A low-power-consumption device wake-up method and device, apparatus, and storage medium

Abstract

This invention discloses a method, apparatus, device, and storage medium for waking up a low-power device. The method includes: acquiring at least one target contour hotspot detected by a millimeter-wave radar from the low-power device; determining at least one local region of a video frame based on the at least one target contour hotspot and a pre-stored mapping relationship between radar detection areas and camera detection areas; performing target detection on each local region of the video frame at a preset period to determine the wake-up positive detection rate corresponding to the local region; and, when the low-power device is in a sleep state, if a target appears in the target local region of the at least one video frame, determining whether the wake-up positive detection rate corresponding to the target local region meets a preset condition; if so, waking the low-power device from sleep state to working state. This solution can accurately distinguish between valid and invalid wake-up sources, ensuring effective and rapid wake-up of the low-power device.

Description

Technical Field

[0001] This invention relates to the field of low-power technology, and in particular to a low-power device wake-up method, apparatus, device, and storage medium. Background Technology

[0002] The rapid development of microelectronics technology has led to a wider range of applications for embedded systems. Energy conservation is a global trend; many embedded chips, previously powered by 5V, now operate at 3.3V or 1.8V, creating more application scenarios for low-power devices. Low-power devices, powered by 3.3V or 1.8V, are characterized by extremely low power consumption and can perform tasks such as video capture, network data transmission, and user interaction even when woken up from sleep mode by an external source. These devices often use batteries, and the most pressing issue is how to reduce power consumption, extend battery life, and improve wake-up detection rate. The wake-up detection rate refers to the accuracy with which a low-power device switches from sleep mode to normal operation after detecting an external wake-up source.

[0003] Two wake-up schemes for low-power devices are provided in related technologies: Scheme 1: Wake up the low-power device by detecting external heat using a pyroelectric infrared (PIR) sensor. However, PIR is susceptible to interference from various heat sources and light sources, is easily blocked, and is easily affected by radio frequency radiation. Its detection sensitivity decreases significantly when the ambient temperature is close to human body temperature, sometimes even causing short-term malfunctions. PIR is also easily affected by environmental interference, such as wind, sunlight, lights, air conditioning, refrigerators, and stoves, which may cause changes in environmental energy and generate wake-up trigger signals. It cannot distinguish whether the trigger is an object or a living person, cannot confirm the trigger location, and has a high false detection rate. Scheme 2: Wake up the low-power device by detecting the target using the electromagnetic wave emission, reflection, and reception signals of a millimeter-wave radar sensor. However, millimeter-wave radar sensors are greatly affected by the environment; for example, the detection results may be inaccurate in rainy or foggy weather. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for waking up low-power devices, which can ensure effective waking up of low-power devices, reduce power consumption caused by invalid waking up, and extend the battery life of low-power devices as much as possible.

[0005] According to one aspect of the present invention, a low-power device wake-up method is provided, comprising:

[0006] When the low-power device is in operation, acquire at least one target contour hotspot detected by the millimeter-wave radar of the low-power device;

[0007] Based on the at least one target contour hot zone and the pre-stored mapping relationship between radar detection area and camera detection area, at least one local region of video frame is determined; wherein, the local region of video frame corresponds one-to-one with the target contour hot zone;

[0008] For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame.

[0009] When the low-power device is in a sleep state, if a target appears in a target video frame local area in at least one video frame local area, it is determined whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition. If so, the low-power device is woken up from the sleep state to the working state.

[0010] According to another aspect of the present invention, a low-power device wake-up device is provided, comprising:

[0011] The target contour hot zone determination module is used to acquire at least one target contour hot zone detected by the millimeter-wave radar of the low-power device when the low-power device is in operation.

[0012] The video frame local region determination module is used to determine at least one video frame local region based on the at least one target contour hot zone and the pre-stored mapping relationship between radar detection area and camera detection area; wherein, the video frame local region corresponds one-to-one with the target contour hot zone;

[0013] The wake-up positive detection rate determination module is used to perform target detection on the local region of each video frame according to a preset period and determine the wake-up positive detection rate corresponding to the local region of the video frame.

[0014] The device wake-up module is used to determine whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition when the low-power device is in a sleep state and a target appears in the target video frame local area of ​​at least one video frame local area. If so, the low-power device is woken up from the sleep state to the working state.

