CN111985309A

CN111985309A - Alarm method, camera device and storage device

Info

Publication number: CN111985309A
Application number: CN202010646626.5A
Authority: CN
Inventors: 郑雪慧
Original assignee: Qiku Internet Technology Shenzhen Co Ltd
Current assignee: Qiku Internet Technology Shenzhen Co Ltd
Priority date: 2020-07-07
Filing date: 2020-07-07
Publication date: 2020-11-24

Abstract

The application discloses an alarming method, a camera device and a storage device, wherein the alarming method comprises the following steps: the method comprises the steps that a current camera device obtains a target position where a target object sending a preset voice command is located; if the target position is not in the field of view, acquiring an original image shot by the target camera device; the shooting range of the target camera device and the shooting range of the current camera device have a complementary relation; analyzing the behavior type of the target object in the original image, and sending a first alarm notice when the behavior type meets a preset condition. According to the scheme, the alarm accuracy can be improved.

Description

Alarm method, camera device and storage device

Technical Field

The present application relates to the field of information technologies, and in particular, to an alarm method, a camera device, and a storage apparatus.

Background

With the development of electronic information technology, imaging devices such as monitoring cameras are gradually applied to scenes such as alarm notification and remote management, so as to meet the requirements of people on aspects of production management, daily life and the like.

Here, the warning notification is one of many key functions of an image pickup device such as a monitoring camera. At present, extensive research is also being conducted around the function of alert notification. However, the existing warning methods all have the problem of low accuracy, so that the normal use of the user may be affected. In view of this, how to improve the alarm accuracy becomes an urgent problem to be solved.

Disclosure of Invention

The technical problem that this application mainly solved is to improve and report an emergency and ask for help or increased vigilance the accuracy.

In order to solve the technical problem, the technical scheme adopted by the application is as follows: provided is an alarm method, including: the method comprises the steps that a current camera device obtains a target position where a target object sending a preset voice command is located; if the target position is not in the field of view, acquiring an original image shot by the target camera device; the shooting range of the target camera device and the shooting range of the current camera device have a complementary relation; analyzing the behavior type of the target object in the original image, and sending a first alarm notice when the behavior type meets a preset condition.

In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a camera device comprising a processor, a memory, a communication circuit, a camera, and a microphone, the memory, the communication circuit, the camera, and the microphone all coupled to the processor, the memory storing program instructions, the processor for executing the program instructions to implement the above-described alerting method in conjunction with the communication circuit, the camera, and the microphone.

In order to solve the above technical problem, the present application adopts another technical solution: there is provided a memory device storing program instructions executable by a processor for implementing the above-described alert method.

The beneficial effect of this application is: different from the situation of the prior art, the warning method provided by the application can enable the current camera device to acquire the target position of the target object which sends the preset voice command, so that when the target position is not in the field of view of the current camera device, the original image which is shot by the target camera device is acquired, the shooting range of the target camera device has a complementary relation with the shooting range of the current camera device, the behavior type of the target object in the original image is further analyzed, and when the behavior type meets the preset condition, a first warning notice is sent out, so that the target position where the target object which sends the command is located can be determined under the trigger of the preset voice command, and when the target position is not in the field of view, the original image which is shot by the target camera device which has the complementary relation with the target position is acquired, so as to make up the deficiency of the field of the target position, and then can send out and report an emergency and ask for help or increased vigilance and notify together to trigger on the basis of follow-up image analysis and preset voice command, so can greatly reduce the probability that the wrong report takes place, improve and report an emergency and ask for help or increased vigilance the accuracy.

Drawings

In order to more clearly illustrate the technical solutions in the present application, the drawings required in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor. Wherein:

FIG. 1 is a schematic flow chart diagram of an embodiment of an alarm method of the present application;

FIG. 2 is a schematic diagram of an embodiment of a horizontal field of view range of an imaging device;

FIG. 3 is a schematic diagram of an embodiment of a vertical field of view range of an imaging device;

FIG. 4 is a schematic flow chart diagram illustrating another embodiment of an alert method of the present application;

FIG. 5 is a schematic view of one embodiment of a state of a mobile device moving to a target position;

FIG. 6 is a schematic diagram of a frame of an embodiment of the image pickup device of the present application;

FIG. 7 is a block diagram of an embodiment of a memory device according to the present application.

Detailed Description

The following describes in detail the embodiments of the present application with reference to the drawings attached hereto.

