rotation in the received rotation instruction.

[0058] The image acquisition device is installed in a vehicle body structure, and a rack and a ring gear are installed on the vehicle body structure; the first mechanism and the second mechanism are fixedly connected with the image acquisition device, the first mechanism is fixedly connected with the first gear, and the second mechanism is fixedly connected with the second gear.

[0059] Then, the vehicle can obtain the face image of the pedestrian collected by the target image acquisition device, and perform identity recognition based on the face image to determine whether the pedestrian is a target user; if yes, a preset vehicle control instruction is executed.

[0060] For example, the collection module of the target image acquisition device can collect an image of the environment around the vehicle, and send the image to the processor of the vehicle through the control module. After obtaining the image, the vehicle can perform identity recognition according to the face image of the pedestrian in the image to determine whether the pedestrian is a target user; if yes, a preset vehicle control instruction is executed.

[0061] Through the above technical solution, the translation instruction and the rotation instruction of the self-adaptive mobile image acquisition device are generated by receiving the measurement information determined by the vehicle-mounted radar. After receiving the instruction, the image acquisition device controls the mechanism based on the instruction and moves through the gear transmission to adjust the position of the image acquisition device, so that the image acquisition device can match the height and orientation of the pedestrian when collecting the image of the pedestrian. In the above process, by combining the vehicle-mounted radar with the self-adaptive mobile image acquisition device, the movement instruction of the image acquisition device can be generated according to the measurement information corresponding to the pedestrian, so that the image acquisition device can adapt to the height and orientation of the pedestrian, improve the accuracy of identity recognition, and improve the user experience without the need for the pedestrian to adjust the posture to adapt to the position of the image acquisition device.

[0062] The self-adaptive mobile image acquisition device and the identity recognition method of the present specification will be described in detail below with reference to the accompanying drawings.

[0063] Please refer to Figure 1 , Figure 1 A schematic diagram of a self-adaptive mobile image acquisition device according to an example embodiment of the present specification. Figure 1 The schematic diagram on the left represents the image acquisition device in a translation state (the ring gear 104, the second mechanism 106 and the second gear 108 are omitted), and the schematic diagram on the right represents a top view of the image acquisition device in a rotation state (the rack 103, the first mechanism 105 and the first gear 107 are omitted).

[0064] As Figure 1 shown, the self-adaptive mobile image acquisition device 101 comprises:

[0065] The acquisition module and the control module; wherein,

[0066] The acquisition module can be used for acquiring images of the environment around the vehicle.

[0067] The image acquisition device 101 can be installed in the vehicle body structure 102 of the vehicle, and the rack 103 and the ring gear 104 are installed on the vehicle body structure 102.

[0068] In the embodiment shown, the vehicle body structure includes a stand column of the vehicle.

[0069] The image acquisition device can be installed in the stand column connected and supported between the vehicle body and the roof of the vehicle, such as the A column, the B column, the C column or the D column of the vehicle.

[0070] The control module can be used for receiving a movement instruction generated by a processor of the vehicle according to a reflection signal received by a radar of the vehicle; and sending the image to the processor of the vehicle for identity recognition.

[0071] The reflection signal is generated by an obstacle in the environment around the vehicle reflecting a radar signal; and the movement instruction includes a translation instruction and a rotation instruction.

[0072] The control module can be used for, in response to the translation instruction, controlling the first mechanism 105 to perform an extension action to make the first gear 107 engage with the rack 103, controlling the second mechanism 106 to perform a contraction action to make the second gear 108 disengage from the ring gear 104, and driving the first gear 107 to drive the image acquisition device 101 to translate along the length direction of the rack 103.

[0073] In one example, when the control module of the image acquisition device 101 receives the translation instruction, it can control the first mechanism 105 to perform an extension action to make the first gear 107 engage with the rack 103, and control the second mechanism 106 to perform a contraction action to make the second gear 108 disengage from the ring gear 104, so as to ensure that the image acquisition device 101 can smoothly complete the translation without interference, and drive the first gear 107 to drive the image acquisition device 101 to translate along the length direction of the rack 103.

[0074] The control module can be used for, in response to the rotation instruction, controlling the first mechanism 105 to perform a contraction action to make the first gear 107 disengage from the rack 103, controlling the second mechanism 106 to perform an extension action to make the second gear 108 engage with the ring gear 104, and driving the second gear 108 to drive the image acquisition device 101 to rotate around the center of the ring gear 104.

[0075] In one example, when the control module of the image acquisition device 101 receives the rotation instruction, it can control the first mechanism 105 to perform a contraction action so that the first gear 107 is separated from the rack 103, and control the second mechanism 106 to perform an extension action so that the second gear 108 is engaged with the gear ring 104, thereby ensuring that the image acquisition device 101 can smoothly complete the rotation without interference, and rotate around the center of the gear ring 104 by driving the second gear 108 to drive the image acquisition device 101.

