CN115393563A

CN115393563A - Package detection method and system and electronic equipment

Info

Publication number: CN115393563A
Application number: CN202211122387.9A
Authority: CN
Inventors: 张兴全
Original assignee: Hangzhou Ezviz Software Co Ltd
Current assignee: Hangzhou Ezviz Software Co Ltd
Priority date: 2022-09-15
Filing date: 2022-09-15
Publication date: 2022-11-25
Also published as: WO2024055698A1

Abstract

The embodiment of the invention provides a parcel detection method, a parcel detection system and electronic equipment, and relates to the technical field of image processing. The method comprises the following steps: determining each image to be detected which is collected at a specified moment according to a preset time interval; detecting the first image to be detected to obtain a pedestrian area and a wrapping area in the image; if the pedestrian area and the parcel area in the image have an overlapping area, detecting each target image to obtain the pedestrian area and the parcel area in the target image; if the pedestrian area and the parcel area in each target image have overlapping areas and the pedestrian area and the parcel area in the target image and the pedestrian area and the parcel area in the image to be detected respectively have overlapping areas, increasing a preset count value by a specified value; and outputting preset alarm information when the preset count value reaches a preset threshold value within the specified time. Compared with the prior art, the scheme provided by the embodiment of the invention can improve the home safety of the user.

Description

Package detection method and system and electronic equipment

Technical Field

The present invention relates to the field of image processing technologies, and in particular, to a package detection method and system, and an electronic device.

Background

With the continuous development of economy, the requirements of people on the quality of life are higher and higher, and correspondingly, the service industry belonging to the third industry is also continuously developed. Such as couriers getting on to send, take-out deliverers getting on to send meals, etc. These services provide convenience to people while reducing the safety of the user's home.

Therefore, for home security, it is desirable for the user to detect that someone has a parcel to go to the home, such as a courier going to the home for delivery, a take-away courier going to the home for meal delivery, and the like.

Therefore, how to detect the situation that people carry parcels to get on the door is a problem which needs to be solved urgently at present, thereby improving the home safety of users.

Disclosure of Invention

An object of the embodiments of the present invention is to provide a package detection method, system and electronic device, so as to implement detection for a situation that someone carries a package to go to the door, thereby improving the home security of a user. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a package detection algorithm, where the method includes:

determining each image to be detected which is acquired by image acquisition equipment at a specified moment according to a preset time interval; wherein the specified time is: detecting a moment when a pedestrian appears in an image acquisition area of the image acquisition device;

carrying out pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected;

if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image; wherein each target image is: removing the image to be detected behind the first image to be detected;

for each target image, if an overlapping area exists between a pedestrian area and a wrapping area in the target image, an overlapping area exists between the pedestrian area in the target image and a pedestrian area in a previous image to be detected, and an overlapping area exists between the wrapping area in the target image and the wrapping area in the previous image to be detected, increasing a preset count value by a specified value;

when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian carries a parcel to get on the door; the starting time of the specified duration is not earlier than the specified time.

Optionally, in a specific implementation manner, in a case that there is no overlapping area between the pedestrian area and the parcel area in the first image to be detected, the method further includes:

judging whether the parcel area meets specified conditions or not; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

and if so, performing the pedestrian detection and the parcel detection on each target image to obtain a pedestrian area and a parcel area in each target image.

Optionally, in a specific implementation manner, for each target image, in a case that there is no overlapping area between a pedestrian area and a parcel area in the target image, the method further includes:

judging whether the parcel area in the target image meets the specified condition or not; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

and if the preset count value is satisfied, and an overlapping region exists between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, increasing the preset count value by the specified value.

Optionally, in a specific implementation manner, the specified time is:

the image acquisition equipment detects the time when the pedestrian appears in the acquired image;

alternatively, the first and second electrodes may be,

the image acquisition equipment detects the time when a pedestrian appears in the acquired image for the first time after a preset pedestrian detection function is triggered; wherein the pedestrian detection function is triggered based on a trigger instruction sent by a specified sensor, and the trigger instruction is: the specified sensor sends the detection result when detecting that a movable object appears in a detection area of the specified sensor, and the range of the detection area is smaller than that of the image acquisition area.

Optionally, in a specific implementation manner, before determining that the image acquisition device starts to acquire each image to be detected at a specified time and according to a preset time interval, the method further includes:

and carrying out pedestrian detection on each acquired image acquired by the acquired image acquisition equipment, and determining the acquisition time of the image acquired at the time when the pedestrian appears as the specified time.

Optionally, in a specific implementation manner, the method further includes:

if the preset counting value does not reach the preset threshold value within the specified duration, outputting preset prompt information; the prompt information is used for prompting that the pedestrian passes through;

alternatively, the first and second liquid crystal display panels may be,

if the continuous time length of the preset counting value which is not changed reaches the preset time length within the specified time length, outputting the preset prompt information; and the preset duration is less than the specified duration.

In a second aspect, an embodiment of the present invention provides a package detection system, where the system includes:

the image acquisition module is used for acquiring an image of an image acquisition area of the image acquisition equipment;

the processor is used for determining each image to be detected, which is acquired by the image acquisition equipment at a specified moment according to a preset time interval; wherein the specified time is: detecting the moment when a pedestrian appears in an image acquisition area of the image acquisition equipment; carrying out pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected; if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image; wherein each target image is: removing the image to be detected behind the first image to be detected; for each target image, if an overlapping region exists between a pedestrian region and a parcel region in the target image, an overlapping region exists between the pedestrian region in the target image and a pedestrian region in a previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, increasing a preset count value by a specified value; when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian carries a parcel to get on the door; the starting time of the specified duration is not earlier than the specified time.

Optionally, in a specific implementation manner, the processor is further configured to:

under the condition that no overlapping area exists between the pedestrian area and the parcel area in the first image to be detected, judging whether the parcel area meets specified conditions; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

for each target image, under the condition that the pedestrian area and the parcel area in the target image do not have an overlapping area, judging whether the parcel area in the target image meets the specified condition or not; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

Optionally, in a specific implementation manner, the specified time is:

alternatively, the first and second liquid crystal display panels may be,

after a preset pedestrian detection function is triggered, the image acquisition equipment detects the moment when a pedestrian appears in the acquired image for the first time; wherein the pedestrian detection function is triggered based on a trigger instruction sent by a specified sensor, and the trigger instruction is: the specified sensor sends when detecting that a movable object appears in a detection area of the specified sensor, and the range of the detection area is smaller than that of the image acquisition area.

and before determining each image to be detected, which is acquired by the image acquisition equipment according to a preset time interval at the appointed moment, the image acquisition equipment performs pedestrian detection on each acquired image acquired by the image acquisition equipment, and determines the acquisition moment of the image acquired at the moment when the pedestrian appears as the appointed moment.