In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, interfaces, techniques, etc. in order to provide a thorough understanding of the present application.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship. Further, the term "plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of an alarm method according to the present application. Specifically, the method may include the steps of:

step S11: the current camera device acquires a target position where a target object which sends a preset voice command is located.

The image pickup device may include, but is not limited to: dome cameras, gun cameras, may include, but are not limited to, according to their operating spectrum: the specific type of the infrared camera, the visible light camera, and the camera device may be set according to the actual application scene, and is not limited herein.

In an implementation scenario, multiple cameras may be configured in the same place, for example, for a home scenario, a camera may be set outside the door to cover a corridor, a camera may be set in the hallway to cover the hallway and a part of the living room, a camera may be set in the living room to cover the living room, and a camera may be set in the kitchen to cover the kitchen, the dining room, and a part of the living room; or, for an office scene, a door may be provided with a camera device for covering a door area, an office area may be provided with at least one camera device for covering the office area, and a conference room may be provided with at least one camera device for covering the conference room. The above examples are only possible arrangements in practical application, and the specific arrangement may be set according to practical scenarios, which is not limited herein.

In the embodiment of the present disclosure, the image pickup device may be provided with a plurality of microphones to form a microphone array, and the microphone array may be a linear array, a circular array, or the like, which is not limited herein, and is used for monitoring the sound of the surrounding environment and positioning the sound. In an implementation scene, the camera device can acquire audio data by using a microphone while acquiring an image, so that the audio data is identified, whether the audio data contains a preset voice instruction or not is judged, and when the audio data contains the preset voice instruction, a preset sound source positioning mode is used for positioning to obtain a target position of a target object. In one particular implementation scenario, speech recognition may be performed in ways including, but not limited to: vector quantization, dynamic time warping, a gaussian mixture model, a hidden markov model, a support vector machine, an artificial neural network and a deep neural network, which can be specifically set according to the actual application requirements and are not limited herein. In another specific implementation scenario, the preset sound source localization mode may include, but is not limited to: MVDR (Minimum Variance Distortionless Response algorithm), MUSIC (Multiple Signal Classification), CBF (Conventional Beam Former), and the like, which may be specifically set according to actual application needs, and are not limited herein. The target position may be a relative position of the target object with respect to the current image capture device, which may include an angle and a distance of the target object with respect to the current image capture device. Referring to fig. 2 and 3 in combination, fig. 2 is a schematic diagram of an embodiment of a horizontal field range of an image pickup device, fig. 3 is a schematic diagram of an embodiment of a vertical field range of an image pickup device, as shown in fig. 2, an angle may include an angle between a connection line of a target object and the image pickup device in a horizontal direction and an optical axis of the image pickup device, such as an angle α between a connection line of the target object a and the image pickup device O in the horizontal direction and the optical axis of the image pickup device, as shown in fig. 3, an angle may also include an angle between a connection line of the target object and the image pickup device in a vertical direction and a normal line of the image pickup device perpendicular to the ground, such as an angle β between a connection line of the target object D and the image pickup device O in. With continuing reference to fig. 2, the distance may include a distance between the target object and the image pickup device in a horizontal direction, such as a distance AO between the target object a and the image pickup device O in the horizontal direction, or, with continuing reference to fig. 3, the distance may also include a distance between the target object and the image pickup device in a vertical direction, such as a distance DO between the target object D and the image pickup device O in the vertical direction, and so on for other scenes, which is not illustrated here.

The target object may be set according to actual application needs, for example, in application scenarios such as fall seeking help, robbery seeking help, and the like, the target object may be a person, and at this time, the preset voice instruction may include but is not limited to: "alarm", "rescue", "help me"; or, in an application scenario such as an unmanned invigilator, the target object may also be a person, and at this time, the preset voice instruction may include any sound of conversation or communication, and may be specifically set according to an actual application requirement, which is not limited herein. In addition, in other possible application scenarios, the target object may also be set as an object other than a person as required. For example, in a scene in which a whistling vehicle is detected in a whistling area, the target object may also be a vehicle, and in this case, the preset voice instruction may include a whistling sound.

Step S12: and judging whether the target position is in the field of view, if not, executing the step S13, otherwise, executing the step S15.

