CN114119408A

CN114119408A - Express delivery detection method and device based on cat eye camera and cat eye camera

Info

Publication number: CN114119408A
Application number: CN202111401264.4A
Authority: CN
Inventors: 辛冠希; 钱贝贝
Original assignee: Orbbec Inc
Current assignee: Orbbec Inc
Priority date: 2021-11-24
Filing date: 2021-11-24
Publication date: 2022-03-01

Abstract

The application relates to the technical field of security protection, in particular to an express delivery detection method and device based on a cat eye camera and the cat eye camera. The express delivery detection method comprises the following steps: acquiring an image to be detected, wherein the image to be detected comprises a large view field image of the ground in front of a door; carrying out distortion correction on the image to be detected to obtain a target image; inputting the target image into an express detection model to obtain a detection result; and if the target image is determined to contain the express delivery according to the detection result, reminding is carried out. The express delivery testing result that obtains the outer region of door that this embodiment can be quick and accurate can improve user's stickness.

Description

Express delivery detection method and device based on cat eye camera and cat eye camera

Technical Field

The application relates to the technical field of security protection, in particular to an express delivery detection method and device based on a cat eye camera and the cat eye camera.

Background

With the continuous development of science and technology, the security technology field also advances an unprecedented new era.

People are increasingly demanding on home security, and the traditional cat eye cannot meet the increasing demand of users, so that the cat eye camera replaces the traditional cat eye.

At present, the cat eye camera commonly used in people's home generally only plays the monitoring effect, can look over the video information in door mouth in real time to reach safety protection's function.

Disclosure of Invention

In view of this, embodiments of the present application provide an express delivery detection method and apparatus based on a cat-eye camera, and the cat-eye camera, which can solve one or more technical problems in the related art.

In a first aspect, an embodiment of the present application provides an express delivery detection method based on a cat eye camera, including:

acquiring an image to be detected, wherein the image to be detected comprises a large view field image of the ground in front of a door;

carrying out distortion correction on the image to be detected to obtain a target image;

inputting the target image into an express detection model to obtain a detection result;

and if the target image is determined to contain the express delivery according to the detection result, reminding is carried out.

The express delivery detection method provided by the embodiment is based on the fact that the cat eye camera collects the large view field image including the ground in front of the door, the express delivery detection model is used for carrying out express delivery detection, the detection result can be obtained quickly and accurately, when the express delivery is detected in the area outside the door, the express delivery detection method can remind the user when the express delivery is detected, more convenient, personalized and intelligent services can be provided, and therefore the user viscosity is improved.

As an implementation manner of the first aspect, the express delivery detection method further includes:

determining the express delivery quantity in the target image according to the detection result;

and reminding the express delivery quantity.

The step of determining the number of the express deliveries is added, the number of the express deliveries can be determined, the number reminding can be performed, and the user loss is reduced.

and if the express delivery quantity is determined to exceed the preset value, reminding is carried out.

As an implementation manner of the first aspect, the express delivery detection model includes a convolution layer, a batch normalization layer, an activation layer, and an output layer connected in series, where the output layer further includes a classification layer and a regression layer.

As an implementation manner of the first aspect, the express delivery detection model is trained by using a mixed loss function including a classification loss function and a regression loss function.

In the embodiment, classification loss and regression loss are considered at the same time, so that the accuracy of the model is improved, and the weights of samples which are output by mistake in mutual judgment are continuously adjusted in learning to avoid overfitting.

As an implementation of the first aspect, a direct sum or a weighted sum of the classification loss function and the regression loss function is used as the mixing loss function.

In a second aspect, an embodiment of the present application provides an express delivery detection device based on cat eye camera, includes:

the system comprises an acquisition module, a detection module and a display module, wherein the acquisition module is used for acquiring an image to be detected, and the image to be detected comprises a large view field image of the ground in front of a door;

the correction module is used for carrying out distortion correction on the image to be detected to obtain a target image;

the detection execution module is used for inputting the target image into an express detection model and outputting a detection result;

and the message sending execution module is used for reminding if the target image comprises the express delivery according to the detection result.

