CN114495154A - Human body detection method, device and apparatus in panorama and storage medium - Google Patents
Human body detection method, device and apparatus in panorama and storage medium Download PDFInfo
- Publication number
- CN114495154A CN114495154A CN202111659069.1A CN202111659069A CN114495154A CN 114495154 A CN114495154 A CN 114495154A CN 202111659069 A CN202111659069 A CN 202111659069A CN 114495154 A CN114495154 A CN 114495154A
- Authority
- CN
- China
- Prior art keywords
- human body
- door opening
- panoramic image
- screenshot
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Closed-Circuit Television Systems (AREA)
Abstract
The embodiment of the application provides a method, equipment and a device for detecting a human body in a panoramic image and a storage medium. In the embodiment of the application, the door opening area contained in the target panoramic image can be detected in response to the detection instruction; intercepting a door opening area from the target panoramic image to generate a door opening screenshot; and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image. Therefore, the pedestrians which are more obvious in the target panoramic image can be detected by carrying out human body detection operation on the target panoramic image, and the door opening screenshot can be obtained by detecting the door opening area contained in the target panoramic image and executing human body detection operation on the door opening screenshot, so that the pedestrians positioned in the door opening area can be accurately detected. Therefore, in the embodiment of the application, the pedestrians in the panoramic image can be detected more comprehensively and accurately, and especially the pedestrians with low resolution or fuzziness in the missed panoramic image can be avoided.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting a human body in a panorama.
Background
In the process of shooting the indoor space by adopting the panoramic camera, people in the indoor space can be shot possibly, pedestrians appear in a panoramic image of the indoor space, and the panoramic representation of the indoor space is influenced.
At present, pedestrians in the panoramic image are usually found manually through a preview mode, but the processing efficiency of the mode is low, and a large amount of manpower and material resources are consumed.
Disclosure of Invention
Aspects of the present disclosure provide a method, device, and apparatus for detecting a human body in a panorama, and a storage medium, so as to more accurately detect a pedestrian in the panorama.
The embodiment of the application provides a human body detection method in a panoramic image, which comprises the following steps:
responding to a detection instruction, and detecting a door opening area contained in the target panoramic image;
intercepting a door opening area from the target panoramic image to generate a door opening screenshot;
and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image.
The embodiment of the present application further provides a human body detection device in a panorama, including:
the first detection module is used for responding to a detection instruction and detecting a door opening area contained in the target panoramic image;
the screenshot module is used for intercepting a door opening area from the target panoramic image so as to generate a door opening screenshot;
and the second detection module is used for respectively executing human body detection operation on the target panoramic image and the door opening screenshot so as to determine a human body area contained in the target panoramic image.
The embodiment of the application also provides a computing device, which comprises a memory and a processor;
the memory is to store one or more computer instructions;
the processor is coupled with the memory for executing the one or more computer instructions for:
responding to a detection instruction, and detecting a door opening area contained in the target panoramic image;
intercepting a door opening area from the target panoramic image to generate a door opening screenshot;
and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image.
Embodiments of the present application also provide a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the aforementioned human body detection method in a panoramic image.