[0076] The above-mentioned driving mode of the first gear 107 and the second gear 108 includes but is not limited to electric driving by a motor connected with the gear shaft.

[0077] In the embodiment shown, the first gear and the second gear include an electrified gear.

[0078] For example, the rotation of the motor in the electrified gear can drive the gear to rotate and realize gear transmission.

[0079] The first mechanism 105 and the second mechanism 106 are respectively fixedly connected with the image acquisition device 101, the first mechanism 105 is fixedly connected with the first gear 107, and the second mechanism 106 is fixedly connected with the second gear 108.

[0080] The above-mentioned fixed connection mode includes but is not limited to bolt connection, rivet connection, welding connection and the like, which are not limited in the present specification.

[0081] In the embodiment shown, the first mechanism at least includes a hydraulic rod, an air cylinder and a threaded rod, and the second mechanism at least includes a hydraulic rod, an air cylinder and a threaded rod.

[0082] It should be noted that the above-mentioned first mechanism and the second mechanism include but are not limited to the above-mentioned mechanisms, and can also be other mechanisms that can complete the extension action and the contraction action.

[0083] On the basis of the above-mentioned embodiments, the present embodiment can also be a vehicle, which includes the self-adaptive mobile image acquisition device as described in any one of the above-mentioned embodiments.

[0084] Please refer to Figure 2 , Figure 2 A flowchart of an identity recognition method is provided for an exemplary embodiment of the present specification. The method can be applied to a vehicle, which is equipped with at least one self-adaptive mobile image acquisition device. As shown in Figure 2 The identity recognition method includes the following steps:

[0085] Step 201: Acquire the reflected signal received by the vehicle-mounted radar, and analyze the reflected signal to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle; wherein, the reflected signal is generated by the radar signal reflected by obstacles in the surrounding environment of the vehicle; the measurement information includes at least the outline of the pedestrian and the reflective area.

[0086] Step 202: Determine the height of the pedestrian based on the outline, generate a translation command for the target image acquisition device based on the height, and send the translation command to the target image acquisition device so that the target image acquisition device moves to a position that adapts to the height of the pedestrian.

[0087] Step 203: Determine the orientation of the pedestrian's face based on the reflective area, generate a rotation command for the target image acquisition device based on the orientation, and send the rotation command to the target image acquisition device so that the target image acquisition device rotates and moves to a position that adapts to the orientation of the pedestrian's face.

[0088] Step 204: Acquire the pedestrian's facial image captured by the target image acquisition device, and perform identity recognition based on the facial image to determine whether the pedestrian is the target user; if so, execute the preset vehicle control command.

[0089] In this embodiment, the vehicle can acquire the reflected signal received by the vehicle-mounted radar and analyze the reflected signal to determine the measurement information corresponding to pedestrians in the surrounding environment of the vehicle.

[0090] The reflected signal is generated by radar signals reflected from obstacles in the vehicle's surrounding environment; the measurement information includes at least the outline of the pedestrian and the reflective area.

[0091] For example, a vehicle can be equipped with an onboard radar. The onboard radar can emit electromagnetic wave signals into the surrounding environment. When there are obstacles in the surrounding environment, the obstacles will reflect the radar signals. The onboard radar can determine whether there are obstacles in the surrounding environment by receiving the reflected signals reflected back from the obstacles.

[0092] Continuing with the example, the vehicle can analyze and process the acquired reflected signals to determine the measurement information corresponding to pedestrians in the surrounding environment. The measurement information that can be determined includes at least the outline of the pedestrian and the reflective area.

[0093] It should be noted that the mounting position and the number of the vehicle-mounted radar can be set as needed, and the present specification does not limit this. In addition, based on the working principle of the vehicle-mounted radar described above, a person skilled in the art can select the type and specific model of the radar as needed, and the present specification does not limit this.

[0094] In an embodiment shown, the reflected signal generated by the radar signal reflected by the obstacle in the surrounding environment of the vehicle can be analyzed to determine the contour and the reflection area of the obstacle, and whether the obstacle is a pedestrian can be determined according to the contour and the reflection area of the obstacle, so as to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle.

[0095] For example, after obtaining the reflected signal generated by the radar signal reflected by the obstacle in the surrounding environment of the vehicle, the reflected signal can be analyzed to determine the contour and the reflection area of the obstacle corresponding to the reflected signal.

[0096] Since different obstacles have different contours and reflection areas, and the contour and the reflection area of a person are quite different from those of an object, whether the obstacle is a pedestrian can be determined according to the contour and the reflection area of the obstacle, so as to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle.

[0097] In the present embodiment, the height of the pedestrian can be determined according to the contour, and a translation instruction for the target image acquisition device can be generated based on the height; the translation instruction can be sent to the target image acquisition device, so that the target image acquisition device moves to a position suitable for the height of the pedestrian by translation.

