Image target detection method, device, equipment, medium and computer program product

Abstract

The present invention provides an image target detection method, device, equipment, medium and computer program product, the method comprising: uniformly processing the image format of a target image set to obtain a set of images to be detected; determining the target to be detected based on the set of images to be detected; performing traversal detection on each image in the set of images to be detected based on the target to be detected according to the image sequence of the set of images to be detected to obtain an image detection result; and outputting the target detection result of each image in the set of images to be detected based on the image detection result according to the image sequence of the set of images to be detected. The present invention improves the efficiency of image target detection by automatically arranging the target detection results of the images output in sequence by sequentially detecting the set of images to be detected and outputting the target detection results in sequence.

Description

Technical Field

[0001] The present invention relates to the field of image detection technology, and in particular to an image target detection method, device, equipment, medium and computer program product. Background Art

[0002] When using existing target detection algorithms to detect targets on images, only the progress of target detection is displayed on the command-line interface (CLI), but the specific detection results of the images are not displayed, and can only be observed one by one; and the detection results displayed by the existing target detection algorithms on the CLI are not sequential.

[0003] In actual image detection scenarios, sequentially adjacent images often come from the same scene and have a temporal relationship. Outputting the image detection results out of sequence will affect the analysis and judgment of the scene. The existing method of manually querying and sorting the target detection results of each image is time-consuming and labor-intensive, resulting in low efficiency in image target detection. Summary of the invention

[0004] The present invention provides an image target detection method, device, equipment, medium and computer program product, which are used to solve the defect of low detection efficiency in the existing image target detection technology and realize more efficient image target detection.

[0005] The present invention provides an image target detection method, comprising the following steps: The image formats of the target image set are uniformly processed to obtain the image set to be detected; Determine a target to be detected based on the set of images to be detected; According to the image sequence of the image set to be detected, each image in the image set to be detected is traversed and detected based on the target to be detected to obtain an image detection result; According to the image sequence of the to-be-detected image set, the target detection result of each image in the to-be-detected image set is output based on the image detection result.

[0006] According to an image target detection method provided by the present invention, the image formats of the target image set are uniformly processed to obtain the image set to be detected, which includes: determining an image format for each image of a target image set; The formats of the target images in the target image set are processed uniformly to obtain a set of images to be detected; the formats of the target images are the formats to be unified.

[0007] According to an image target detection method provided by the present invention, determining the target to be detected based on the set of images to be detected includes: When receiving an image target input by a user, taking the image target as a target to be detected; In the case where no image target input by the user is received, determining the target type contained in each image of the to-be-detected image set and the initial detection result of each target type; Receiving an initial detection target input by a user based on the target type and the initial detection result, and using the initial detection target as a target to be detected; Alternatively, when an image target input by a user is received and the image target does not belong to the initial detection result of the image set to be detected, an initial detection target input by the user based on the target type and the initial detection result is received, and the initial detection target is used as the target to be detected.

[0008] According to an image object detection method provided by the present invention, the image object detection method further includes: According to the image sequence of the image set to be detected, each image in the image set to be detected is traversed and detected based on the target to be detected, so as to obtain an image detection result of each image in the image set to be detected; the image detection result includes the number of the targets to be detected and the image position of the targets to be detected; When receiving a query request input by a user based on a target image in the set of images to be detected, and the target image contains the target to be detected, the quantity information and position identifier of the target to be detected in the target image are output.

[0009] According to an image target detection method provided by the present invention, outputting the target detection result of each image in the image set to be detected based on the image detection result according to the image order of the image set to be detected comprises: Determining a sequence identifier and a detection time for each image in the set of images to be detected; The target detection result of each image in the set of images to be detected is output based on the image detection result; the target detection result includes the sequence identifier, the detection time, the detection identifier and the detection number of the targets to be detected.

