CN114746910A - Object exchange behavior detection method and device, electronic equipment and storage medium - Google Patents

Abstract

Provided are a method, a device, an electronic device and a storage medium for detecting object exchange behaviors, wherein the method comprises the following steps: acquiring a video stream of a target scene; performing compliance detection on the type of an object to be exchanged based on a current image under the condition that a first person is detected to place the object to be exchanged in a first preset area from the current image in a video stream to obtain a first detection result; and under the condition that the first detection result is not in compliance, outputting alarm prompt information for representing the type error of the object to be redeemed.

Description

Object exchange behavior detection method and device, electronic equipment and storage medium

Cross Reference to Related Applications

The present disclosure claims priority of the singapore intellectual property office, singapore patent application No. 10202106719W filed on 21/6/2021, the entire contents of which are incorporated herein by reference.

Technical Field

The present disclosure relates to the field of computer vision technologies, and in particular, to a method and an apparatus for detecting an object exchange behavior, an electronic device, and a storage medium.

Background

At present, for some specific scenes needing to exchange articles, corresponding exchange processes and rules are usually set, and personnel in charge of exchange need to exchange according to the exchange processes and rules.

However, because people may have subjective reasons such as wrong understanding, tension, fatigue and the like, the problem that the wrong exchange occurs in the exchange process is caused, the exchange is failed, and the exchange needs to be carried out again.

Disclosure of Invention

The embodiment of the disclosure is expected to provide a method and a device for detecting object exchange behaviors, electronic equipment and a storage medium.

The technical scheme of the embodiment of the disclosure is realized as follows:

the embodiment of the disclosure provides a method for detecting object exchange behaviors, which includes the following steps:

acquiring a video stream of a target scene;

performing compliance detection on the type of an object to be redeemed based on a current image under the condition that a first person is detected to place the object to be redeemed in a first preset area from the current image in the video stream to obtain a first detection result;

and outputting alarm prompt information representing the type error of the object to be exchanged under the condition that the first detection result is not in compliance.

In some embodiments, the performing compliance detection on the type of the object to be redeemed based on the current image to obtain a first detection result includes:

acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to the target scene;

determining that the first detection result is in compliance under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information; and/or

And determining that the first detection result is not compliant when the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

In some embodiments, further comprising:

before performing compliance detection on the type of the object to be redeemed based on the current image to obtain a first detection result, sequentially detecting a preset removing action of the first person and the object to be redeemed in the first preset area aiming at least one frame of image in the video stream, wherein the preset removing action comprises an action of removing the object to be redeemed from a preset object placing area;

and determining at least one frame of image in which the preset taking action of the first person is detected and the object to be redeemed appears in the first preset area as the current image.

In some embodiments, further comprising:

after the fact that the first person places the object to be redeemed in the first preset area is detected from the current image, continuously acquiring a first image of the first person placing a target object to be redeemed in a second preset area based on the video stream; the target exchange object is used for exchanging the object to be exchanged;

performing compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result;

and outputting alarm prompt information representing the type error of the target exchange object under the condition that the second detection result is not in compliance.

In some embodiments, the performing compliance detection on the type of the target redemption object based on the first image to obtain a second detection result includes:

acquiring preset type configuration information;

determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeeming object according to the preset type configuration information; and/or

And under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redeeming object according to the preset type configuration information, determining that the second detection result is not compliant.

In some embodiments, the performing compliance detection on the type of the target redemption object based on the first image to obtain a second detection result includes:

acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to the target scene;

determining that the second detection result is in compliance under the condition that the type of the target exchange object is matched with the object type corresponding to the character information and the preset exchangeable type information; and/or

And determining that the second detection result is not compliant when the type of the target redemption object is not matched with the object type corresponding to the character information or the preset redeemable type information.

In some embodiments, further comprising:

before performing compliance detection on the type of the target exchange object to obtain a second detection result, sequentially detecting a first preset placing action of the first person and the target exchange object in the second preset area aiming at least one frame of image behind the current image in the video stream, wherein the first preset placing action comprises an action of placing the target exchange object in the second preset area;

determining at least one frame of image in which the first preset placing action of the first person is detected and the target redemption object appears in the second preset area as the first image.

In some embodiments, further comprising:

after the first image is obtained, based on the video stream, a second image of the first person pushing the target exchange object out of the second preset area is continuously obtained;

under the condition that the second image is obtained, respectively detecting the value of the target exchange object and the value of the object to be exchanged based on the first image and the current image;

and under the condition that the values of the target exchange object and the object to be exchanged are not equal, outputting alarm prompt information representing the value error of the target exchange object.

In some embodiments, further comprising:

before the values of the target exchange object and the object to be exchanged are respectively detected based on the first image and the current image, sequentially detecting a second preset placing action of the first person and the target exchange object in a preset object placing area outside the second preset area aiming at least one frame of image behind the first image in the video stream, wherein the second preset placing action comprises an action of placing the target exchange object in the preset object placing area;

determining at least one frame of image in which the second preset placing action of the first person is detected and the target redemption object appears in the second preset area as the second image.

In some embodiments, further comprising:

after the second image is obtained, based on the video stream, continuously obtaining a third image which does not comprise the object to be exchanged in the first preset area;

and under the condition that the time length when the third image is not acquired reaches a preset time length, outputting alarm prompt information representing that the object to be exchanged is not recovered.