The field of view range of the image pickup device may include a field of view range that the image pickup device can cover in the horizontal direction and a field of view range that the image pickup device can cover in the vertical direction. Referring to fig. 2 and fig. 3, as shown in fig. 2, the dotted line indicates the optical axis of the image pickup device, and the image pickup device has view field ranges with an angle θ at both sides of the optical axis, respectively, so that the image pickup device has a view field range of 2 θ in the horizontal direction, and therefore, the angle between a and the optical axis in the horizontal direction is smaller than θ, and therefore, a is within the view field range of the image pickup device in the horizontal direction, whereas, the angle between B and the optical axis in the horizontal direction is larger than θ, and therefore, B is outside the view field range of the image pickup device in. As shown in fig. 3, the straight arrows indicate the field of view of the imaging device in the vertical direction, so C is out of the field of view of the imaging device in the vertical direction, whereas D is within the field of view of the imaging device in the vertical direction, and so on, and the description is not limited herein. When the field of view ranges in both the horizontal direction and the vertical direction of the imaging device are present, the target position can be considered to be within the field of view range. In addition, camera device can also include the cloud platform, and then camera device's visual field scope can also be the scope that can cover after the cloud platform drives the rotation, for example, the cloud platform can drive and rotate in the horizontal direction, and perhaps, the cloud platform can drive and rotate in the vertical direction, and it is no longer repeated here.

Step S13: and acquiring an original image shot by the target camera device.

In the embodiment of the present disclosure, the shooting range of the target image pickup device has a complementary relationship with the shooting range of the current image pickup device.

In an implementation scenario, the complementary relationship includes a field of view complementary relationship, for example, in the home scenario, the cameras in the hallway, the living room and the prescription place can all shoot the living room, and because the three are installed at different positions, the shooting ranges of the three are different, that is, any one of the three can shoot the field of view which cannot be covered by the other two, for example, the camera installed in the living room can cover most of the living room, but usually still has a certain blind area, such as cannot cover the right lower side of the living room, the field of view of the cameras in the hallway and the kitchen can complement the blind area, the cameras in the hallway and the kitchen can complement the blind area of the field of view, and in this case, the camera in the living room has the field of view complementary relationship with the camera in the hallway and the camera in the kitchen, similarly, the camera device of the entrance has a field-of-view complementary relationship with the camera device of the living room and the camera device of the kitchen, and the camera device of the kitchen has a field-of-view complementary relationship with the camera device of the entrance and the camera device of the living room. Other scenarios, which may be analogized, are not illustrated here. Therefore, a first original image captured by a first target imaging device having a field-of-view complementary relationship with the current imaging device can be acquired, and whether a target object exists in the first original image can be detected.

In another implementation scenario, the complementary relationship may further include a shielding complementary relationship, and in the above home scenario, a partition such as a screen may be installed in the home environment, so that the field of view of the image pickup device can cover the partition such as the screen, but due to the shielding of the partition such as the screen, the image pickup device cannot effectively cover the back of the partition such as the screen. Other scenarios, which may be analogized, are not illustrated here. Therefore, a second original image shot by a second target camera device having an occlusion complementary relationship with the current camera device can be acquired, and whether a target object exists in the second original image or not can be detected.

In a specific implementation scenario, the step of detecting whether the target object exists may be implemented by detecting the image by using a pre-trained target detection model, specifically, the target detection model may include a support vector machine, an AdaBoost and other traditional classifiers, or may include a yolo (young Only Look one), a fast R-CNN and other neural networks, and may be specifically set according to application needs, which is not limited herein.

In another specific implementation scenario, the current image pickup device and the target image pickup device are configured in the same network through a network device, and the network device may specifically include: the router, the mobile phone and the like can acquire configuration information input by a user through network equipment, the configuration information comprises the relationship between every two image pickup devices in the network, specifically comprises any one of a complementary relationship and a non-relationship, and further the configuration information can be analyzed to determine a target image pickup device having a complementary relationship with the current image pickup device. For example, the image pickup device a, the image pickup device B, and the image pickup device C are configured in the same network through a router, a mobile phone, and other network devices, and each image pickup device can acquire configuration information input by a user through the mobile phone and the router, where the configuration information includes: the camera device A and the camera device B have no relation, the camera device B and the camera device C have a view field complementary relation, and the camera device A and the camera device C have a shielding complementary relation, so that the camera device A can determine the target camera device C having the shielding complementary relation after analyzing the configuration information, the camera device B can determine the target camera device C having the view field complementary relation after analyzing the configuration information, and the camera device C can determine the target camera device B having the view field complementary relation and the target camera device A having the shielding complementary relation after analyzing the configuration information. The above example is only one kind of configuration information that may exist in actual application, and the specific implementation may be set according to actual application requirements, which is not described herein.

Step S14: analyzing the behavior type of a target object in an original image shot by a target camera device, and sending a first alarm notice when the behavior type meets a preset condition.