[0010] According to an image target detection method provided by the present invention, the target detection result of each image in the image set to be detected is output based on the image detection result according to the image order of the image set to be detected, and then includes: Upon receiving a save instruction input by a user based on the target detection result, saving the target detection result of each image in the set of images to be detected; Upon receiving an update instruction input by a user based on the target detection result, determining a first detection target corresponding to the update instruction; In the case that the first detection target and the target to be detected are different, the target detection result of each image in the set of images to be detected is updated based on the first detection target according to the image sequence of the set of images to be detected.

[0011] The present invention also provides an image target detection device, comprising the following modules: An image format unification module is used to unify the image formats of the target image set to obtain an image set to be detected; A to-be-detected target determination module, used to determine the to-be-detected target based on the to-be-detected image set; An image traversal detection module is used to perform traversal detection on each image in the image set to be detected based on the target to be detected in accordance with the image sequence of the image set to be detected, so as to obtain an image detection result; The image object detection output module is used to output the object detection result of each image in the image set to be detected based on the image detection result according to the image sequence of the image set to be detected.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned image target detection methods is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the image target detection method described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the image target detection method described above is implemented.

[0015] The image target detection method, device, equipment, medium and computer program product provided by the present invention uniformly process the image format in the image set before detecting the target in the image to obtain the image set to be detected, and then determine the target to be detected based on the image set to be detected; according to the image sequence in the image set to be detected, traverse and detect each image in the image set to be detected based on the target to be detected to obtain the image detection result of the image set to be detected; finally, according to the image sequence in the image set to be detected, process the image detection result, and output the target detection result of each image in the image set to be detected in sequence. The present application improves the efficiency of image target detection by automatically arranging the target detection results of the images output in sequence by sequentially detecting the image set to be detected and outputting the target detection results in sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the flow charts of the image target detection method provided by the present invention.

[0018] Figure 2 It is a schematic diagram of target detection results of the image target detection method provided by the present invention.

[0019] Figure 3 This is the second flow chart of the image target detection method provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the image target detection device provided by the present invention.

[0021] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Combine the following Figure 1-Figure 5 The present invention describes the image object detection method, apparatus, device, medium and computer program product.

[0024] Figure 1 It is one of the flow charts of the image target detection method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100, uniformly process the image formats of the target image set to obtain an image set to be detected; Specifically, the image target detection method provided by the present invention includes the following main steps.

[0025] Step 1. Since the image formats of the detection results of different image target detection algorithms are inconsistent, for example, the image format of the target detection results of some image target detection algorithms is png format; the image format of the target detection results of some image target detection algorithms is jpg format. Before performing target detection (character recognition) on the image, the image target detection method provided by the present invention performs unified processing on the formats of the images in the target image set. The unified processing process does not change the original image order in the target image set. After the image format is unified, the image identifiers (including the sequence number) in the target image set are renamed in order to obtain an image set that can be used for target detection, that is, the image set to be detected in this embodiment.

[0026] Step 200: determining a target to be detected based on the set of images to be detected; Specifically, before detecting the image in the image set to be detected, it is necessary to determine the target to be detected, that is, the characters that may be contained in the image. In actual image detection applications, the image to be detected often carries some interfering characters (such as watermarks in the image). In order to detect only specific characters without being affected by interfering characters, it is necessary to first determine the target to be detected (the target to be detected can be determined and set in the configured json file). The determination of the target to be detected in this embodiment can be based on the user's input, or it can be based on the automatic generation and input of the image target detection method of this application.

[0027] Step 300, performing traversal detection on each image in the image set to be detected based on the target to be detected in accordance with the image sequence of the image set to be detected, to obtain an image detection result; Step 400: Outputting the target detection result of each image in the to-be-detected image set based on the image detection result in accordance with the image sequence of the to-be-detected image set.