In a third aspect, an embodiment of the present application provides a cat-eye camera, including an acquisition module, a memory, a processor, and a computer program stored in the memory and executable on the processor, where the acquisition module is configured to acquire an image to be detected, where the image to be detected includes a large field image of a ground in front of a door, and the processor implements the steps of the express delivery detection method according to the first aspect or any implementation manner of the first aspect when executing the computer program.

As an implementation manner of the third aspect, the acquisition module is a wide-angle camera, and respectively acquires the RGB image and the infrared image according to a preset time period.

In a fourth aspect, an embodiment of the present application provides a computer storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the courier detection method according to the first aspect or any implementation manner of the first aspect are implemented.

In a fifth aspect, an embodiment of the present application provides a computer program product, which when running on a cat-eye camera, enables the cat-eye camera to implement the steps of the express delivery detection method described in the first aspect or any implementation manner of the first aspect.

It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic structural diagram of a cat-eye camera according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart illustrating an implementation of an express delivery detection method according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of an express delivery detection model in an express delivery detection method according to an embodiment of the present application;

fig. 4 is a schematic flow chart illustrating an implementation of another express delivery detection method according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an express delivery detection device according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of another express delivery detection device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

The term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

Further, in the description of the present application, "a plurality" means two or more. The terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.

At present, the cat eye camera is generally installed on the user door for play the monitoring effect, and the user can look over the video information in door mouth in real time through the cat eye camera to reach safety protection's function. The function of the visible cat eye camera is relatively limited, and the intelligent degree is insufficient. Moreover, the ordinary camera that uses of current cat eye camera, its visual field is less, when the user looked over the outdoor condition through cat eye camera, has the field of vision blind area.

Therefore, the embodiment of the application provides a detection method based on the cat eye camera, and the image based on the cat eye camera of wide angle gathers carries out the target detection, when detecting the target, then reminds to provide more convenient, individualized, intelligent service, improve user's stickness.

In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.

Fig. 1 is a schematic structural diagram of a cat eye camera provided in an embodiment of the present application. The cat-eye camera may include one or more processors 10 (only one shown in fig. 1), a memory 11, and a computer program 12, e.g., a program for courier detection, stored in the memory 11 and executable on the one or more processors 10. The one or more processors 10 may implement the steps of the courier detection method embodiments described later when executing the computer program 12, or the one or more processors 10 may implement the functions of the modules/units of the courier detection apparatus embodiments described later when executing the computer program 12. The cat eye camera also includes collection module 13, and collection module 13 includes one or more cameras, and one or more cameras can be used to gather including the ground in front of the door big visual field image or video. The communication means between the one or more cameras and the processor includes wired communication and/or wireless communication, which is not limited herein.

Illustratively, the computer program 12 may be divided into one or more modules/units, which are stored in the memory 11 and executed by the processor 10 to accomplish the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing certain functions and which are used to describe the execution of computer program 12 in the processing unit. For example, the computer program 12 may be divided into several modules as follows. The specific functions of each module are as follows:

the acquisition module is used for acquiring an image to be detected, wherein the image to be detected comprises a large view field image of the ground in front of a door;

the detection execution module is used for inputting the target image into the express delivery detection model and outputting a detection result;

Further, the Processor 10 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 11 may be an internal storage unit of the processing unit, such as a hard disk or a memory of the processing unit. The memory 11 may also be an external storage device of the processing unit, such as a plug-in hard disk (hdd) provided on the processing unit, a Smart Memory Card (SMC), a Secure Digital (SD) card, a flash memory card (flash card), and the like. Further, the memory 11 may also include both an internal storage unit of the processing unit and an external storage device. The memory 11 is used for storing computer programs and other programs and data required by the processing unit. The memory 11 may also be used to temporarily store data that has been output or is to be output.