alternatively, the first and second electrodes may be,

In a third aspect, an embodiment of the present invention provides a package detection apparatus, where the apparatus includes:

the image to be detected determining module is used for determining each image to be detected which is acquired by the image acquisition equipment at a specified moment according to a preset time interval; wherein the specified time is: detecting a moment when a pedestrian appears in an image acquisition area of the image acquisition device;

the first area detection module is used for carrying out pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected;

the second area detection module is used for carrying out pedestrian detection and parcel detection on each target image to obtain a pedestrian area and a parcel area in the target image if the pedestrian area and the parcel area in the first image to be detected have an overlapping area; wherein each target image is: removing the first image to be detected to obtain a to-be-detected image;

the counting value increasing module is used for increasing a preset counting value by a specified value if an overlapping region exists between a pedestrian region and a wrapping region in the target image, an overlapping region exists between the pedestrian region in the target image and a pedestrian region in a previous image to be detected, and an overlapping region exists between the wrapping region in the target image and the wrapping region in the previous image to be detected, aiming at each target image;

the information output module is used for outputting preset alarm information when the preset count value reaches a preset threshold value within a specified time length; the warning information is used for prompting that a pedestrian enters the door with a parcel; the starting time of the specified duration is not earlier than the specified time.

Optionally, in a specific implementation manner, the apparatus further includes:

the first judging module is used for judging whether the parcel area meets the specified condition or not under the condition that the pedestrian area and the parcel area in the first image to be detected do not have an overlapping area; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

the second judgment module is used for judging whether the parcel area in the target image meets the specified condition or not under the condition that the pedestrian area and the parcel area in the target image do not have an overlapping area for each target image; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

and if the number of the pedestrian areas in the target image and the pedestrian areas in the image to be detected are in the overlapping area, and the wrapping area in the target image and the wrapping area in the image to be detected are in the overlapping area, increasing the preset counting value by the specified value.

Optionally, in a specific implementation manner, the specified time is:

alternatively, the first and second electrodes may be,

and the appointed time determining module is used for carrying out pedestrian detection on each image acquired by the acquired image acquisition equipment before each image to be detected is acquired by the image acquisition equipment at the appointed time according to the preset time interval, and determining the acquisition time of the image acquired at the time when the pedestrian appears as the appointed time.

the prompt information output module is used for outputting preset prompt information if the preset count value does not reach the preset threshold value within the specified duration; the prompt information is used for prompting that the pedestrian passes through; or, if the continuous time length of the unchanged preset count value reaches the preset time length within the specified time length, outputting the preset prompt message; and the preset duration is less than the specified duration.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;

a memory for storing a computer program;

a processor, configured to implement the method steps of any of the package detection methods provided by the first aspect when executing a program stored in the memory.

In a fifth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the method steps of any of the package detection methods provided in the first aspect.

In a sixth aspect, embodiments of the present invention provide a computer program product containing instructions which, when run on a computer, cause the computer to perform the method steps of any of the package detection methods provided in the first aspect above.

The embodiment of the invention has the following beneficial effects:

as can be seen from the above, by applying the scheme provided by the embodiment of the present invention, when detecting that a person carries a parcel to enter a door, the time when the pedestrian appears in the image acquisition area of the image acquisition device can be determined as the specified time, so that each image to be detected acquired by the image acquisition device at the specified time according to the preset time interval can be determined, and thus, the pedestrian detection and the parcel detection can be performed on the first image to be detected, so as to obtain the pedestrian area and the parcel area in the first image to be detected. If the pedestrian area and the parcel area in the first image to be detected have an overlapping area, pedestrian detection and parcel detection can be performed on each target image except the first image to be detected, so that the pedestrian area and the parcel area in the target image are obtained. Therefore, for each target image, if an overlapping region exists between the pedestrian region and the parcel region in the target image, an overlapping region exists between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, the preset count value can be increased by a specified value. When the preset count value reaches the preset threshold value within the specified time, the preset alarm information for prompting the pedestrian to get on the door with the parcel can be output.

Based on this, by applying the scheme provided by the embodiment of the invention, the pedestrian detection and the parcel detection can be carried out on each image to be detected acquired by the image acquisition equipment, and when the pedestrian carrying parcel is detected to be on the door, the preset warning information for prompting the existence of the pedestrian carrying parcel on the door is output to prompt the user, so that the home safety of the user is improved.

In addition, the moment that the pedestrian appears in the image acquisition region of detecting image acquisition equipment begins, detects the image to be detected that image acquisition equipment gathered and carries out pedestrian detection and parcel detection, avoids detecting the image to be detected and carries out real-time detection to, thereby, can practice thrift electronic equipment's power consumption, and then, improve electronic equipment's operating duration. And on the basis of carrying out pedestrian detection on the image to be detected, package detection is carried out on the image to be detected, so that invalid detection on the image to be detected can be avoided under the condition that no main package exists, and the like, and therefore the false detection rate of the electronic equipment is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other embodiments can be obtained by those skilled in the art according to the drawings.

FIG. 1 is a schematic flow chart of a package inspection method according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of another package inspection method according to an embodiment of the present invention;

FIG. 3 is a schematic representation of another embodiment of the present invention;

fig. 4 is a schematic structural diagram of a package inspection device according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a package inspection system according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived from the embodiments given herein by one of ordinary skill in the art, are within the scope of the invention.

At present, how to detect to someone carrying the condition of wrapping up to, improve user's safety at home, become the current problem that needs to solve urgently.

In order to solve the above technical problem, an embodiment of the present invention provides a package detection method.

The method is applicable to various application scenes that people need to carry packages to be detected, for example, packages are detected when couriers get to the doors for delivery, and sales are detected when takeaway delivery staffs get to the doors for delivery. Based on this, the embodiment of the present invention does not limit the application scenario and the execution subject of the method.

The parcel detection method provided by the embodiment of the invention can comprise the following steps:

for each target image, if an overlapping region exists between a pedestrian region and a parcel region in the target image, an overlapping region exists between a pedestrian region in the target image and a pedestrian region in a previous image to be detected, and an overlapping region exists between the parcel region in the target image and a parcel region in a previous image to be detected, increasing a preset count value by a specified value;

when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian enters the door with a parcel; the starting time of the specified duration is not earlier than the starting time of the target video stream.

As can be seen from the above, by applying the scheme provided by the embodiment of the present invention, when detecting that a person carries a parcel to enter a door, the time when the pedestrian appears in the image acquisition area of the image acquisition device can be determined as the specified time, so that each image to be detected acquired by the image acquisition device at the specified time according to the preset time interval can be determined, and thus, the pedestrian detection and the parcel detection can be performed on the first image to be detected, so as to obtain the pedestrian area and the parcel area in the first image to be detected. If the overlapping area exists between the pedestrian area and the parcel area in the first image to be detected, the pedestrian detection and the parcel detection can be carried out on each target image except the first image to be detected, and therefore the pedestrian area and the parcel area in the target image are obtained. Therefore, for each target image, if an overlapping region exists between the pedestrian region and the parcel region in the target image, an overlapping region exists between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, the preset count value can be increased by a specified value. When the preset count value reaches the preset threshold value within the specified time, the preset alarm information for prompting the pedestrian to get on the door with the parcel can be output.