In an implementation scenario, when the complementary relationship includes a field-of-view complementary relationship, a first original image captured by a first target imaging device having the field-of-view complementary relationship with a current imaging device may be acquired, whether a target object exists in the first original image is detected, and when the target object exists in the first original image, a behavior type of the target object in the first original image is analyzed, so that when the behavior type meets a preset condition, a first warning notification is issued.

In another implementation scenario, the complementary relationship further includes an occlusion complementary relationship, and when the first original image does not have the target object, it may be determined that the target object is occluded, and a second original image captured by a second target imaging device having the occlusion complementary relationship with the current imaging device is obtained, so as to detect whether the second original image has the target object, and when the second original image has the target object, a behavior type of the target object in the second original image is analyzed, so that when the behavior type meets a preset condition, a first warning notification is sent.

In a specific implementation scenario, the behavior type analysis manner may be obtained by analyzing a pre-trained behavior recognition model, where the behavior recognition model may specifically include a convolutional neural network, and a specific structure of the convolutional neural network is not described herein again.

In another specific implementation scenario, the preset conditions include: the behavior type is a preset type. Specifically, the preset types may be set according to actual application needs, for example, in application scenarios such as fall seeking help and robbery seeking help, the preset types may include: at least one of falling and fighting; or, in an application scenario such as an unmanned invigilator, the preset types may include: turning to talk, watching a mobile phone, and the like, and other scenes can be analogized, and the method is not limited herein.

In another specific implementation scenario, if there is no target object in the first original image and there is no second target image pickup device with an occlusion complementary relationship in the current image pickup device, a second warning notification is issued, and if there is no target object in the second original image, a third warning notification is issued, since the first warning notification is triggered by the preset voice command and the behavior type together, and the false alarm rate of the warning is the lowest, i.e. the determination degree of the warning is the highest, the importance level of the first warning notification is the highest, and the second warning notification and the third warning notification are triggered only by the preset voice command, there is a certain false alarm rate, but the difference is that the second warning notification does not combine with the occlusion complementary, so there is a probability that the target object is actually occluded, i.e. the determination degree of the warning is the second, and the third warning notification combines with the field of view complementary and the occlusion complementary without finding the target object, i.e. the degree of determination of the alert is again such that the importance level of the first alert notification is higher than the importance level of the second alert notification, which is higher than the importance level of the third alert notification. Therefore, through the alarm notification with different importance degrees, the people notified by the alarm can timely know the severity of the alarm, and the user experience is favorably improved.

In another specific implementation scenario, the first alarm notification, the second alarm notification, and the third alarm notification may be sent to a pre-associated terminal (e.g., a mobile phone) of a contact through a network, and may be specifically set according to an actual application requirement, which is not limited herein.

Step S15: and acquiring an original image shot by the current camera device.

When the target position is within the field of view of the current camera device, the original image shot by the current camera device can be directly obtained.

Step S16: analyzing the behavior type of a target object in an original image shot by the current camera device, and sending a first alarm notice when the behavior type meets a preset condition.

Specifically, target detection may be performed on an original image captured by the current image capture device, a target object may be determined, behavior analysis may be performed on the target object, and a behavior type of the target object is obtained, and the target detection and behavior analysis may specifically refer to the foregoing description, which is not described herein again.

In a specific implementation scenario, if an original image captured by a current image capture device does not include a target object, it may be considered that the target object is within a field of view of the current image capture device, but is probably occluded, so that a second original image captured by a second target image capture device having an occlusion complementary relationship with the target object may be obtained, and target detection may be performed on the second original image to determine the target object, and perform behavior analysis on the target object to obtain a behavior type of the target object, which may specifically refer to the foregoing description, and will not be described herein again.

According to the scheme, the current camera device obtains the target position of the target object which sends the preset voice command, so that when the target position is not in the field of view of the current camera device, the original image shot by the target camera device is obtained, the shooting range of the target camera device has a complementary relation with the shooting range of the current camera device, the behavior type of the target object in the original image is analyzed, and when the behavior type meets the preset condition, a first alarm notice is sent, so that the target position where the target object which sends the command is located can be determined under the trigger of the preset voice command, and when the target position is not in the field of view, the original image shot by the target camera device which has the complementary relation with the target object can be obtained to make up the deficiency of the field of view of the current camera device, and then the alarm notice can be sent based on the common trigger of subsequent image analysis and the preset voice command, therefore, the probability of false alarm occurrence can be greatly reduced, and the alarm accuracy is improved.