[0098] For example, the height of the pedestrian can be determined according to the height difference of the contour corresponding to the pedestrian, such as the height difference between the top of the head and the bottom of the foot, and a translation instruction for the target image acquisition device can be generated based on the height.

[0099] Continuing the example, the translation instruction can be sent to the target image acquisition device.

[0100] As described previously, the target image acquisition device can respond to the translation instruction to control the first mechanism to perform an extension action to make the first gear engage with the rack, control the second mechanism to perform a contraction action to make the second gear disengage from the gear ring, and drive the image acquisition device to translate along the length direction of the rack by driving the first gear, so that the target image acquisition device moves to a position suitable for the height of the pedestrian by translation.

[0101] In the embodiment, the orientation of the face of the pedestrian can be determined according to the reflection area, and a rotation instruction for the target image acquisition device is generated based on the orientation; the rotation instruction is sent to the target image acquisition device, so that the target image acquisition device moves to a position that is adapted to the orientation of the face of the pedestrian by rotating.

[0102] For example, the orientation of the face of the pedestrian can be determined according to the size of the reflection area corresponding to the pedestrian, such as the reflection area of the face, and a rotation instruction for the target image acquisition device is generated based on the orientation.

[0103] Continuing the example, the rotation instruction can be sent to the target image acquisition device.

[0104] As described above, the target image acquisition device can control the first mechanism to perform a contraction action to separate the first gear from the rack, control the second mechanism to perform an extension action to engage the second gear with the gear ring, and drive the image acquisition device to rotate around the center of the gear ring by driving the second gear.

[0105] In an embodiment, the translation instruction includes at least a distance, a speed and a direction of translation of the target image acquisition device, and the rotation instruction includes at least an angle, a speed and a direction of rotation of the target image acquisition device.

[0106] For example, the target image acquisition device can translate a corresponding distance based on the direction and speed included in the translation instruction.

[0107] For another example, the target image acquisition device can rotate a corresponding angle based on the direction and speed included in the rotation instruction.

[0108] In an embodiment, the height of the pedestrian can be determined according to the contour, and a translation instruction for the target image acquisition device is generated based on a height difference between a current height of the target image acquisition device and the height of the pedestrian.

[0109] The orientation of the face of the pedestrian can be determined according to the reflection area, and a rotation instruction for the target image acquisition device is generated based on an angle difference between a current orientation of the target image acquisition device and the orientation of the face of the pedestrian.

[0110] In one example, after determining the height of the pedestrian according to the contour, a target position to which the target image capturing device needs to move can be determined according to the height difference between the current height of the target image capturing device and the height of the pedestrian, and a translation instruction for the target image capturing device can be generated so that the target image capturing device can move to the target position in response to the translation instruction, thereby ensuring that the height of the target image capturing device after moving is adapted to the height of the pedestrian.

[0111] In another example, after determining the orientation of the face of the pedestrian according to the reflection area, a target position to which the target image capturing device needs to move can be determined according to the angle difference between the current orientation of the target image capturing device and the orientation of the face of the pedestrian, and a rotation instruction for the target image capturing device can be generated so that the target image capturing device can move to the target position in response to the rotation instruction, thereby ensuring that the orientation of the target image capturing device after moving is adapted to the orientation of the face of the pedestrian.

[0112] In one embodiment shown, the position adapted to the height of the pedestrian includes:

[0113] a height position at which the height difference between the height of the target image capturing device and the height of the pedestrian is within a third threshold.

[0114] Further, whether the height difference reaches a preset third threshold can be determined according to the height difference between the current height of the target image capturing device and the height of the pedestrian, and if so, a translation instruction for the target image capturing device can be generated based on the height difference.

[0115] The position adapted to the height of the pedestrian can be a height position at which the height difference between the height of the target image capturing device and the height of the pedestrian is within a third threshold.

[0116] For example, assuming that the height of a pedestrian is 175 cm, if the third threshold is 5 cm, when the height of the target image capturing device is within the range of 170-180 cm, it can be considered that the target image capturing device has moved to a position adapted to the height of the pedestrian.

[0117] Continuing the example, when generating the translation instruction, whether the height difference reaches a preset third threshold can be determined according to the height difference between the current height of the target image capturing device and the height of the pedestrian, and if so, a translation instruction for the target image capturing device can be generated based on the height difference.

[0118] For example, if the height difference between the current height of the target image capture device and the height of the person is 6 cm, since the height difference is greater than 5 cm, a translation instruction for the target image capture device can be generated based on the height difference; if the height difference is 3 cm, which is less than 5 cm, it can be considered that the target image capture device does not need to be adjusted in position, and no translation instruction is generated.

[0119] In an embodiment shown, the position adapted to the orientation of the face of the pedestrian includes:

[0120] an angular position in which the angle difference between the orientation of the target image capture device and the orientation of the face of the pedestrian is within a fourth threshold value;

[0121] Further, whether the angle difference reaches a preset fourth threshold value can be determined according to the angle difference between the current orientation of the target image capture device and the orientation of the face of the pedestrian; if yes, a rotation instruction for the target image capture device is generated based on the angle difference.