In addition, the moment that the pedestrian appears in the image acquisition region that detects image acquisition equipment begins, waits to detect the image and carry out pedestrian detection and parcel detection to image acquisition equipment collection, avoids waiting to detect the image and carries out real-time detection to, can practice thrift electronic equipment's power consumption, and then, improve electronic equipment's operating duration. Moreover, on the basis of carrying out pedestrian detection on the image to be detected, package detection is carried out on the image to be detected, so that invalid detection on the image to be detected can be avoided under the conditions of no main package and the like, and the false detection rate of the electronic equipment is reduced.

The following describes a package detection method according to an embodiment of the present invention with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a package detection method according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps S101 to S105.

S101: determining each image to be detected which is acquired by image acquisition equipment at a specified moment according to a preset time interval;

wherein the specified time is: the time when a pedestrian is present in an image capturing area of an image capturing apparatus is detected.

For the home safety of the user, the outdoor environment of the user can be monitored in real time by using the image acquisition equipment. For example, the image acquisition equipment is arranged on the door or on the door side, and the area in front of the door is contained in the image acquisition area of the image acquisition equipment to the maximum extent, so that the dynamic outside the door can be more truly and comprehensively restored.

Therefore, the image acquisition area of the image acquisition device can be monitored in real time by the image acquisition device, so that a plurality of images about the image acquisition area are obtained. In order to save the power consumption of the electronic device, the image acquisition device is determined to start from the images by taking the time when the pedestrian appears in the image acquisition area of the image acquisition device as a specified time, and the images to be detected are acquired according to a preset time interval, so that the pedestrian detection and the parcel detection can be carried out on the images to be detected.

The preset time interval may be a time interval corresponding to an image capturing frequency of the image capturing device itself, for example, 0.01 second; it may also be a preset time interval preset by the user, for example, 0.1 second, etc. The embodiment of the present invention is not particularly limited.

The time interval preset by the user is not less than the time interval corresponding to the image acquisition frequency of the image acquisition equipment.

For example, the specified time is 13:25:22 with a preset time interval of 0.1 seconds. Thus, the image acquisition device can be switched from 13:25: beginning at 22, each image acquired at time intervals of 0.1 second is determined to be each image to be detected.

Optionally, in a specific implementation, the specified time is: the image capturing device detects the time when a pedestrian appears in the captured image.

In this specific implementation manner, the image capturing device performs pedestrian detection on each captured image, and determines a time when the pedestrian is detected as a specified time.

The time when the pedestrian is detected is the time when the pedestrian is detected, wherein the time when the pedestrian is detected is the time when the pedestrian is detected, and the time when the pedestrian is detected can be used as the time when the pedestrian is detected in the next frame image of the last frame image in the continuous multi-frame images and the pedestrian is represented to appear in the acquisition area of the image acquisition equipment.

Optionally, in a specific implementation, the specified time is: after a preset pedestrian detection function is triggered, the image acquisition equipment detects the time when a pedestrian appears in an acquired image for the first time;

the pedestrian detection function is triggered based on a trigger instruction sent by a specified sensor; the trigger instruction is: the designated sensor transmits when detecting the presence of a movable object within a detection area of the designated sensor, the detection area having a range less than the range of the image capture area.

In this specific implementation manner, a specific sensor for detecting whether a movable object exists in the detection area, for example, a PIR (Passive Infrared Detector or body sensor) sensor or the like, may be provided.

That is, a given sensor, upon detecting a movable object within the detection area, such as a limb, pedestrian, etc. blown by the wind, sends a corresponding command or signal to a given device.

Since the specific sensor cannot determine whether the movable object existing in the detection area of the specific sensor is a pedestrian, the time when the specific sensor detects that the movable object exists in the detection area of the specific sensor cannot be determined as the specific time, but the specific sensor sends a trigger instruction to the image acquisition device when detecting that the movable object exists in the detection area of the specific sensor, so that the image acquisition device triggers the pedestrian detection function after receiving the trigger instruction, performs pedestrian detection on each acquired image, and determines the time when the pedestrian is first detected in the acquired image as the specific time.

The designated sensor can be installed in the image acquisition device or can be independent of the image acquisition device. The embodiment of the present invention is not particularly limited.

In addition, in order to avoid the situation that no pedestrian appears in the image acquisition area of the image acquisition device after the specified sensor sends the trigger instruction to the image acquisition device, the range of the detection area of the specified sensor is smaller than the range of the image acquisition area of the image acquisition device.

The above-mentioned specified moment can also be determined by the electronic device itself, in addition to the above-mentioned way of determining the specified moment by means of other electronic devices.

Optionally, in a specific implementation manner, as shown in fig. 2, before the step S101, the method for detecting a package according to an embodiment of the present invention may further include the following step S201:

s201: and carrying out pedestrian detection on each acquired image acquired by the acquired image acquisition equipment, and determining the acquisition time of the image acquired at the time when the pedestrian appears as the specified time.

In this concrete implementation, above-mentioned image acquisition equipment sends each image to electronic equipment after gathering each image in this image acquisition equipment's image acquisition region, electronic equipment is after receiving each image that above-mentioned image acquisition equipment gathered, alright in order to carry out pedestrian detection to each image that acquires, thereby, can be with the collection moment of the image of gathering the moment that detects the pedestrian appearance, confirm as appointed moment, so that confirm each in each subsequent image and wait to detect the image, thereby, can improve electronic equipment's work efficiency, improve the efficiency that the parcel detected.

The electronic device can determine all images in the preset time interval as images to be detected according to the length of the time interval, and can also determine partial images in the preset time interval as images to be detected. The embodiment of the present invention is not particularly limited.

The time interval may be a time interval corresponding to the image capturing frequency of the image capturing device itself, or may be a preset time interval preset by the user. The embodiment of the present invention is not particularly limited.

For example, the acquisition timing of an image acquired at the timing at which the presence of a pedestrian is detected is 13:25:22, therefore, 13:25:22 is determined as the specified time of day.

S102: and carrying out pedestrian detection and parcel detection on the first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected.

After determining that the image acquisition equipment starts to acquire each image to be detected according to the preset time interval at the appointed moment, the pedestrian detection and the parcel detection can be performed on the first image to be detected, so that the pedestrian area and the parcel area in the first image to be detected can be obtained.

Like this, to waiting to examine the detection image simultaneously to detect pedestrian and parcel detection, can avoid under the condition such as only parcel exists, waiting to examine the detection image to each and continuously detect and report an emergency and ask for help or increased vigilance to, reduce the false retrieval rate that electronic equipment detected about the pedestrian, and save electronic equipment's power consumption.

