WO2022105622A1 - Procédé et appareil de segmentation d'image, support lisible et dispositif électronique - Google Patents

Procédé et appareil de segmentation d'image, support lisible et dispositif électronique Download PDF

Info

Publication number
WO2022105622A1
WO2022105622A1 PCT/CN2021/128958 CN2021128958W WO2022105622A1 WO 2022105622 A1 WO2022105622 A1 WO 2022105622A1 CN 2021128958 W CN2021128958 W CN 2021128958W WO 2022105622 A1 WO2022105622 A1 WO 2022105622A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
center point
feature information
segmented
pixel
Prior art date
Application number
PCT/CN2021/128958
Other languages
English (en)
Chinese (zh)
Inventor
喻冬东
王长虎
Original Assignee
北京有竹居网络技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京有竹居网络技术有限公司 filed Critical 北京有竹居网络技术有限公司
Publication of WO2022105622A1 publication Critical patent/WO2022105622A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds

Definitions

  • the present disclosure relates to the technical field of image processing, and in particular, to an image segmentation method, apparatus, readable medium, and electronic device.
  • Image segmentation has important applications in the field of image processing technology.
  • Image segmentation refers to the process of dividing an image into several regions with similar properties, that is, dividing the image into several disjoint regions.
  • image segmentation can segment the area where the foreground object is located from the background area.
  • the present disclosure provides an image segmentation method, the method comprising: acquiring predicted object center point feature information of each pixel of a plurality of pixels in an image to be segmented, where the predicted object center point feature information is used to represent The pixel point is the reliability of the center point of the object; according to the feature information of the predicted object center point of each pixel point, determine the center point position information of the object in the image to be segmented; The to-be-segmented image is subjected to image segmentation.
  • the present disclosure provides an image segmentation device, the device comprising: an acquisition module for acquiring predicted object center point feature information of each pixel of a plurality of pixels in an image to be segmented, the predicted object center point The feature information is used to characterize the reliability that the pixel point is the center point of the object; the determination module is used to determine the center point position information of the object in the image to be segmented according to the feature information of the predicted object center point of each pixel point ; an image segmentation module, configured to perform image segmentation on the to-be-segmented image according to the center point position information.
  • the present disclosure provides a non-transitory computer-readable medium on which a computer program is stored, and when the program is executed by a processing apparatus, implements the steps of the method provided in the first aspect of the present disclosure.
  • the present disclosure provides an electronic device, including: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device, so as to implement the computer program provided in the first aspect of the present disclosure. the steps of the method.
  • the present disclosure provides a computer program comprising: instructions that, when executed by a processor, cause the processor to perform the image segmentation method of the first aspect.
  • the present disclosure provides a computer program product comprising instructions that, when executed by a processor, cause the processor to perform the image segmentation method of the first aspect.
  • Fig. 1 is a flowchart of an image segmentation method according to an exemplary embodiment.
  • Fig. 2 is a flow chart of a method for determining center point position information of an object in an image to be segmented according to an exemplary embodiment.
  • Fig. 3 is a flowchart of an image segmentation method according to another exemplary embodiment.
  • Fig. 4 is a block diagram of an image segmentation apparatus according to an exemplary embodiment.
  • Fig. 5 is a schematic structural diagram of an electronic device according to an exemplary embodiment.
  • the term “including” and variations thereof are open-ended inclusions, ie, "including but not limited to”.
  • the term “based on” is “based at least in part on.”
  • the term “one embodiment” means “at least one embodiment”; the term “another embodiment” means “at least one additional embodiment”; the term “some embodiments” means “at least some embodiments”. Relevant definitions of other terms will be given in the description below.
  • the inventor of the present disclosure found that in the related art, when an image is segmented, it is easily interfered by the background area in the image, so that the segmentation effect of the objects in the image is not good, and when there are situations such as objects being partially occluded, the It will make the image segmentation result inaccurate.
  • embodiments of the present disclosure provide an image segmentation method to reduce interference of background regions in an image.
  • Fig. 1 is a flow chart of an image segmentation method according to an exemplary embodiment.
  • the method can be applied to an electronic device with processing capability, such as a terminal or a server.
  • the method may include step S101 ⁇ S103.
  • step S101 the feature information of the predicted object center point of each pixel point of a plurality of pixel points in the image to be divided is acquired.
  • the image to be segmented may be a pre-stored image, an image collected in real time, or an image frame in a video, which is not specifically limited in the present disclosure.
  • Objects may include human bodies and objects. For example, there are one or more vehicles or one or more people in the image to be segmented. Segmentation can divide the area where the foreground object in the image is located and the background area in the image.
  • the feature information of the predicted object center point of the pixel point can be used to represent the reliability of the pixel point as the object center point, that is, the possibility or probability that the pixel point is the object center point.
  • an object center point prediction module may be integrated into the electronic device, and the object center point prediction module may generate a heatmap corresponding to the image to be segmented.
