WO2021208254A1 - Procédé et dispositif de récupération de cible de suivi, et caméra portative - Google Patents

Procédé et dispositif de récupération de cible de suivi, et caméra portative Download PDF

Info

Publication number
WO2021208254A1
WO2021208254A1 PCT/CN2020/099831 CN2020099831W WO2021208254A1 WO 2021208254 A1 WO2021208254 A1 WO 2021208254A1 CN 2020099831 W CN2020099831 W CN 2020099831W WO 2021208254 A1 WO2021208254 A1 WO 2021208254A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
retrieved
newly
tracking
added
Prior art date
Application number
PCT/CN2020/099831
Other languages
English (en)
Chinese (zh)
Inventor
霍磊
梁峰
Original Assignee
上海摩象网络科技有限公司
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 上海摩象网络科技有限公司 filed Critical 上海摩象网络科技有限公司
Publication of WO2021208254A1 publication Critical patent/WO2021208254A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects

Definitions

  • the embodiments of the present application relate to the field of image recognition technology, and in particular, to a method, equipment, and handheld camera for retrieving a tracking target.
  • the smart handheld camera needs to constantly change the position to obtain the panoramic image. Therefore, when the number of tracking targets is large and the tracking target positions are scattered, the smaller field of view cannot support the demand for real-time multi-target tracking. It is easy for the tracking target to be lost. Therefore, how to retrieve the lost tracking target and continue tracking is an urgent problem to be solved.
  • one of the technical problems solved by the embodiments of the present invention is to provide a tracking target retrieval method, device, and handheld camera to solve the problem of how to retrieve the lost tracking target and continue tracking in the prior art .
  • an embodiment of the present application provides a method for retrieving a tracked target, including:
  • the newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target is in the current image frame and the previous M M is an integer greater than or equal to 0 among the image frames that do not belong to the tracking target being shot; the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and The N+1th image frame before the current image frame belongs to the tracking target, and N is an integer greater than or equal to 1;
  • the target to be retrieved is re-determined as the tracking target.
  • the target to be retrieved is an object that has not been identified and/or overlaps with other objects in the N image frames before the current image frame.
  • the newly added occurrence target is an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects.
  • the method before matching the newly-added target with the target to be retrieved based on the similarity information between the newly-added target and the target to be retrieved, the method includes:
  • the similarity between the feature data of the newly-appearing target and the feature data of the target to be retrieved is calculated to obtain the similarity information.
  • the matching the newly-added target with the target to be recovered according to the similarity information between the newly-added target and the target to be recovered includes:
  • the Hungarian algorithm is used to match the newly appeared target with the target to be retrieved.
  • the tracking target, the target to be retrieved, and the newly-added target all include corresponding identification information; correspondingly, when the newly-added target and the target to be retrieved When matching, re-determining the target to be retrieved as the tracking target includes:
  • the method further includes:
  • the identification information corresponding to the newly added target is deleted.
  • the method further includes:
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • the method further includes:
  • the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • an embodiment of the present application provides a tracking target retrieval device, including: a memory, a processor, and a video collector, the video collector is used to collect the target to be tracked in the target area; the memory is used to store Program code; the processor calls the program code, and when the program code is executed, it is used to perform the following operations:
  • the newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target is in the current image frame and the previous M M is an integer greater than or equal to 0 among the image frames that do not belong to the tracking target being shot; the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and The N+1th image frame before the current image frame belongs to the tracking target, and N is an integer greater than or equal to 1;
  • the target to be retrieved is re-determined as the tracking target.
  • the target to be retrieved is an object that has not been identified and/or overlaps with other objects in the N image frames before the current image frame.
  • the newly added occurrence target is an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects.
  • the method before matching the newly-added target with the target to be retrieved based on the similarity information between the newly-added target and the target to be retrieved, the method includes:
  • the similarity between the feature data of the newly-appearing target and the feature data of the target to be retrieved is calculated to obtain the similarity information.
  • the matching the newly-added target with the target to be recovered according to the similarity information between the newly-added target and the target to be recovered includes:
  • the Hungarian algorithm is used to match the newly appeared target with the target to be retrieved.
  • the tracking target, the target to be retrieved, and the newly-added target all include corresponding identification information; correspondingly, when the newly-added target and the target to be retrieved When matching, re-determining the target to be retrieved as the tracking target includes:
  • the processor is further configured to:
  • the identification information corresponding to the newly added target is deleted.
  • the processor is further configured to:
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • the processor is further configured to:
  • the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • an embodiment of the present application provides a handheld camera, including any one of the aforementioned tracking target retrieval devices, and further including: a carrier, which is fixedly connected to the video capture device for At least a part of the video collector is carried.
  • the carrier includes, but is not limited to, a handheld pan/tilt.
  • the handheld pan/tilt is a handheld three-axis pan/tilt.
  • the video capture device includes, but is not limited to, a handheld three-axis pan-tilt camera.