Optionally, the pedestrian detection may be performed on each image to be detected by using a Gaussian Mixture model (Mixture of Gaussian model), a frame difference algorithm, background modeling, and the like. The embodiment of the present invention is not particularly limited.

Optionally, the package detection may be performed on each image to be detected by using an algorithm such as a yolov3 target detection model (3 rd version of yolo target detection model, abbreviation of yolo, you only look once) based on a deep convolutional neural network. The embodiment of the present invention is not particularly limited.

Optionally, when the pedestrian detection and the parcel detection are performed on the first image to be detected, if the parcel region is not detected, the electronic device may output preset prompt information for prompting the existence of the pedestrian.

S103: if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image;

wherein each target image is: and (4) removing the image to be detected after the first image to be detected.

After each image to be detected is determined, the image to be detected acquired by the image acquisition equipment except the first image to be detected can be determined as a target image.

If the pedestrian area and the parcel area in the first image to be detected have an overlapping area, pedestrian detection and parcel detection can be continuously performed on each target image, so that the pedestrian area and the parcel area in each target image can be obtained.

In some cases, due to the problems of the shooting angle of the image acquisition equipment, the size of the package carried by the pedestrian and the like, after the image of the pedestrian carrying the package to enter the door is detected, the obtained detection result is as follows: there is no overlapping area between the pedestrian area and the parcel area in the image.

For example, when the courier sends a delivery, the courier may use a small cart to deliver the delivery of a large item, and at this time, in the first image to be detected acquired by the image acquisition device, there may be no overlapping area between the detected pedestrian area and the parcel area, so that, in order to avoid the occurrence of false detection and missed detection, the position relationship between the parcel area and the pedestrian area in the first image to be detected may be determined according to the area size of the parcel area and/or the distance between the parcel area and the pedestrian area.

Optionally, in a specific implementation manner, under a condition that there is no overlapping area between a pedestrian area and a parcel area in the first image to be detected, the parcel detection method provided in an embodiment of the present invention may further include the following steps 11 to 12:

step 11: judging whether the parcel area meets specified conditions or not;

wherein the specified conditions include: the wrapping area is larger than the preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than the preset distance;

step 12: and if so, carrying out pedestrian detection and parcel detection on each target image to obtain a pedestrian area and a parcel area in each target image.

In this particular implementation, there may be a case where a pedestrian uses a tool to ship a package, for example, an oversized package, an excessive number of packages, and the like, so that there is no overlapping area between the pedestrian area and the package area in the first image to be detected.

Therefore, when the pedestrian area and the parcel area in the first image to be detected do not have the overlapping area, whether the parcel meets the specified conditions or not can be judged, if so, the first image to be detected is represented as an image for the pedestrian carrying the parcel to enter the door, therefore, the pedestrian detection and the parcel detection can be continuously carried out on each target image, the pedestrian area and the parcel area in each target image are obtained, and whether the pedestrian carrying the parcel to enter the door or not is determined.

Wherein, the specified conditions include: the wrapping area is larger than the preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than the preset distance.

Optionally, the above specified conditions include: when the parcel area is greater than the preset area, the electronic device can judge whether the parcel area is greater than the preset area for the parcel area in the first image to be detected, and if the judgment result of the step 11 is: the parcel region satisfies the specified condition, and parcel region is greater than the preset area promptly, and then the parcel size that the sign pedestrian carried is very big, and the first image of waiting to detect carries the image of parcel overhead door for having the pedestrian, and electronic equipment can continue to carry out pedestrian detection and parcel detection to every target image, obtains pedestrian region and parcel region in every target image.

For example, when a courier goes to a door to dispatch a large courier, the cart is used to ship the large courier. At this time, the pedestrian region and the parcel region in the first image to be detected may be determined by performing pedestrian detection and parcel detection on the first image to be detected. A predetermined area of 30 x 30 and a parcel area of 50 x 50, wherein 30 x 30 and 50 x 50, then characterizes that the parcel area 50 x 50 is greater than the predetermined area 30 x 30, and the parcel is a bulk express delivery.

The setting mode of the preset area may include: according to the ratio of the area of the predetermined preset region to the area of the whole image, after the area of the whole image is obtained, the area of the preset region may be determined, or the area of the preset region may be set according to a manual input of a user, which is not specifically limited in the embodiment of the present invention.

Optionally, if the determination result in the step 11 is: the parcel area does not meet specified conditions. That is to say, the parcel region in the first image to be detected is less than the preset area, and the parcel size that the sign pedestrian carried is very little, then electronic equipment can output the predetermined prompt message that is used for the suggestion to have the pedestrian to pass through.

In the case of a pedestrian shipping a package with the tool, there may be a distance between the package area and the pedestrian area, resulting in no overlapping area between the pedestrian area and the package area in the first image to be detected.

Optionally, the above specified conditions include: when the distance between the parcel area and the pedestrian area is smaller than the preset distance, it can be determined whether the distance between the parcel area and the pedestrian area is smaller than the preset distance, and if the determination result of the step 11 is: the parcel region satisfies the specified condition, and the distance between parcel region and the pedestrian region is less than the preset distance promptly, and then the distance between sign pedestrian region and the parcel region is less than the preset distance, and the first image of waiting to detect carries the image of parcel overhead for having the pedestrian, and electronic equipment can continue to carry out pedestrian detection and parcel detection to every target image to, obtain pedestrian region and parcel region in every target image.

For example, when a courier is to be sent at home, a cart is used to ship a plurality of couriers. At this time, the pedestrian region and the parcel region in the first image to be detected may be determined by performing pedestrian detection and parcel detection on the first image to be detected. The preset distance is 8 centimeters, the distance between the wrapping area and the pedestrian area is 7 centimeters, wherein the 7-inch piles are 8, and then the distance between the representation wrapping area and the pedestrian area is smaller than the preset distance.

Optionally, if the determination result in the step 11 is: the parcel area does not meet specified conditions. That is to say, the distance between the pedestrian area and the parcel area in the first image to be detected is greater than the preset distance, and the characteristic pedestrian is separated from the parcel. For example, if a pedestrian just passes through a package, the electronic device may output a preset prompt message for prompting the existence of the pedestrian.

Optionally, the above specified conditions include: the parcel region is greater than the preset area, and when the distance between parcel region and the pedestrian region is less than the preset distance, electronic equipment alright judge whether the parcel region is greater than the preset region, if the size of the parcel in the first image to be detected is greater than the preset region, then can judge whether the distance between parcel region and the pedestrian region is less than the preset distance, if the distance between the parcel region in the first image to be detected and the pedestrian region is less than the preset distance, then can continue to carry out pedestrian detection and parcel detection to each target image, thereby, obtain pedestrian region and parcel region in each target image.