Referring to fig. 4, fig. 4 is a schematic flowchart illustrating an alarm method according to another embodiment of the present application. Specifically, the method may include the steps of:

step S41: the current camera device acquires a target position where a target object which sends a preset voice command is located.

Reference may be made in particular to the relevant steps in the embodiments of the foregoing disclosure.

Step S42: and judging whether the target position is in the field of view. If not, step S43 is executed, and if yes, step S44 is executed.

Step S43: and acquiring an original image shot by the target camera device.

Step S44: and acquiring an original image shot by the current camera device.

Step S45: and detecting whether the original image has the target object, if so, executing the step S46, otherwise, executing the step S47.

The manner of detecting whether the target object exists may specifically refer to the related description in the foregoing disclosed embodiments, and is not described herein again.

Step S46: analyzing the behavior type of the target object in the original image, and sending a first alarm notice when the behavior type meets a preset condition.

Step S47: determining that the target object is not within the current shooting range of the camera device and the target camera device, and sending a movement prompt to the movable equipment to prompt the movable equipment to move to the target position.

In the embodiment of the present disclosure, when the target object does not exist in the original image, it may be determined that the target object is not within the shooting ranges of the current image pickup device and the target image pickup device.

In an implementation scene, the target object is not in the shooting range of the current camera device and the target camera device, and the target position of the target object is seriously shielded, so that the current camera device and the target camera device cannot be effectively covered; or, although the target position of the target object is not blocked, the currently configured imaging device is still insufficient to completely cover the scene. Taking a home scene as an example, an image pickup device is not usually installed in a private place such as a bathroom or a bedroom, and at this time, if a target object is in such a private place, the target object is severely shielded by a wall and the like, so that the target object cannot be effectively photographed by both the current image pickup device and the target image pickup device. For example, when a target object falls down and cannot move when bathing in a bathroom, a preset voice command such as 'rescue me' can be used for triggering the camera device to analyze the behavior type of the target object, and at the moment, the camera device cannot shoot the target object; or, for example, when the elderly people living alone fall down in the bedroom and cannot climb up, the behavior type of the target object can be analyzed by triggering the camera device through a preset voice instruction such as "help me", and the camera device cannot shoot the target object at the moment, and other situations can be analogized, so that the examples are not repeated.

In an implementation scenario, the original image may include at least one of an original image captured by a current image capturing device, a first original image captured by a first target image capturing device having a field-of-view complementary relationship with the current image capturing device, and a second original image captured by a second target image capturing device having an occlusion complementary relationship with the current image capturing device, and may be specifically set according to an actual application situation, which is not limited herein. For example, if the current image pickup device corresponds to a first target image pickup device having a field of view complementary relationship with the current image pickup device, when there is no target object in the original image captured by the current image pickup device and the first original image captured by the first target image pickup device, it may be determined that the target object is not within the capturing range of the current image pickup device and the target image pickup device; alternatively, for example, if the current image pickup device corresponds to a first target image pickup device having a field of view complementary relationship with the current image pickup device and a second target image pickup device having an occlusion complementary relationship with the current image pickup device, it may be determined that the target object is not within the shooting ranges of the current image pickup device and the target image pickup device when there is no target object in the original image shot by the current image pickup device, the first original image shot by the first target image pickup device, and the second original image shot by the second target image pickup device.

In an implementation scenario, the mobile device and the current image pickup device are configured in the same network through a network device, and specifically, the network device may include a router, a mobile phone, and the like, which is not limited herein. The movable device may specifically include at least one of a sweeping robot, an educational robot, and a service robot, which are not limited herein.

In one implementation scenario, the movement cue may include a target location such that the mobile device, upon receiving the movement cue, may move to the target object according to the target location. Specifically, when the mobile device is used for the first time, the mobile device may acquire the scene map through full-scene scanning, and prompt the user to label other devices such as the image pickup device on the scene map, so as to receive labeling information (e.g., device location and device identification) of the user to the other devices such as the image pickup device, the current image pickup device may package the device identification and the target location as a movement prompt, and send the movement prompt to the mobile device, the mobile device analyzes the movement prompt to obtain the device identification and the target location, and may determine the device location of the current image pickup device in the scene map according to the device identification, so that according to the device location and the target location, the mobile device may determine a navigation path to the target object, and may arrive at the target object according to the navigation path. Referring to fig. 5 in combination, fig. 5 is a schematic state diagram of an embodiment in which the mobile device moves to a target position, as shown in fig. 5, when the mobile device is used for the first time, a scene map can be obtained by scanning a whole scene, and other devices marked in the scene map by a user include an image pickup device a and an image pickup device B, and the target position where the target object can be obtained by positioning is 30 degrees and 6 meters north of the current image pickup device a, when the mobile device receives a movement prompt, the current image pickup device can be determined as the image pickup device a according to a device identifier, and the position of the target object in the scene map (i.e., the position where the black dot in fig. 5 is located) is determined by combining the target position and the position of the image pickup device a in the scene map, and the mobile device can generate a navigation path shown by a dotted arrow in fig. 5 using the position as a destination, and moving to the target object according to the navigation path. The navigation path shown in fig. 5 is only one possible path in practical application, and may be specifically set according to practical application conditions, and is not limited herein.