[0122] The position adapted to the orientation of the face of the pedestrian can be an angular position in which the angle difference between the orientation of the target image capture device and the orientation of the face of the pedestrian is within a fourth threshold value.

[0123] See Figure 3 , Figure 3 A schematic diagram of an orientation is provided for an exemplary embodiment of the present specification. As Figure 3 shown, the orientation of the face of the pedestrian can be represented by the included angle a between the normal of the face of the pedestrian and the center axis of the vehicle, and the orientation of the target image capture device can be represented by the included angle β between the pointing direction of the lens of the target image capture device and the center axis of the vehicle.

[0124] For example, if the fourth threshold value is 2°, when the difference between a and β is within ±2°, it can be considered that the target image capture device has moved to a position adapted to the orientation of the face of the pedestrian.

[0125] For example, if |a-β|>2°, a rotation instruction for the target image capture device can be generated based on the angle difference between a and β; if |a-β| is less than 2°, it can be considered that the target image capture device does not need to be adjusted in position, and no rotation instruction is generated.

[0126] For example, if |a-β|>2°, a rotation instruction for the target image capture device can be generated based on the angle difference between a and β; if |a-β| is less than 2°, it can be considered that the target image capture device does not need to be adjusted in position, and no rotation instruction is generated.

[0127] It is worth mentioning that the above-mentioned orientation of the target image acquisition device and the orientation of the face of the pedestrian are not unique, and those skilled in the art can determine them according to the above-mentioned principles.

[0128] In addition, since the pedestrian may turn his face during movement, or even change his posture, the target image acquisition device needs to be dynamically adjusted to adapt to the changes of the pedestrian. Correspondingly, the above-mentioned translation and rotation instructions are also dynamically generated to control the target image acquisition device to adjust in time.

[0129] In an embodiment shown, the measurement information further includes the distance and the advancing direction of the pedestrian relative to the vehicle;

[0130] Further, the target image acquisition device for tracking the pedestrian can be determined from the plurality of image acquisition devices according to the distance and the advancing direction of the pedestrian relative to the vehicle, and the position distribution of the image acquisition devices on the vehicle.

[0131] For example, the distance and the advancing direction of the pedestrian relative to the vehicle can also be determined by analyzing the reflection signal. When the vehicle is equipped with a plurality of self-adaptive image acquisition devices, the target image acquisition device in the best image acquisition position can be determined from the plurality of image acquisition devices according to the distance and the advancing direction of the pedestrian relative to the vehicle, and the position distribution of the image acquisition devices on the vehicle, and the pedestrian is tracked and the image of the pedestrian is acquired by the target image acquisition device.

[0132] Please refer to Figure 4 , Figure 4 A schematic diagram of an identity recognition method provided by an exemplary embodiment of the present specification is shown. As shown in Figure 4 , the vehicle can be equipped with four image acquisition devices, which are respectively located at the four corners of the vehicle.

[0133] In one example, when the pedestrian is located at position 1, the pedestrian is closer to the image acquisition device 1, and the advancing direction of the pedestrian is to approach the image acquisition device 1, so the image acquisition device 1 can be determined as the target image acquisition device.

[0134] In another example, when the pedestrian is located at position 2, although the pedestrian is closer to the image acquisition device 1, the advancing direction of the pedestrian is to move away from the image acquisition device 1 and approach the image acquisition device 2, so the image acquisition device 2 can be determined as the target image acquisition device.

[0135] Based on the above-mentioned principles, those skilled in the art can determine the specific details of the selection of the target image acquisition device, which are not limited in the present specification.

[0136] In an embodiment shown, in response to the distance reaching a first distance threshold, a height of the pedestrian is determined according to the contour, and a translation instruction for the target image acquisition device is generated based on the height; in response to the distance reaching a second distance threshold, an orientation of a face of the pedestrian is determined according to the reflection area, and a rotation instruction for the target image acquisition device is generated based on the orientation; wherein the first distance threshold is greater than the second distance threshold.

[0137] For example, on the one hand, the closer the distance, the larger the proportion of the pedestrian in the image, and the more accurate the identity recognition; on the other hand, the closer the pedestrian to the vehicle, the more likely it is a user with the intention to get on the vehicle. Therefore, the first distance threshold and the second distance threshold can be set, so that different operations are taken according to the distance between the pedestrian and the vehicle, so that the image acquisition device can be more flexible to adapt.

[0138] For example, assuming that the first distance threshold is 6m and the second distance threshold is 3m, when the pedestrian is outside 6m, no operation can be taken; when the pedestrian enters the range of 6m, a translation instruction can be generated to make the target image acquisition device translate to an appropriate height; and when the pedestrian enters the range of 3m, a rotation instruction can be generated to make the target image acquisition device rotate to an appropriate angle.