Optionally, if the determination result in the step 11 is: the parcel area does not meet specified conditions. That is to say, the parcel region in the first image to be detected is less than the preset area, and the distance between parcel region and the pedestrian region is greater than the preset distance, and the sign parcel size is very little, and parcel and pedestrian are separated, then electronic equipment can output the predetermined prompt message that is used for the suggestion existence pedestrian passes.

Optionally, if the image capturing device is a depth camera, a preset size may be preset, so that the depth camera may be used to directly determine the size of the package, and if the determined size of the package is larger than the preset size, the package is characterized to be oversized.

Optionally, the area ratio between the pedestrian area and the parcel area may be calculated, and if the ratio exceeds a preset ratio, it is determined that the size of the parcel is too large.

For example, the area ratio between the parcel region and the pedestrian region in the image Q to be detected may be calculated by using the following formula, and if the ratio exceeds a preset ratio, it is determined that the size of the parcel is too large, and the above formula may be expressed as:

wherein S is _parcel Characterizing the area of the region of interest in the image Q to be detected, S _person And characterizing the area of the pedestrian region in the image Q to be detected, and A characterizing a preset ratio between the parcel region and the pedestrian region in the image Q to be detected.

S104: and for each target image, if an overlapping area exists between the pedestrian area and the parcel area in the target image, an overlapping area exists between the pedestrian area in the target image and the pedestrian area in the previous image to be detected, and an overlapping area exists between the parcel area in the target image and the parcel area in the previous image to be detected, increasing the preset count value by a specified value.

Carry the parcel at the pedestrian and remove the in-process before the door, image acquisition equipment can continuously carry out image acquisition to this image acquisition equipment's image acquisition region to, realize following the shooting to above-mentioned pedestrian.

If the pedestrian is always in a state of carrying the parcel for movement, the pedestrian area between two adjacent frames of images acquired by the image acquisition equipment and/or the parcel area can have an overlapping area.

Therefore, after the pedestrian area and the parcel area in each target image are obtained, whether the pedestrian area and the parcel area in the target image have an overlapping area can be judged.

If the pedestrian area and the parcel area in the target image have an overlapping area, it may be determined whether the pedestrian area in the target image and the pedestrian area in the previous image to be detected have an overlapping area, and whether the parcel area in the target image and the parcel area in the previous image to be detected have an overlapping area.

If there is an overlapping region between the pedestrian region and the parcel region in the target image, an overlapping region between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region between the parcel region in the target image and the parcel region in the previous image to be detected, the preset count value may be increased by a specified value.

The numerical value of the preset count value is used for reflecting the number of images in which the overlapped area exists between the included pedestrian area and the wrapping area, the overlapped area exists between the included pedestrian area and the pedestrian area in the image to be detected, and the overlapped area exists between the included wrapping area and the wrapping area in the image to be detected.

That is to say, for an image to be detected, if there is an overlapping region between a pedestrian region and a parcel region in the image, an overlapping region between a pedestrian region in the image and a pedestrian region in an image to be detected, and an overlapping region between a parcel region in the image and a parcel region in an image to be detected, the image can be used to characterize a pedestrian carrying parcel entering the door. Therefore, the numerical value of the preset count value can reflect the number of images to be detected for representing the pedestrian carrying the package door-to-door image, and therefore the numerical value of the preset count value can be used for representing the confidence of the detection result of the pedestrian carrying the package door-to-door image.

The confidence degree of the detection result can represent the reliability of the detection result, and further the accuracy of the detection result is represented, and the higher the confidence degree of the detection result is, the higher the reliability of the detection result can be considered, and therefore the greater the accuracy of the detection result can be considered, therefore, when the numerical value of the preset counting value reaches the preset threshold value, the confidence degree of the detection result representing that the pedestrian carries the package upper door reaches the preset threshold value, and further, the detection result representing that the detected pedestrian carries the package upper door can be shown to be credible, namely, the accuracy of the detection result representing that the detected pedestrian carries the package upper door is greater, so that the detected pedestrian can be considered to carry the package upper door, and the existence of the pedestrian carrying the package upper door can be prompted through the alarm information.

Therefore, the false detection rate and the missing detection rate of the electronic equipment can be reduced based on the detection of a plurality of continuous images to be detected, and the accuracy of package detection is improved.

If the pedestrian area and the parcel area in the target image have an overlapping area, but the pedestrian area in the target image does not have an overlapping area with the pedestrian area in the previous image to be detected, and/or the parcel area in the target image does not have an overlapping area with the parcel area in the previous image to be detected, it is characterized that no pedestrian carrying parcel is present in the target image, and therefore the electronic device can output preset prompt information for prompting the existence of the pedestrian to pass through.

For example, a neighbor carries a package through the user's door.

Optionally, for each target image, if there is no overlapping area between the pedestrian area and the parcel area in the target image, the electronic device may output preset prompting information for prompting that a pedestrian passes through.

In some cases, due to the problems of the shooting angle of the image acquisition equipment, the size of the package carried by the pedestrian and the like, after the image of the pedestrian carrying the package to the door is detected, the obtained detection result is as follows: the pedestrian area and the parcel area in the image do not have an overlapping area, for example, when a courier gets on the door to send a parcel, the courier may use a small cart to deliver an express delivery of a large parcel, and at this time, in each target image acquired by the image acquisition device, the detected pedestrian area and the parcel area may not have an overlapping area, so that the situations of false detection and missed detection are avoided.

Based on this, optionally, in a specific implementation manner, for each target image, in a case that there is no overlapping area between the pedestrian area and the parcel area in the target image, the parcel detection method provided in the embodiment of the present invention may further include the following steps 22 to 23:

step 22: judging whether the parcel area in the target image meets the specified condition or not;

step 23: and if the target image meets the requirement, and an overlapping region exists between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, increasing the preset count value by a specified value.

In this particular implementation, there may be situations where a pedestrian uses a tool to ship a package, such as an oversized package, an excessive number of packages, etc., such that there is no overlapping area between the pedestrian area and the package area in each target image.

Therefore, when there is no overlapping area between the pedestrian area and the parcel area in each target image, it may be determined whether the parcel area in the target image satisfies the specified condition, and if the determination result in step 22 is: the parcel area in the target image meets the specified condition, an overlapping area exists between the pedestrian area in the target image and the pedestrian area in the image to be detected, and the overlapping area exists between the parcel area in the target image and the parcel area in the image to be detected, so that the target image is represented as an image which is a pedestrian carrying parcel and is on the door, and the preset counting value is increased by a specified numerical value.

Optionally, for each target image, the above specified conditions include: when the parcel area in the target image is larger than the preset area, the electronic device may determine whether the parcel area in the target image is larger than the preset area according to the parcel area in the target image. If the determination result in the step 22 is: the parcel area in the target image is larger than the preset area, the size of the parcel carried by the representative pedestrian is large, the target image is an image of the pedestrian carrying the parcel to enter the door, and the electronic equipment can increase the preset count value by a specified value.