An embodiment of the present application further provides another preferred embodiment of the cat-eye camera, in this embodiment, the cat-eye camera includes one or more processors, and the one or more processors are configured to execute the following program modules stored in the memory:

Those skilled in the art will appreciate that fig. 1 is merely an example of a cat-eye camera and is not intended to be limiting. The cat-eye camera may include more or fewer components than shown, or combine certain components, or different components, e.g., the cat-eye camera may also include input-output devices, network access devices, buses, communication modules, etc.

Fig. 2 is a schematic flow chart illustrating an implementation of an express delivery detection method based on a cat-eye camera according to an embodiment of the present application. The express detection method in the embodiment is suitable for the situation that express detection needs to be performed on the area outside the door, and can be executed by an express detection device which is usually integrated in a cat-eye camera. By way of example and not limitation, the courier detection method may be applied to the cat-eye camera shown in fig. 1.

As shown in fig. 2, the express delivery detection method may include the following steps S110, S120, S130, and S140.

And S110, acquiring an image to be detected.

Wherein the image to be detected comprises an image of a large field of view of the ground in front of the door. The image to be detected may be an image or an image frame in a video sequence.

In some embodiments, the cat eye camera can acquire a large field image of the ground in front of the door of the user through the acquisition module as an image to be detected. The acquisition module may be a camera, such as a wide-angle camera. The camera collects a large view field image of the ground in front of the door of the user as an image to be detected. The processor acquires and waits to detect the image, and then judges whether have the express delivery in the image and gives accurate positioning, judges promptly whether have the express delivery in the image to generate the express delivery and detect the frame when having the express delivery, and then confirm whether the express delivery has been placed outdoors.

In one embodiment, the collection module may collect RGB images and infrared images, and preferably, the RGB images and the infrared images may be collected according to a preset time period, for example, the RGB images may be collected in a daytime time period, and the infrared images may be collected in a night time period, so that ambient light influence may be effectively filtered, and it is ensured that whether express delivery exists outside a user may be accurately detected in any time period. It should be noted that the acquisition module may include an RGB camera and an infrared camera, and may also include only one camera, and the camera acquires an RGB image and an infrared image respectively by controlling the switching filter, which is not limited herein.

In some embodiments, images to be detected can be acquired according to a preset time interval, power consumption of the cat eye camera is reduced, and whether express delivery exists outdoors or not is detected at intervals by the cat eye camera.

And S120, carrying out distortion correction on the image to be detected to obtain a target image.

Before the cat-eye camera is used, the cat-eye camera needs to be calibrated, and internal parameters and distortion parameters of an acquisition module such as the camera are determined through calibration. The calibration method is not particularly limited in the embodiments of the present application, and all calibration methods for the acquisition module can be used to implement the technical solution of the present application. After the collection module is calibrated, the internal parameters and the distortion parameters can be stored in a memory of the cat eye camera and can be called when the cat eye camera is used.

And after the image to be detected is obtained, calling the internal parameters and the distortion parameters to carry out distortion correction on the image to be detected so as to obtain a target image. The accuracy of subsequent detection results can be improved by carrying out distortion correction on the image to be detected.

And S130, inputting the target image into the express delivery detection model to obtain a detection result.

The express delivery detection model is used for detecting express deliveries in the target image.

In some embodiments, the express delivery detection model is deployed in the cat eye camera in advance, can be stored in a memory of the cat eye camera, and can be called when used. In other embodiments, the express detection model is deployed in a server or a cloud in advance, and the cat eye camera performs data interaction with the server or the cloud, specifically, the cat eye camera sends a target image to the server or the cloud, and the server or the cloud calls the express detection module, outputs a detection result, and feeds the detection result back to the cat eye camera.

The express delivery detection model may include, but is not limited to, a Support Vector Machine (SVM), Adaboost, or a neural network model. The embodiment of the application does not specifically limit the express detection model.

In some embodiments, the express delivery detection model employs a neural network model. The neural network model is used for marking a target object in a target image on one hand, such as generating a target object detection frame; on the other hand, the object is classified to determine its category, and for example, a category label of the object such as express delivery, non-express delivery, or the like is output. The express delivery detection model can finally output a target image with an express delivery detection frame. The neural network model may be an untrained initial model or a trained model. The untrained initial model and the trained model may have the same structure, except that the network parameters are not the same. The trained model has more accurate detection result and better robustness because the network parameters are subjected to iterative optimization.