Step S48: analyzing the behavior type of the target object in the scanned image, and sending a first alarm notice when the behavior type meets a preset condition.

In one implementation scenario, the movable device may be integrated with a camera, and the scanned image may be a visible light image, and in another implementation scenario, the movable device may be integrated with a radar, and the scanned image may be a depth image, which may be specifically set according to an actual application situation, and is not limited herein. When the scanned image is a visible light image, a pre-trained behavior recognition model may be used to perform recognition processing on the scanned image to obtain a behavior type of the target object, which may specifically refer to the relevant description in the foregoing disclosed embodiment, and details are not described here. When the scanned image is a depth image, feature analysis may be performed on the depth image to determine whether a target object having a preset behavior type exists in the depth image. For example, when the target object is a person, feature analysis may be performed on the depth image, and if there is a contour feature of the person, it may be determined that the person exists in the depth image, at this time, a markov random field model may be used to perform skeleton division on the depth image, and divide the human body into a head, four limbs, a trunk, and the like, so that the state of the person may be determined according to the states of the head, the four limbs, the trunk, and the like, and specifically, the setting may be performed according to actual application requirements, which is not illustrated herein.

In another implementation scenario, the movable device may not reach the target location, and as shown in FIG. 5, when the door through which the navigation path indicated by the arrow in FIG. 5 passes is closed, the movable device may not reach the target object, and a fourth alert notification may be issued, and the importance level of the fourth alert notification may be set to be lower than that of the first alert notification. In yet another implementation scenario, the scanned image scanned by the mobile device may not include the target object, and a fourth alert notification may be issued.

Different from the embodiment disclosed in the foregoing, when the target object does not exist in the original image, it is determined that the target object is not within the shooting range of the current image pickup device and the target image pickup device, and a movement prompt is sent to the mobile device to prompt that the mobile device is moved to the target position, so as to obtain a scanned image scanned at the target position by the mobile device, analyze the behavior type of the target object in the scanned image, and send a first alarm notification when the behavior type meets a preset condition.

Referring to fig. 6, fig. 6 is a schematic diagram of a frame of an embodiment of an image pickup device 60 according to the present application. The camera device 60 comprises a processor 61, a memory 62, a communication circuit 63, a camera 64 and a microphone 65, the memory 62, the communication circuit 63, the camera 64 and the microphone 65 are all coupled to the processor 61, the memory 62 stores program instructions, and the processor 61 is configured to execute the program instructions to implement the steps in any of the above-described embodiments of the alert method in conjunction with the communication circuit 63, the camera 64 and the microphone 65. In one implementation scenario, the image capture device 60 may include, but is not limited to: a dome camera, a gun camera, etc., which can be specifically set according to the actual application requirement, and are not limited herein.

Specifically, the communication circuit 63 is used for communicating with other devices, the camera 64 is used for collecting image data, and the microphone 65 is used for collecting audio data. The processor 61 may also be referred to as a CPU (Central Processing Unit). The processor 61 may be an integrated circuit chip having signal processing capabilities. The Processor 61 may also be a general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 61 may be commonly implemented by a plurality of integrated circuit chips.

In the embodiment of the present disclosure, the processor 61 is configured to control the microphone 65 to obtain a target position where a target object that sends a preset voice instruction is located, the processor 61 is configured to control the communication circuit 63 to obtain an original image captured by the target image capturing device when the target position is not within the field of view, where the capturing range of the target image capturing device has a complementary relationship with the capturing range of the current image capturing device, and the processor 61 is configured to analyze a behavior type of the target object in the original image and send a first warning notification when the behavior type meets a preset condition.

In some disclosed embodiments, the complementary relationship comprises a field of view complementary relationship, the processor 61 is further configured to control the communication circuit 63 to obtain a first raw image captured by a first target imaging device having a field of view complementary relationship with a current imaging device, the processor 61 is further configured to detect whether a target object exists in the first raw image, and the processor 61 is further configured to analyze a behavior type of the target object in the first raw image when the target object exists in the first raw image.