If the determination result in the step 22 is: the parcel area in the target image does not satisfy a specified condition. That is to say, the parcel area in the target image is smaller than the preset area, and the size of the parcel representing the pedestrian is small, then the electronic device may output the preset prompt information for prompting the existence of the pedestrian passing.

For example, the preset count value is 0, and a value of 1 is designated. When the courier goes to the door to dispatch the express, the trolley is used for consigning the express. At this time, the pedestrian area and the parcel area in each target image may be determined by performing pedestrian detection and parcel detection on each target image by traversing the target image. The preset area is 30 × 30, and the parcel area is 50 × 50, wherein 30 × 30 is restricted to 50 × 50, which indicates that the parcel area 50 × 50 is greater than the preset area 30 × 30, the parcel is a large express delivery, and the electronic device can increase by 1 on the basis of a preset count value of 0.

The setting mode of the preset area may include: the area of the preset region may be determined after the area of the whole image is obtained according to a ratio of the area of the preset region to the area of the whole image, or the area of the preset region may be set according to a manual input of a user, which is not specifically limited in the embodiment of the present invention.

In the case of a pedestrian shipping a package with a tool, there may be a distance between the package area and the pedestrian area, resulting in no overlapping area of the pedestrian area and the package area in the target image.

Optionally, for each target image, the above specified conditions include: when the distance between the parcel area and the pedestrian area in the target image is smaller than the preset distance, the electronic device may determine whether the distance between the parcel area and the pedestrian area in the target image is smaller than the preset distance, and if the determination result in the step 22 is: the parcel region in this target image satisfies the specified condition, and then the distance that represents between pedestrian's region and the parcel region is less than and predetermines the distance, and this target image is for having the image that the pedestrian carried the parcel to go to the gate, and electronic equipment alright with in order to increase the count value of predetermineeing and appointing the numerical value.

If the determination result in the step 22 is: the parcel area in the target image does not satisfy a specified condition. That is, the distance between the pedestrian area and the parcel area in the target image is greater than the preset distance, indicating that the pedestrian is separated from the parcel. For example, if the pedestrian just passes through the package, the electronic device may output a preset prompt message for prompting the pedestrian to pass through.

For example, the preset count value is 0, and a value of 1 is designated. When the courier gets on the door to send the express, the trolley is used for consigning a plurality of express. At this time, the pedestrian area and the parcel area in each target image may be determined by performing pedestrian detection and parcel detection on each target image by traversing the target image. The preset distance is 8 centimeters, the distance between the parcel area and the pedestrian area is 7 centimeters, wherein 7-s 8 represents that the distance between the parcel area and the pedestrian area is smaller than the preset distance, and the electronic equipment can increase by 1 on the basis of a preset count value of 0.

Optionally, for each target image, if the parcel area is larger than the preset area and the distance between the parcel area and the pedestrian area is smaller than the preset distance, the electronic device may determine whether the parcel area in the target image is larger than the preset area, and if the size of the parcel in the target image is larger than the preset area, the electronic device may increase the preset count value by a specified value and may determine whether the distance between the parcel area and the pedestrian area in the target image is smaller than the preset distance.

If the distance between the parcel area and the pedestrian area in the target image is smaller than the preset distance, the electronic device may increase the preset count value by the designated value again.

If the determination result in the step 22 is: the parcel area in the target image does not satisfy a specified condition. That is to say, the parcel area in the target image is smaller than the preset area, and the distance between the parcel area and the pedestrian area is greater than the preset distance, which represents that the parcel size is small, and the parcel is separated from the pedestrian, then the electronic device can output the preset prompt information for prompting the existence of the pedestrian passing.

For example, the preset count value is 0, the designated value is 1, and when the courier goes to the door to dispatch the express, the trolley is used for shipping the express. At this time, the pedestrian area and the parcel area in each target image may be determined by performing pedestrian detection and parcel detection on each target image by traversing the target image. The preset area is 30 × 30, and the parcel area is 50 × 50, where 30 × 30<50 × 50 indicates that the parcel area 50 × 50 is greater than the preset area 30 × 30, the parcel is a large express, and the electronic device may increment by 1 on the basis of a preset count value of 0 to obtain a current preset count value of 1. Then, since the preset distance is 8 centimeters, the distance between the parcel area and the pedestrian area is 7 centimeters, wherein 7-s 8 represents that the distance between the parcel area and the pedestrian area is smaller than the preset distance, the electronic device may increase 1 on the basis of the preset count value 1 to obtain the current preset count value of 2.

Therefore, the images to be detected are sequentially traversed, and the specified numerical value can be increased for the preset counting value according to the judgment result of each image to be detected.

Illustratively, taking the courier's door-to-door dispatch as an example, as shown in fig. 3, a diagram of a specific embodiment of the present invention is provided.

The method comprises the steps of obtaining a video sequence collected by image collecting equipment, extracting each frame of image from the video sequence, and inputting the frame of image into a package detection model, so that a pedestrian detection frame and a package detection frame in each frame of image can be obtained. Then, it is possible to determine whether there is overlap between the pedestrian detection frames and whether there is overlap between the parcel detection frames in the two images between the preceding and succeeding frames.

If the pedestrian detection frames in the two images between the front frame and the rear frame are overlapped and the parcel detection frames in the two images between the front frame and the rear frame are overlapped, whether the parcel is a large parcel can be judged.

If the package is a big package, judging whether the package is at the pedestrian side, and if the package is at the pedestrian side, adding 1 to the frame count; if the parcel is not at the side of the pedestrian, the frame count n can be added with 1 when the pedestrian detection frame and the parcel detection frame are overlapped, otherwise, the frame image is ignored;

if the parcel is not a large parcel, the frame count n may be incremented by 1 when the pedestrian detection box and the parcel detection box overlap; otherwise, ignoring the frame image;

if the pedestrian detection frames in the two images between the front and rear frames are not overlapped and the parcel detection frames in the two images between the front and rear frames are not overlapped, the frame image can be ignored.

And when the frame count n is greater than T, outputting information that the courier dispatches the express at the door.

S105: when the preset count value reaches a preset threshold value within the specified time, outputting preset alarm information;

wherein, the warning information is used for prompting that the pedestrian carries the parcel to get on the door; the start time of the specified duration is no earlier than the specified time.

Since the range of the image capturing area of the image capturing device is determined, when it is determined that the time when the image capturing device is detected that the pedestrian is present in the image capturing area of the image capturing device is detected, a specified period of time from the time when the image capturing device is detected that the pedestrian is present in the image capturing area of the image capturing device to the time when the pedestrian is moved to the front of the door can be estimated based on the predetermined range of the walking speed of the human.

Then, based on the specified duration, a threshold value that can be reached by a preset count value when the electronic device continuously detects each image to be detected acquired by the image acquisition device is preset, so that a preset threshold value is set.