[0139] In addition, the above distance and distance threshold can be determined with the calibration center of the vehicle as the endpoint, or with the calibration center of the vehicle-mounted radar as the endpoint, which can be selected by those skilled in the art.

[0140] In this embodiment, the face image of the pedestrian acquired by the target image acquisition device can be acquired, and identity recognition can be performed based on the face image to determine whether the pedestrian is a target user; if so, a preset vehicle control instruction is executed.

[0141] For example, after the target image acquisition device moves to a position suitable for the pedestrian, image acquisition can be performed to acquire the face image of the pedestrian. Then, the vehicle can acquire the face image of the pedestrian acquired by the target image acquisition device, and perform identity recognition based on the face image to determine whether the pedestrian is a target user according to whether the facial features match the preset features; if so, a preset vehicle control instruction is executed, such as pre-opening of the vehicle door, starting of the air conditioner, etc.

[0142] By the above technical solution, the translation instructions and the rotation instructions for the adaptively moving image acquisition device are generated by receiving the measurement information determined by the vehicle-mounted radar. After the image acquisition device receives the instructions, the mechanism is controlled based on the instructions, and the movement is realized through the gear transmission to adjust the position of the image acquisition device, so that the image acquisition device can match the height and orientation of the pedestrian when collecting the image of the pedestrian. In the above process, by combining the vehicle-mounted radar with the adaptively moving image acquisition device, the movement instructions of the image acquisition device can be generated according to the measurement information corresponding to the pedestrian, so that the image acquisition device can adapt to the height and orientation of the pedestrian, improve the accuracy of identity recognition, and the user experience is improved without the need for the pedestrian to adjust the posture to adapt to the position of the image acquisition device.

[0143] Please refer to Figure 5 , Figure 5 An architecture diagram of an identity recognition system is provided for an exemplary embodiment of the present specification. As shown in Figure 5 , the system comprises:

[0144] at least one adaptively moving image acquisition device 501, a vehicle-mounted radar 502, and a processor 503 of a vehicle; wherein

[0145] The at least one adaptively moving image acquisition device 501 is configured to track pedestrians in the environment around the vehicle and collect facial images of the pedestrians.

[0146] The vehicle-mounted radar 502 is configured to receive a reflected signal, which is generated by reflecting a radar signal by an obstacle in the environment around the vehicle.

[0147] The processor 503 of the vehicle is configured to:

[0148] analyze and process the reflected signal to determine measurement information corresponding to the pedestrians in the environment around the vehicle; the measurement information at least includes an outline of the pedestrians and a reflection area;

[0149] determine the height of the pedestrians according to the outline, generate translation instructions for a target image acquisition device based on the height, and send the translation instructions to the target image acquisition device to make the target image acquisition device move to a position that adapts to the height of the pedestrians through translation;

[0150] determine the orientation of the face of the pedestrians according to the reflection area, generate rotation instructions for the target image acquisition device based on the orientation, and send the rotation instructions to the target image acquisition device to make the target image acquisition device move to a position that adapts to the orientation of the face of the pedestrians through rotation;

[0151] Obtaining a face image of the pedestrian collected by the target image collection device, and performing identity recognition based on the face image to determine whether the pedestrian is a target user; if yes, executing a preset vehicle control instruction.

[0152] The implementation process is specifically described in the implementation process of the corresponding steps in the above-mentioned safe driving warning method, and the relevant parts are described in the method implementation part. Here, it will not be repeated.

[0153] In the exemplary embodiments of the present specification, a device capable of implementing the above-mentioned method is also provided.

[0154] Figure 6 is a schematic structural diagram of a device provided by an exemplary embodiment. Please refer to Figure 6 At the hardware level, the device includes a processor 602, an internal bus 604, a network interface 606, a memory 608, and a non-volatile memory 610, and of course, it can also include other hardware required by the business. One or more embodiments of the present specification can be implemented in a software manner, such as reading a corresponding computer program from the non-volatile memory 610 into the memory 608 by the processor 602 and then running. Of course, in addition to the software implementation, one or more embodiments of the present specification do not exclude other implementation manners, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0155] Please refer to Figure 7 In a software implementation, an identity recognition apparatus 700 is provided, which is applied to a vehicle, and the vehicle is equipped with at least one image collection device that can adaptively move. As shown in Figure 7 The apparatus 700 includes:

[0156] The analysis module 701 obtains the reflected signal received by the vehicle-mounted radar, and performs analysis processing on the reflected signal to determine the measurement information of the pedestrian in the environment around the vehicle; wherein the reflected signal is generated by the radar signal reflected by the obstacle in the environment around the vehicle; the measurement information at least includes the contour of the pedestrian, and the reflection area;

[0157] The translation instruction generation module 702 determines the height of the pedestrian according to the contour, generates a translation instruction for the target image collection device based on the height, and sends the translation instruction to the target image collection device, so that the target image collection device moves to a position that adapts to the height of the pedestrian through translation;

[0158] The rotation instruction generation module 703 determines the orientation of the face of the pedestrian according to the reflection area, generates a rotation instruction for the target image acquisition device based on the orientation, and sends the rotation instruction to the target image acquisition device, so that the target image acquisition device moves to a position that adapts to the orientation of the face of the pedestrian by rotating.