[0015] According to another aspect of the present invention, a low-power device is provided, the low-power device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the low-power device wake-up method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the low-power device wake-up method according to any embodiment of the present invention.

[0020] The low-power device wake-up scheme of this invention involves the following steps: When the low-power device is in operation, at least one target contour hotspot detected by the millimeter-wave radar of the low-power device is acquired; based on the at least one target contour hotspot and a pre-stored mapping relationship between radar detection areas and camera detection areas, at least one local region of a video frame is determined; wherein, each local region of the video frame corresponds one-to-one with the target contour hotspot; for each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame; when the low-power device is in sleep mode, if a target appears in the target local region of the at least one local region of the video frame, it is determined whether the wake-up positive detection rate corresponding to the target local region of the video frame meets a preset condition; if so, the low-power device is woken up from sleep mode to operation mode. Through the technical solution provided by this invention, the low-power device can accurately and quickly distinguish between valid and invalid wake-up sources, thereby ensuring effective and rapid wake-up of the low-power device, reducing power consumption caused by invalid wake-ups, and extending the battery life of the low-power device as much as possible.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a low-power device wake-up method provided in Embodiment 1 of the present invention;

[0024] Figure 2This is a schematic diagram of the distribution of thermal zones of a target contour provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram illustrating the mapping relationship between a radar detection area and a camera detection area, provided in an embodiment of the present invention.

[0026] Figure 4 This is a flowchart of a low-power device wake-up method provided in Embodiment 2 of the present invention;

[0027] Figure 5 This invention provides a schematic diagram illustrating the positional relationship between a local region of a video frame and its various sub-regions.

[0028] Figure 6 A schematic diagram of a low-power device wake-up device provided in Embodiment 3 of the present invention;

[0029] Figure 7 A schematic diagram of the structure of a low-power device for implementing the low-power device wake-up method of this embodiment of the invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1This is a flowchart of a low-power device wake-up method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations requiring the wake-up of low-power devices. The method can be executed by a low-power device wake-up device, which can be implemented in hardware and / or software and can be configured within the low-power device. Figure 1 As shown, the method includes:

[0034] S110. When the low-power device is in operation, acquire at least one target contour hot zone detected by the millimeter-wave radar of the low-power device.

[0035] In this embodiment of the invention, the low-power device is a device powered by 3.3V or 1.8V, capable of performing video capture, network data transmission, and user interaction services through external wake-up from its normal sleep state. When the low-power device is in operation, its millimeter-wave radar performs target object detection in real time or at preset intervals, determining at least one target contour hotspot detected by the millimeter-wave radar. The target contour hotspot can be understood as the contour region of the target detected by the millimeter-wave radar of the low-power device. Since the millimeter-wave radar of the low-power device may detect one or multiple targets simultaneously, the target contour hotspot detected by the millimeter-wave radar can be one or multiple, with at least one target appearing in a single target contour hotspot.

[0036] Optionally, acquiring at least one target contour hotspot detected by the millimeter-wave radar of the low-power device includes: acquiring a set of location points of at least one target detected by the millimeter-wave radar of the low-power device; and determining at least one target contour hotspot based on the set of location points of the at least one target. Optionally, the millimeter-wave radar of the low-power device transmits a first electromagnetic wave signal to the target scene in real time or at preset intervals, and receives a second electromagnetic wave signal reflected by the target in the target scene; the first electromagnetic wave signal and the second electromagnetic wave signal are analyzed to determine radar detection data of the target scene, wherein the radar detection data can be point cloud data, and the radar detection data includes the target position of the target in the target scene, and may also include information such as the number of targets, target speed, and target distance. Specifically, the radar device transmits electromagnetic waves to the target scene and receives the reflected electromagnetic waves. After signal extraction and analysis, the signals are converted into point cloud data (i.e., radar detection data). By analyzing the radar detection data, a set of location points of at least one target detected by the millimeter-wave radar of the low-power device is obtained, wherein the set of location points consists of at least two location points of the target detected by the millimeter-wave radar. A corresponding target contour hotspot is determined based on the set of location points of each target.