  • the information of each pixel in the figure can be used to represent the feature information of the predicted object center point of the corresponding pixel in the image to be segmented. Among them, if the possibility of the pixel point being the center point of the object is high, the feature information of the predicted object center point of the pixel point is relatively high; The center point feature information is relatively low.
  • the present disclosure does not limit the specific representation of the feature information of the predicted object center point, for example, it can be represented by a value between 0 and 1.
  • step S102 according to the feature information of the predicted object center point of each pixel point, the center point position information of the object in the image to be segmented is determined.
  • the position information of the center point of the object may refer to the coordinate information of the center point of the object in the image to be segmented.
  • step S103 image segmentation is performed on the image to be segmented according to the center point position information.
  • the area where the object is located can be more prominent in the image to be segmented, and the difference between it and the background area is more significant, so it is easier to segment the foreground object when the image to be segmented is segmented. Effectively reduce the interference in the background area.
  • the center point position information of the object will not be affected by the surface features of the object (such as color, size, etc.).
  • the center point position information of the object is not It will be affected by other similar objects. Therefore, image segmentation based on the center point position information of the object can accurately segment the area where the object is located, and improve the accuracy and segmentation effect of image segmentation.
  • the center point position information of the object in the image to be segmented can be determined, and then according to the object center point feature information
  • the position information of the center point is used to segment the image to be segmented.
  • the area where the object is located can be made more prominent in the image to be segmented, and the difference between it and the background area is more significant, so that the foreground can be more accurately segmented when the image to be segmented is segmented.
  • the object is segmented to effectively reduce the interference of the background area.
  • the center point position information of the object will not be affected. Accurate segmentation can improve the accuracy and segmentation effect of image segmentation.
  • determining the center point position information of the object in the image to be segmented may include: The position information of the pixel corresponding to the local maximum value in the information is determined as the position information of the center point of the object.
  • this embodiment can be used to determine the center point position information of the object.
  • the pixel point corresponding to the local maximum value may refer to the pixel point with the largest predicted feature information of the center point of the object among the pixel points in the area where the object is located. If there are multiple objects in the to-be-segmented image, in the pixels of each object's area, there are points with relatively large feature information of the predicted object center point, so multiple local maximum points can be determined, and different local maximum points can be determined. Large value points correspond to the center points of different objects.
  • a local maximum point can be determined, and the local maximum point is also the pixel with the largest feature information of the predicted object center point, and the position information of the pixel point can be determined as the point to be The position information of the center point of the object in the segmented image.
  • the feature information of the predicted object center point of a pixel point can be used to represent the possibility that the pixel point is the object center point, and the pixel point corresponding to the local maximum value in the predicted object center point feature information of multiple pixel points is determined as the object's center point.
  • the position information of the respective center points of the multiple objects can be accurately determined.
  • FIG. 2 is a flow chart of a method for determining center point position information of an object in an image to be segmented according to this embodiment.
  • the above-mentioned step S102 may include steps S1021 to S1023 .
  • step S1021 the predicted center point of the object in the image to be segmented is determined according to the center point position information of the object in the reference image frame and the motion track information of the object.
  • the reference image frame may be an image frame in the video that is different from the image to be segmented.
  • the reference image frame may be the first image frame in the video, or may be the previous frame of the image to be divided in the video, which is not specifically limited in the present disclosure.
  • the image frames in the video have a certain continuity
  • the motion track information of the object can include the object's motion direction information, moving speed, moving acceleration, etc.
  • the moment in the video from the reference image frame can be determined.
  • the center point position information of the object in the reference image frame may be predetermined, and the predicted center point of the object in the to-be-segmented image can be determined according to the center point position information of the object in the reference image frame and the motion track information of the object.
  • the predicted center point is the possible center point position of the object that is initially determined according to the motion trajectory of the object.
  • step S1022 a preset number of pixels with the largest feature information of the predicted object center point in the region where the object is located in the image to be segmented is determined.
  • K may represent a preset number, and K is greater than or equal to 1, and its value is not specifically limited in the present disclosure.