In some embodiments, further comprising:

acquiring character information of a second character associated with the object to be exchanged;

and under the condition that the second image is acquired, the association between the object to be redeemed and the character information is released, and the target redeeming object is associated with the character information.

In some embodiments, the target scene comprises a gaming table scene; the object to be exchanged comprises game coins, and the first preset area and the second preset area comprise preset operation areas of the first character on the game table.

The embodiment of the present disclosure provides a detection apparatus for object exchange behavior, including:

the acquisition module is used for acquiring a video stream of a target scene;

the detection module is used for carrying out compliance detection on the type of the object to be exchanged based on the current image under the condition that the object to be exchanged is placed in a first preset area by a first person is detected from the current image in the video stream, so as to obtain a first detection result;

and the warning module is used for outputting warning prompt information representing that the type of the object to be exchanged is wrong under the condition that the first detection result is not in compliance.

In some embodiments, the detection module is specifically configured to acquire character information of a second character associated with the object to be redeemed, and preset redeemable type information corresponding to the target scene; determining that the first detection result is in compliance under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information; and/or determining that the first detection result is not in compliance when the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

The detection module is further configured to sequentially detect a preset removing action of the first person and the object to be exchanged in the first preset area for at least one frame of image in the video stream before performing compliance detection on the type of the object to be exchanged based on the current image to obtain a first detection result, where the preset removing action includes an action of removing the object to be exchanged from a preset object placement area; and determining at least one frame of image in which the preset taking action of the first person is detected and the object to be redeemed appears in the first preset area as the current image.

In some embodiments, the detection module is further configured to, after the detection module detects that the first person places the object to be redeemed in the first preset area from the current image, continuously acquire, based on the video stream, a first image of the first person placing a target object to be redeemed in a second preset area; the target exchange object is used for exchanging the object to be exchanged; performing compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result;

the alarm module is further configured to output alarm prompt information indicating that the type of the target exchange object is wrong when the second detection result is that the target exchange object is not compliant.

In some embodiments, the detection module is specifically configured to obtain preset type configuration information; determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeeming object according to the preset type configuration information; and/or determining that the second detection result is not compliant under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redemption object according to the preset type configuration information.

In some embodiments, the detection module is specifically configured to acquire character information of a second character associated with the object to be redeemed, and preset redeemable type information corresponding to the target scene; determining that the second detection result is in compliance under the condition that the type of the target exchange object is matched with the object type corresponding to the character information and the preset exchangeable type information; and/or determining that the second detection result is not in compliance when the type of the target redemption object is not matched with the object type corresponding to the character information or the preset redeemable type information.

In some embodiments, the detection module is further configured to, before performing compliance detection on the type of the target redemption object and obtaining a second detection result, sequentially detect, for at least one frame of image subsequent to the current image in the video stream, a first preset placement action of the first person and the target redemption object in the second preset area, where the first preset placement action includes an action of placing the target redemption object in the second preset area; determining at least one frame of image in which the first preset placing action of the first person is detected and the target redemption object appears in the second preset area as the first image.

In some embodiments, the detection module is further configured to, after acquiring the first image, continuously acquire, based on the video stream, a second image in which the first person pushes the target redemption object out of the second preset area; under the condition that the second image is obtained, the values of the target exchange object and the object to be exchanged are respectively detected based on the first image and the current image;

the warning module is further configured to output warning prompt information representing that the value of the target exchange object is wrong when the values of the target exchange object and the object to be exchanged are not equal.

In some embodiments, the detection module is further configured to, before detecting the value of the target exchange object and the value of the object to be exchanged based on the first image and the current image, sequentially detect, for at least one frame of image after the first image in the video stream, a second preset placing action of the first person and the target exchange object in a preset object placing area outside the second preset area, where the second preset placing action includes an action of placing a target exchange object in the preset object placing area; determining at least one frame of image in which the second preset placing action of the first person is detected and the target redemption object appears in the second preset area as the second image.

In some embodiments, the detection module is further configured to, after the second image is acquired, based on the video stream, continue to acquire a third image that does not include the object to be redeemed in the first preset area;

the alarm module is further configured to output alarm prompt information indicating that the object to be exchanged is not recovered when the time length when the detection module does not acquire the third image reaches a preset time length.

In some embodiments, the detection module is further configured to obtain character information of a second character associated with the object to be redeemed; under the condition that the second image is obtained, the association between the object to be redeemed and the character information is released, and the target redeeming object is associated with the character information.

In some embodiments, the target scene comprises a gaming table scene; the object to be exchanged comprises game coins, and the first preset area and the second preset area comprise preset operation areas of the first character on the game table.

An embodiment of the present disclosure provides an electronic device, including: a processor, a memory, and a communication bus; wherein, the first and the second end of the pipe are connected with each other,

the communication bus is used for realizing connection communication between the processor and the memory;

the processor is used for executing one or more programs stored in the memory so as to realize the detection method of the object exchange behavior.

The embodiment of the disclosure provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method for detecting object redemption behavior.

The disclosure provides a method and a device for detecting object exchange behaviors, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a video stream of a target scene; performing compliance detection on the type of an object to be exchanged based on a current image under the condition that a first person is detected to place the object to be exchanged in a first preset area from the current image in the video stream to obtain a first detection result; and under the condition that the first detection result is not in compliance, outputting alarm prompt information for representing the type error of the object to be redeemed. According to the technical scheme provided by the embodiment of the disclosure, in the process of judging the exchange, whether the type of the object to be exchanged in the scene is in compliance or not is detected, and information for reminding correction of error operation in the scene is output in time under the condition of non-compliance, so that the correct rate of object exchange is improved.