[0037] For example, the millimeter-wave radar of a low-power device detects two sets of target location points, namely, set H1(x,y) and set H2(x,y), where set H1(x,y) = {t1(x1,y1), t2(x2,y2), t3(x3,y3)...tn(xn,yn)}, and set H2(x,Y) = {T1(x1,Y1), T2(x2,Y2), T3(x3,Y3)...Tn(xm,Tm)}. The corresponding target contour hotspot H1 is determined based on set H1(x,y), and the corresponding target contour hotspot H2 is determined based on set H2(x,Y). For example, Figure 2 This is a schematic diagram illustrating the distribution of a target contour heat area according to an embodiment of the present invention. It should be noted that the target contour heat area can be a regularly shaped region or an irregularly shaped region, and the shape and size of the target contour heat area can be the same or different.

[0038] S120. Based on the at least one target contour hot zone and the pre-stored mapping relationship between the radar detection area and the camera detection area, determine at least one local region of a video frame; wherein, the local region of the video frame corresponds one-to-one with the target contour hot zone.

[0039] In this embodiment of the invention, a pre-stored mapping relationship between a radar detection area and a camera detection area is obtained. The radar detection area is the region detectable by the millimeter-wave radar of the low-power device, and the camera detection area is the region monitored by the camera of the low-power device. For example, the radar detection area R(x,y) and the camera detection area R(x,y)' of the low-power device are determined, and the mapping relationship Q between the radar detection area R(x,y) and the camera detection area R(x,y)' is determined. Since both the radar detection area R(x,y) and the camera detection area R(x,y)' are composed of multiple location points, the mapping relationship Q can include the mapping relationship between each location point in the radar detection area R(x,y) and the corresponding location point in the camera detection area R(x,y)', as well as the coordinate transformation relationship between the two location points with the mapping relationship. For example, Figure 3 This is a schematic diagram illustrating the mapping relationship between a radar detection area and a camera detection area, provided as an embodiment of the present invention. Figure 3As shown, position point A(0, 0) in the radar detection area R(x, y) corresponds to A'(0, 0) in the camera detection area R(x, y)'; position point B(0, Ry) in the radar detection area R(x, y) corresponds to B'(0, Ry') in the camera detection area R(x, y)'; position point C(Rx, Ry) in the radar detection area R(x, y)' corresponds to C'(Rx', Ry') in the camera detection area R(x, y)'; and position point D(Rx, 0) in the radar detection area R(x, y)' corresponds to D'(Rx', 0) in the camera detection area R(x, y)'. Taking position points C(Rx, Ry) and C'(Rx', Ry') as an example, the coordinate transformation relationship between the two position points is: Qx = Rx / Rx', Qy = Ry / Ry'.

[0040] For each target contour hotspot in at least one target contour hotspot, a local region of the video frame corresponding to the target contour hotspot is determined based on the mapping relationship Q between the target contour hotspot and the radar detection area and the camera detection area. For example, based on the set of position points H1(x,y) corresponding to the target contour hotspot H1 and the mapping relationship Q, the set of camera detection position points H1(x,y)' corresponding to the set of position points H1(x,y) is determined. For instance, for the first position point t1(x1,y1) of H1(x,y), based on the first position point t1(x1,y1) and the mapping relationship Q, the first camera detection position point t1(x1',y1')' corresponding to the first position point t1(x1,y1) in H1(x,y) can be determined, where x1' = x1 / Qx, y1' = y1 / Qy; for H... Given the second position point t2(x2,y2) of H1(x,y), and the mapping relationship Q, the second camera detection position point t2(x2',y2')' corresponding to the second position point t2(x2,y2) in H1(x,y) can be determined, where x2' = x2 / Qx and y2' = y2 / Qy. Similarly, the nth camera detection position point tn(xn',yn')' corresponding to the nth position point tn(xn,yn) in H1(x,y) can be determined, where xn' = xn / Qx and yn' = yn / Qy. Based on these n camera detection position points, a set of camera detection position points H1(x,y)' can be constructed. Then, based on the set of camera detection position points H1(x,y)', the local video frame region H1' corresponding to the target contour hotspot H1 can be determined. The local region H2' of the video frame corresponding to the target contour hot zone H2 can be determined using the above method.

[0041] Optionally, before determining the local region of the video frame corresponding to each target contour hotspot, at least one target contour hotspot can be sorted in descending order of area. Following this descending order of area, the local region of the video frame corresponding to each target contour hotspot is determined sequentially based on the target contour hotspot and the pre-stored mapping relationship between the radar detection area and the camera detection area.

[0042] S130. For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame.

[0043] For example, for each local region of at least one video frame, an image corresponding to the local region can be acquired at a preset period. Then, target detection is performed on the image corresponding to each local region based on a preset target detection algorithm. The wake-up detection rate corresponding to the local region is determined based on the target detection results. The target detection object varies depending on the application scenario of the low-power device. For example, if the low-power device is an entrance door monitoring device, the target detection object can be a human figure, meaning human figure detection is performed on each local region of the video frame. Similarly, if the low-power device is a road monitoring device, the target detection object can be a vehicle, meaning vehicle detection is performed on each local region of the video frame.

[0044] Optionally, for each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame, including: for each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period, and the total number of detected targets and the number of detected targets that are preset type targets are counted; the ratio of the number of detected targets that are preset type targets to the total number of detected targets is used as the wake-up positive detection rate corresponding to the local region of the video frame.

[0045] For example, for each local region of a video frame, target detection is performed on the local region at a preset period, and the total number of detected targets and the number of targets that are preset types are counted. The total number of detected targets can be understood as the total number of times target detection is performed on the local region of the video frame at the preset period, and the number of targets that are preset types can be understood as the number of targets such as human figures or vehicles detected in multiple target detections. The ratio of the number of targets that are preset types to the total number of detected targets is used as the wake-up positive detection rate for the local region of the video frame. It is understood that when performing target detection on the local region of the video frame at the preset period, the wake-up positive detection rate for the local region of the video frame changes dynamically as the number of target detections increases. The wake-up positive detection rates for each local region of the video frame can be the same or different.

[0046] For example, a user can manually assign an initial positive detection rate to a local region of each video frame, and then perform target detection on the local region of the video frame according to a preset period, counting the number of detected targets of a preset type. Whenever the number of detected targets of a preset type corresponding to a local region of the video frame reaches a preset threshold within a preset number of detection periods, the initial positive detection rate of the local region of the video frame is increased by a preset step size, and the increased initial positive detection rate is used as the wake-up positive detection rate corresponding to the local region of the video frame. It should be noted that the wake-up positive detection rate corresponding to each local region of the video frame is less than the preset positive detection rate threshold. When the wake-up positive detection rate corresponding to a local region of the video frame reaches the preset positive detection rate threshold, the wake-up positive detection rate corresponding to the local region of the video frame remains unchanged.

[0047] S140. When the low-power device is in a sleep state, if a target appears in the target video frame local area of ​​the at least one video frame local area, determine whether the wake-up positive detection rate corresponding to the target video frame local area meets the preset condition. If so, wake up the low-power device from the sleep state to the working state.

[0048] In this embodiment of the invention, to reduce the power consumption of the low-power device and extend its battery life, the low-power device is controlled to be in a low-power mode, i.e., in a sleep state, when it is not performing corresponding business operations. When the low-power device is in sleep state, if at least one target contour hotspot is detected by the millimeter-wave radar of the low-power device, the corresponding local area of ​​the video frame can be determined to contain the target based on the correspondence between the local area of ​​the video frame and the target contour hotspot. For ease of description, the local area of ​​the video frame containing the target is referred to as the target video frame local area. For example, it is determined whether there is a wake-up positive detection rate greater than a preset wake-up threshold in the wake-up positive detection rate corresponding to the target video frame local area. If so, it indicates that there is a valid wake-up source in the target video frame local area of ​​the low-power device, and the low-power device is woken up from sleep state to working state. If not, it indicates that there is no valid wake-up source in the target video frame local area of ​​the low-power device, and the low-power device remains in sleep state.

[0049] Optionally, if a target appears in a target video frame local area within the at least one video frame local area, determine whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition. If so, wake up the low-power device from the sleep state to the working state, including: if a target appears in one of the at least one video frame local areas, determine whether the wake-up positive detection rate corresponding to the target video frame local area is greater than a wake-up threshold. If so, wake up the low-power device from the sleep state to the working state; if at least two target video frame local areas appear in the at least one video frame local area, wake up the low-power device from the sleep state to the working state when one of the wake-up positive detection rates corresponding to the at least two target video frame local areas is greater than the wake-up threshold.