Like this, when the numerical value of count value in appointed duration reaches above-mentioned predetermined threshold value in advance, then the sign pedestrian carries the parcel and has moved to before the door, and electronic equipment alright in order to output alarm information to, can indicate the user, so that the user can in time receive the information that electronic equipment sent, and then, improve user's use and experience.

The starting time of the specified time length is not earlier than the specified time, that is, the specified time length can be started to time after the specified time is determined, or the specified time length can be started to time after a specified time period after the specified time is determined.

For example, when a takeaway distributor delivers food at home, if a preset count value recorded by the electronic device reaches a preset threshold 6 within a specified time, the electronic device may send, to the user, an alarm message for prompting that a pedestrian carrying a parcel is present, so that the user can make a corresponding preparation in advance after receiving the alarm message sent by the electronic device.

Optionally, the warning signal may include one or more of various signals such as a sound signal, a color signal, a vibration signal, a text signal, and the like. The embodiment of the present invention is not particularly limited.

In some cases, the electronic device may detect that there is an overlapping region between the pedestrian region and the parcel region in each target image, there is an overlapping region between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and there is an overlapping region between the parcel region in the target image and the parcel region in the previous image to be detected, however, what the user receives is prompt information sent by the electronic device to prompt the pedestrian to pass. In the above case, the pedestrian carrying the package simply passes through the image capturing area of the above image capturing apparatus.

Based on this, optionally, in a specific implementation manner, the package detection method provided in the embodiment of the present invention may further include the following step 33:

step 33: if the preset count value does not reach the preset threshold value within the specified time, outputting preset prompt information; the prompt information is used for prompting that the pedestrian passes.

In this concrete implementation, when in appointed time, above-mentioned predetermined count value does not reach above-mentioned predetermined threshold value, then the sign is in appointed time, and the pedestrian carries the parcel and does not remove to the door in front, and electronic equipment can output the predetermined prompt message that is used for the suggestion to have the pedestrian to pass through to, can indicate the user, so that the user can in time receive the prompt message that electronic equipment sent, and then, improve user's use and experience.

For example, if the specified time period is 10 seconds, the preset threshold value may be set to 10. The time length of the pedestrian carrying the package passing through the image acquisition area of the image acquisition device is 3 seconds. Within the above 3 seconds, the preset count value recorded by the electronic device is 3, wherein 3 is 10, and if the preset threshold value is not reached, preset prompt information for prompting that pedestrians pass is output to prompt the user.

Correspondingly, optionally, in a specific implementation manner, the package detection method provided in the embodiment of the present invention may further include the following step 34:

step 34: if the continuous time length of which the preset count value is not changed reaches the preset time length within the specified time length, outputting preset prompt information; wherein the preset duration is less than the specified duration.

In this specific implementation manner, a preset time length may be preset, when the preset count value reaches the preset time length for the changed continuous time length within the specified time length, the representation is within the specified time length, when the electronic device performs pedestrian detection and parcel detection on each image to be detected acquired by the image acquisition device, a situation that a parcel area does not meet specified conditions may exist, and when the continuous time length occurring in the situation reaches the preset time length, the electronic device may output preset prompt information for prompting that a pedestrian passes through.

Wherein the preset time length is less than the specified time length.

Therefore, the package detection of each target image can be finished when the continuous time length of the unchanged preset counting value reaches the preset time length within the specified time length, so that the equipment power consumption of the electronic equipment is reduced, and the working time length of the electronic equipment is prolonged.

For example, the specified time period is 10 seconds, and the preset time period is 5 seconds. If the preset count value is that the unchanged continuous time length reaches 5 seconds within 10 seconds, the package detection of each target image can be finished, and preset prompt information for prompting the existence of pedestrians is output.

For example, if the preset time period is 5 seconds and the specified time period is 10 seconds, the preset threshold may be set to 10. The moment when the pedestrian takes the package to appear in the image acquisition area of the image acquisition device is 15:35:25, at 15:35:25 to 15:35: and within 8 seconds of 33, after the electronic equipment increases the recorded preset counting value to 3 in the 3 rd second, the preset counting value recorded by the electronic equipment is not changed until the 8 th second. Because the preset time is 5 seconds, and the continuous time during which the preset count value recorded by the electronic device is not changed is 5 seconds, wherein 5=5, the electronic device can output preset prompt information for prompting that a pedestrian passes by to prompt a user.

As can be seen from the above, by applying the scheme provided by the embodiment of the present invention, when detecting that a person carries a parcel to enter a door, the time when the pedestrian appears in the image acquisition area of the image acquisition device can be determined as the specified time, so that each image to be detected acquired by the image acquisition device at the specified time according to the preset time interval can be determined, and thus, the pedestrian detection and the parcel detection can be performed on the first image to be detected, so as to obtain the pedestrian area and the parcel area in the first image to be detected. If the overlapping area exists between the pedestrian area and the parcel area in the first image to be detected, the pedestrian detection and the parcel detection can be carried out on each target image except the first image to be detected, and therefore the pedestrian area and the parcel area in the target image are obtained. Therefore, for each target image, if an overlapping region exists between the pedestrian region and the parcel region in the target image, an overlapping region exists between the pedestrian region in the target image and the pedestrian region in the previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, the preset count value can be increased by a specified value. When the preset count value reaches the preset threshold value within the specified time, the preset alarm information for prompting the existence of the pedestrian carrying the parcel to enter the door can be output.

In addition, the moment that the pedestrian appears in the image acquisition region of detecting image acquisition equipment begins, detects the image to be detected that image acquisition equipment gathered and carries out pedestrian detection and parcel detection, avoids detecting the image to be detected and carries out real-time detection to, thereby, can practice thrift electronic equipment's power consumption, and then, improve electronic equipment's operating duration. Moreover, on the basis of carrying out pedestrian detection on the image to be detected, package detection is carried out on the image to be detected, so that invalid detection on the image to be detected can be avoided under the conditions of no main package and the like, and the false detection rate of the electronic equipment is reduced.

Corresponding to the parcel detection method provided by the embodiment of the invention, the embodiment of the invention also provides a parcel detection device.

Fig. 4 is a schematic structural diagram of a package detection device according to an embodiment of the present invention, and as shown in fig. 4, the device may include the following modules:

an image to be detected determining module 410, configured to determine each image to be detected that the image acquisition device starts to acquire at a specified time according to a preset time interval; wherein the specified time is: detecting the moment when a pedestrian appears in an image acquisition area of the image acquisition equipment;

the first region detection module 420 is configured to perform pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian region and a parcel region in the first image to be detected;

the second area detection module 430 is configured to perform pedestrian detection and parcel detection on each target image if an overlapping area exists between a pedestrian area and a parcel area in the first image to be detected, so as to obtain a pedestrian area and a parcel area in the target image; wherein each target image is: removing the first image to be detected to obtain a to-be-detected image;

a count value increasing module 440, configured to increase, for each target image, a preset count value by a specified value if an overlapping region exists between a pedestrian region and a parcel region in the target image, an overlapping region exists between a pedestrian region in the target image and a pedestrian region in an image to be detected, and an overlapping region exists between a parcel region in the target image and a parcel region in an image to be detected;

the information output module 450 is configured to output preset alarm information when the preset count value reaches a preset threshold value within a specified duration; the warning information is used for prompting that a pedestrian carries a parcel to get on the door; the starting time of the specified duration is not earlier than the specified time.