As a non-limiting example, the courier detection model is a binary model, and the category label information may include couriers and non-couriers. It should be understood that if the category label information corresponding to a certain target object in a certain target image is express, the target object in the target image is express; if the category label information corresponding to a certain target object in a certain target image is non-express, the target object in the target image is not express.

As another non-limiting example, the human detection model is a model of more than three categories, and the category label information may include parcels, couriers, and spam, among others. It should be understood that if the category label information corresponding to a certain target object in a certain target image is a package or an express, the target object in the target image is an express; if the category label information corresponding to a certain target object in a certain target image is garbage, the target object in the certain target image is not express.

It should be noted that, in the model with more than three categories, express delivery or non-express delivery may be further subdivided, which is not limited in the embodiment of the present application.

In some embodiments, the courier inspection model includes a convolutional layer, a batch normalization layer, an activation layer, and an output layer in series, the output layer further including a classification layer and a regression layer. In one embodiment, as shown in FIG. 3, the courier inspection model includes 3 sets of convolutional layers, batch normalization layers, and activation layers in series, and also includes the last two output layers. The last two output layers are a classification layer and a regression layer respectively. The classification layer and the regression layer are arranged in parallel. The system comprises a convolution layer, a batch normalization layer and an activation layer, wherein the convolution layer, the batch normalization layer and the activation layer all output characteristic graphs, the convolution layer is used for carrying out linear transformation on an image, the batch normalization layer is used for preventing overfitting and accelerating convergence, and the activation layer comprises an activation function to provide nonlinearity; the regression layer is used for generating a target object detection frame corresponding to each target object in the normalized image; the classification layer is used for generating a classification label of the target object in each target object detection frame. It should be noted that, in some other embodiments, the courier inspection model may include at least one of a convolutional layer, a batch normalization layer, and an activation layer, and the number of the convolutional layer, the batch normalization layer, and the activation layer is not limited in the embodiments of the present application.

In some embodiments, the courier detection model is trained using a hybrid loss function that includes a classification loss function and a regression loss function. Because classification loss and regression loss are considered at the same time, the accuracy of the model is improved, and the weights of samples which output misjudgments are continuously adjusted in learning to avoid overfitting.

As an implementation, a direct sum or a weighted sum of the classification loss function and the regression loss function is used as the mixed loss function.

As a non-limiting example, the loss function of a class is a class cross entropy loss function, denoted L:

where N is expressed as the number of categories, y_ikRepresenting an indicator variable, wherein if the prediction class label is the same as the sample class label in the preset training set, the value is 1, otherwise, the value is 0; p is a radical of_ikRepresenting the prediction probability that the prediction class belongs to class K.

It should be noted that the preset training set includes a plurality of positive samples and a plurality of negative samples obtained under different environments, the positive samples include the target object, and the negative samples do not include the target object. Each positive sample comprises a normalized depth image sample and its target object marker box and sample class label, and each negative sample comprises a normalized depth image sample; the sample can be RGB image or infrared image, uses any image to have no obvious influence to express delivery detection model, only needs to change the parameter in the model, and different parameters can be preserved according to different images in advance to express delivery detection model, and the switching corresponds the parameter during the use can. For example, the parameters of the express delivery detection model with the sample being the RGB image training are used as the first model parameters, and the parameters of the express delivery detection model with the sample being the infrared image training are used as the second model parameters. The method comprises the steps that an image to be detected collected in the daytime is an RGB image, the RGB image after distortion correction is input into an express detection model with first model parameters, and a detection result is obtained; and the image to be detected collected in the night time period is an infrared image, and the infrared image after distortion correction is input into the express detection model with the second model parameters to obtain a detection result. The express detection models with different parameters are respectively suitable for different environments, namely a day time period and a night time period, so that the training difficulty of the models can be reduced, and the learning efficiency is improved; on the other hand, whether express delivery exists in the area outside the door of the user can be accurately detected in any time period.