[0050] In this embodiment of the invention, since a single target or multiple targets may appear simultaneously in the same local area of ​​a video frame, or multiple targets may appear simultaneously in different local areas of video frames, the target video frame local area where the target appears can be one or multiple. If there is only one target video frame local area, it is determined whether the wake-up positive detection rate corresponding to the target video frame local area is greater than the wake-up threshold. If so, the low-power device is woken up from the sleep state to the working state; otherwise, the low-power device remains in the sleep state. If there are multiple target video frame local areas, it is determined whether there is a wake-up positive detection rate greater than the wake-up threshold among the multiple target video frame local areas, that is, whether there is a target video frame local area whose wake-up positive detection rate is greater than the wake-up threshold. If so, the low-power device is woken up from the sleep state to the working state; otherwise, the low-power device remains in the sleep state. It should be noted that when determining whether there is a wake-up positive detection rate greater than the wake-up threshold among the multiple target video frame local areas, the wake-up thresholds corresponding to each target video frame local area can be the same or different. For example, the wake-up threshold can be a predetermined threshold, or it can be determined according to the area of ​​a local region of the target video frame. The larger the area of ​​the local region of the target video frame, the larger the corresponding wake-up threshold.

[0051] Optionally, after waking the low-power device from sleep mode to working mode, the method further includes: updating the wake-up positive detection rate corresponding to the local area of ​​the target video frame based on whether the target appearing in the local area of ​​the target video frame is a positive detection target. For example, after waking the low-power device from sleep mode to working mode, the camera of the low-power device can capture an image of the target appearing in the local area of ​​the target video frame, and target detection can be performed on the target image. Based on the detection result, it is determined whether the target appearing in the local area of ​​the target video frame is a positive detection target, that is, whether the target appearing in the local area of ​​the target video frame is a preset type target (such as a human or vehicle target). The wake-up positive detection rate corresponding to the local area of ​​the target video frame is updated based on whether the target appearing in the local area of ​​the target video frame is a positive detection target. For example, if the target appearing in the local area of ​​the target video frame is a positive detection target, the wake-up positive detection rate corresponding to the local area of ​​the target video frame is increased; if the target appearing in the local area of ​​the target video frame is not a positive detection target, the wake-up positive detection rate corresponding to the local area of ​​the target video frame is decreased. For example, if target detection is performed on a local area of ​​the target video frame according to a preset period, and the ratio of the number of detected targets of a preset type to the total number of detected targets is used as the wake-up positive detection rate for the local area of ​​the target video frame, then when the target appearing in the local area of ​​the target video frame is a positive detection target, the number of detected targets of the preset type and the total number of detected targets can be incremented by 1 respectively, and the ratio of the two can be used as the updated wake-up positive detection rate for the local area of ​​the target video frame; when the target appearing in the local area of ​​the target video frame is not a positive detection target, the number of detected targets of the preset type can be kept unchanged, and the total number of detected targets can be incremented by 1 respectively, and the ratio of the two can be used as the updated wake-up positive detection rate for the local area of ​​the target video frame.

[0052] The low-power device wake-up method of this invention involves the following steps: When the low-power device is in a working state, at least one target contour hotspot detected by the millimeter-wave radar of the low-power device is acquired; based on the at least one target contour hotspot and a pre-stored mapping relationship between radar detection areas and camera detection areas, at least one local region of a video frame is determined; wherein, each local region of the video frame corresponds one-to-one with the target contour hotspot; for each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame; when the low-power device is in a sleep state, if a target appears in the target local region of the at least one local region of the video frame, it is determined whether the wake-up positive detection rate corresponding to the target local region of the video frame meets a preset condition; if so, the low-power device is woken up from the sleep state to the working state. Through the technical solution provided by this invention, the low-power device can accurately and quickly distinguish between valid and invalid wake-up sources, thereby ensuring effective and rapid wake-up of the low-power device, reducing power consumption caused by invalid wake-ups, and extending the battery life of the low-power device as much as possible.

[0053] Example 2

[0054] Figure 4 This is a flowchart of a low-power device wake-up method provided in Embodiment 2 of the present invention, as follows: Figure 4 As shown, the method includes:

[0055] S410. When the low-power device is in operation, acquire at least one target contour hot zone detected by the millimeter-wave radar of the low-power device.

[0056] S420. Based on the at least one target contour hot zone and the pre-stored mapping relationship between the radar detection area and the camera detection area, determine at least one local region of a video frame; wherein, the local region of the video frame corresponds one-to-one with the target contour hot zone.

[0057] S430. For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame.

[0058] S440. Divide the camera detection area of ​​the low-power device into at least two sub-regions, and determine the region positive detection rate corresponding to each sub-region.