  • the above newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target is in the current image frame and the previous The M image frames do not belong to the tracking target being tracked and M is an integer greater than or equal to 0; the target to be retrieved does not belong to the above-mentioned tracking target in the N image frames before the current image frame, and is in the current image
  • the N+1th image frame before the frame belongs to the tracking target, and N is an integer greater than or equal to 1; when the newly-added target matches the target to be retrieved, the target to be retrieved is re-determined as the tracking target Target.
  • the above method matches the newly-added target with the target to be recovered. If it matches, it means that the newly-added target is extremely similar to the target to be recovered. Therefore, it is determined that the newly-added target is the target to be recovered. The target to be retrieved is determined as the tracking target again.
  • FIG. 1 is a schematic flowchart of a method for retrieving a tracking target according to an embodiment of the application
  • FIG. 2 is another schematic flowchart of a method for retrieving a tracking target provided by an embodiment of the application
  • FIG. 3 is a schematic structural diagram of a tracking target retrieval device provided by an embodiment of the application.
  • FIG. 4 is a schematic structural diagram of a handheld pan/tilt provided by an embodiment of the application.
  • FIG. 5 is a schematic diagram of a handheld PTZ and a mobile device (such as a mobile phone) provided by an embodiment of the application being coupled and connected through an adapter;
  • FIG. 6 is a schematic structural diagram of the cover plate of the handheld platform provided by the embodiment of the application after being clamped to cover the receiving slot.
  • FIG. 1 is a schematic flowchart of a method for retrieving a tracking target provided by an embodiment of the application, including:
  • Step 101 According to the similarity information between the newly appeared target and the target to be retrieved, the newly appeared target and the target to be retrieved are matched, wherein the newly appearing target is in the current image frame and the previous M image frames M is an integer greater than or equal to 0; the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and is the N+1th target before the current image frame Each image frame belongs to the tracking target, and N is an integer greater than or equal to 1.
  • the tracking target is an object that is tracked and photographed by the photographing device.
  • the photographing device can adjust the shooting angle according to the movement of the tracking target.
  • the newly-appearing target is a newly recognized object in the most recent frame or multiple frames of captured image frames, and has not been determined as a tracking target.
  • the newly appearing target may be expressed as a tracking target that is not tracked and shot in the current image frame and the previous M image frames, and M is an integer greater than or equal to 0. That is, when M is equal to 0, it indicates that the newly-added target is a newly recognized object in the current image frame and does not belong to the tracking target being tracked; when M is greater than 0, it indicates that the newly-added target is in the current image frame and before Objects that are continuously identified in the M image frames of, and do not belong to the tracking target being tracked and photographed.
  • the target to be retrieved is an unrecognized object in the latest frame or multiple frames of captured image frames, but it was previously determined as a tracking target. If the target to be retrieved appears later, it will be Can be re-identified as a tracking target for tracking shooting.
  • the target to be retrieved can be expressed as that it does not belong to the tracking target in the N image frames before the current image frame, and belongs to the tracking target at least in the N+1th image frame before the current image frame, and N is greater than or An integer equal to 1. That is, the target to be retrieved belongs to the tracking target at least in the N+1th image frame before the current image frame, and can also belong to the tracking target in more image frames before N+2, N+3, etc., in this embodiment There is no restriction here.
  • a preset image recognition algorithm can be used to perform image recognition on the newly-appearing target and the target to be retrieved, and the corresponding recognition results are recorded, so that the corresponding recognition results can be calculated based on the newly-appearing target and the target to be retrieved
  • the similarity between the two does not limit the preset image recognition algorithm, similarity calculation method, and matching method here.
  • Step 102 When the newly added target matches the target to be retrieved, the target to be retrieved is re-determined as the tracking target.
  • the target to be retrieved when the newly appeared target matches the target to be retrieved, it indicates that the newly appearing target and the target to be retrieved are the same object, or the possibility that the newly appearing target is the target to be retrieved is extremely high.
  • the target to be retrieved has reappeared in the shooting screen and can be used as a tracking target for tracking shooting again. Therefore, if the newly added target matches the target to be retrieved, the target to be retrieved can be re-determined as the tracking target.
  • the above-mentioned embodiment provides a tracking target retrieval method, according to the similarity information between the newly appearing target and the target to be retrieved, the above newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target The target in the current image frame and the previous M image frames does not belong to the tracked target, M is an integer greater than or equal to 0; the target to be retrieved does not belong to the above tracking in the N image frames before the current image frame Target, and belongs to the tracking target in the N+1th image frame before the current image frame, and N is an integer greater than or equal to 1; when the newly-added target matches the target to be retrieved, the target The retrieved target is re-identified as the above-mentioned tracking target.
  • the lost tracking target can be retrieved.
  • FIG. 2 is another schematic flowchart of a tracking target retrieval method provided by an embodiment of the application, as shown in Fig. 2, including:
  • Step 201 Calculate the similarity between the feature data of the newly-appearing target and the feature data of the target to be retrieved to obtain similarity information.