In the embodiment of the application, the door opening area contained in the target panoramic image can be detected in response to the detection instruction; intercepting a door opening area from the target panoramic image to generate a door opening screenshot; and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image. Therefore, the pedestrians which are more obvious in the target panoramic image can be detected by carrying out human body detection operation on the target panoramic image, and the door opening screenshot can be obtained by detecting the door opening area contained in the target panoramic image and executing human body detection operation on the door opening screenshot, so that the pedestrians positioned in the door opening area can be accurately detected. Therefore, in the embodiment of the application, the pedestrians in the panoramic image can be detected more comprehensively and accurately, and especially the pedestrians with low resolution or fuzziness in the missed panoramic image can be avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flowchart of a human body detection method in a panoramic view according to an exemplary embodiment of the present application;
FIG. 2 is a logic diagram of a human body detection method in a panoramic view according to an exemplary embodiment of the present application;
fig. 3a and 3b are schematic diagrams of an application scenario provided in an exemplary embodiment of the present application;
FIG. 4 is a schematic structural diagram of a human body detecting device in a panoramic view according to another exemplary embodiment of the present application;
fig. 5 is a schematic structural diagram of a computing device according to another exemplary embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
At present, pedestrians in the panoramic image are usually found manually through a preview mode, but the processing efficiency of the mode is low, and a large amount of manpower and material resources are consumed. To this end, in some embodiments of the present application: the door opening area contained in the target panoramic image can be detected in response to a detection instruction; intercepting a door opening area from the target panoramic image to generate a door opening screenshot; and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image. Therefore, the pedestrians which are more obvious in the target panoramic image can be detected by carrying out human body detection operation on the target panoramic image, and the door opening screenshot can be obtained by detecting the door opening area contained in the target panoramic image and executing human body detection operation on the door opening screenshot, so that the pedestrians positioned in the door opening area can be accurately detected. Therefore, in the embodiment of the application, the pedestrians in the panoramic image can be detected more comprehensively and accurately, and especially the low-resolution or fuzzy pedestrians in the panoramic image can be prevented from being missed.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a human body detection method in a panorama according to an exemplary embodiment of the present application, where the method may be performed by a human body detection apparatus, which may be implemented as a combination of software and/or hardware, and the structure of the human body detection apparatus will be described in detail later, and the human body detection apparatus may be integrated in a computing device. Referring to fig. 1, the method includes:
and 102, respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image.
The technical scheme provided by the embodiment can be applied to various application scenes needing human body detection in the panoramic image, such as VR house watching and other application scenes. In this embodiment, the panorama may be an image for showing a panorama of the target space, and the implementation form of the panorama may be an equidistant columnar projection map or the like. In practical application, a panoramic image may be obtained by performing panoramic shooting on a target space through shooting equipment such as a fisheye camera, or a panoramic image may be obtained by stitching a plurality of local images corresponding to the target space. The target space shown by the panorama can be an indoor space, for example, an internal space of a room source in a VR watching scene.
The inventor finds that in the process of constructing the panoramic image, due to the fact that panoramic shooting needs to be carried out on the target space, the problem that pedestrians located in the target space are shot into the panoramic image often occurs, and the rendering effect of the panoramic image is affected. Therefore, the embodiment provides an efficient and accurate human body detection scheme to detect whether the panorama includes a pedestrian.
In this embodiment, a user operation interface may be provided through the electronic terminal, and a user may input the target panorama to be detected through the user operation interface and perform a detection triggering operation (for example, click a "detection" control, etc.) to initiate a detection instruction. In the latter case, the electronic terminal may provide the target panorama and the detection instruction to the server to trigger the server to execute the human body detection scheme of this embodiment, and the execution main body of the human body detection scheme is not limited in this embodiment. Based on this, referring to fig. 1, in step 100, a door opening area included in the target panorama may be detected in response to a detection instruction. It should be noted that the door opening area in this embodiment refers to an opening area through which pedestrians can pass in the panoramic image, and the door opening area may include, but is not limited to, a door opening area, a window area, a communication area between two different spaces, and the like.
In an embodiment, the door opening area included in the target panorama can be detected in any available manner, which is not limited to this embodiment. For example, the objects such as a door body, a window body and the like included in the object panorama can be detected through an object detection algorithm, and then the area occupied by each object such as the door body, the window body and the like is taken as a door opening area.
Fig. 2 is a logic diagram of a human body detection method in a panoramic image according to an exemplary embodiment of the present application. Referring to fig. 2, in the present embodiment, a door opening detection model may be provided for detecting a door opening region included in the target panorama. Therefore, in this embodiment, a door opening detection model may be constructed in advance, and the door opening detection model may adopt detection models such as R-CNN, YOLO, SSD, and the like. An exemplary door opening detection model training process may be: acquiring a sample graph containing a door opening area; marking a door opening area in the sample graph; and providing the marked sample picture for a door opening detection model so as to train the door opening detection model. Based on this, the input of the door opening detection model may be any picture, and the output of the door opening detection model may be the door opening area contained in the picture, for example, the door opening area in the picture may be shown in the form of a labeled box.
Based on this, in the embodiment, the target panorama can be input into the door opening detection model; and detecting a door opening area in the target panoramic image by using a door opening detection model. In this way, by performing door opening detection on the target panorama, information such as the position and number of door opening areas included in the target panorama can be determined.