Different from the foregoing embodiment, the complementary relationship is set to include a field of view complementary relationship, and by acquiring a first original image captured by a first target camera device having the field of view complementary relationship with a current camera device and analyzing a behavior type of a target object in the first original image when the target object exists in the first original image, the field of view blind area of the current camera device can be made up by using the first target camera device, so that the accuracy of warning can be improved.

In some disclosed embodiments, the complementary relationship further includes an occlusion complementary relationship, the processor 61 is further configured to determine that the target object is occluded when the target object does not exist in the first original image, and control the communication circuit 63 to acquire a second original image captured by a second target imaging device having an occlusion complementary relationship with the current imaging device, the processor 61 is further configured to detect whether the target object exists in the second original image, and the processor 61 is further configured to analyze a behavior type of the target object in the second original image when the target object exists in the second original image.

Different from the foregoing embodiment, the complementary relationship further includes an occlusion complementary relationship, when the target object does not exist in the first original image, it is determined that the target object is occluded, and a second original image captured by a second target camera device having the occlusion complementary relationship with the current camera device is obtained, so that when the target object exists in the second original image, the behavior type of the target object in the second original image is analyzed, the occlusion blind area of the current camera device can be made up by using the second target camera device, and the alarm accuracy can be improved.

In some disclosed embodiments, the processor 61 is further configured to issue a second warning notification when the target object does not exist in the first original image and the current image capture device does not exist a second target image capture device having an occlusion complementary relationship, and the processor 61 is further configured to issue a third warning notification when the target object does not exist in the second original image, and an importance level of the first warning notification is higher than an importance level of the second warning notification, and an importance level of the second warning notification is higher than an importance level of the third warning notification.

Different from the embodiment, the alarm notification with different important levels is sent out under different conditions, so that people notified of the alarm notification can know the degree of the alarm in time, and the user experience is improved.

In some disclosed embodiments, the processor 61 is further configured to determine that the target object is not within the shooting range of the current image pickup device and the target image pickup device when the target object does not exist in the original image, and send a movement prompt to the movable device to prompt the movable device to move to the target position, the processor 61 is further configured to control the communication circuit 63 to acquire a scanned image scanned at the target position by the movable device, and the processor 61 is further configured to analyze a behavior type of the target object in the scanned image, and issue a first warning notification when the behavior type satisfies a preset condition.

Different from the embodiment, when the target object does not exist in the original image, the target object is determined not to be in the shooting range of the current camera device and the target camera device, the movement prompt is sent to the movable equipment to prompt the movable equipment to move to the target position, so that the scanned image scanned at the target position by the movable equipment is obtained, the behavior type of the target object in the scanned image is analyzed, and the first alarm notification is sent when the behavior type meets the preset condition.

In some disclosed embodiments, the processor 61 is further configured to issue a fourth alert notification when the mobile device is detected to be unable to reach the target location, or when the target object is not included in the scanned image, and the importance level of the first alert notification is higher than the importance level of the fourth alert notification. And/or the movable equipment and the current camera device are configured in the same network through network equipment, and the movable equipment comprises at least one of a sweeping robot, an educational robot and a service robot.

Different from the foregoing embodiment, when it is detected that the mobile device cannot reach the target position or the scanned image does not include the target object, the fourth warning notification is sent, and the importance level of the first warning notification is higher than that of the fourth warning notification, so that when the mobile device cannot reach the target position or the scanned image does not include the target object, a warning notification with a lower importance level can be sent, a person notified of the warning notification can timely know the urgency and the lightness of the warning, and the improvement of user experience is facilitated.

In some disclosed embodiments, the current image capturing device and the target image capturing device are configured in the same network through a network device, the processor 61 is further configured to control the communication circuit 63 to obtain configuration information input by a user through the network device, the configuration information includes a relationship between every two image capturing devices in the network, the relationship includes any one of a complementary relationship and a non-relationship, and the processor 61 is further configured to parse the configuration information and determine the target image capturing device having a complementary relationship with the current image capturing device.

Different from the foregoing embodiment, the current image capturing device and the target image capturing device are configured in the same network through the network device, so as to obtain the configuration information input by the user through the network device, and the configuration information includes a relationship between every two image capturing devices in the network, where the relationship includes any one of a complementary relationship and a non-relationship, so as to analyze the configuration information and determine the target image capturing device having a complementary relationship with the current image capturing device, so that the user can customize the relationship between the image capturing devices according to the actual placement position of the image capturing device, and each image capturing device can analyze and obtain the target image capturing device having a complementary relationship with the image capturing device, thereby widening the application range of the warning method.

In some disclosed embodiments, the preset conditions include: the behavior type is a preset type; wherein the preset type comprises at least one of falling and fighting.

Referring to fig. 7, fig. 7 is a schematic diagram of a memory device 70 according to an embodiment of the present application. The memory device 70 stores program instructions 701 executable by the processor, the program instructions 701 being for implementing the steps in any of the alert method embodiments described above.

According to the scheme, the current camera device can acquire the original image shot by the target camera device with the complementary relation with the current camera device so as to make up the deficiency of the field range of the current camera device, and further can send out the alarm notification based on the common triggering of the subsequent image analysis and the preset voice instruction, so that the probability of the occurrence of false alarm can be greatly reduced, and the alarm accuracy is improved.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

The foregoing description of the various embodiments is intended to highlight various differences between the embodiments, and the same or similar parts may be referred to each other, and for brevity, will not be described again herein.

In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely one type of logical division, and an actual implementation may have another division, for example, a unit or a component may be combined or integrated with another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Claims

1. An alert method, comprising:

the method comprises the steps that a current camera device obtains a target position where a target object sending a preset voice command is located;

if the target position is not in the field of view, acquiring an original image shot by a target camera device; the shooting range of the target camera device and the shooting range of the current camera device have a complementary relation;

analyzing the behavior type of the target object in the original image, and sending a first alarm notice when the behavior type meets a preset condition.

2. The method of claim 1, wherein the complementary relationship comprises a field of view complementary relationship; the acquiring of the original image captured by the target imaging device includes:

acquiring a first original image shot by a first target camera device having the field of view complementary relation with the current camera device;

detecting whether the target object exists in the first original image;

the analyzing the behavior type of the target object in the original image comprises:

if the target object exists in the first original image, analyzing the behavior type of the target object in the first original image.

3. The method of claim 2, wherein the complementary relationship further comprises an occlusion complementary relationship; the method further comprises the following steps:

if the target object does not exist in the first original image, determining that the target object is blocked, and acquiring a second original image shot by a second target camera device having the blocking complementary relation with the current camera device;

detecting whether the target object exists in the second original image;

and if the target object exists in the second original image, analyzing the behavior type of the target object in the second original image.

4. The method of claim 3, further comprising:

if the target object does not exist in the first original image and the current camera device does not have a second target camera device with the shielding complementary relation, sending a second alarm notification;

if the target object does not exist in the second original image, sending a third alarm notification;

wherein the importance level of the first alert notification is higher than the importance level of the second alert notification, and the importance level of the second alert notification is higher than the importance level of the third alert notification.

5. The method of claim 1, further comprising:

if the target object does not exist in the original image, determining that the target object is not in the shooting ranges of the current camera device and the target camera device, and sending a movement prompt to the movable equipment to prompt the movable equipment to move to the target position;

acquiring a scanning image obtained by scanning the movable equipment at the target position;

analyzing the behavior type of the target object in the scanned image, and sending the first alarm notification when the behavior type meets the preset condition.

6. The method of claim 5, further comprising:

if the mobile equipment is detected to be incapable of reaching the target position or the scanned image does not contain the target object, sending a fourth alarm notification, wherein the importance level of the first alarm notification is higher than that of the fourth alarm notification;

and/or the movable equipment and the current camera device are configured in the same network through network equipment, and the movable equipment comprises at least one of a sweeping robot, an educational robot and a service robot.

7. The method of claim 1, wherein the current camera and the target camera are configured in the same network through a network device; before the acquiring an original image captured by a target imaging device, the method further includes:

acquiring configuration information input by a user through the network equipment; wherein the configuration information contains a relationship between each two image capture devices in the network, and the relationship includes any one of the complementary relationship and the no relationship;

and analyzing the configuration information and determining the target camera device having the complementary relation with the current camera device.

8. The method according to claim 1, wherein the preset condition comprises: the behavior type is a preset type; wherein the preset type comprises at least one of a fall and a fight.

9. A camera device comprising a processor, a memory, a communication circuit, a camera, and a microphone, the memory, the communication circuit, the camera, and the microphone all coupled to the processor, the memory storing program instructions for execution by the processor to implement the alert method of any of claims 1 to 8 in conjunction with the communication circuit, the camera, and the microphone.

10. A storage device storing program instructions executable by a processor for implementing the alert method of any one of claims 1 to 8.