  • the newly-added appearance target may be an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects, that is, the newly-added appearance target and the objects that include the newly-added appearance target Other objects in the image frame do not overlap or are too close to be distinguished.
  • M is an integer greater than or equal to 0.
  • the feature data of the newly-appearing target is data extracted from the current image frame and at least one image frame of the previous M image frames through a preset image recognition algorithm.
  • the feature data of the target to be retrieved is also the data extracted from the image of the target to be retrieved through the preset image recognition algorithm. Since the target to be retrieved has been determined as the tracking target, the target will be retrieved. Therefore, the recorded feature data of the target to be retrieved can be used directly, or the corresponding feature data can be retrieved from one or more image frames in which the target to be retrieved is determined to be the tracking target. This embodiment is not limited.
  • the target to be retrieved may be an object that is not recognized and/or overlaps with other objects in the N image frames before the current image frame, where N is an integer greater than or equal to 1.
  • the similarity calculation method in the prior art can be used to calculate the similarity between the extracted feature data of the newly-appearing target and the feature data of the target to be retrieved, which is not done in this embodiment. limit. Calculating the similarity based on the characteristic data of the newly-appearing target and the characteristic data of the target to be retrieved is beneficial to improve the accuracy of matching between the newly-appearing target and the target to be retrieved in the subsequent steps.
  • Step 202 Based on the similarity information, match the newly appeared target with the target to be retrieved.
  • the Hungarian algorithm can be used to match the newly appeared target and the target to be retrieved.
  • the required parameters for matching the newly appeared target and the target to be retrieved using the Hungarian algorithm can be obtained from the similarity information calculated in step 201 above. That is, based on the similarity information, all newly-appearing targets and all to-be-recovered targets can be paired by the Hungarian algorithm, and then according to the matching degree, it can be determined whether the newly-appearing target and the to-be-recovered target match.
  • the specific object in order to facilitate the management of the specific object during the tracking and shooting process, the specific object may be identified, that is, the tracking target, the target to be retrieved, and the newly appeared target may all include corresponding identification information.
  • the identifier corresponding to the tracking target may be "Tracking", the identifier corresponding to the target to be retrieved may be "Crossing” or “Losting”; the identifier corresponding to the newly appeared target may be "Initial”.
  • Step 203 When the newly added target matches the target to be retrieved, the identification information corresponding to the target to be retrieved is replaced with the identification information corresponding to the tracking target, and the identification information corresponding to the newly appearing target is deleted.
  • the newly-added target when the newly-added target matches with the target to be retrieved, the newly-added target can be considered to be the target to be retrieved. Therefore, there is no need to record and store information about the newly-added target, and the newly-added target can be deleted.
  • the identification information corresponding to the target appears; alternatively, the characteristic data corresponding to the newly-added target can be used to update the corresponding characteristic data of the target to be retrieved, and then the identification information corresponding to the newly-added target is deleted, so that the characteristics corresponding to the target to be retrieved are deleted.
  • the data is more complete.
  • the target to be found when the newly-added target matches the target to be found, it can be considered that the target to be found has reappeared in the shooting screen and can be used as a tracking target for tracking and shooting. Therefore, the target to be found can be corresponded to The identification information of is replaced with the identification information corresponding to the tracking target.
  • the identifier corresponding to the target to be retrieved is "Crossing”
  • the identifier "Crossing” corresponding to the target to be retrieved can be replaced with "Tracking”, and then the identification information corresponding to the newly appeared target can be deleted.
  • Step 204 When the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • the newly-added target does not match the target to be retrieved, it indicates that the possibility that the newly-added target is the target to be retrieved is very low, or it indicates that the newly-added target and the target to be retrieved are not the same object.
  • the newly appeared target can be determined as the tracking target.
  • the identification information corresponding to the newly-added target may be replaced with the identification information corresponding to the tracking target.
  • the identifier corresponding to the newly added target can be replaced from "Initial" to "Tracking".
  • step S204 may further include:
  • the newly appearing target When the newly appearing target does not match the target to be retrieved, and the newly appearing target appears in X consecutive image frames, the newly appearing target can be determined as the tracking target, where X is an integer greater than or equal to 1, And X is greater than M. In practical applications, it can be set reasonably according to the tracking requirements and the data processing capability of the shooting device, so that the newly-added target appears in the latest captured image frame for a long enough time before the newly-added target is determined as the tracking target.
  • the tracking target retrieval method provided in the above embodiment uses the Hungarian algorithm to match the newly appeared target with the target to be retrieved, and then according to the matching result, the identification information corresponding to the target to be retrieved is changed, and the identification information can be changed by changing the identification information
  • the status of newly appearing targets or targets to be retrieved is added, so that it is easy to identify which objects need to be tracked and photographed during subsequent processing, and the identification information corresponding to newly-added targets that do not need to be tracked is deleted, which is beneficial to subsequent image processing save time.