[0159] The identity recognition module 704 acquires the face image of the pedestrian collected by the target image acquisition device, performs identity recognition based on the face image, and determines whether the pedestrian is a target user. If yes, a preset vehicle control instruction is executed.

[0160] Optionally, the analysis module 701 further:

[0161] analyzes the reflection signal generated by the radar signal reflected by the obstacle in the surrounding environment of the vehicle, determines the contour and reflection area of the obstacle, and determines whether the obstacle is a pedestrian according to the contour and reflection area of the obstacle, to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle.

[0162] Optionally, the measurement information further includes the distance and the advancing direction of the pedestrian relative to the vehicle.

[0163] The device 700 further includes:

[0164] The target image acquisition device determination module 705 (not shown in the figure) determines the target image acquisition device for tracking the pedestrian from the image acquisition devices according to the distance and the advancing direction of the pedestrian relative to the vehicle, and the position distribution of the image acquisition devices on the vehicle.

[0165] Optionally, the translation instruction generation module 702 further:

[0166] in response to the distance reaching a first distance threshold, determines the height of the pedestrian according to the contour, and generates a translation instruction for the target image acquisition device based on the height.

[0167] The rotation instruction generation module 703 further:

[0168] in response to the distance reaching a second distance threshold, determines the orientation of the face of the pedestrian according to the reflection area, and generates a rotation instruction for the target image acquisition device based on the orientation.

[0169] The first distance threshold is greater than the second distance threshold.

[0170] Optionally, the translation instruction generation module 702 further:

[0171] determine a height of the pedestrian according to the contour, and generate a translation instruction for the target image collection device according to a height difference between a current height of the target image collection device and the height of the pedestrian;

[0172] The rotation instruction generation module 703 further:

[0173] determine an orientation of a face of the pedestrian according to the reflection area, and generate a rotation instruction for the target image collection device according to an angle difference between a current orientation of the target image collection device and the orientation of the face of the pedestrian.

[0174] Optionally, the position adapted to the height of the pedestrian comprises:

[0175] a height position at which a height difference between the height of the target image collection device and the height of the pedestrian is within a third threshold;

[0176] The translation instruction generation module 702 further:

[0177] determine whether the height difference reaches a preset third threshold according to the height difference between the current height of the target image collection device and the height of the pedestrian; if so, generate a translation instruction for the target image collection device based on the height difference.

[0178] Optionally, the position adapted to the orientation of the face of the pedestrian comprises:

[0179] an angle position at which an angle difference between the orientation of the target image collection device and the orientation of the face of the pedestrian is within a fourth threshold;

[0180] The rotation instruction generation module 703 further:

[0181] determine whether the angle difference reaches a preset fourth threshold according to the angle difference between the current orientation of the target image collection device and the orientation of the face of the pedestrian; if so, generate a rotation instruction for the target image collection device based on the angle difference.

[0182] Optionally, the translation instruction at least comprises a distance, a speed and a direction of translation of the target image collection device; and the rotation instruction at least comprises an angle, a speed and a direction of rotation of the target image collection device.

[0183] The implementation process of the functions and roles of each module in the above device 700 is specifically described in the implementation process of the corresponding steps in the above identity recognition method, and the related parts refer to the part of the method implementation mode for explanation, which will not be repeated here.

[0184] The implementation of the apparatus described above is merely illustrative, and the units shown as separate units can or can not be physically separate, and the units shown as units can or can not be physical modules, i.e., can be located in one place, or can be distributed to multiple network modules. Part or all of the units or modules can be selected according to actual needs to achieve the purposes of the schemes in the specification. Those skilled in the art can understand and implement without creative labor.

[0185] The system, apparatus, module or unit illustrated in the above embodiments can be implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer, and the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0186] In a typical configuration, a computer includes one or more processors (CPUs), input / output interfaces, network interfaces, and memories.

[0187] The memory can include non-persistent memory in computer readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or Flash memory. The memory is an example of computer readable media.

[0188] Computer readable media includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, disk storage, quantum memory, graphene-based storage medium or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition in this paper, computer readable media does not include transitory computer readable media, such as modulated data signals and carriers.

[0189] It is also to be noted that the terms "comprising", "including", and "having" or variations thereof herein, are intended to be open-ended terms that specify the presence of the stated elements but do not preclude the presence of additional elements. It is also to be noted that the term "if' as used herein, is intended to mean "when" or "if the condition is met" and therefore indicates that the events happening after it are dependent on the event of interest occurring or the condition being met.