[0028] Specifically, after determining the target to be detected, traverse and detect each image in the image set to be detected according to the image order in the image set to be detected, and obtain the image detection results of the entire image set to be detected. According to the image order in the image set to be detected, the image detection results of the entire image set to be detected are sorted to obtain the target detection results of each image in the image set to be detected. Figure 2 As shown, the target detection results include the detection time of each image, the detection result (INFO means the target is detected; ERROR means the target is not detected), the image sequence number, the number of detected targets, and the detected targets, such as the characters "rock" and "person".

[0029] The following specific embodiment is used to describe in order the main steps of the image object detection method provided by the present application.

[0030] The image set to be detected includes 500 images, which are numbered in sequence from 001 to 500, and the unified format of the images is png format. The program that performs image target detection has been verified. In actual detection applications, the image to be detected often has some interfering characters. In order to avoid the influence of interfering characters when detecting specific characters, it is necessary to set the target characters to be detected in the configured json file in advance before the optical character recognition (OCR) detection. The various parameters of the configuration include the targets to be detected (the characters "rock" and "person"). The program that performs image target detection can complete target detection for more images by switching accounts. The image target detection results sorted in sequence are as follows. Figure 2 shown.

[0031] The image target detection method provided by the present embodiment performs unified processing on the image format in the image set before detecting the target in the image to obtain the image set to be detected, and then determines the target to be detected based on the image set to be detected; performs traversal detection on each image in the image set to be detected based on the target to be detected according to the order of the images in the image set to be detected to obtain the image detection result of the image set to be detected; finally, processes the image detection result according to the order of the images in the image set to be detected, and outputs the target detection result of each image in the image set to be detected in sequence. The present application improves the efficiency of image target detection by automatically arranging the target detection results of the images output in sequence by performing sequential detection on the image set to be detected and outputting the target detection results in sequence.

[0032] In one embodiment, the image object detection method provided in the embodiment of the present application may further include: Step 110, determining the image format of each image in the target image set; Step 120: Unify the formats of the target images in the target image set to obtain a set of images to be detected; the formats of the target images are the formats to be unified.

[0033] Specifically, according to the above content, it can be known that the premise of unifying the formats of the images in the target image set is that the formats of the images in the target image set are diverse, that is, there are at least two image formats in the target image set. Therefore, before the format is unified, the image format of each image in the target image set is first determined, and then the image format that needs to be unified is determined. The format to be unified in this embodiment is a format other than the image format that needs to be unified. For example, the image format that needs to be unified is png format, and the consideration is: png format is a bitmap format that uses a lossless compression algorithm, and supports index, grayscale, RGB three-color scheme and Alpha channel (alpha channel) and other features. It can be understood that the image format that needs to be unified in this embodiment can be determined based on different considerations.

[0034] After determining the image format to be unified, the target images in the target image set whose format is to be unified are processed in a unified manner, that is, the format of the target image is changed to the image format to be unified, so as to obtain the image set to be detected.

[0035] This embodiment adapts to various image object detection algorithms by unifying the image format, thereby improving the adaptability of image object detection.

[0036] In one embodiment, the image object detection method provided in the embodiment of the present application may further include: Step 210: when receiving an image target input by a user, taking the image target as a target to be detected; Step 220: in the case where no image target input by the user is received, determining the target type contained in each image of the to-be-detected image set and the initial detection result of each target type; Step 230: receiving an initial detection target input by a user based on the target type and the initial detection result, and using the initial detection target as a target to be detected; Step 240, alternatively, when an image target input by a user is received and the image target does not belong to the initial detection result of the image set to be detected, an initial detection target input by the user based on the target type and the initial detection result is received, and the initial detection target is used as the target to be detected.

[0037] Specifically, in order to ensure that the image target can be detected (if the target cannot be detected in the image set to be detected, the practical application of this application is of little significance), this application provides multiple methods for determining the target to be detected. One is user input. If the user knows the image set to be detected, the target that the image in the image set to be detected will contain can be input, that is, the image target in this embodiment, and the image target input by the user is used as the target to be detected.