[0059] In this embodiment of the invention, the camera detection area of ​​the low-power device is divided into blocks, such as dividing the camera detection area into M equal sub-regions: area1, area2, area3, area4, ..., areaM, and determining the region positive detection rate corresponding to each sub-region, namely p(area1), p(area2), p(area3), ..., p(areaM). The region positive detection rate corresponding to each sub-region can be initially given. For example, the probability of a valid wake-up source appearing in each sub-region within a preset historical time period is statistically analyzed, and the region positive detection rate of the corresponding sub-region is determined based on the probability of a valid wake-up source appearing in each sub-region.

[0060] S450. For each of the video frame local regions, determine each target sub-region contained in the video frame local region from the at least two sub-regions.

[0061] For each local region of a video frame in at least one local region of a video frame, each sub-region contained within the local region of the video frame is determined from M sub-regions, and the sub-region contained within the local region of the video frame is taken as the target sub-region. For example, Figure 5 This is a schematic diagram illustrating the positional relationship between a local region and its sub-regions in a video frame, provided as an embodiment of the present invention. For example... Figure 5 As shown, the target sub-regions contained in the local region H1' of the video frame include 12 sub-regions in the upper left corner of the camera detection area.

[0062] S460. Determine the wake-up threshold corresponding to the local region of the video frame based on the region positive detection rate corresponding to each of the target sub-regions.

[0063] For example, for each local region of a video frame, the average of the region positive detection rates corresponding to all target sub-regions corresponding to the local region of the video frame is calculated, and the average of the region positive detection rates corresponding to all target sub-regions is used as the wake-up threshold corresponding to the local region of the video frame. Optionally, determining the wake-up threshold corresponding to the local region of the video frame based on the region positive detection rates corresponding to each of the target sub-regions includes: determining the area occupied by the local region of the video frame for each of the target sub-regions; determining the proportion of the area occupied by the local region of the video frame for the target sub-regions based on the occupied area and the area of ​​the corresponding target sub-region; wherein the proportion of the occupied area is the ratio of the occupied area to the area; and determining the wake-up threshold corresponding to the local region of the video frame based on the region positive detection rates corresponding to each of the target sub-regions and the proportion of the occupied area.

[0064] In this embodiment of the invention, each local region of a video frame may contain multiple target sub-regions. However, the area occupied by the local region of the video frame for each target sub-region may be the same or different. Therefore, the area occupied by the local region of the video frame for each corresponding target sub-region is determined. The ratio of the occupied area to the area of ​​the corresponding target sub-region is calculated, and this ratio is used as the proportion of the occupied area of ​​the local region of the video frame for the target sub-region. The proportion of the occupied area reflects the size of the coverage area of ​​the local region of the video frame for each target sub-region. Based on the positive detection rate of all target sub-regions corresponding to the local region of the video frame and the proportion of the occupied area for each target sub-region, the wake-up threshold corresponding to the local region of the video frame is calculated. For example, the weight of the positive detection rate of the target sub-region is calculated based on the proportion of the occupied area for each target sub-region. For instance, the proportion of the occupied area for each target sub-region is normalized, and the normalized proportion of the occupied area is used as the weight of the positive detection rate of the corresponding target sub-region. The weighted sum of the positive detection rates of all target sub-regions corresponding to the local region of the video frame is used as the wake-up threshold corresponding to the local region of the video frame. For example, the wake-up threshold corresponding to a local region of a video frame can be calculated according to the following formula: P'=E1*p(area1)+E2*p(area2)+E3*p(area3)+……+EM*p(areaM), where P' represents the wake-up threshold, and E1, E3, ..., EM represent the weights corresponding to each target sub-region.

[0065] S470: When the low-power device is in a sleep state, if a target appears in the target video frame local area of ​​the at least one video frame local area, determine whether the wake-up positive detection rate corresponding to the target video frame local area is greater than the wake-up threshold corresponding to the target video frame local area. If yes, execute S480; otherwise, execute S490.

[0066] S480, Wake up the low-power device from sleep state to working state.

[0067] S490, Control the low-power device to remain in sleep mode.

[0068] The low-power device wake-up method of this invention can dynamically adjust the wake-up threshold corresponding to the local area of ​​each video frame according to the environment in which the low-power device is located. This enables the low-power device to more accurately and quickly distinguish between valid wake-up sources and invalid wake-up sources, further ensuring the effective and rapid wake-up of the low-power device, reducing the power consumption caused by invalid wake-ups, and extending the battery life of the low-power device as much as possible.