  • the position information of the pixel point with the closest distance to the prediction center point among the preset number of pixel points is determined as the center point position information.
  • the distance between the pixel and the prediction center point can be calculated, and the pixel point with the closest distance to the prediction center point is not only the possibility of the object center point.
  • the distance between the prediction center point determined according to the motion trajectory of the object is relatively high, so the position information of the pixel point can be used as the center point position information of the object in the image to be segmented.
  • S1021 and S1022 may be executed first and then S1021 may be executed, or both may be executed in parallel, and FIG. 2 is only an example.
  • the reference image frame in the video and the motion trajectory information of the object can be combined to determine the center point information of the object in the image to be segmented.
  • the motion track information can make the determined position information of the center point of the object more accurate.
  • Fig. 3 is a flowchart of an image segmentation method according to another exemplary embodiment. As shown in Fig. 3 , the method may include steps S301 to S304, wherein the above step S103 may include S303 and S304.
  • step S301 the feature information of the predicted object center point of each pixel point of a plurality of pixel points in the image to be divided is acquired.
  • step S301 reference may be made to step S101.
  • step S302 according to the feature information of the predicted object center point of each pixel point, the center point position information of the object in the image to be segmented is determined.
  • the method of determining the position information of the center point of the object provided by any embodiment of the present disclosure may be used.
  • step S303 according to the center point position information and the predicted object center point feature information, the target object center point feature information of each pixel point of the plurality of pixels in the image to be segmented is determined.
  • the center point feature information of the target object of the pixel corresponding to the center point position information is greater than the predicted object center point feature information of the pixel point, and the pixel point corresponding to the center point position information is the center point of the object, that is, to further improve the center point of the object
  • the feature information of the point for example, the Gaussian algorithm can be used to increase the feature information of the center point of the object.
  • step S304 image segmentation is performed on the image to be segmented according to the feature information of the center point of the target object.
  • the feature information of the target object center point of the pixel corresponding to the center point position information is greater than the predicted object center point feature information of the pixel, the feature information of the object center point is higher, so the image segmentation is performed according to the target object center point feature information,
  • the foreground objects can be more accurately segmented, and the accuracy and segmentation effect of image segmentation can be further improved.
  • This step S304 may further include: acquiring preset feature information of each pixel of the multiple pixels in the image to be segmented; information to perform image segmentation on the image to be segmented.
  • the preset feature information may include at least one of image semantic feature information and image edge feature information. Among them, each pixel in the image to be segmented can be classified to determine the semantic label to which each pixel belongs, and the image semantic feature information of pixels belonging to the same semantic label can be the same.
  • the edge of an image may refer to the part of the image with the most significant change in brightness or gray level, and the image edge feature information of pixels located in the edge part is relatively large.
  • performing image segmentation on the to-be-segmented image according to the target object center point feature information and preset feature information of each pixel of the plurality of pixels in the to-be-segmented image may include: The target feature information of the target object center point and the preset feature information of each pixel point are used to determine the target feature information of the pixel point; according to the target feature information of each pixel point of the plurality of pixel points, image segmentation is performed on the image to be segmented.
  • the preset feature information includes one of image semantic feature information and image edge feature information
  • the feature information of the center point of the target object of the pixel point in the image to be segmented and the preset feature information of the pixel point can be compared.
  • the product is used as the target feature information of the pixel.
  • the preset feature information includes image semantic feature information and image edge feature information
  • the product of feature information is used as the target feature information of the pixel.
  • the feature information point of the target object center point of a pixel point is multiplied by the preset feature information of the pixel point.
  • the target object center point feature information of the pixel points in the object center point area is relatively low, so multiplying the target object center point feature information of the pixel point with the preset feature information can make the target object feature information of the object center point higher. In this way, when the image is segmented according to the target feature information, the region where the object is located can be made more prominent in the image to be segmented, and the foreground object can be segmented from the image to be segmented more accurately.
  • an exemplary implementation of performing image segmentation on the image to be segmented according to the target feature information of each pixel of the plurality of pixels may be: dividing the image to be segmented and the target feature of each pixel of the plurality of pixels.
  • the information is input into the image segmentation model to perform image segmentation on the image to be segmented by the image segmentation model.