Referring to fig. 1, in step 101, a door opening area may be cut out from a target panorama to generate a door opening screenshot. As mentioned above, through the aforementioned door opening detection process, the information such as the position and number of the door opening areas included in the target panorama is known, so that the door opening screenshot can be accurately captured from the target panorama in step 101 according to the information. Here, the number of door opening screenshots taken from the target panorama may be one or more. The screenshot of the door opening is used as one of the bases for human body detection.
With continued reference to fig. 1, in step 102, a human body detection operation may be performed on the target panorama and the door opening screenshot, respectively, to determine a human body region contained in the target panorama. Here, by performing a human detection operation on the target panorama, more prominent pedestrians included in the target panorama can be detected, including but not limited to pedestrians that are not occluded and/or have higher resolution. The human body detection operation is executed on the door opening screenshot, so that the pedestrians in the door opening area can be detected, and the pedestrians in the door opening area can not be detected in the process of detecting the human body of the target panorama due to the fact that the pedestrians are blocked and/or the pedestrians are low in resolution and the like. Therefore, in this embodiment, on the basis of human body detection performed on the target panoramic image, the human body detection operation is performed on the door opening screenshot, so that the pedestrians hidden in the door opening area can be accurately detected, and the pedestrians in the target panoramic image can be detected more comprehensively and accurately.
Referring to fig. 2, in the present embodiment, a human body detection model may be provided for performing a human body detection operation. For this reason, in this embodiment, a human body detection model may be constructed in advance, and the human body detection model may adopt detection models such as R-CNN, YOLO, SSD, etc., but this embodiment is not limited thereto, and the human body detection model may also adopt other detection models capable of realizing the target detection function. An exemplary human detection model training process may be: acquiring a sample map containing pedestrians; marking a pedestrian area in the sample graph; and providing the labeled sample graph for a human body detection model so as to train the human body detection model. Based on this, the input of the human body detection model may be any picture, and the output of the human body detection model may be a human body region included in the picture, for example, the human body region in the picture may be shown in the form of a labeled box.
Based on this, in the embodiment, the target panorama and the door opening screenshot can be respectively input into the human body detection model; and respectively carrying out human body detection on the target panoramic image and the door opening screenshot by using a human body detection model so as to determine a human body area contained in the target panoramic image. The human body detection model can carry out human body detection on the target panoramic image and output a human body area detected from the target panoramic image; the human body detection model can also carry out human body detection on the door opening screenshot and output a human body area detected from the door opening screenshot; in this embodiment, both the human body region detected from the target panorama and the human body region detected from the door opening screenshot may be determined as the human body region included in the target panorama.
In consideration of the fact that the resolution of pedestrians in the door opening area is low, in the embodiment, the door opening screenshot can be amplified, and the amplified door opening screenshot is input into the human body detection model. The human body detection model can perform human body detection on the amplified door opening screenshot, so that the human body area contained in the door opening screenshot can be detected more accurately.
Referring to fig. 2, in this embodiment, the output result of the human body detection model may also be screened to correct the output result. In this embodiment, it can be determined whether a human body region output by the human body detection model performing human body detection on the target panoramic image meets a preset region shape condition or not according to an input result obtained after the human body detection on the target panoramic image by the human body detection model; and deleting the human body area which does not meet the area form condition. Wherein, the region morphology condition may include but is not limited to:
the overlapping degree between the human body area and a designated object area existing in the target panoramic image is lower than a preset overlapping degree threshold value, and the designated object is an object possibly bearing a human body picture;
the width-height ratio of the human body region conforms to the human body ratio range; and/or the presence of a gas in the gas,
the occupied area of the human body area in the target panoramic image accords with a preset area range.
The overlap between the human body area and the designated object area can be calculated according to the positions of the human body area and the designated object area in the target panoramic image, for example, if the positions of the human body area and the designated object area in the target panoramic image are 60% overlapped, the overlap between the human body area and the designated object area can be output to be 0.6. The preset overlap threshold in this embodiment may be set according to actual needs, for example, may be set to 0.5, so that, when the overlap between the human body region and the designated object region is lower than 0.5, it may be characterized that the human body region is not carried in the designated object region and corresponds to a real pedestrian; and when the overlapping degree between the human body area and the designated object area is higher than 0.5, the human body area can be represented to be borne in the designated object area and not be a real pedestrian. The screening dimension is mainly used for eliminating human body regions in object regions such as televisions, wall paintings and the like so as to optimize output results.