[0069] Example 3

[0070] Figure 6This is a schematic diagram of a low-power device wake-up device provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes:

[0071] The target contour hot zone determination module 610 is used to acquire at least one target contour hot zone detected by the millimeter-wave radar of the low-power device when the low-power device is in operation.

[0072] The video frame local region determination module 620 is used to determine at least one video frame local region based on the at least one target contour hot zone and the pre-stored mapping relationship between radar detection area and camera detection area; wherein, the video frame local region corresponds one-to-one with the target contour hot zone;

[0073] The wake-up positive detection rate determination module 630 is used to perform target detection on the local region of each video frame according to a preset period and determine the wake-up positive detection rate corresponding to the local region of the video frame.

[0074] The device wake-up module 640 is used to determine whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition when the low-power device is in a sleep state and a target appears in the target video frame local area of ​​at least one video frame local area. If so, the low-power device is woken up from the sleep state to the working state.

[0075] Optionally, the device wake-up module is used for:

[0076] If a target video frame local region appears in at least one video frame local region, determine whether the wake-up positive detection rate corresponding to the target video frame local region is greater than the wake-up threshold. If so, wake up the low-power device from the sleep state to the working state.

[0077] If at least two target video frame local regions contain targets, then when the wake-up positive detection rate corresponding to the at least two target video frame local regions is greater than the wake-up threshold, the low-power device is woken up from the sleep state to the working state.

[0078] Optional, also includes:

[0079] The region positive detection rate determination module is used to divide the camera detection area of ​​the low-power device into at least two sub-regions and determine the region positive detection rate corresponding to each sub-region before determining whether the wake-up positive detection rate corresponding to the local region of the target video frame meets the preset conditions.

[0080] The target sub-region determination module is used to determine, for each of the video frame local regions, each target sub-region contained in the video frame local region from the at least two sub-regions;

[0081] The wake-up threshold determination module is used to determine the wake-up threshold corresponding to the local region of the video frame based on the region positive detection rate corresponding to each of the target sub-regions.

[0082] Optionally, the wake-up threshold determination module is used for:

[0083] Determine the area occupied by the local region of the video frame for each of the target sub-regions;

[0084] Based on the occupied area and the area of ​​the corresponding target sub-region, the proportion of the occupied area of ​​the local region of the video frame to the target sub-region is determined; wherein, the proportion of the occupied area is the ratio of the occupied area to the area of ​​the region;

[0085] The wake-up threshold corresponding to the local region of the video frame is determined based on the region positive detection rate and the occupied area ratio of each target sub-region.

[0086] Optionally, the wake-up positive detection rate determination module is used for:

[0087] For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period, and the total number of detected targets and the number of detected targets of a preset type are counted.

[0088] The ratio of the number of targets of a preset type to the total number of targets is used as the wake-up positive detection rate for a local region of the video frame.

[0089] Optionally, the device further includes:

[0090] The region positive detection rate update module is used to update the wake-up positive detection rate corresponding to the local area of ​​the target video frame based on whether the target appearing in the local area of ​​the target video frame is a positive detection target after waking the low-power device from the sleep state to the working state.

[0091] Optionally, the target contour hot zone determination module is used for:

[0092] Obtain a set of location points of at least one target detected by the millimeter-wave radar of the low-power device;

[0093] At least one target profile hot zone is determined based on the set of location points of the at least one target.

[0094] The low-power device wake-up device provided in the embodiments of the present invention can execute the low-power device wake-up method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0095] Example 4

[0096] Figure 7 A schematic diagram of a low-power device 10, which can be used to implement embodiments of the present invention, is shown. The term "low-power device" is intended to represent various forms of digital computers, such as laptops, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Low-power devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0097] like Figure 7 As shown, the low-power device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the low-power device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0098] Multiple components in the low-power device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network interface card, modem, wireless transceiver, etc. The communication unit 19 allows the low-power device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0099] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as low-power device wake-up methods.

[0100] In some embodiments, the low-power device wake-up method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the low-power device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the low-power device wake-up method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the low-power device wake-up method by any other suitable means (e.g., by means of firmware).

[0101] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0102] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0103] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0104] To provide interaction with a user, the systems and techniques described herein can be implemented on a low-power device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the low-power device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including sound input, voice input, or haptic input).