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • L image frames can also be set according to requirements, and L is an integer greater than N. It can be seen from the foregoing embodiment that N is an integer greater than or equal to 1.
  • N is an integer greater than or equal to 1.
  • an embodiment of the present application also provides a tracking target retrieval device, as shown in FIG. 3, including: a memory 30, a processor 31,
  • the video capture device 32 is used to capture the target to be tracked in the target area;
  • the memory 30 is used to store program code;
  • the processor 31 is used to call the program code, and when the program code is executed, it is used to perform the following operations:
  • the newly appearing target and the target to be retrieved are matched; among them, the newly appearing target does not belong to the current image frame and the previous M image frames
  • M is an integer greater than or equal to 0
  • the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and is the N+1th image frame before the current image frame Is a tracking target
  • N is an integer greater than or equal to 1;
  • the target to be retrieved is re-determined as the tracking target.
  • the target to be retrieved is an object that has not been identified and/or overlaps with other objects in the N image frames before the current image frame.
  • the newly added occurrence target is an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects.
  • the method includes:
  • matching the newly appeared target and the target to be recovered according to the similarity information between the newly appeared target and the target to be recovered includes:
  • the Hungarian algorithm is used to match the newly appeared target and the target to be retrieved.
  • the tracking target, the target to be retrieved, and the newly-added target all include corresponding identification information; correspondingly, when the newly-added target matches the target to be retrieved, the target to be retrieved is re-determined as tracking Goals include:
  • the processor 31 is further configured to:
  • the identification information corresponding to the newly-added target is deleted.
  • the processor 31 is further configured to:
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • the processor 31 is further configured to:
  • the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • a handheld camera including any one of the above tracking target retrieval equipment, and further including: a carrier, which is fixedly connected to the video collector, and is used to carry the video capture At least part of the device.
  • the carrier includes, but is not limited to, a handheld pan/tilt.
  • the handheld pan/tilt is a handheld three-axis pan/tilt.
  • the video capture device includes, but is not limited to, a handheld three-axis pan-tilt camera.
  • the handheld pan/tilt head of the embodiment of the present invention includes a handle 11 and a photographing device 12 mounted on the handle 11.
  • the photographing device 12 may include a three-axis pan/tilt camera, In other embodiments, a pan-tilt camera with two axes or more than three axes is included.
  • the handle 11 is provided with a display screen 13 for displaying the shooting content of the shooting device 12.
  • the invention does not limit the type of the display screen 13.
  • the display screen 13 By setting the display screen 13 on the handle 11 of the handheld PTZ 1, the display screen can display the shooting content of the shooting device 12, so that the user can quickly browse the pictures or videos shot by the shooting device 12 through the display screen 13, thereby improving The interaction and fun of the handheld PTZ 1 with the user meets the diverse needs of the user.
  • the handle 11 is further provided with an operating function unit for controlling the camera 12, and by operating the operating function unit, the operation of the camera 12 can be controlled, for example, the opening and closing of the camera 12 can be controlled. Turning off and controlling the shooting of the shooting device 12, controlling the posture change of the pan-tilt part of the shooting device 12, etc., so that the user can quickly operate the shooting device 12.
  • the operation function part may be in the form of a button, a knob or a touch screen.
  • the operating function unit includes a photographing button 14 for controlling the photographing of the photographing device 12, a power/function button 15 for controlling the opening and closing of the photographing device 12 and other functions, as well as controlling the pan/tilt.
  • the universal key 16 may also include other control buttons, such as image storage buttons, image playback control buttons, etc., which can be set according to actual needs.
  • the operation function part and the display screen 13 are arranged on the same side of the handle 11.
  • the operation function part and the display screen 13 shown in the figure are both arranged on the front of the handle 11, which conforms to ergonomics.
  • the appearance layout of the whole handheld PTZ 1 is more reasonable and beautiful.
  • the side of the handle 11 is provided with a function operation key A, which is used to facilitate the user to quickly and intelligently form a sheet with one key.
  • a function operation key A which is used to facilitate the user to quickly and intelligently form a sheet with one key.
  • the handle 11 is further provided with a card slot 17 for inserting a storage element.
  • the card slot 17 is provided on the side of the handle 11 adjacent to the display screen 13, and a memory card is inserted into the card slot 17 to store the images taken by the camera 12 in the memory card. .
  • arranging the card slot 17 on the side does not affect the use of other functions, and the user experience is better.
  • a power supply battery for supplying power to the handle 11 and the imaging device 12 may be provided inside the handle 11.
  • the power supply battery can be a lithium battery with large capacity and small size to realize the miniaturized design of the handheld pan/tilt 1.
  • the handle 11 is also provided with a charging interface/USB interface 18.
  • the charging interface/USB interface 18 is provided at the bottom of the handle 11 to facilitate connection with an external power source or storage device, so as to charge the power supply battery or perform data transmission.
  • the handle 11 is further provided with a sound pickup hole 19 for receiving audio signals, and the sound pickup hole 19 communicates with a microphone inside.
  • the sound pickup hole 19 may include one or more. It also includes an indicator light 20 for displaying status. The user can realize audio interaction with the display screen 13 through the sound pickup hole 19.