Drawings

Fig. 1 is a first flowchart illustrating a method for detecting object redemption behavior according to an embodiment of the present disclosure;

fig. 2 is a schematic flowchart illustrating a second method for detecting object redemption behavior according to an embodiment of the present disclosure;

fig. 3 is a third schematic flowchart of a method for detecting object redemption behavior according to an embodiment of the present disclosure;

fig. 4 is a fourth flowchart illustrating a method for detecting object redemption behavior according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram illustrating an exemplary detection process of an object redemption process provided by an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an apparatus for detecting object redemption behavior according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure.

The disclosed embodiments provide a method for detecting an object exchange behavior, an execution subject of which may be a device for detecting an object exchange behavior, for example, the method for detecting an object exchange behavior may be executed by a terminal device or a server or other electronic devices, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like. In some possible implementations, the method for detecting object redemption behavior may be implemented by a processor invoking computer-readable instructions stored in a memory.

Fig. 1 is a first flowchart illustrating a method for detecting an object redemption behavior according to an embodiment of the present disclosure. As shown in fig. 1, in an embodiment of the present disclosure, a method for detecting a subject redemption behavior mainly includes the following steps:

s101, video stream of a target scene is obtained.

In an embodiment of the present disclosure, the detection device may acquire a video stream of the target scene.

It should be noted that, in the embodiment of the present disclosure, the target scene may be any scene in which it is necessary to exchange one object for another object, for example, a specific game table scene. Specific object scenarios embodiments of the present disclosure are not limited.

It should be noted that, in the embodiment of the present disclosure, the detection device may include a camera module, and the detection device is disposed around the target scene, so that image acquisition may be performed on the target scene. In addition, the image acquisition of the target scene can also be carried out by deploying an independent camera around the target scene, and the camera acquires the video stream of the target scene so as to transmit the video stream to the detection device. The specific acquisition mode of the video stream of the target scene may be determined according to actual requirements and device configuration, and the embodiment of the present disclosure is not limited.

S102, performing compliance detection on the type of the object to be exchanged based on the current image under the condition that the object to be exchanged is placed in a first preset area by a first person is detected from the current image in the video stream, and obtaining a first detection result.

In the embodiment of the disclosure, the detection device performs compliance detection on the type of the object to be exchanged based on the current image when detecting that the first person places the object to be exchanged in the first preset area from the current image in the video stream, so as to obtain a first detection result.

It should be noted that, in the embodiment of the present disclosure, the target scene may be a game table scene, in the game table scene, different types of game coins that different types of game players need to use are different, and therefore, game coin exchange needs to be performed, where a game coin that a player provides and needs to exchange may be an object to be exchanged, and a person providing a game coin exchange service for the player may be a first character, where the first preset area includes a preset operation area of the first character on the game table. The specific first person, the object to be redeemed, and the first preset area may be determined according to an actual target scene, and the embodiment of the disclosure is not limited.

Specifically, in the embodiment of the present disclosure, the performing, by a detection apparatus, compliance detection on a type of an object to be exchanged based on a current image to obtain a first detection result includes: acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to a target scene; under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information, determining that the first detection result is in compliance; and/or determining that the first detection result is not compliant under the condition that the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

It is understood that, in the embodiment of the present disclosure, a person of an object to be redeemed, that is, a second person associated with the object to be redeemed is provided, the detection device may obtain person information of the second person, where the person information may include information about whether the person is a member, and the like, a specific second person, and the person information of the second person, and the embodiment of the present disclosure is not limited. The type of the object to be redeemed may or may not match the type of the object corresponding to the character information, and the type of the object to be redeemed corresponding to the character information represents the type of the object to be redeemed, which is allowed to be used by the second character. For example, the character information includes that the second character is a member, and the corresponding object type is an object type that only the member can exchange, and when the type of the object to be exchanged is an object type only for the member, the type of the object to be exchanged matches with the object type corresponding to the character information.

It should be noted that, in the embodiment of the present disclosure, the second person associated with the object to be redeemed, and the person information of the second person may be pre-stored in the detection apparatus, and of course, the detection apparatus may be obtained from other management devices. In addition, if the detection means does not store the personal information of the second person locally or in other management devices, the second person may be directly selected by the first person and the personal information may be input to the detection means. Specific manner of acquiring the personal information is not limited in the embodiment of the present disclosure.

It can be understood that, in the embodiment of the present disclosure, for a target scene, object types convertible thereto are limited, and the detection apparatus may directly obtain preset convertible type information corresponding to the target scene, which includes object types convertible in the target scene. Since the type of the object to be redeemed is not necessarily the target scene in which the object can be redeemed, the type of the object to be redeemed needs to be matched with the preset redeemable type information.

It should be noted that, in the embodiment of the present disclosure, the type of the object to be redeemed needs to be matched with the object type corresponding to the character information and the preset redeemable type information at the same time, and the first detection result is a compliance, otherwise, the first detection result is a non-compliance.

It should be noted that, in the embodiment of the present disclosure, before the detecting device performs compliance detection on the type of the object to be exchanged based on the current image to obtain the first detection result, the following steps may be further performed: sequentially detecting a preset removing action of a first person and an object to be exchanged in a first preset area aiming at least one frame of image in a video stream, wherein the preset removing action comprises an action of removing the object to be exchanged from a preset object placing area; and determining at least one frame of image in which the preset taking-away action of the first person is detected and the object to be exchanged appears in the first preset area as a current image.