The human body proportion range can be set by referring to the common sense of life, and the specific example is not taken here. If the width-to-height ratio of the human body region does not conform to the human body ratio range, the characteristic human body region may be misrecognized and not a real pedestrian, and thus the human body region can be deleted. The screening dimension is mainly used for eliminating human body regions which identify non-pedestrians as pedestrians mistakenly so as to optimize output results.
As mentioned above, the output result of the human body detection may provide position information of the human body region in the target panorama, and based on this, the occupied area of the human body region in the target panorama may be calculated, for example, the occupied area may be represented by the number of pixels occupied by the human body region in the target panorama. If the occupied area of the human body area in the target panoramic image is too large or too small, the characteristic human body area is possibly identified by mistake and is not a real pedestrian, so that the human body area can be deleted. The screening dimension is also mainly used for eliminating human body regions which wrongly identify non-pedestrians as pedestrians so as to optimize output results.
On the basis, the human body area remained after the human body area detected from the target panoramic image is screened and the human body area detected from the door opening screenshot can be determined as the human body area contained in the target panoramic image.
Accordingly, in the present embodiment, the door opening area included in the target panorama can be detected in response to the detection instruction; intercepting a door opening area from the target panoramic image to generate a door opening screenshot; and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image. Therefore, the pedestrians which are more obvious in the target panoramic image can be detected by carrying out human body detection operation on the target panoramic image, and the door opening screenshot can be obtained by detecting the door opening area contained in the target panoramic image and executing human body detection operation on the door opening screenshot, so that the pedestrians positioned in the door opening area can be accurately detected. Therefore, in the embodiment, the pedestrians in the panoramic image can be detected more comprehensively and accurately, and especially, the pedestrians with low resolution or fuzziness in the panoramic image can be prevented from being missed.
Fig. 3a and 3b are schematic diagrams of an application scenario provided in an exemplary embodiment of the present application. Referring to fig. 3a, the panoramic view is used to show the interior space of the house source. According to the human body detection method provided by the embodiment:
1. the panorama can be input into a door opening detection model, so that a door opening area contained in the panorama can be detected by using the door opening detection model, and referring to fig. 3a, two door opening areas, namely a door opening position and a window position, are detected in the panorama, such as dashed frame areas a and B in fig. 3.
2. From this panorama, two door opening screenshots are taken, with reference to fig. 3b, from the panorama of fig. 3 a.
3. And respectively inputting the panoramic picture and the door opening screenshot into a human body detection model, so that human body detection can be carried out on the panoramic picture by using the door opening detection model, and human body detection can be carried out on the door opening screenshot. Referring to fig. 3a, the human body regions C, D and E can be detected through a human body detection operation on the panorama. Referring to fig. 3b, human body regions F and G can be detected by performing a human body detection operation on the door opening screenshot.
4. And screening the human body areas C, D and E detected from the panoramic image according to a preset area form condition, wherein the human body areas D and E are respectively overlapped with the picture frame area and the television area to represent that the human body areas D and E are not real pedestrians, so that the human body areas D and E are removed, and the human body area C is reserved. Finally, C, F and G can be determined as the body regions contained in the panorama.
Therefore, the human body detection scheme provided by the embodiment can comprehensively and accurately detect the pedestrians contained in the panoramic image.
It should be noted that in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 100, 101, etc., are merely used for distinguishing different operations, and the sequence numbers do not represent any execution order per se. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel.
Fig. 4 is a schematic structural diagram of a human body detection apparatus in a panoramic view according to another exemplary embodiment of the present application. Referring to fig. 4, the human body detecting device may include:
the first detection module 40 is used for responding to a detection instruction and detecting a door opening area contained in the target panoramic image;
a screenshot module 41, configured to capture a door opening area from the target panorama to generate a door opening screenshot;
and the second detection module 42 is configured to perform human body detection operations on the target panoramic image and the door opening screenshot respectively to determine a human body area included in the target panoramic image.