  • the indicator light 20 can serve as a reminder, and the user can obtain the power status of the handheld PTZ 1 and the current execution function status through the indicator light 20.
  • the sound pickup hole 19 and the indicator light 20 can also be arranged on the front of the handle 11, which is more in line with the user's usage habits and operation convenience.
  • the imaging device 12 includes a pan-tilt support and a camera mounted on the pan-tilt support.
  • the imager may be a camera, or an image pickup element composed of a lens and an image sensor (such as CMOS or CCD), etc., which can be specifically selected according to needs.
  • the camera may be integrated on the pan-tilt support, so that the photographing device 12 is a pan-tilt camera; it may also be an external photographing device, which can be detachably connected or clamped to be mounted on the pan-tilt support.
  • the pan/tilt support is a three-axis pan/tilt support
  • the photographing device 12 is a three-axis pan/tilt camera.
  • the three-axis pan/tilt head bracket includes a yaw axis assembly 22, a roll axis assembly 23 movably connected to the yaw axis assembly 22, and a pitch axis assembly 24 movably connected to the roll axis assembly 23.
  • the camera is mounted on the pitch axis assembly 24.
  • the yaw axis assembly 22 drives the camera 12 to rotate in the yaw direction.
  • the pan/tilt support can also be a two-axis pan/tilt, a four-axis pan/tilt, etc., which can be specifically selected according to needs.
  • a mounting portion is further provided, the mounting portion is provided at one end of the connecting arm connected to the roll shaft assembly, and the yaw shaft assembly may be set in the handle, and the yaw shaft assembly drives The camera 12 rotates in the yaw direction together.
  • the handle 11 is provided with an adapter 26 for coupling with a mobile device 2 (such as a mobile phone), and the adapter 26 and the handle 11 can be Disconnect the connection.
  • the adapter 26 protrudes from the side of the handle for connecting to the mobile device 2.
  • the adapter 26 is connected to the mobile device 2, the handheld platform 1 and The adapter 26 is docked and used to be supported at the end of the mobile device 2.
  • the handle 11 is provided with an adapter 26 for connecting with the mobile device 2 to connect the handle 11 and the mobile device 2 to each other.
  • the handle 11 can be used as a base of the mobile device 2.
  • the user can hold the other end of the mobile device 2 Let's pick up and operate the handheld PTZ 1 together, the connection is convenient and fast, and the product is beautiful.
  • a communication connection between the handheld pan-tilt 1 and the mobile device 2 can be realized, and the camera 12 and the mobile device 2 can transmit data.
  • the adapter 26 and the handle 11 are detachably connected, that is, the adapter 26 and the handle 11 can be mechanically connected or removed. Further, the adapter 26 is provided with an electrical contact portion, and the handle 11 is provided with an electrical contact matching portion that matches with the electrical contact portion.
  • the adapter 26 can be removed from the handle 11.
  • the adapter 26 is installed on the handle 11 to complete the mechanical connection between the adapter 26 and the handle 11, and at the same time through the electrical contact part and the electrical contact mating part. The connection ensures the electrical connection between the two, so as to realize the data transmission between the camera 12 and the mobile device 2 through the adapter 26.
  • the side of the handle 11 is provided with a receiving groove 27, and the adapter 26 is slidably clamped in the receiving groove 27. After the adapter 26 is installed in the receiving slot 27, the adapter 26 partially protrudes from the receiving slot 27, and the portion of the adapter 26 protruding from the receiving slot 27 is used to connect with the mobile device 2.
  • the adapter 26 when the adapter 26 is inserted into the receiving groove 27 from the adapter 26, the adapter part is flush with the receiving groove 27, and then The adapter 26 is stored in the receiving groove 27 of the handle 11.
  • the adapter 26 can be inserted into the receiving groove 27 from the adapter part, so that the adapter 26 protrudes from the receiving groove 27, So that the mobile device 2 and the handle 11 are connected to each other
  • the adapter 26 can be taken out of the receiving slot 27 of the handle 11, and then inserted into the receiving slot from the adapter 26 in the reverse direction 27, the adapter 26 is further stored in the handle 11.
  • the adapter 26 is flush with the receiving groove 27 of the handle 11. After the adapter 26 is stored in the handle 11, the surface of the handle 11 can be ensured to be flat, and the adapter 26 is stored in the handle 11 to make it easier to carry.
  • the receiving groove 27 is semi-opened on one side surface of the handle 11, which makes it easier for the adapter 26 to be slidably connected to the receiving groove 27.
  • the adapter 26 can also be detachably connected to the receiving slot 27 of the handle 11 by means of a snap connection, a plug connection, or the like.
  • the receiving slot 27 is provided on the side of the handle 11.
  • the receiving slot 27 is clipped and covered by the cover 28 shown in FIG. 6, which is convenient for the user to operate without affecting The overall appearance of the front and sides of the handle.
  • the electrical contact part and the electrical contact mating part may be electrically connected in a contact contact manner.
  • the electrical contact portion can be selected as a telescopic probe, can also be selected as an electrical plug-in interface, or can be selected as an electrical contact.
  • the electrical contact portion and the electrical contact mating portion can also be directly connected to each other in a surface-to-surface contact manner.
  • a method for retrieving a tracking target characterized in that the method includes:
  • the newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target is in the current image frame and the previous M M is an integer greater than or equal to 0 among the image frames that do not belong to the tracking target being shot; the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and The N+1th image frame before the current image frame belongs to the tracking target, and N is an integer greater than or equal to 1;
  • the target to be retrieved is re-determined as the tracking target.
  • A2 The method according to A1, wherein the target to be retrieved is an object that has not been identified and/or overlaps other objects in the N image frames before the current image frame.
  • A3 The method according to A1, wherein the newly added occurrence target is an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects.