  • the image segmentation model can be any network model, such as a fully convolutional network model.
  • the image segmentation model may be pre-trained.
  • the target feature information of a pixel is obtained according to the feature information of the center point of the target object of the pixel, and the image semantic feature information and/or the image edge feature information.
  • the image segmentation model performs image segmentation on the image to be segmented, due to the object
  • the target feature information of the center point is relatively higher, so the difference between the area where the object is located and the background area is more significant.
  • the target feature information of each pixel point the area where the object is located can be more accurately segmented, thereby improving image segmentation. Effects and image segmentation accuracy.
  • FIG. 4 is a block diagram of an image segmentation device according to an exemplary embodiment. As shown in FIG. 4 , the device 400 may include:
  • the obtaining module 401 is used to obtain the predicted object center point feature information of each pixel point of a plurality of pixel points in the image to be divided, the predicted object center point feature information is used to represent the reliability of the pixel point as the object center point ;
  • a determination module 402 configured to determine the center point position information of the object in the to-be-segmented image according to the feature information of the predicted object center point of each pixel;
  • the image segmentation module 403 is configured to perform image segmentation on the to-be-segmented image according to the center point position information.
  • the above-mentioned device first obtain the feature information of the predicted object center point of each pixel point in the image to be segmented, and then determine the center point position information of the object in the image to be segmented according to the feature information of the predicted object center point of each pixel point. , and then perform image segmentation on the image to be segmented according to the position information of the center point of the object.
  • the position information of the center point of the object considering the position information of the center point of the object, the area where the object is located can be made more prominent in the image to be segmented, and the difference between it and the background area is more significant, so that the foreground can be more accurately segmented when the image to be segmented is segmented.
  • the object is segmented to effectively reduce the interference of the background area. Moreover, even if the object is partially occluded or other similar objects appear in the image, the center point position information of the object will not be affected. Accurate segmentation can improve the accuracy and segmentation effect of image segmentation.
  • the image segmentation module 403 may include: a first determination sub-module, configured to determine a plurality of pixel points in the image to be segmented according to the center point position information and the predicted object center point feature information.
  • the image segmentation sub-module is configured to perform image segmentation on the to-be-segmented image according to the feature information of the center point of the target object.
  • the first image segmentation sub-module may include: an acquisition sub-module for acquiring preset feature information of each pixel of a plurality of pixels in the to-be-segmented image, where the preset feature information includes: at least one of image semantic feature information and image edge feature information; a second segmentation sub-module, used for the target object center point feature information of each pixel point in the image to be segmented and the Preset feature information, and perform image segmentation on the to-be-segmented image.
  • the second segmentation sub-module may include: a second determination sub-module, which is configured to, according to the feature information of the center point of the target object and the Preset feature information to determine target feature information of the pixel, wherein, in the case that the preset feature information includes one of the image semantic feature information and the image edge feature information, the to-be-to-be-featured feature information is The product of the target object center point feature information of a pixel in the segmented image and the preset feature information of the pixel is taken as the target feature information of the pixel, where the preset feature information includes the image semantic feature.
  • a second determination sub-module which is configured to, according to the feature information of the center point of the target object and the Preset feature information to determine target feature information of the pixel, wherein, in the case that the preset feature information includes one of the image semantic feature information and the image edge feature information, the to-be-to-be-featured feature information is The product of the target object center point feature information of a pixel in the segmente
  • a third segmentation sub-module configured to perform image segmentation on the to-be-segmented image according to the target feature information of each pixel point of a plurality of pixel points.
  • the third segmentation sub-module may include: an input sub-module for inputting the to-be-segmented image and the target feature information of each pixel into an image segmentation model, so as to divide the image through the image segmentation.
  • the model performs image segmentation on the image to be segmented.
  • the determining module 402 may include: a third determining sub-module, configured to determine the position information of the pixel corresponding to the local maximum value in the feature information of the predicted object center point of the plurality of pixel points as the location information of the center point.
  • the to-be-segmented image is an image frame in a video
  • the determining module 402 may include: a fourth determining sub-module, configured to determine the object according to the center point position information of the object in the reference image frame and the object