As a non-limiting example, the regression loss function is a smooth (smooth) L1 loss function, denoted as smooth L1:

where x represents the error between the trained acquired target marker box and the actual target marker box (i.e., the target marker box in the positive sample before training).

And S140, prompting if the target image comprises the express delivery according to the detection result.

In step S130, the express item detection model may output the target image with the express item detection box, and thus may determine whether the target image includes the express item. And when the target image is determined to contain the express delivery according to the detection result, reminding is carried out. It should be noted that when it is determined that the target image does not include the express delivery according to the detection result, the reminding may not be performed.

In some embodiments, the cat-eye camera further comprises a reminder module. The reminding module can adopt one or more reminding devices such as an indicator light, a warning bell, a display screen and the like. And when the target image is determined to contain the express delivery according to the detection result, lighting an indicator lamp, and/or starting a warning bell, and/or displaying information.

In other embodiments, when it is determined that the target image includes the express delivery according to the detection result, a message is sent to the bound electronic device for reminding. And when the target image does not contain the express delivery according to the detection result, the reminding message is not sent to the bound electronic equipment. Electronic devices include, but are not limited to, cell phones or tablets, etc. The electronic equipment is bound with the cat eye camera in advance. The electronic equipment bound with the cat eye camera is informed of the detection result, so that more convenient and intelligent service can be provided, and the viscosity of the user is further improved.

The express delivery detection method provided by the embodiment is based on the large view field image of the ground in front of the door of the user, acquired by the cat-eye camera, and the express delivery detection is carried out by utilizing the express delivery detection model, so that the detection result can be quickly and accurately obtained, and when the express delivery is detected, the express delivery detection method can remind the user of providing more convenient, personalized and intelligent services, thereby improving the viscosity of the user.

On the basis of the express delivery detection method provided by the embodiment shown in fig. 2, as shown in fig. 4, the express delivery detection method provided by another embodiment of the present application is provided. As shown in fig. 4, the express delivery detection method may include steps S110, S120, S130, S140, and S150. The embodiment shown in fig. 4 is the same as the embodiment shown in fig. 2, and the description thereof is omitted here for brevity.

S110, obtaining an image to be detected, wherein the image to be detected comprises a large view field image of the ground in front of the door.

And S140, determining the express quantity in the target image according to the detection result.

S150, reminding the express delivery quantity.

The express delivery detection model can output the target image with the express delivery detection frame, so that whether express delivery is included in the target image or not and the express delivery quantity in the target image can be determined, and the cat eye camera can remind the express delivery quantity.

In some embodiments, the cat eye camera can remind express delivery quantity through reminding the module. In one embodiment, the express delivery quantity can be reminded by lighting the same indicator lamp as the express delivery quantity. In one embodiment, the alarm bell can be turned on to send out the ringing times which are the same as the express quantity, so that the express quantity can be reminded. In one embodiment, information corresponding to the express quantity can be displayed through the display screen to remind the express quantity.

In other embodiments, the cat-eye camera can send a message including the courier quantity to the bound electronic device.

It should be noted that, in other embodiments, a combination of multiple reminding manners may be adopted to remind the number of the express delivery, which is not limited in the present application.

In some embodiments, after the express quantity in the target image is determined according to the detection result, if the express quantity is determined to exceed a preset value, reminding is performed.

As a non-limiting example, if it is determined that the number of deliveries is 0, no reminding may be performed, for example, the reminding module is not turned on, and/or a message is not sent to the bound electronic device; if the express delivery quantity is not 0, reminding is carried out, for example, a reminding module is started, and/or a message is sent to the bound electronic equipment.

In some embodiments, the message sent to the electronic device may include, but is not limited to, the number of couriers, the category of couriers, and the like. Courier categories include, but are not limited to, packages or couriers, and the like.