It can be understood that, in the embodiment of the present disclosure, the detection apparatus needs to determine the current image from the video stream of the target scene before performing the compliance detection on the type of the object to be exchanged based on the current image. The detection device sequentially detects the preset taking-away action of the first person aiming at least one frame of image in the video stream, and particularly can be realized by detecting the action of the first person based on continuous multi-frame images and also can be realized by continuously detecting the position of the object to be exchanged and operating whether a person to which the hand of the object to be exchanged belongs is the first person or not through the video stream. The specific current image may be a frame image or a multi-frame image, and the embodiment of the present disclosure is not limited.

S103, outputting alarm prompt information representing the type error of the object to be exchanged under the condition that the first detection result is not in compliance.

In the embodiment of the disclosure, after obtaining the first detection result, the detection device outputs the warning prompt information representing the type error of the object to be redeemed under the condition that the first detection result is not compliant.

It can be understood that, in the embodiment of the present disclosure, when the first detection result is that the object to be exchanged is not in compliance, that is, the object to be exchanged is not in compliance in type, the object to be exchanged cannot be exchanged in the target scene, and therefore, the detection device may output the warning prompt information indicating that the object to be exchanged is in the wrong type in time, so that the first person placing the object to be exchanged in the first preset area may timely know that the object to be exchanged is not in exchange, and the object to be exchanged is returned to the associated second person, thereby improving the correct rate of object exchange.

Fig. 2 is a schematic flowchart of a second method for detecting an object redemption behavior according to an embodiment of the disclosure. As shown in fig. 2, in the embodiment of the present disclosure, after the detecting device performs step S101, the following steps may also be performed:

s201, after a first person is detected from a current image and an object to be exchanged is placed in a first preset area, continuously acquiring a first image of the first person and a target exchange object placed in a second preset area based on a video stream; the target redemption object is an object used for redeeming the object to be redeemed.

In the embodiment of the disclosure, the detection device may continue to acquire a target exchange object to be used for exchanging the object to be exchanged by the first person and a first image to be placed in a second preset area based on the video stream when detecting that the object to be exchanged by the first person is placed in the first preset area from the current image.

It should be noted that, in the embodiment of the present disclosure, the target scene includes a game table scene, the second preset area includes a preset operation area of the first character on the game table, and the specific second preset area is not limited in the embodiment of the present disclosure.

Specifically, in the embodiment of the present disclosure, the detection apparatus sequentially detects, for at least one frame of image after a current image in a video stream, a first preset placing action of a first person and a target exchange object in a second preset area, where the first preset placing action includes an action of placing the target exchange object in the second preset area; determining at least one frame of image in which the first preset placing action of the first person is detected and the target exchange object appears in the second preset area as a first image.

It can be understood that, in the embodiment of the present disclosure, the current image is an image in which a first person in a video stream places an object to be redeemed in a first preset area, and then the first person actually needs to place a target redemption object for redeeming the object to be redeemed in a second preset area. The detection device sequentially detects a first preset placing action of a first person aiming at least one frame of image behind a current image in the video stream, specifically, the first preset placing action can be realized by detecting the action of the first person based on continuous multi-frame images, and the detection device can also be realized by continuously detecting the position of a target exchange object and whether a person to which a hand of an operation target exchange object belongs is the first person through the video stream. The specific first image may be a frame image or a multi-frame image, and the embodiment of the present disclosure is not limited.

S202, carrying out compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result.

In an embodiment of the disclosure, in a case that the detection apparatus obtains the first image, that is, the target redemption object is already placed in the second preset area, compliance detection may be performed on the type of the target redemption object based on the first image, so as to obtain a second detection result.

Specifically, in an embodiment of the present disclosure, the detecting device performs compliance detection on the target exchange object based on the first image to obtain a second detection result, including: acquiring preset type configuration information; determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeeming object according to the preset type configuration information; and/or determining that the second detection result is not compliant under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redeeming object according to the preset type configuration information.

It should be noted that, in the embodiment of the present disclosure, the preset type configuration information is an object type that is exchangeable for different types of objects that are set. The specific preset type configuration information may be set according to actual needs and application scenarios, and the embodiment of the present disclosure is not limited.

Illustratively, in an embodiment of the present disclosure, the preset type configuration information includes: the object with the type A is matched with the exchange objects with the types B and C, and the object with the type B is matched with the exchange objects with the types A and D. If the type of the object to be redeemed is A and the type of the target redeeming object is D, the object of the type A and the object of the type D are not matched in the preset type configuration information, so that the detection device can determine that the second detection result is not compliant. If the type of the object to be redeemed is A and the type of the target redeeming object is B, the object of the type A is not matched with the object of the type B in the preset type configuration information, and therefore the detection device can determine that the second detection result is in compliance.

It should be noted that, in the embodiment of the present disclosure, the detection device performs compliance detection on the type of the target redemption object, and may detect whether the type of the target redemption object matches the type of the object to be redeemed, and may also perform detection based on other type setting rules, which is not limited in the embodiment of the present disclosure.

Specifically, in an embodiment of the present disclosure, the detecting device performs compliance detection on the type of the target redemption object based on the first image to obtain a second detection result, and may further include: acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to a target scene; determining that the second detection result is in compliance under the condition that the type of the target exchange object is matched with the object type corresponding to the character information and the preset exchangeable type information; and/or determining that the second detection result is not compliant under the condition that the type of the target exchange object is not matched with the object type corresponding to the character information or the preset exchangeable type information.

It is understood that, in the embodiment of the present disclosure, the detecting means may acquire the personal information of the second person, and the personal information may include information on whether the person is a member or not. The type of the target exchange object may be matched with the object type corresponding to the character information, for example, the character information is that the second character is a member, and only the member can exchange the object of the target exchange object type, that is, allow the target exchange object to be exchanged to the second character. Of course, the type of the target exchange object may not match the type of the object corresponding to the character information, for example, if the character information is that the second character is a non-member, only the member can exchange the object of the target exchange object type, that is, the target exchange object is not allowed to be exchanged to the second character.

It can be understood that, in the embodiment of the present disclosure, for a target scene, the object types that can be exchanged out are limited, and the detection device may directly obtain preset exchangeable type information corresponding to the target scene, where the preset exchangeable type information includes object types that can be exchanged out in the target scene. Since the type of the target redemption object is not necessarily redeemable in the target scene, the type of the target redemption object needs to be matched with the preset redeemable type information.

And S203, outputting alarm prompt information representing the type error of the target exchange object under the condition that the second detection result is not in compliance.

In the embodiment of the disclosure, after obtaining the second detection result, the detection device may output an alarm prompt message indicating that the target redemption object type is wrong if the second detection result is not compliant.

It can be understood that, in the embodiment of the present disclosure, when the second detection result is that the target exchange object is not in compliance, that is, the type of the target exchange object is not in compliance, the target exchange object cannot be exchanged in the target scene, and therefore, the detection device may output the warning prompt information indicating that the type of the target exchange object is wrong in time, so that the first person may timely know that the target exchange object cannot be exchanged, retrieve the target exchange object, and improve the correct rate of object exchange.

Fig. 3 is a third schematic flowchart of a detection method for a redemption object behavior according to an embodiment of the present disclosure. As shown in fig. 3, in the embodiment of the present disclosure, after the detecting device performs step S201, the following steps may also be performed:

s301, after the first image is obtained, a second image of the first person pushing the target exchange object out of a second preset area is continuously obtained based on the video stream.

In an embodiment of the disclosure, after acquiring the first image, the detection device may continue to acquire a second image of the first person pushing the target redemption object out of the second preset area based on the video stream.

Specifically, in the embodiment of the present disclosure, the detection apparatus sequentially detects, for at least one frame of image after the first image in the video stream, a second preset placing action of the first person and a target exchange object in a preset object placing area outside the second preset area, where the second preset placing action includes an action of placing the target exchange object in the preset object placing area; and determining at least one frame of image in which the second preset placing action of the first person is detected and the target exchange object appears in the second preset area as a second image.

It can be understood that, in the embodiment of the present disclosure, the detection device sequentially detects, for at least one frame of image after the current image in the video stream, the first preset placing action of the first person, specifically, may be implemented by detecting an action of the first person based on consecutive multi-frame images, and may also be implemented by continuously detecting, by the video stream, the position of the target redemption object and whether a person to which a hand operating the target redemption object belongs is the first person. The specific second image may be a frame image or a multi-frame image, and the embodiment of the present disclosure is not limited.

S302, under the condition that the second image is obtained, the values of the target exchange object and the object to be exchanged are respectively detected based on the first image and the current image.

In the embodiment of the disclosure, the detection device, when acquiring the second image, that is, the first person pushes the target exchange object out of the second preset area, at this time, represents that the first person has confirmed that the selected target exchange object can be exchanged for the object to be exchanged, and thus the detection device further detects the value of the target exchange object and the value of the object to be exchanged based on the first image and the current image respectively.

It can be understood that, in the embodiment of the present disclosure, the target exchange object is used for exchanging the object to be exchanged, the exchange principle is that the value of the two exchanged objects is equal, and the value represented by the target exchange object selected by the first person may be misjudged and is not equal to the value of the object to be exchanged, so the detection apparatus needs to further detect the values of the two exchanged objects.

S303, under the condition that the value of the target exchange object is not equal to that of the object to be exchanged, outputting alarm prompt information representing the value error of the target exchange object.

In the embodiment of the disclosure, after the detection device detects the values of the target exchange object and the object to be exchanged respectively, under the condition that the values of the target exchange object and the object to be exchanged are not equal, the detection device outputs the alarm prompt information representing the value error of the object to be exchanged.

It can be understood that, in the embodiment of the disclosure, when the values of the target exchange object and the object to be exchanged are not equal, the exchange cannot be performed in the target scene, and therefore, the detection device can output warning prompt information representing that the value of the object to be exchanged is wrong in time, so that the first person can be reminded to adjust the number of the target exchange objects, the value of the target exchange objects is equal to the value of the object to be exchanged, the object exchange is realized, and the correct rate of the object exchange is improved.

Fig. 4 is a fourth schematic flowchart of a detection method according to an embodiment of the present disclosure. As shown in fig. 4, in the embodiment of the present disclosure, after the detecting device performs step S301, the following steps may also be performed:

s401, after the second image is obtained, continuously obtaining a third image which does not comprise the object to be exchanged in the first preset area based on the video stream.

In the embodiment of the disclosure, after the detection device acquires the second image, the detection device may continue to acquire a third image that does not include the object to be redeemed in the first preset area based on the video stream.

It is understood that, in the embodiment of the present disclosure, the detecting device may sequentially detect whether the object to be redeemed is included in the first preset area for at least one frame of image after the second image in the video stream, so as to determine, as the third image, the at least one frame of image in which the object to be redeemed is not detected in the first preset area.