  • the similarity between the feature data of the newly-appearing target and the feature data of the target to be retrieved is calculated to obtain the similarity information.
  • A5. The method according to A1, wherein the matching of the newly-added target and the target to be recovered according to the similarity information between the newly-added target and the target to be recovered includes :
  • the Hungarian algorithm is used to match the newly appeared target with the target to be retrieved.
  • A6 The method according to A1, wherein the tracking target, the target to be retrieved, and the newly-added target all include corresponding identification information; correspondingly, when the newly-added target appears When matching with the target to be retrieved, re-determining the target to be retrieved as the tracking target includes:
  • the identification information corresponding to the newly added target is deleted.
  • A8 The method according to A6, characterized in that the method further comprises:
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • A9 The method according to A1, characterized in that the method further comprises:
  • the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • a tracking target retrieval device comprising: a memory, a processor, and a video collector, the video collector is used to collect the target to be tracked in the target area; the memory is used to store program code; The processor calls the program code, and when the program code is executed, it is used to perform the following operations:
  • the newly appearing target and the target to be retrieved are matched; wherein, the newly appearing target is in the current image frame and the previous M M is an integer greater than or equal to 0 among the image frames that do not belong to the tracking target being shot; the target to be retrieved does not belong to the tracking target in the N image frames before the current image frame, and The N+1th image frame before the current image frame belongs to the tracking target, and N is an integer greater than or equal to 1;
  • the target to be retrieved is re-determined as the tracking target.
  • A11 The device according to A10, wherein the target to be retrieved is an object that has not been identified and/or overlaps other objects in the N image frames before the current image frame.
  • A12 The device according to A10, wherein the newly added occurrence target is an object that is identified in the current image frame and the previous M image frames and does not overlap with other objects.
  • the device according to A10 characterized in that, before matching the newly-added target and the target to be recovered according to the similarity information between the newly-added target and the target to be recovered, include:
  • the similarity between the feature data of the newly-appearing target and the feature data of the target to be retrieved is calculated to obtain the similarity information.
  • the device according to A10, wherein the matching the newly-added target and the target to be recovered according to the similarity information between the newly-added target and the target to be recovered includes :
  • the Hungarian algorithm is used to match the newly appeared target with the target to be retrieved.
  • A15 The device according to A10, wherein the tracking target, the target to be retrieved, and the newly-added target all include corresponding identification information; correspondingly, when the newly-added target appears When matching with the target to be retrieved, re-determining the target to be retrieved as the tracking target includes:
  • A16 The device according to A15, wherein the processor is further configured to:
  • the identification information corresponding to the newly added target is deleted.
  • A17 The device according to A15, wherein the processor is further configured to:
  • the identification information corresponding to the target to be retrieved is deleted, and L is an integer greater than N.
  • the newly-added target does not match the target to be retrieved, the newly-added target is determined as the tracking target.
  • a handheld camera characterized by comprising the tracking target retrieval device described in any one of A10-A18, characterized by further comprising: a carrier, which is fixedly connected to the video capturer, It is used to carry at least a part of the video collector.
  • A20 The handheld camera according to A19, wherein the carrier includes, but is not limited to, a handheld pan/tilt.
  • A21 The handheld camera according to A20, wherein the handheld pan/tilt is a handheld three-axis pan/tilt.
  • A22 The handheld camera according to A21, wherein the video capture device includes, but is not limited to, a handheld three-axis pan-tilt camera.
  • the improvement of a technology can be clearly distinguished between hardware improvements (for example, improvements in circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements in method flow).
  • hardware improvements for example, improvements in circuit structures such as diodes, transistors, switches, etc.
  • software improvements improvements in method flow.
  • the improvement of many methods and processes of today can be regarded as a direct improvement of the hardware circuit structure.
  • Designers almost always get the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be realized by the hardware entity module.
  • a programmable logic device for example, a Field Programmable Gate Array (Field Programmable Gate Array, FPGA)
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • the controller can be implemented in any suitable manner.
  • the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the memory control logic.
  • controllers in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded logic.
  • the same function can be realized in the form of a microcontroller or the like. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for realizing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • this application can be provided as a method, a system, or a computer program product. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • This application may be described in the general context of computer-executable instructions executed by a computer, such as a program module.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific transactions or implement specific abstract data types.
  • This application can also be practiced in distributed computing environments. In these distributed computing environments, remote processing devices connected through a communication network execute transactions.
  • program modules can be located in local and remote computer storage media including storage devices.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