Optionally, in a specific implementation manner, the specified time is:

alternatively, the first and second electrodes may be,

after a preset pedestrian detection function is triggered, the image acquisition equipment detects the moment when a pedestrian appears in the acquired image for the first time; wherein the pedestrian detection function is triggered based on a trigger instruction sent by a specified sensor, and the trigger instruction is: the specified sensor sends the detection result when detecting that a movable object appears in a detection area of the specified sensor, and the range of the detection area is smaller than that of the image acquisition area.

the prompt information output module is used for outputting preset prompt information if the preset count value does not reach the preset threshold value within the specified duration; the prompt information is used for prompting that pedestrians pass through; or if the continuous time length of the unchanged preset count value reaches the preset time length within the specified time length, outputting the preset prompt information; and the preset duration is less than the specified duration.

Corresponding to the parcel detection method provided by the embodiment of the invention, the embodiment of the invention also provides a parcel detection system.

Fig. 5 is a schematic structural diagram of a package detection system according to an embodiment of the present invention, and as shown in fig. 5, the system may include the following modules:

an image acquisition module 510, configured to perform image acquisition on an image acquisition area of the image acquisition device;

a processor 520, configured to determine each to-be-detected image that the image capturing apparatus starts to capture at a specified time according to a preset time interval; wherein the specified time is: detecting a moment when a pedestrian appears in an image acquisition area of the image acquisition device; carrying out pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected; if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image; wherein each target image is: removing the first image to be detected to obtain a to-be-detected image; for each target image, if an overlapping area exists between a pedestrian area and a wrapping area in the target image, an overlapping area exists between the pedestrian area in the target image and a pedestrian area in a previous image to be detected, and an overlapping area exists between the wrapping area in the target image and the wrapping area in the previous image to be detected, increasing a preset count value by a specified value; when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian enters the door with a parcel; the starting time of the specified duration is not earlier than the specified time.

Optionally, in a specific implementation manner, the processor 520 is further configured to:

under the condition that the pedestrian area and the parcel area in the first image to be detected do not have an overlapping area, judging whether the parcel area meets a specified condition; wherein the specified conditions include: the wrapping area is larger than a preset area, and/or the distance between the wrapping area and the pedestrian area is smaller than a preset distance;

Optionally, in a specific implementation manner, the specified time is:

alternatively, the first and second electrodes may be,

Corresponding to the package detection method provided by the embodiment of the present invention, an embodiment of the present invention further provides an electronic device, as shown in fig. 6, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, where the processor 601, the communication interface 602, and the memory 603 complete mutual communication through the communication bus 604,

a memory 603 for storing a computer program;

the processor 601 is configured to implement the steps of any package detection method provided in the above embodiments of the present invention when executing the program stored in the memory 603.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In yet another embodiment provided by the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any of the above-mentioned package detection methods.

In yet another embodiment provided by the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the package detection methods of the above embodiments.

In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, apparatus embodiments, system embodiments, computer-readable storage medium embodiments, and computer program product embodiments are described for simplicity as they are substantially similar to method embodiments, where relevant, reference may be made to some descriptions of method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method of package inspection, the method comprising:

if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image; wherein each target image is: removing the first image to be detected to obtain a to-be-detected image;

for each target image, if an overlapping region exists between a pedestrian region and a parcel region in the target image, an overlapping region exists between the pedestrian region in the target image and a pedestrian region in a previous image to be detected, and an overlapping region exists between the parcel region in the target image and the parcel region in the previous image to be detected, increasing a preset count value by a specified value;

when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian enters the door with a parcel; the starting time of the specified duration is not earlier than the specified time.

2. The method according to claim 1, wherein in the absence of an overlapping region between the pedestrian region and the parcel region in the first image to be detected, the method further comprises:

3. The method of claim 1, wherein for each target image, in the absence of an overlapping region in the pedestrian region and the parcel region in the target image, the method further comprises:

4. A method according to any of claims 1-3, wherein the specified time is:

the image acquisition equipment detects the time when a pedestrian appears in the acquired image;

alternatively, the first and second electrodes may be,

5. The method according to claim 1, wherein before determining that the image capturing apparatus starts capturing the respective images to be detected at the specified time and at the preset time interval, the method further comprises:

6. The method of claim 1, further comprising:

alternatively, the first and second electrodes may be,

if the continuous time length of the unchanged preset counting value reaches the preset time length within the specified time length, outputting the preset prompt message; and the preset duration is less than the specified duration.

7. A package inspection system, the system comprising:

the processor is used for determining each image to be detected, which is acquired by the image acquisition equipment at a specified moment according to a preset time interval; wherein the specified time is: detecting a moment when a pedestrian appears in an image acquisition area of the image acquisition device; carrying out pedestrian detection and parcel detection on a first image to be detected to obtain a pedestrian area and a parcel area in the first image to be detected; if the pedestrian area and the parcel area in the first image to be detected have an overlapping area, carrying out pedestrian detection and parcel detection on each target image to obtain the pedestrian area and the parcel area in the target image; wherein each target image is: removing the image to be detected behind the first image to be detected; for each target image, if an overlapping area exists between a pedestrian area and a wrapping area in the target image, an overlapping area exists between the pedestrian area in the target image and a pedestrian area in a previous image to be detected, and an overlapping area exists between the wrapping area in the target image and the wrapping area in the previous image to be detected, increasing a preset count value by a specified value; when the preset count value reaches a preset threshold value within a specified time, outputting preset alarm information; the warning information is used for prompting that a pedestrian enters the door with a parcel; the starting time of the specified duration is not earlier than the specified time.

8. The system of claim 7, wherein the processor is further configured to:

9. The system of claim 7, wherein the processor is further configured to:

10. The system according to any one of claims 7-9, wherein the specified time is:

alternatively, the first and second electrodes may be,

the image acquisition equipment detects the time when a pedestrian appears in the acquired image for the first time after a preset pedestrian detection function is triggered; wherein the pedestrian detection function is triggered based on a trigger instruction sent by a specified sensor, and the trigger instruction is: the specified sensor sends when detecting that a movable object appears in a detection area of the specified sensor, and the range of the detection area is smaller than that of the image acquisition area.

11. The system of claim 7, wherein the processor is further configured to:

12. The system of claim 7, wherein the processor is further configured to:

alternatively, the first and second liquid crystal display panels may be,

13. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1-6 when executing a program stored in the memory.

14. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 6.