S402, under the condition that the time length when the third image is not acquired reaches the preset time length, outputting alarm prompt information representing that the object to be exchanged is not recovered.

In the embodiment of the disclosure, the detection device outputs warning prompt information indicating that the object to be exchanged is not recovered when the time length when the third image is not acquired reaches the preset time length.

It should be noted that, in the embodiment of the present disclosure, a preset duration is stored in the detection device, and a specific preset duration may be set according to an actual requirement and an application scenario, which is not limited in the embodiment of the present disclosure.

It can be understood that, in the embodiment of the disclosure, when the detection device starts to acquire the third image after the values of the target exchange object and the object to be exchanged are equal, timing is performed, if the third image is not acquired within a preset time period, that is, the object to be exchanged is always located in the first preset area, that is, the first person may forget to recover the object to be exchanged after exchanging the target exchange object, so that the detection device may output warning prompt information indicating that the object to be exchanged is not recovered, and the first person may recover the object to be exchanged in time after checking the warning prompt information.

It should be noted that, in the embodiment of the present disclosure, after the detection apparatus completes the redemption, the following steps may also be performed: acquiring character information of a second character associated with the object to be exchanged; and under the condition that the second image is acquired, the association between the object to be redeemed and the character information is released, and the target redeeming object is associated with the character information.

It can be understood that in the embodiment of the disclosure, after the redemption is completed, the object held by the second person is actually changed, so that the detection device releases the association between the object to be redeemed and the person information of the second person, and increases the association between the target redemption object and the person information of the second person, thereby facilitating tracing and obtaining the related information of the person associated with the target redemption object in the subsequent target redemption object application process, so as to perform corresponding processing, and ensure the correctness of the use. In addition, the object to be redeemed can also be provided for other people to use, and the object utilization rate is improved.

Fig. 5 is a schematic detection flow diagram of an exemplary object redemption process provided by an embodiment of the present disclosure. As shown in fig. 5, in the embodiment of the present disclosure, in a case that a second person associated with an object to be redeemed requires to redeem the object to be redeemed, a detection device may acquire a current image of a first person placing the object to be redeemed in a first preset area, and then may acquire a first image of a first person placing a target object to be redeemed in a second preset area, and detect whether types of the object to be redeemed and the target object are compliant, so that corresponding warning prompt information is output in a case that the types of the object to be redeemed and the target object are not compliant, and the first person may adjust. And under the condition of compliance, acquiring a second image of pushing the target exchange object out of a second preset area by the first person, detecting whether the value of the object to be exchanged is consistent with that of the target exchange object, and if not, outputting corresponding alarm prompt information.

It should be noted that, in the embodiment of the present disclosure, after detecting whether the types of the object to be redeemed and the target redemption object are in compliance, the detection apparatus outputs corresponding warning prompt information in the case that the types of the object to be redeemed and the target redemption object are not in compliance, and in the case that the types of the object to be redeemed and the target redemption object are in compliance, the person information of the second person may be sent to other management devices and stored in the other management devices.

The embodiment of the disclosure provides a method for detecting object exchange behaviors, which includes: acquiring a video stream of a target scene; performing compliance detection on the type of an object to be exchanged based on a current image under the condition that a first person is detected to place the object to be exchanged in a first preset area from the current image in a video stream to obtain a first detection result; and under the condition that the first detection result is not in compliance, outputting alarm prompt information representing the type error of the object to be exchanged. According to the detection method for the object exchange behavior provided by the embodiment of the disclosure, in the process of judging the exchange, whether the type of the object to be exchanged is in compliance in a scene is detected, and information for reminding correction of error operation in the scene is timely output under the condition of non-compliance, so that the correct rate of object exchange is improved.

The embodiment of the disclosure provides a detection device for object exchange behaviors. Fig. 6 is a schematic structural diagram of an apparatus for detecting an object redemption behavior according to an embodiment of the present disclosure. As shown in fig. 6, the detection device includes:

an obtaining module 601, configured to obtain a video stream of a target scene;

a detection module 602, configured to perform compliance detection on the type of an object to be redeemed based on a current image when it is detected that a first person places the object to be redeemed in a first preset area from the current image in the video stream, so as to obtain a first detection result;

and an alarm module 603, configured to output alarm prompt information indicating that the type of the object to be redeemed is wrong when the first detection result is that the object to be redeemed is not compliant.

In an embodiment of the present disclosure, the detection module 602 is specifically configured to obtain character information of a second character associated with the object to be redeemed, and preset redeemable type information corresponding to the target scene; determining that the first detection result is in compliance under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information; and/or determining that the first detection result is not in compliance when the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, before performing compliance detection on the type of the object to be redeemed based on the current image to obtain a first detection result, sequentially detect, for at least one frame of image in the video stream, a preset removing action of the first person and the object to be redeemed in the first preset area, where the preset removing action includes an action of removing the object to be redeemed from a preset object placing area; and determining at least one frame of image in which the preset taking action of the first person is detected and the object to be redeemed appears in the first preset area as the current image.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, after the detecting module detects that the first person places the object to be exchanged in the first preset area from the current image, continuously obtain, based on the video stream, a first image of the first person placing a target object to be exchanged in a second preset area; the target exchange object is used for exchanging the object to be exchanged; performing compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result;

the warning module 603 is further configured to output warning prompt information indicating that the type of the target redemption object is wrong when the second detection result is that the target redemption object is not compliant.