[0190] The above description of the preferred embodiments of the present application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the present application to the precise form described, and many modifications, equivalents and variations are possible in light of these teachings. It is intended that the scope of the present application be limited not with this detailed description, but rather by the claims appended hereto.

[0191] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0192] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. Preferred embodiments of the present application are described herein, including the best mode known to the inventors of practicing the application. Functions carried out by the components described herein can be carried out in various ways and the application should not be limited to those specific embodiments that have been specifically described.

[0193] The above description of the preferred embodiments of the present application has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the present application to the precise form described, and many modifications, equivalents and variations are possible in light of these teachings. It is intended that the scope of the present application be limited not with this detailed description, but rather by the claims appended hereto.

Claims

1. An image acquisition device for adaptive movement, comprising: an acquisition module for acquiring images of an environment surrounding a vehicle; wherein the image acquisition device is installed in a body structure of the vehicle, and a rack and a pinion are installed on the body structure; a control module for receiving a movement instruction generated by a processor of the vehicle according to a reflection signal received by a radar of the vehicle; sending the images to the processor of the vehicle for identity recognition; wherein the reflection signal is generated by an obstacle in the environment surrounding the vehicle reflecting a radar signal; the movement instruction comprises a translation instruction and a rotation instruction; and for, in response to the translation instruction, controlling a first mechanism to perform an extension action to engage a first gear with the rack, controlling a second mechanism to perform a contraction action to disengage a second gear from the pinion, and moving the image acquisition device along a length direction of the rack by driving the first gear; and for, in response to the rotation instruction, controlling the first mechanism to perform a contraction action to disengage the first gear from the rack, controlling the second mechanism to perform an extension action to engage the second gear with the pinion, and rotating the image acquisition device by driving the second gear with the center of the pinion as the center; wherein the first mechanism and the second mechanism are respectively fixedly connected with the image acquisition device, the first mechanism is fixedly connected with the first gear, and the second mechanism is fixedly connected with the second gear.

2. The image capture device of claim 1, the first mechanism comprising at least: a hydraulic rod, an air cylinder, or a threaded rod; the second mechanism at least comprises a hydraulic rod, an air cylinder, or a threaded rod.

3. The image acquisition device according to claim 1, wherein the first gear and the second gear comprise energized gears.

4. The image acquisition device according to claim 1, wherein the body structure comprises a stand column of the vehicle.

5. A vehicle comprising the image acquisition device according to any one of claims 1 to 4.

6. An identity recognition method applied to a vehicle, wherein the vehicle is equipped with at least one image acquisition device according to any one of claims 1 to 4, and the method comprises: acquiring a reflection signal received by a radar of the vehicle, and performing analysis processing on the reflection signal to determine measurement information corresponding to a pedestrian in an environment surrounding the vehicle; wherein the reflection signal is generated by an obstacle in the environment surrounding the vehicle reflecting a radar signal; and the measurement information at least comprises an outline of the pedestrian and a reflection area; determining a height of the pedestrian according to the outline, generating a translation instruction for a target image acquisition device based on the height, and sending the translation instruction to the target image acquisition device to move the target image acquisition device to a position adapted to the height of the pedestrian by translation; determining an orientation of a face of the pedestrian according to the reflection area, generating a rotation instruction for the target image acquisition device based on the orientation, and sending the rotation instruction to the target image acquisition device to move the target image acquisition device to a position adapted to the orientation of the face of the pedestrian by rotation. Obtaining a face image of the pedestrian collected by the target image collection device, and performing identity recognition based on the face image to determine whether the pedestrian is a target user; if so, executing a preset vehicle control instruction.

7. The method of claim 6, wherein the analyzing the reflected signal to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle comprises: analyzing the reflected signal reflected by an obstacle in the surrounding environment of the vehicle to determine an outline and a reflection area of the obstacle, and determining whether the obstacle is a pedestrian based on the outline and the reflection area of the obstacle to determine the measurement information corresponding to the pedestrian in the surrounding environment of the vehicle.

8. The method of claim 6, wherein the measurement information further comprises a distance and a heading of the pedestrian relative to the vehicle. The method further comprises: determining, from the image collection devices, a target image collection device for tracking the pedestrian based on the distance and the heading of the pedestrian relative to the vehicle and a position distribution of the image collection devices on the vehicle.

9. The method of claim 8, wherein the determining a height of the pedestrian based on the outline and generating a translation instruction for the target image collection device based on the height comprises: in response to the distance reaching a first distance threshold, determining the height of the pedestrian based on the outline and generating a translation instruction for the target image collection device based on the height; the determining an orientation of a face of the pedestrian based on the reflection area and generating a rotation instruction for the target image collection device based on the orientation comprises: in response to the distance reaching a second distance threshold, determining the orientation of the face of the pedestrian based on the reflection area and generating a rotation instruction for the target image collection device based on the orientation; wherein the first distance threshold is greater than the second distance threshold.