  • the motion trajectory information of the to-be-segmented image determines the predicted center point of the object in the to-be-segmented image, wherein the reference image frame is an image frame in the video that is different from the to-be-segmented image
  • the fifth determination sub-module uses In determining the area where the object is located in the to-be-segmented image, the preset number of pixels with the largest feature information of the center point of the predicted object
  • the sixth determination sub-module is used to determine the number of pixels in the preset number of pixels.
  • the position information of the pixel with the closest distance to the prediction center point is determined as the center point position information.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (eg, mobile terminals such as in-vehicle navigation terminals), etc., and stationary terminals such as digital TVs, desktop computers, and the like.
  • the electronic device shown in FIG. 5 is only an example, and should not impose any limitation on the function and scope of use of the embodiments of the present disclosure.
  • an electronic device 500 may include a processing device (eg, a central processing unit, a graphics processor, etc.) 501 that may be loaded into random access according to a program stored in a read only memory (ROM) 502 or from a storage device 508 Various appropriate actions and processes are executed by the programs in the memory (RAM) 503 . In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored.
  • the processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504 .
  • I/O interface 505 input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speakers, vibration
  • An output device 507 such as a computer
  • a storage device 508 including, for example, a magnetic tape, a hard disk, etc.
  • Communication means 509 may allow electronic device 500 to communicate wirelessly or by wire with other devices to exchange data. While FIG. 5 shows electronic device 500 having various means, it should be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
  • embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via the communication device 509, or from the storage device 508, or from the ROM 502.
  • the processing apparatus 501 When the computer program is executed by the processing apparatus 501, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are executed.
  • the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
  • the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, electrical wire, optical fiber cable, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the client and server can use any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) to communicate, and can communicate with digital data in any form or medium Communication (eg, a communication network) interconnects.
  • HTTP HyperText Transfer Protocol
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks), as well as any currently known or future development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or may exist alone without being assembled into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the predicted object center point feature information of each pixel in the image to be segmented, and the described The feature information of the predicted object center point is used to represent the reliability of the pixel point as the object center point; according to the predicted object center point feature information of each pixel point, the center point position information of the object in the image to be segmented is determined; Image segmentation is performed on the to-be-segmented image according to the center point position information.
  • Computer program code for performing operations of the present disclosure may be written in one or more programming languages, including but not limited to object-oriented programming languages—such as Java, Smalltalk, C++, and This includes conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to via Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in dedicated hardware-based systems that perform the specified functions or operations , or can be implemented in a combination of dedicated hardware and computer instructions.
  • the modules involved in the embodiments of the present disclosure may be implemented in software or hardware. Wherein, the name of the module does not constitute a limitation of the module itself under certain circumstances, for example, the acquisition module may also be described as a "central point feature information acquisition module".
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs Systems on Chips
  • CPLDs Complex Programmable Logical Devices
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • Example 1 provides an image segmentation method, the method comprising: acquiring predicted object center point feature information of each pixel of a plurality of pixels in an image to be segmented, the prediction The feature information of the object center point is used to represent the reliability of the pixel point as the object center point; according to the predicted object center point feature information of each pixel point, the center point position information of the object in the to-be-segmented image is determined; The center point position information is used to perform image segmentation on the to-be-segmented image.
  • Example 2 provides the method of Example 1, wherein performing image segmentation on the to-be-segmented image according to the center point position information includes: according to the center point position information and The predicted object center point feature information is to determine the target object center point feature information of each pixel of a plurality of pixels in the image to be segmented, wherein the target object center of the pixel corresponding to the center point position information The point feature information is greater than the feature information of the predicted object center point of the pixel point; image segmentation is performed on the to-be-segmented image according to the center point feature information of the target object.
  • Example 3 provides the method of Example 2, wherein performing image segmentation on the image to be segmented according to the feature information of the center point of the target object includes: acquiring the image to be segmented The preset feature information of each pixel point of the multiple pixels in the image, the preset feature information includes at least one of image semantic feature information and image edge feature information; The target object center point feature information and the preset feature information of the pixel points are used to perform image segmentation on the to-be-segmented image.