Les modes de réalisation de la présente demande concernent un procédé et un dispositif de récupération de cible de suivi, ainsi qu'une caméra portative. Selon des informations de similarité entre une cible nouvellement apparue et une cible à récupérer, on réalise une mise en correspondance sur la cible nouvellement apparue et la cible à récupérer ; dans une trame d'image courante et M trames d'image avant la trame d'image courante, la cible nouvellement apparue n'est pas une cible de suivi qui est suivie et photographiée, M est supérieur ou égal à 0, la cible à récupérer n'est pas une cible de suivi dans N trames d'image avant la trame d'image courante, mais est une cible de suivi dans un (N+1)-ième trame d'image avant la trame d'image courante, et N est supérieur ou égal à 1 ; si la cible nouvellement apparue correspond à la cible à récupérer, on redétermine la cible à récupérer en tant que cible de suivi. Dans le procédé ci-dessus, on réalise une mise en correspondance sur une cible nouvellement apparue et une cible à récupérer ; si les deux correspondent l'une à l'autre, cela signifie que la cible nouvellement apparue est extrêmement similaire à la cible à récupérer, et on détermine que la cible nouvellement apparue est la cible à récupérer ; puis, on redétermine la cible à récupérer en tant que cible de suivi.
PCT/CN2020/099831 2020-04-15 2020-07-02 Procédé et dispositif de récupération de cible de suivi, et caméra portative WO2021208254A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010297276.6A CN111508001A (zh) 2020-04-15 2020-04-15 一种跟踪目标的找回方法、设备以及手持相机
CN202010297276.6 2020-04-15