In some embodiments, when the message sent to the electronic device does not include the number of express deliveries, the user can also actively retrieve, through the electronic device, the number of express deliveries detected in the history period by the cat eye camera, so as to determine whether any express delivery is lost.

The express detection method provided by the embodiment adds the step of determining the express quantity, so that the express quantity can be determined, a user can know quantity information, and the loss of the user is reduced.

It should be noted that the step numbers are not to be construed as limiting the time sequence of the steps. It should be understood that in other embodiments, the order of steps may be reversed based on logical relationships between the steps, without affecting the implementation of the present solution.

Corresponding to the express detection method, an embodiment of the present application further provides an express detection device. The express delivery detection device is not described in detail in the description of the method.

Fig. 5 is a schematic structural diagram of an express delivery detection device according to an embodiment of the present application. Express delivery detection device includes: an acquisition module 51, a correction module 52, a detection execution module 53 and a reminder execution module 54.

The acquiring module 51 is configured to acquire an image to be detected, where the image to be detected includes a large view field image of the ground in front of the door;

the correction module 52 is configured to perform distortion correction on the image to be detected to obtain a target image;

the detection execution module 53 is used for inputting the target image into the express delivery detection model and outputting a detection result;

and the reminding execution module 54 is configured to remind the user if the target image includes the express delivery according to the detection result.

Fig. 6 is a schematic structural diagram of another express delivery detection device according to an embodiment of the present application. Express delivery detection device includes: an acquisition module 51, a correction module 52, a detection execution module 53, a number determination module 55 and a reminder execution module 54.

the quantity determining module 55 is used for determining the express quantity in the target image according to the detection result;

and the reminding execution module 54 is used for reminding the express delivery quantity.

In some embodiments, based on the embodiment shown in fig. 5 or fig. 6, the express delivery detection model includes a convolutional layer, a batch normalization layer, an activation layer, and an output layer in series, and the output layer includes a classification layer and a regression layer.

In some embodiments, based on the embodiments shown in fig. 5 or fig. 6, the express delivery detection model is trained by using a mixed loss function including a classification loss function and a regression loss function.

In some embodiments, a direct sum or a weighted sum of the classification loss function and the regression loss function is used as the mixed loss function on the basis of the embodiments shown in fig. 5 or fig. 6.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps in the foregoing express delivery detection method embodiments may be implemented.

The embodiment of the application provides a computer program product, and when the computer program product runs on a cat eye camera, the cat eye camera can realize the steps in each express delivery detection method embodiment.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed device/cat-eye camera and method may be implemented in other ways. For example, the device/cat-eye camera embodiments described above are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and another division may be implemented in practice, for example, multiple units or components may be combined or integrated into 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 through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

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 modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.

The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. The express delivery detection method based on the cat eye camera is characterized by comprising the following steps of:

2. The courier detection method of claim 1, further comprising:

and reminding the express delivery quantity.

3. The courier detection method of claim 2, further comprising:

4. The courier inspection method of any of claims 1 to 3, wherein the courier inspection model includes a convolutional layer, a batch normalization layer, an activation layer, and an output layer in series, the output layer further including a classification layer and a regression layer.

5. The courier detection method of any of claims 1 to 3, wherein the courier detection model is trained using a mixture loss function comprising a classification loss function and a regression loss function.

6. The courier detection method of claim 5, wherein a direct sum or a weighted sum of the classification loss function and the regression loss function is employed as the blending loss function.

7. The utility model provides an express delivery detection device based on cat eye camera which characterized in that includes:

and the reminding execution module is used for reminding if the target image comprises the express delivery according to the detection result.

8. A cat-eye camera comprising an acquisition module, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the acquisition module is configured to acquire an image to be detected, the image to be detected comprises a large field of view image of the ground in front of a door, and the processor implements the express delivery detection method according to any one of claims 1 to 6 when executing the computer program.

9. The cat eye camera according to claim 8, wherein the collection module is a wide-angle camera for collecting RGB images and infrared images respectively for a predetermined period of time.

10. A computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the courier detection method of any of claims 1 to 6.