10. The method of claim 6, wherein the determining a height of the pedestrian based on the outline and generating a translation instruction for the target image collection device based on the height comprises: determining the height of the pedestrian based on the outline and generating a translation instruction for the target image collection device based on a height difference between a current height of the target image collection device and the height of the pedestrian; the determining an orientation of a face of the pedestrian based on the reflection area and generating a rotation instruction for the target image collection device based on the orientation comprises: determining the orientation of the face of the pedestrian based on the reflection area and generating a rotation instruction for the target image collection device based on an angle difference between a current orientation of the target image collection device and the orientation of the face of the pedestrian.

11. The method of claim 10, wherein the position adapted to the height of the pedestrian comprises: a height position at which a height difference between the height of the target image collection device and the height of the pedestrian is within a third threshold; and the generating the translation instruction for the target image collection device based on the height difference between the current height of the target image collection device and the height of the pedestrian comprises: determining whether the height difference reaches a preset third threshold value according to the height difference between the current height of the target image acquisition device and the height of the pedestrian; if yes, generating a translation instruction for the target image acquisition device based on the height difference.

12. The method of claim 10, wherein the position that adapts to the orientation of the pedestrian's face comprises: an angular position in which the angle difference between the orientation of the target image acquisition device and the orientation of the pedestrian's face is within a fourth threshold value; and generating a rotation instruction for the target image acquisition device according to the angle difference between the current orientation of the target image acquisition device and the orientation of the pedestrian's face comprises: determining whether the angle difference reaches a preset fourth threshold value according to the angle difference between the current orientation of the target image acquisition device and the orientation of the pedestrian's face; if yes, generating a rotation instruction for the target image acquisition device based on the angle difference.

13. The method of claim 6, wherein the translation instruction comprises at least a distance, a speed and a direction of the translation of the target image acquisition device; and the rotation instruction comprises at least an angle, a speed and a direction of the rotation of the target image acquisition device.

14. An identity recognition system applied to a vehicle, the system comprising: at least one image acquisition device as claimed in any one of claims 1 to 4, configured to track a pedestrian in the surroundings of the vehicle and acquire a facial image of the pedestrian; a vehicle-mounted radar configured to receive a reflected signal generated by reflecting a radar signal by an obstacle in the surroundings of the vehicle; a processor of the vehicle configured to: perform an analysis on the reflected signal to determine measurement information corresponding to the pedestrian in the surroundings of the vehicle, the measurement information comprising at least an outline of the pedestrian and a reflection area; determine a height of the pedestrian according to the outline, generate a translation instruction for a target image acquisition device based on the height, and send the translation instruction to the target image acquisition device to enable the target image acquisition device to move to a position that adapts to the height of the pedestrian through translation; determine an orientation of a face of the pedestrian according to the reflection area, generate a rotation instruction for the target image acquisition device based on the orientation, and send the rotation instruction to the target image acquisition device to enable the target image acquisition device to move to a position that adapts to the orientation of the face of the pedestrian through rotation; acquire the facial image of the pedestrian acquired by the target image acquisition device, and perform identity recognition based on the facial image to determine whether the pedestrian is a target user; if yes, execute a preset vehicle control instruction.

15. An identity recognition apparatus applied to a vehicle, the vehicle being equipped with at least one image acquisition device as claimed in any one of claims 1 to 4, the apparatus comprising: ​ The analysis module acquires a reflected signal received by the vehicle-mounted radar and performs analysis processing on the reflected signal to determine measurement information corresponding to a pedestrian in the environment around the vehicle. The reflected signal is generated by an obstacle in the environment around the vehicle reflecting a radar signal. The measurement information includes at least an outline of the pedestrian and a reflection area. The translation instruction generation module determines the height of the pedestrian according to the outline, generates a translation instruction for a target image acquisition device based on the height, and sends the translation instruction to the target image acquisition device to cause the target image acquisition device to move by translation to a position that accommodates the height of the pedestrian. The rotation instruction generation module determines the orientation of the face of the pedestrian according to the reflection area, generates a rotation instruction for the target image acquisition device based on the orientation, and sends the rotation instruction to the target image acquisition device to cause the target image acquisition device to move by rotation to a position that accommodates the orientation of the face of the pedestrian. The identity recognition module acquires a face image of the pedestrian collected by the target image acquisition device and performs identity recognition based on the face image to determine whether the pedestrian is a target user. If so, a preset vehicle control instruction is executed.

16. An electronic device comprising: a processor; a memory for storing processor-executable instructions; wherein the processor implements the method of any one of claims 6-13 by executing the executable instructions.

17. A machine-readable storage medium having stored thereon machine-readable instructions that, when executed by a processor, implement the steps of the method of any one of claims 6-13.

Images