In an embodiment of the present disclosure, the detecting module 602 is specifically configured to obtain preset type configuration information; determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeeming object according to the preset type configuration information; and/or determining that the second detection result is not compliant under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redemption object according to the preset type configuration information.

In an embodiment of the present disclosure, the detection module 602 is specifically configured to obtain character information of a second character associated with the object to be redeemed, and preset redeemable type information corresponding to the target scene; determining that the second detection result is in compliance under the condition that the type of the target exchange object is matched with the object type corresponding to the character information and the preset exchangeable type information; and/or determining that the second detection result is not in compliance when the type of the target redemption object is not matched with the object type corresponding to the character information or the preset redeemable type information.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, before performing compliance detection on the type of the target redemption object and obtaining a second detection result, sequentially detect, for at least one frame of image after the current image in the video stream, a first preset placing action of the first person and the target redemption object in the second preset area, where the first preset placing action includes an action of placing the target redemption object in the second preset area; determining at least one frame of image in which the first preset placing action of the first person is detected and the target redemption object appears in the second preset area as the first image.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, after the first image is obtained, based on the video stream, continue to obtain a second image in which the first person pushes the target redemption object out of the second preset area; under the condition that the second image is obtained, respectively detecting the value of the target exchange object and the value of the object to be exchanged based on the first image and the current image;

the warning module 603 is further configured to output warning prompt information indicating that the value of the target exchange object is wrong when the values of the target exchange object and the object to be exchanged are not equal.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, before the values of the target exchange object and the object to be exchanged are respectively detected based on the first image and the current image, sequentially detect, for at least one frame of image after the first image in the video stream, a second preset placing action of the first person and the target exchange object in a preset object placing area outside the second preset area, where the second preset placing action includes an action of placing the target exchange object in the preset object placing area; determining at least one frame of image in which the second preset placing action of the first person is detected and the target redemption object appears in the second preset area as the second image.

In an embodiment of the present disclosure, the detecting module 602 is further configured to, after the second image is obtained, based on the video stream, continue to obtain a third image that does not include the object to be redeemed in the first preset area;

the warning module 603 is further configured to output warning prompt information indicating that the object to be redeemed is not recovered when the duration that the third image is not acquired by the detection module 602 reaches a preset duration.

In an embodiment of the present disclosure, the detection module 602 is further configured to obtain the character information of a second character associated with the object to be redeemed; under the condition that the second image is obtained, the association between the object to be redeemed and the character information is released, and the target redeeming object is associated with the character information.

In some embodiments, the target scene comprises a gaming table scene; the object to be exchanged comprises game coins, and the first preset area and the second preset area comprise preset operation areas of the first character on the game table.

The embodiment of the disclosure provides an electronic device. Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic apparatus includes: a processor 701, a memory 702, and a communication bus 703; wherein the content of the first and second substances,

the communication bus 703 is used for realizing connection communication between the processor 701 and the memory 702;

the processor 701 is configured to execute one or more programs stored in the memory 702 to implement the method for detecting the object redemption behavior.

The embodiment of the disclosure also provides a computer-readable storage medium, which stores one or more programs, where the one or more programs may be executed by one or more processors to implement the method for detecting the object redemption behavior. The computer-readable storage medium may be a volatile Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile Memory (non-volatile Memory), such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard Disk (Hard Disk Drive, HDD) or a Solid-State Drive (SSD); or may be a respective device, such as a mobile phone, computer, tablet device, personal digital assistant, etc., that includes one or any combination of the above-mentioned memories.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable signal processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable signal processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable signal processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable signal processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only for the preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure.

Claims (21)

1. A method for detecting object redemption behavior, the method comprising:

acquiring a video stream of a target scene;

performing compliance detection on the type of the object to be redeemed based on a current image under the condition that the object to be redeemed is placed in a first preset area by a first person is detected from the current image in the video stream, so as to obtain a first detection result;

and outputting alarm prompt information representing the type error of the object to be exchanged under the condition that the first detection result is not in compliance.

2. The method of claim 1, wherein the performing compliance detection on the type of the object to be redeemed based on the current image to obtain a first detection result comprises:

acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to the target scene;

determining that the first detection result is in compliance under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information; and/or

And determining that the first detection result is not compliant when the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

before performing compliance detection on the type of the object to be redeemed based on the current image to obtain a first detection result, sequentially detecting a preset taking-away action of the first person and the object to be redeemed in the first preset area aiming at least one frame of image in the video stream, wherein the preset taking-away action comprises an action of taking away the object to be redeemed from a preset object placing area;

and determining at least one frame of image in which the preset taking action of the first person is detected and the object to be redeemed appears in the first preset area as the current image.

4. The method of claim 1, further comprising:

after the first person is detected to place the object to be redeemed in the first preset area from the current image, continuously acquiring a first image of the first person for placing a target object to be redeemed in a second preset area based on the video stream; the target exchange object is used for exchanging the object to be exchanged;

performing compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result;

and outputting alarm prompt information representing the type error of the target exchange object under the condition that the second detection result is not in compliance.

5. The method of claim 4, wherein the performing compliance detection on the type of the target redemption object based on the first image to obtain a second detection result comprises:

acquiring preset type configuration information;

determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeemed object according to the preset type configuration information; and/or

And under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redeeming object according to the preset type configuration information, determining that the second detection result is not compliant.