In an alternative embodiment, the first detection module 40, in detecting the door opening area included in the target panorama, may be configured to:
inputting the target panorama into a door opening detection model;
and detecting a door opening area in the target panoramic image by using a door opening detection model.
In an alternative embodiment, the first detecting module 40 can be used to:
acquiring a sample graph containing a door opening area;
marking a door opening area in the sample graph;
and providing the marked sample picture for a door opening detection model so as to train the door opening detection model.
In an optional embodiment, the second detection module 42, in the process of performing the human body detection operation on the target panorama and the door opening screenshot respectively to determine the human body area contained in the target panorama, may be configured to:
respectively inputting the target panorama and the door opening screenshot into a human body detection model;
and respectively carrying out human body detection on the target panoramic image and the door opening screenshot by using a human body detection model so as to determine a human body area contained in the target panoramic image.
In an alternative embodiment, the second detection module 42, during the process of inputting the door opening screenshot into the human body detection model, can be used to:
carrying out amplification operation on the door opening screenshot;
and inputting the amplified screenshot of the door opening into a human body detection model.
In an alternative embodiment, the second detection module 42 may be further configured to:
judging whether a human body region output by the human body detection model for human body detection of the target panoramic image meets a preset region form condition or not;
and deleting the human body area which does not meet the area form condition.
In an alternative embodiment, the region morphology conditions include:
the overlapping degree between the human body area and a designated object area existing in the target panoramic image is lower than a preset overlapping degree threshold value, and the designated object is an object possibly bearing a human body picture;
the width-height ratio of the human body region conforms to the human body ratio range; and/or the presence of a gas in the gas,
the occupied area of the human body area in the target panoramic image accords with a preset area range.
It should be noted that, for the technical details in the embodiments of the human body detecting apparatus in the panoramic view, reference may be made to the related description in the foregoing method embodiments, and for the sake of brevity, detailed description is not repeated herein, but this should not cause a loss of the scope of the present application.
Fig. 5 is a schematic structural diagram of a computing device according to another exemplary embodiment of the present application. As shown in fig. 5, the computing device includes: a memory 50 and a processor 51.
A processor 51, coupled to the memory 50, for executing the computer program in the memory 50 for:
responding to a detection instruction, and detecting a door opening area contained in the target panoramic image;
intercepting a door opening area from the target panoramic image to generate a door opening screenshot;
and respectively executing human body detection operation on the target panoramic image and the door opening screenshot so as to determine a human body area contained in the target panoramic image.
In an alternative embodiment, the processor 51, in detecting the door opening area contained in the target panorama, may be configured to:
inputting the target panorama into a door opening detection model;
and detecting a door opening area in the target panoramic image by using a door opening detection model.
In an alternative embodiment, the processor 51, in the process of training the door opening detection model, may be configured to:
acquiring a sample graph containing a door opening area;
marking a door opening area in the sample graph;
and providing the marked sample picture for a door opening detection model so as to train the door opening detection model.
In an alternative embodiment, the processor 51, in performing the human body detection operation on the target panorama and the door opening screenshot respectively to determine the human body region contained in the target panorama, may be configured to:
respectively inputting the target panoramic picture and the door opening screenshot into a human body detection model;
and respectively carrying out human body detection on the target panoramic image and the door opening screenshot by using a human body detection model so as to determine a human body area contained in the target panoramic image.
In an alternative embodiment, the processor 51, in entering the door opening screenshot into the human detection model, may be configured to:
carrying out amplification operation on the door opening screenshot;
and inputting the amplified screenshot of the door opening into a human body detection model.
In an alternative embodiment, the processor 51 is further operable to:
judging whether a human body region output by the human body detection model for human body detection of the target panoramic image meets a preset region form condition or not;
and deleting the human body area which does not meet the area form condition.
In an alternative embodiment, the region morphology conditions include:
the overlapping degree between the human body area and a designated object area existing in the target panoramic image is lower than a preset overlapping degree threshold value, and the designated object is an object possibly bearing a human body picture;
the width-height ratio of the human body region conforms to the human body ratio range; and/or the presence of a gas in the gas,
the occupied area of the human body area in the target panoramic image accords with a preset area range.