Publications (1)

Publication Number Publication Date
WO2021208254A1 true WO2021208254A1 (fr) 2021-10-21

Family

ID=71877570

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/099831 WO2021208254A1 (fr) 2020-04-15 2020-07-02 Procédé et dispositif de récupération de cible de suivi, et caméra portative

Country Status (2)

Country Link
CN (1) CN111508001A (fr)
WO (1) WO2021208254A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023207582A1 (fr) * 2022-04-28 2023-11-02 北京字跳网络技术有限公司 Procédé et appareil de suivi multi-objet, dispositif et support de stockage lisible

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104794731A (zh) * 2015-05-12 2015-07-22 成都新舟锐视科技有限公司 用于球机控制策略的多目标检测跟踪方法
CN108269269A (zh) * 2016-12-30 2018-07-10 纳恩博（北京）科技有限公司 目标跟踪方法和装置
CN109949341A (zh) * 2019-03-08 2019-06-28 广东省智能制造研究所 一种基于人体骨架结构化特征的行人目标跟踪方法
CN110021034A (zh) * 2019-03-20 2019-07-16 华南理工大学 一种基于头肩检测的跟踪录播方法及系统
US20200042704A1 (en) * 2018-08-01 2020-02-06 International Business Machines Corporation Time and frequency domain analysis of bytecode for malware detection

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN210401976U (zh) * 2019-09-12 2020-04-24 北京字节跳动网络技术有限公司 一种云台相机

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104794731A (zh) * 2015-05-12 2015-07-22 成都新舟锐视科技有限公司 用于球机控制策略的多目标检测跟踪方法
CN108269269A (zh) * 2016-12-30 2018-07-10 纳恩博（北京）科技有限公司 目标跟踪方法和装置
US20200042704A1 (en) * 2018-08-01 2020-02-06 International Business Machines Corporation Time and frequency domain analysis of bytecode for malware detection
CN109949341A (zh) * 2019-03-08 2019-06-28 广东省智能制造研究所 一种基于人体骨架结构化特征的行人目标跟踪方法
CN110021034A (zh) * 2019-03-20 2019-07-16 华南理工大学 一种基于头肩检测的跟踪录播方法及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023207582A1 (fr) * 2022-04-28 2023-11-02 北京字跳网络技术有限公司 Procédé et appareil de suivi multi-objet, dispositif et support de stockage lisible

Also Published As

Publication number Publication date
CN111508001A (zh) 2020-08-07

Similar Documents

Publication Publication Date Title
WO2021208256A1 (fr) Procédé et appareil de traitement vidéo, et caméra portative
US11606482B2 (en) Methods for camera movement compensation
WO2021208253A1 (fr) Procédé et dispositif de détermination d'objet de suivi, et caméra portative
US9007431B1 (en) Enabling the integration of a three hundred and sixty degree panoramic camera within a consumer device case
US9031610B2 (en) Camera attachment for phone
WO2021208249A1 (fr) Procédé et dispositif de traitement d'images et caméra tenue à la main
US20190014242A1 (en) Wearable video camera medallion with circular display
CN105704369B (zh) 一种信息处理方法及装置、电子设备
CN106657455B (zh) 一种带可旋转摄像头的电子设备
KR102446264B1 (ko) 이동 단말기
CN109922253A (zh) 镜头防抖方法及装置、移动设备
CN107844049A (zh) 一种双屏智能手表
WO2021208255A1 (fr) Procédé et dispositif de marquage de clip vidéo, et caméra portative
WO2021208251A1 (fr) Procédé de suivi facial et dispositif de suivi facial
WO2021208254A1 (fr) Procédé et dispositif de récupération de cible de suivi, et caméra portative
WO2021208252A1 (fr) Procédé de détermination de cible de suivi, dispositif et caméra portative
WO2021208257A1 (fr) Procédé et dispositif de détermination d'état de suivi et caméra portative
US6487069B1 (en) Portable personal computer having a camera mounted thereon
WO2021208258A1 (fr) Procédé et appareil de recherche d'objet suivi, et caméra portative associée
WO2021208259A1 (fr) Procédé et dispositif de pilotage de cardan, et caméra portative
CN110661979B (zh) 摄像方法、装置、终端及存储介质
WO2021208261A1 (fr) Procédé et dispositif d'extraction de cible de suivi, et caméra portative
WO2021208260A1 (fr) Procédé et dispositif pour afficher la trame de suivi d'un objet cible, et appareil photo portatif
CN111539283B (zh) 人脸跟踪方法及人脸跟踪设备
CN114697570B (zh) 用于显示图像的方法、电子设备及芯片

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: 20931527

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: 20931527

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 17/07/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20931527

Country of ref document: EP

Kind code of ref document: A1