6. The method of claim 4, wherein the performing compliance detection on the type of the target redemption object based on the first image to obtain a second detection result comprises:

acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to the target scene;

determining that the second detection result is in compliance under the condition that the type of the target exchange object is matched with the object type corresponding to the character information and the preset exchangeable type information; and/or

And determining that the second detection result is not compliant when the type of the target exchange object is not matched with the object type corresponding to the character information or the preset exchange type information is not matched.

7. The method of claim 4, further comprising:

before performing compliance detection on the type of the target exchange object to obtain a second detection result, sequentially detecting a first preset placing action of the first person and the target exchange object in the second preset area aiming at least one frame of image behind the current image in the video stream, wherein the first preset placing action comprises an action of placing the target exchange object in the second preset area;

determining at least one frame of image in which the first preset placing action of the first person is detected and the target redemption object appears in the second preset area as the first image.

8. The method of claim 4, further comprising:

after the first image is obtained, continuously obtaining a second image of pushing the target exchange object out of the second preset area by the first person on the basis of the video stream;

under the condition that the second image is obtained, respectively detecting the value of the target exchange object and the value of the object to be exchanged based on the first image and the current image;

and under the condition that the values of the target exchange object and the object to be exchanged are not equal, outputting alarm prompt information representing the value error of the target exchange object.

9. The method of claim 8, further comprising:

before the values of the target exchange object and the object to be exchanged are respectively detected based on the first image and the current image, sequentially detecting a second preset placing action of the first person and the target exchange object in a preset object placing area outside the second preset area aiming at least one frame of image behind the first image in the video stream, wherein the second preset placing action comprises an action of placing the target exchange object in the preset object placing area;

determining at least one frame of image in which the second preset placing action of the first person is detected and the target redemption object appears in the second preset area as the second image.

10. The method of claim 8, further comprising:

after the second image is obtained, based on the video stream, continuously obtaining a third image which does not comprise the object to be exchanged in the first preset area;

and under the condition that the time length when the third image is not acquired reaches a preset time length, outputting alarm prompt information representing that the object to be exchanged is not recovered.

11. The method of claim 8, further comprising:

acquiring character information of a second character associated with the object to be exchanged;

and under the condition that the second image is acquired, the association between the object to be redeemed and the character information is released, and the target redeeming object is associated with the character information.

12. The method of any of claims 8-11, wherein the target scene comprises a gaming table scene; the object to be exchanged comprises game coins, and the first preset area and the second preset area comprise preset operation areas of the first character on the game table.

13. An apparatus for detecting object redemption behavior, comprising:

the acquisition module is used for acquiring a video stream of a target scene;

the detection module is used for carrying out compliance detection on the type of the object to be exchanged based on the current image under the condition that the object to be exchanged is placed in a first preset area by a first person is detected from the current image in the video stream, so as to obtain a first detection result;

and the warning module is used for outputting warning prompt information representing that the type of the object to be exchanged is wrong under the condition that the first detection result is not in compliance.

14. The apparatus of claim 13,

the detection module is specifically used for acquiring character information of a second character associated with the object to be exchanged and preset exchangeable type information corresponding to the target scene; determining that the first detection result is in compliance under the condition that the type of the object to be redeemed is matched with the object type corresponding to the character information and the preset redeemable type information; and/or determining that the first detection result is not in compliance when the type of the object to be redeemed is not matched with the object type corresponding to the character information or the preset redeemable type information.

15. The apparatus of claim 13 or 14,

the detection module is further configured to sequentially detect a preset removing action of the first person and the object to be exchanged in the first preset area for at least one frame of image in the video stream before performing compliance detection on the type of the object to be exchanged based on the current image to obtain a first detection result, where the preset removing action includes an action of removing the object to be exchanged from a preset object placement area; and determining at least one frame of image in which the preset taking-away action of the first person is detected and the object to be redeemed appears in the first preset area as the current image.

16. The apparatus of claim 13,

the detection module is further configured to, after it is detected from the current image that the first person places the object to be exchanged in the first preset area, continuously acquire, based on the video stream, a first image in which the first person places a target object to be exchanged in a second preset area; the target exchange object is used for exchanging the object to be exchanged; performing compliance detection on the type of the target exchange object based on the first image under the condition of acquiring the first image to obtain a second detection result;

and the alarm module is further used for outputting alarm prompt information representing the type error of the target exchange object under the condition that the second detection result is not in compliance.

17. The apparatus of claim 16,

the detection module is specifically used for acquiring preset type configuration information; determining that the second detection result is in compliance under the condition that the type of the object to be redeemed is determined to be matched with the type of the target redeeming object according to the preset type configuration information; and/or determining that the second detection result is not compliant under the condition that the type of the object to be redeemed is determined to be not matched with the type of the target redemption object according to the preset type configuration information.

18. An electronic device, comprising: a processor, a memory, and a communication bus; wherein the content of the first and second substances,

the communication bus is used for realizing connection communication between the processor and the memory;

the processor is configured to execute one or more programs stored in the memory to implement the method for detecting object redemption behavior of any one of claims 1-12.

19. A computer-readable storage medium, storing one or more programs, which are executable by one or more processors, to implement the method for detecting object redemption behavior of any one of claims 1-12.

20. A computer program stored in a memory, wherein the computer program, when executed by a processor, implements a method of detecting object redemption behavior of any one of claims 1 to 12.

21. A computer program, wherein the computer program comprises computer readable code which, when executed in an electronic device, causes a processor in the electronic device to perform the method of any of claims 1-12.

Images