[0038] Second, when no image target is received from the user (including when the user input is empty), it means that the user does not know which targets are contained in the images in the image set to be detected. In this case, preliminary target detection is performed on the images in the image set to be detected, and the target type contained in each image in the image set to be detected and the detection target under each target type are output for the user to select. When the initial detection target input by the user based on the target type and the initial detection result is received, the initial detection target input by the user is used as the target to be detected.

[0039] Third, when the user inputs an image target, but the image in the image set to be detected does not detect the image target, the target type contained in each image in the image set to be detected and the detection target under each target type are output for the user to select according to the above method. When the initial detection target input by the user based on the target type and the initial detection result is received, the initial detection target input by the user is used as the target to be detected.

[0040] This embodiment improves the accuracy of determining the target to be detected through the above-mentioned multiple methods for determining the target to be detected.

[0041] In one embodiment, the image object detection method provided in the embodiment of the present application may further include: Step 10: performing traversal detection on each image in the image set to be detected based on the target to be detected according to the image sequence of the image set to be detected, and obtaining an image detection result of each image in the image set to be detected; the image detection result includes the number of the targets to be detected and the image position of the targets to be detected; Step 20: upon receiving a query request input by a user based on a target image in the set of images to be detected, and the target image contains the target to be detected, outputting quantity information and position identifiers of the target to be detected in the target image.

[0042] Specifically, Figure 2 As shown, the image detection result of each image in the image set to be detected includes the detection time, the detection result, the image sequence number, the number of detected targets and the detected targets. In addition to the first time, this embodiment also provides a detection target query method, which receives a query request input by a user based on the target image of the image set to be detected, for example, to query an image with a certain sequence number, and in the case that the queried target image does not contain the target to be detected, the target image can be directly output for the user to check; in the case that the queried target image contains the target to be detected, while outputting the target image, a position identifier of the target to be detected, such as a rectangular detection frame, is displayed in the target image.

[0043] It is understandable that the output target image can be combined with the accuracy of target detection, that is, the user can provide feedback on the accuracy of target detection of the image to improve the accuracy of target detection of the image.

[0044] This embodiment can improve the accuracy of image object detection by querying image object detection and combining it with accuracy feedback of object detection.

[0045] In one embodiment, the image object detection method provided in the embodiment of the present application may further include: Step 410: Determine the sequence identifier and detection time of each image in the set of images to be detected; Step 420: output the target detection result of each image in the set of images to be detected based on the image detection result; the target detection result includes the sequence identifier, the detection time, the detection identifier and the detection number of the targets to be detected.

[0046] Specifically, the above content has described the target detection results of each image in the image set to be detected, mainly including information such as the sequence identifier, detection time, detection identifier, and the number of detections of the target to be detected. This embodiment expands it. When there are many targets to be detected or the character length is long, it can be replaced with abbreviated characters, and other target detection results can also be replaced. In the case of limited output content, as many detection results as possible are displayed. When the user queries the detection results, more detection results can be further output.

[0047] This embodiment simplifies the target detection results by replacing characters in the detection results, and displays as many detection results as possible when the output content is limited.

[0048] Figure 3 This is the second flow chart of the image target detection method provided by the present invention, such as Figure 3 As shown, the method may also include: Step 500: upon receiving a save instruction input by a user based on the target detection result, save the target detection result of each image in the set of images to be detected; Step 600: upon receiving an update instruction input by a user based on the target detection result, determining a first detection target corresponding to the update instruction; Step 700: When the first detection target and the target to be detected are different, update the target detection result of each image in the set of images to be detected based on the first detection target in accordance with the image sequence of the set of images to be detected.

[0049] Specifically, the image target detection method provided by the present application also supports automatic saving of target detection results and manual saving by the user. In addition to saving target detection results, the image target detection method provided by the present application also supports updating of target detection results, that is, the user inputs a new detection target, that is, the first detection target in this embodiment, and when the first detection target and the target to be detected are different, target detection is performed on the image set to be detected in sequence according to the above-mentioned target detection method, and then the previous target detection result is updated.

[0050] This embodiment improves the flexibility of image target detection by saving or updating the target detection result.

[0051] The image object detection device provided by the present invention is described below. The image object detection device described below and the image object detection method described above can be referred to each other.

[0052] Please refer to Figure 4 The present invention also provides an image target detection device, comprising: An image format unification module 401 is used to unify the image formats of the target image set to obtain an image set to be detected; A to-be-detected target determination module 402, configured to determine the to-be-detected target based on the to-be-detected image set; An image traversal detection module 403 is used to perform traversal detection on each image in the image set to be detected based on the target to be detected according to the image sequence of the image set to be detected, so as to obtain an image detection result; The image object detection output module 404 is used to output the object detection result of each image in the image set to be detected based on the image detection result according to the image sequence of the image set to be detected.

[0053] Optionally, the image format unification module includes: an image format determination unit, used for determining an image format of each image in a target image set; The image format unification processing unit is used to unify the formats of the target images in the target image set to obtain the image set to be detected; the format of the target image is the format to be unified.

[0054] Optionally, the to-be-detected target determination module includes: A first to-be-detected target determining unit, configured to, upon receiving an image target input by a user, use the image target as a to-be-detected target; an initial detection result determination unit, configured to determine the target type contained in each image of the to-be-detected image set and the initial detection result of each target type without receiving an image target input by a user; A second to-be-detected target determining unit, configured to receive an initial detection target input by a user based on the target type and the initial detection result, and use the initial detection target as the to-be-detected target; The third unit for determining the target to be detected is used to receive an initial detection target input by the user based on the target type and the initial detection result, and take the initial detection target as the target to be detected when an image target input by the user does not belong to the initial detection result of the image set to be detected.

[0055] Optionally, the image object detection device further includes: An image traversal detection module, configured to perform traversal detection on each image in the image set to be detected based on the target to be detected in accordance with the image sequence of the image set to be detected, and obtain an image detection result for each image in the image set to be detected; the image detection result includes the number of the targets to be detected and the image position of the targets to be detected; The target detection information output module is used to output the quantity information and position identification of the target to be detected in the target image when receiving a query request input by a user based on the target image of the set of images to be detected and the target image contains the target to be detected.

[0056] Optionally, the image object detection output module includes: A target detection information determination unit, used to determine the sequence identifier and detection time of each image in the set of images to be detected; The target detection information output unit is used to output the target detection result of each image in the set of images to be detected based on the image detection result; the target detection result includes the sequence identifier, the detection time, the detection identifier and the detection number of the targets to be detected.

[0057] Optionally, the image object detection device further includes: The target detection result saving module is used to save the target detection result of each image in the set of images to be detected when receiving a saving instruction input by the user based on the target detection result; A first detection target determination module, configured to, upon receiving an update instruction input by a user based on the target detection result, determine a first detection target corresponding to the update instruction; The target detection result updating module is used to update the target detection result of each image in the set of images to be detected based on the first detection target in accordance with the image order of the set of images to be detected when the first detection target and the set of images to be detected are different.

[0058] Figure 5An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the image target detection method, which includes: uniformly processing the image format of the target image set to obtain the image set to be detected; determining the target to be detected based on the image set to be detected; traversing and detecting each image of the image set to be detected based on the target to be detected according to the image sequence of the image set to be detected to obtain the image detection result; outputting the target detection result of each image of the image set to be detected based on the image detection result according to the image sequence of the image set to be detected.

[0059] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0060] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the image target detection method provided by the above-mentioned methods, which includes: uniformly processing the image format of the target image set to obtain a set of images to be detected; determining the target to be detected based on the set of images to be detected; traversing and detecting each image in the set of images to be detected based on the target to be detected according to the image order of the set of images to be detected to obtain an image detection result; and outputting the target detection result of each image in the set of images to be detected based on the image detection result according to the image order of the set of images to be detected.

[0061] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the image target detection method provided by the above-mentioned methods, the method comprising: uniformly processing the image format of the target image set to obtain a set of images to be detected; determining the target to be detected based on the set of images to be detected; traversing and detecting each image in the set of images to be detected based on the target to be detected in accordance with the image sequence of the set of images to be detected to obtain an image detection result; and outputting the target detection result for each image in the set of images to be detected based on the image detection result in accordance with the image sequence of the set of images to be detected.

[0062] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0063] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting an image target, characterized in that: include: The image formats of the target image set are uniformly processed to obtain the image set to be detected; Determine a target to be detected based on the set of images to be detected; According to the image sequence of the image set to be detected, each image in the image set to be detected is traversed and detected based on the target to be detected to obtain an image detection result; According to the image sequence of the to-be-detected image set, the target detection result of each image in the to-be-detected image set is output based on the image detection result.

2. The image target detection method according to claim 1, characterized in that: The image formats of the target image set are uniformly processed to obtain the image set to be detected, including: determining an image format for each image of a target image set; The formats of the target images in the target image set are processed uniformly to obtain a set of images to be detected; the formats of the target images are the formats to be unified.

3. The image target detection method according to claim 1, characterized in that: Determining the target to be detected based on the set of images to be detected comprises: When receiving an image target input by a user, taking the image target as a target to be detected; In the case where no image target input by the user is received, determining the target type contained in each image of the to-be-detected image set and the initial detection result of each target type; receiving an initial detection target input by a user based on the target type and the initial detection result, and using the initial detection target as a target to be detected; Alternatively, when an image target input by a user is received and the image target does not belong to the initial detection result of the image set to be detected, an initial detection target input by the user based on the target type and the initial detection result is received, and the initial detection target is used as the target to be detected.

4. The image target detection method according to claim 1, characterized in that: The image target detection method further includes: According to the image sequence of the image set to be detected, each image in the image set to be detected is traversed and detected based on the target to be detected, so as to obtain an image detection result of each image in the image set to be detected; the image detection result includes the number of the targets to be detected and the image position of the targets to be detected; When receiving a query request input by a user based on a target image in the set of images to be detected, and the target image contains the target to be detected, the quantity information and position identifier of the target to be detected in the target image are output.

5. The image target detection method according to claim 1, characterized in that: Outputting the target detection result of each image in the set of images to be detected based on the image detection result according to the image sequence of the set of images to be detected comprises: Determining a sequence identifier and a detection time for each image in the set of images to be detected; The target detection result of each image in the set of images to be detected is output based on the image detection result; the target detection result includes the sequence identifier, the detection time, the detection identifier and the detection number of the targets to be detected.

6. The image target detection method according to claim 1, characterized in that: Outputting the target detection result of each image in the to-be-detected image set based on the image detection result according to the image sequence of the to-be-detected image set, and then comprising: Upon receiving a save instruction input by a user based on the target detection result, saving the target detection result of each image in the set of images to be detected; Upon receiving an update instruction input by a user based on the target detection result, determining a first detection target corresponding to the update instruction; In the case that the first detection target and the target to be detected are different, the target detection result of each image in the set of images to be detected is updated based on the first detection target according to the image sequence of the set of images to be detected.

7. An image target detection device, characterized in that: include: An image format unification module is used to unify the image formats of the target image set to obtain an image set to be detected; A to-be-detected target determination module, used to determine the to-be-detected target based on the to-be-detected image set; An image traversal detection module is used to perform traversal detection on each image in the image set to be detected based on the target to be detected in accordance with the image sequence of the image set to be detected, so as to obtain an image detection result; The image object detection output module is used to output the object detection result of each image in the image set to be detected based on the image detection result according to the image sequence of the image set to be detected.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the image object detection method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the image object detection method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the image object detection method according to any one of claims 1 to 6 is implemented.

Images