[0105] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0106] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0107] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0108] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A low-power device wake-up method, characterized in that, include: When the low-power device is in operation, acquire at least one target contour hotspot detected by the millimeter-wave radar of the low-power device; Based on the at least one target contour hot zone and the pre-stored mapping relationship between radar detection area and camera detection area, at least one local region of video frame is determined; wherein, the local region of video frame corresponds one-to-one with the target contour hot zone; For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame. When the low-power device is in a sleep state, if a target appears in a target video frame local area in at least one video frame local area, it is determined whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition. If so, the low-power device is woken up from the sleep state to the working state.

2. The method according to claim 1, characterized in that, If a target is found in the target video frame local region of the at least one video frame local region, determine whether the wake-up positive detection rate corresponding to the target video frame local region meets a preset condition. If so, wake up the low-power device from the sleep state to the working state, including: If a target video frame local region appears in at least one video frame local region, determine whether the wake-up positive detection rate corresponding to the target video frame local region is greater than the wake-up threshold. If so, wake up the low-power device from the sleep state to the working state. If at least two target video frame local regions contain targets, then when the wake-up positive detection rate corresponding to the at least two target video frame local regions is greater than the wake-up threshold, the low-power device is woken up from the sleep state to the working state.

3. The method according to claim 2, characterized in that, Before determining whether the wake-up positive detection rate corresponding to the local region of the target video frame meets the preset condition, the method further includes: The camera detection area of ​​the low-power device is divided into at least two sub-regions, and the positive detection rate of each sub-region is determined. For each local region of the video frame, each target sub-region contained in the local region of the video frame is determined from the at least two sub-regions; The wake-up threshold corresponding to the local region of the video frame is determined based on the region positive detection rate corresponding to each of the target sub-regions.

4. The method according to claim 3, characterized in that, Determining the wake-up threshold corresponding to the local region of the video frame based on the region positive detection rate corresponding to each of the target sub-regions includes: Determine the area occupied by the local region of the video frame for each of the target sub-regions; Based on the occupied area and the area of ​​the corresponding target sub-region, the proportion of the occupied area of ​​the local region of the video frame to the target sub-region is determined; wherein, the proportion of the occupied area is the ratio of the occupied area to the area of ​​the region; The wake-up threshold corresponding to the local region of the video frame is determined based on the region positive detection rate and the occupied area ratio of each target sub-region.

5. The method according to claim 1, characterized in that, For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period to determine the wake-up positive detection rate corresponding to the local region of the video frame, including: For each local region of the video frame, target detection is performed on the local region of the video frame according to a preset period, and the total number of detected targets and the number of detected targets of a preset type are counted. The ratio of the number of targets of a preset type to the total number of targets is used as the wake-up positive detection rate for a local region of the video frame.

6. The method according to claim 1, characterized in that, After waking the low-power device from sleep mode to operating mode, the method further includes: The wake-up positive detection rate corresponding to the local area of ​​the target video frame is updated based on whether the target appearing in the local area of ​​the target video frame is a positive detection target.

7. The method according to claim 1, characterized in that, Acquiring at least one target contour thermal area detected by the millimeter-wave radar of the low-power device includes: Obtain a set of location points of at least one target detected by the millimeter-wave radar of the low-power device; At least one target profile hot zone is determined based on the set of location points of the at least one target.

8. A low-power device wake-up device, characterized in that, include: The target contour hot zone determination module is used to acquire at least one target contour hot zone detected by the millimeter-wave radar of the low-power device when the low-power device is in operation. The video frame local region determination module is used to determine at least one video frame local region based on the at least one target contour hot zone and the pre-stored mapping relationship between radar detection area and camera detection area; wherein, the video frame local region corresponds one-to-one with the target contour hot zone; The wake-up positive detection rate determination module is used to perform target detection on the local region of each video frame according to a preset period and determine the wake-up positive detection rate corresponding to the local region of the video frame. The device wake-up module is used to determine whether the wake-up positive detection rate corresponding to the target video frame local area meets a preset condition when the low-power device is in a sleep state and a target appears in the target video frame local area of ​​at least one video frame local area. If so, the low-power device is woken up from the sleep state to the working state.

9. A low-power device, characterized in that, The low-power device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the low-power device wake-up method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the low-power device wake-up method according to any one of claims 1-7.

Images