Further, as shown in fig. 5, the computing device further includes: communication components 52, power components 53, and the like. Only some of the components are schematically shown in fig. 5, and the computing device is not meant to include only the components shown in fig. 5.
It should be noted that, for the technical details in the embodiments of the computing device, reference may be made to the related description in the foregoing method embodiments, and for the sake of brevity, detailed description is not provided herein, but this should not cause a loss of scope of the present application.
Accordingly, the present application further provides a computer-readable storage medium storing a computer program, where the computer program can implement the steps that can be executed by a computing device in the foregoing method embodiments when executed.
The memory of FIG. 5, described above, is used to store a computer program and may be configured to store other various data to support operations on a computing platform. Examples of such data include instructions for any application or method operating on the computing platform, contact data, phonebook data, messages, pictures, videos, and so forth. The memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The communication component in fig. 5 is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as a WiFi, a 2G, 3G, 4G/LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
The power supply assembly of fig. 5 described above provides power to the various components of the device in which the power supply assembly is located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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 data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data 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 data 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 data 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A human body detection method in a panoramic image is characterized by comprising the following steps:
responding to a detection instruction, and detecting a door opening area contained in the target panoramic image;
intercepting a door opening area from the target panoramic image to generate a door opening screenshot;
and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image.
2. The method of claim 1, wherein the detecting the door opening area contained in the target panorama comprises:
inputting the target panorama into a door opening detection model;
and detecting a door opening area in the target panoramic image by using the door opening detection model.
3. The method of claim 2, wherein the training process of the door opening detection model comprises:
acquiring a sample graph containing a door opening area;
marking a door opening area in the sample graph;
and providing the marked sample picture for the door opening detection model so as to train the door opening detection model.
4. The method of claim 1, wherein the performing a human body detection operation on the target panorama and the door opening screenshot respectively to determine a human body region contained in the target panorama comprises:
respectively inputting the target panoramic picture and the door opening screenshot into a human body detection model;
and respectively carrying out human body detection on the target panoramic image and the door opening screenshot by using the human body detection model so as to determine a human body area contained in the target panoramic image.
5. The method of claim 4, wherein the inputting the door opening screenshot into a human body detection model comprises:
performing amplification operation on the door opening screenshot;
and inputting the amplified screenshot of the door opening into the human body detection model.
6. The method of claim 4, further comprising:
judging whether a human body region output by the human body detection model for performing human body detection on the target panoramic image meets a preset region form condition or not;
and deleting the human body area which does not meet the area form condition.
7. The method of claim 6, wherein the zonal morphological conditions comprise:
the overlapping degree between the human body area and a designated object area existing in the target panoramic image is lower than a preset overlapping degree threshold value, and the designated object is an object which is likely to bear a human body picture;
the width-height ratio of the human body region conforms to the human body ratio range; and/or the presence of a gas in the gas,
and the occupied area of the human body area in the target panoramic image accords with a preset area range.
8. A human body detecting apparatus in a panorama, comprising:
the first detection module is used for responding to a detection instruction and detecting a door opening area contained in the target panoramic image;
the screenshot module is used for intercepting a door opening area from the target panoramic image so as to generate a door opening screenshot;
and the second detection module is used for respectively executing human body detection operation on the target panoramic image and the door opening screenshot so as to determine a human body area contained in the target panoramic image.
9. A computing device comprising a memory and a processor;
the memory is to store one or more computer instructions;
the processor is coupled with the memory for executing the one or more computer instructions for:
responding to a detection instruction, and detecting a door opening area contained in the target panoramic image;
intercepting a door opening area from the target panoramic image to generate a door opening screenshot;
and respectively executing human body detection operation on the target panoramic image and the door opening screenshot to determine a human body area contained in the target panoramic image.