  • Example 4 provides the method of Example 3, wherein the target object center point feature information of each pixel point of a plurality of pixel points in the to-be-segmented image and the prediction method are provided in Example 4. Assuming feature information, performing image segmentation on the to-be-segmented image includes: determining the target object center point feature information and the preset feature information of each pixel point of a plurality of pixel points in the to-be-segmented image.
  • the target feature information of the pixel point wherein, in the case where the preset feature information includes one of the image semantic feature information and the image edge feature information, the target of the pixel point in the image to be segmented
  • the product of the feature information of the object center point and the preset feature information of the pixel point is used as the target feature information of the pixel point, and the preset feature information includes the image semantic feature information and the image edge feature.
  • the product of the target object center point feature information of the pixel points in the image to be segmented, the image semantic feature information of the pixel points and the image edge feature information of the pixel points is used as the pixel point.
  • Example 5 provides the method of Example 4, wherein performing image segmentation on the to-be-segmented image according to the target feature information of each pixel includes: dividing the to-be-segmented image The image and the target feature information of each pixel point are input into the image segmentation model, so as to perform image segmentation on the to-be-segmented image through the image segmentation model.
  • Example 6 provides the method of Example 1, wherein according to the feature information of the predicted object center point of each pixel point of the plurality of pixel points, determine the object in the image to be segmented.
  • the center point position information includes: determining the position information of the pixel point corresponding to the local maximum value in the predicted object center point feature information of the plurality of pixel points as the center point position information.
  • Example 7 provides the method of Example 1, wherein the image to be segmented is an image frame in a video; the predicted object center point according to each pixel point of a plurality of pixel points feature information, and determining the center point position information of the object in the image to be segmented includes: determining the center point location information of the object in the reference image frame and the motion track information of the object The predicted center point of the object, wherein the reference image frame is an image frame in the video that is different from the image to be segmented; determine the center point feature of the predicted object in the area where the object is located in the image to be segmented A preset number of pixels with the largest information; the position information of the pixel with the closest distance to the predicted center point among the preset number of pixels is determined as the center point position information.
  • Example 8 provides an apparatus for image segmentation, the apparatus includes: an acquisition module configured to acquire feature information of predicted object center points of each pixel point of a plurality of pixel points in an image to be segmented , the feature information of the predicted object center point is used to represent the reliability of the pixel point as the object center point; the determination module is used to determine the image to be segmented according to the predicted object center point feature information of each pixel point The center point position information of the object in the middle; the image segmentation module is configured to perform image segmentation on the to-be-segmented image according to the center point position information.
  • Example 9 provides a non-transitory computer-readable medium having stored thereon a computer program that, when executed by a processing apparatus, implements the method described in any one of Examples 1-7 A step of.
  • Example 10 provides an electronic device, including: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to achieve The steps of the method of any of Examples 1-7.
  • a computer program comprising: instructions which, when executed by a processor, cause the processor to perform the image segmentation method as previously described.
  • a computer program product comprising instructions that, when executed by a processor, cause the processor to perform the image segmentation method as previously described.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé et un appareil de segmentation d'image, un support lisible et un dispositif électronique. Le procédé comprend les étapes consistant à : acquérir des informations de caractéristique de point central d'objet prédit de chacun de multiples pixels dans une image à segmenter, les informations de caractéristique de point central d'objet prédit indiquant un niveau de fiabilité que le pixel est le point central d'un objet ; déterminer des informations de position de point central d'un objet dans l'image selon les informations de caractéristique de point central d'objet prédit de chaque pixel ; et effectuer une segmentation d'image sur l'image selon les informations de position de point central. Du fait que le procédé prend en considération des informations de position de point central d'un objet dans une image à segmenter, une région dans laquelle l'objet est situé est accentuée et peut être distinguée clairement d'une région d'arrière-plan, de telle sorte que l'objet dans le premier plan peut être séparé avec précision lorsque l'image est soumise à une segmentation d'image, ce qui permet de réduire efficacement l'interférence de la région d'arrière-plan, et d'améliorer la précision de la segmentation d'image et de la performance de segmentation.
PCT/CN2021/128958 2020-11-18 2021-11-05 Procédé et appareil de segmentation d'image, support lisible et dispositif électronique WO2022105622A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011295274.X 2020-11-18
CN202011295274.XA CN112418232A (zh) 2020-11-18 2020-11-18 图像分割方法、装置、可读介质及电子设备

Publications (1)

Publication Number Publication Date
WO2022105622A1 true WO2022105622A1 (fr) 2022-05-27

Family

ID=74773075

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/128958 WO2022105622A1 (fr) 2020-11-18 2021-11-05 Procédé et appareil de segmentation d'image, support lisible et dispositif électronique

Country Status (2)

Country Link
CN (1) CN112418232A (fr)
WO (1) WO2022105622A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115908459A (zh) * 2023-03-10 2023-04-04 中科慧远视觉技术(北京)有限公司 一种图像分割方法、装置、计算机设备和可读存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112418232A (zh) * 2020-11-18 2021-02-26 北京有竹居网络技术有限公司 图像分割方法、装置、可读介质及电子设备
CN114037715A (zh) * 2021-11-09 2022-02-11 北京字节跳动网络技术有限公司 图像分割方法、装置、设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105844641A (zh) * 2016-03-24 2016-08-10 武汉工程大学 一种动态环境下的自适应阈值分割方法
CN106204538A (zh) * 2016-06-28 2016-12-07 陕西师范大学 一种图像分割方法及系统
CN108090908A (zh) * 2017-12-07 2018-05-29 深圳云天励飞技术有限公司 图像分割方法、装置、终端及存储介质
CN108509820A (zh) * 2017-02-23 2018-09-07 百度在线网络技术（北京）有限公司 障碍物分割方法及装置、计算机设备及可读介质
CN110838125A (zh) * 2019-11-08 2020-02-25 腾讯医疗健康(深圳)有限公司 医学图像的目标检测方法、装置、设备、存储介质
CN112418232A (zh) * 2020-11-18 2021-02-26 北京有竹居网络技术有限公司 图像分割方法、装置、可读介质及电子设备

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110930419A (zh) * 2020-02-13 2020-03-27 北京海天瑞声科技股份有限公司 图像分割方法、装置、电子设备及计算机存储介质
CN111598902B (zh) * 2020-05-20 2023-05-30 抖音视界有限公司 图像分割方法、装置、电子设备及计算机可读介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105844641A (zh) * 2016-03-24 2016-08-10 武汉工程大学 一种动态环境下的自适应阈值分割方法
CN106204538A (zh) * 2016-06-28 2016-12-07 陕西师范大学 一种图像分割方法及系统
CN108509820A (zh) * 2017-02-23 2018-09-07 百度在线网络技术（北京）有限公司 障碍物分割方法及装置、计算机设备及可读介质
CN108090908A (zh) * 2017-12-07 2018-05-29 深圳云天励飞技术有限公司 图像分割方法、装置、终端及存储介质
CN110838125A (zh) * 2019-11-08 2020-02-25 腾讯医疗健康(深圳)有限公司 医学图像的目标检测方法、装置、设备、存储介质
CN112418232A (zh) * 2020-11-18 2021-02-26 北京有竹居网络技术有限公司 图像分割方法、装置、可读介质及电子设备

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115908459A (zh) * 2023-03-10 2023-04-04 中科慧远视觉技术(北京)有限公司 一种图像分割方法、装置、计算机设备和可读存储介质

Also Published As

Publication number Publication date
CN112418232A (zh) 2021-02-26

Similar Documents

Publication Publication Date Title
WO2022105622A1 (fr) Procédé et appareil de segmentation d'image, support lisible et dispositif électronique
CN110413812B (zh) 神经网络模型的训练方法、装置、电子设备及存储介质
CN111784712B (zh) 图像处理方法、装置、设备和计算机可读介质
CN111222509B (zh) 目标检测方法、装置及电子设备
WO2022028253A1 (fr) Procédé d'optimisation de modèle de positionnement, procédé de positionnement, dispositif de positionnement, et support de stockage
CN110866524A (zh) 车牌检测方法、装置、设备及存储介质
CN111311609B (zh) 一种图像分割方法、装置、电子设备及存储介质
CN110852242A (zh) 基于多尺度网络的水印识别方法、装置、设备及存储介质
WO2022052889A1 (fr) Procédé et appareil de reconnaissance d'image, dispositif électronique et support lisible par ordinateur
WO2022116947A1 (fr) Procédé et appareil de recadrage vidéo, support d'enregistrement et dispositif électronique
CN111680754B (zh) 图像分类方法、装置、电子设备及计算机可读存储介质
CN111737575B (zh) 内容分发方法、装置、可读介质及电子设备
CN110348374B (zh) 车辆检测方法、装置、电子设备及存储介质
CN114004229A (zh) 文本识别方法、装置、可读介质及电子设备
CN112488947A (zh) 模型训练和图像处理方法、装置、设备和计算机可读介质
CN112418233A (zh) 图像处理方法、装置、可读介质及电子设备
CN114359673B (zh) 基于度量学习的小样本烟雾检测方法、装置和设备
CN110991312A (zh) 生成检测信息的方法、装置、电子设备和介质
CN112070163B (zh) 图像分割模型训练和图像分割方法、装置、设备
CN111797932B (zh) 图像分类方法、装置、设备和计算机可读介质
CN113744259B (zh) 基于灰度值增加数量序列的森林火灾烟雾检测方法和设备
WO2022194157A1 (fr) Procédé et appareil de suivi de cible, dispositif et support
CN113808050B (zh) 3d点云的去噪方法、装置、设备及存储介质
CN111814807B (zh) 用于处理图像的方法、装置、电子设备和计算机可读介质
WO2023109385A1 (fr) Procédé et appareil de détection de clic sur une icône, dispositif et support de stockage

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21893769

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21893769

Country of ref document: EP

Kind code of ref document: A1