10. A computer-readable storage medium storing computer instructions, which when executed by one or more processors, cause the one or more processors to perform the method of human detection in a panorama of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659069.1A CN114495154A (en) | 2021-12-30 | 2021-12-30 | Human body detection method, device and apparatus in panorama and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659069.1A CN114495154A (en) | 2021-12-30 | 2021-12-30 | Human body detection method, device and apparatus in panorama and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114495154A true CN114495154A (en) | 2022-05-13 |
Family
ID=81507838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111659069.1A Pending CN114495154A (en) | 2021-12-30 | 2021-12-30 | Human body detection method, device and apparatus in panorama and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114495154A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001338283A (en) * | 2000-05-26 | 2001-12-07 | Noritz Corp | Detection area setting method for human body detector |
| CN108447105A (en) * | 2018-02-02 | 2018-08-24 | 微幻科技(北京)有限公司 | A kind of processing method and processing device of panoramic picture |
| CN111242076A (en) * | 2020-01-20 | 2020-06-05 | 江铃汽车股份有限公司 | Pedestrian detection method and system |
| CN112036257A (en) * | 2020-08-07 | 2020-12-04 | 华中师范大学 | Non-perception face image acquisition method and system |
| CN112329497A (en) * | 2019-07-18 | 2021-02-05 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
| US20210250498A1 (en) * | 2020-02-07 | 2021-08-12 | Samsung Electronics Co., Ltd. | Electronic device and method for displaying image in electronic device |
-
2021
- 2021-12-30 CN CN202111659069.1A patent/CN114495154A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001338283A (en) * | 2000-05-26 | 2001-12-07 | Noritz Corp | Detection area setting method for human body detector |
| CN108447105A (en) * | 2018-02-02 | 2018-08-24 | 微幻科技(北京)有限公司 | A kind of processing method and processing device of panoramic picture |
| CN112329497A (en) * | 2019-07-18 | 2021-02-05 | 杭州海康威视数字技术股份有限公司 | Target identification method, device and equipment |
| CN111242076A (en) * | 2020-01-20 | 2020-06-05 | 江铃汽车股份有限公司 | Pedestrian detection method and system |
| US20210250498A1 (en) * | 2020-02-07 | 2021-08-12 | Samsung Electronics Co., Ltd. | Electronic device and method for displaying image in electronic device |
| CN112036257A (en) * | 2020-08-07 | 2020-12-04 | 华中师范大学 | Non-perception face image acquisition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11195284B2 (en) | Target object tracking method and apparatus, and storage medium | |
| EP3457683B1 (en) | Dynamic generation of image of a scene based on removal of undesired object present in the scene | |
| WO2020042800A1 (en) | Auxiliary method for capturing damage assessment image of vehicle, device, and apparatus | |
| US8477228B2 (en) | Camera data management and user interface apparatuses, systems, and methods | |
| WO2018086527A1 (en) | Video processing method and device | |
| US20210383166A1 (en) | Method and apparatus for context-embedding and region-based object detection | |
| CN105763812A (en) | Intelligent photographing method and device | |
| CN103916589A (en) | Method for running camera and electronic device thereof | |
| CN112434809B (en) | Active learning-based model training method and device and server | |
| US20200296324A1 (en) | Video management system and video management method | |
| CN106131441A (en) | Photographic method and device, electronic equipment | |
| CN109413760A (en) | A kind of wireless connection method and equipment | |
| CN113052788A (en) | System, management apparatus, and computer-readable medium for abnormality detection | |
| CN113947103A (en) | High-altitude parabolic model updating method, high-altitude parabolic detection system and storage medium | |
| CN112969032A (en) | Illumination pattern recognition method and device, computer equipment and storage medium | |
| CN114495154A (en) | Human body detection method, device and apparatus in panorama and storage medium | |
| US11899916B2 (en) | User interface for modifying pictures | |
| CN106161743B (en) | Media resource processing method, device and terminal | |
| KR102321205B1 (en) | Apparatus for Providing AI Service and Driving Method Thereof | |
| CN114494486A (en) | Home map generation method, device and storage medium | |
| US10885343B1 (en) | Repairing missing frames in recorded video with machine learning | |
| CN113627388A (en) | Method and device for determining bare soil coverage condition | |
| CN110223320B (en) | Object detection tracking method and detection tracking device | |
| CN112580379A (en) | Data processing system and method, electronic device, and computer-readable storage medium | |
| KR102274913B1 (en) | Apparatus for Bounding Box Redundancy Removal and Driving Method Thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |