The presently disclosed subject matter includes tracking method and system wherein a succession images is generated at a sensing unit; one or more moving object in the succession of images is identified; an object tag is assigned to at least one of the moving objects to yield in a respective tagged
The presently disclosed subject matter includes tracking method and system wherein a succession images is generated at a sensing unit; one or more moving object in the succession of images is identified; an object tag is assigned to at least one of the moving objects to yield in a respective tagged object; responsive to a command received from a control unit indicative of a selected object, identifying a location of the selected object in a latest available captured image, wherein: if the selected object is a moving object, the selected object is identified in the latest available captured image based on a respective object tag; and if the selected object is a stationary object, the selected object is identified using an image or piece thereof comprising the at least one selected object.
대표청구항▼
1. A tracking system comprising: a sensing unit comprising an image sensor, and a control unit;wherein the sensing unit is configured to: communicate over a communication link with the control unit;capture, with the help of the image sensor, two or more images of a scene;generate a succession of ima
1. A tracking system comprising: a sensing unit comprising an image sensor, and a control unit;wherein the sensing unit is configured to: communicate over a communication link with the control unit;capture, with the help of the image sensor, two or more images of a scene;generate a succession of images;identify one or more moving objects in said succession of images;assign an object-tag to at least one of said moving objects to yield a respective tagged object;send, to the control unit, data including at least: an image of the succession of images; andthe tagged object;trace the tagged object, from an earlier image in said succession of images to a later image in said succession of images, thereby maintaining a given object-tag continuously associated with a respective moving object along said succession of images;wherein the control unit is configured to: receive input indicative of a selection of at least one object in an image received from the sensing unit; andresponsive to the selection of the object in said image, determine whether the at least one selected object is a moving object or a stationary object; in the case the at least one selected object is a moving object: identify an object-tag assigned to the at least one selected object; andgenerate a first type of command comprising said object-tag;in the case the at least one selected object is a stationary object: generate a second type of command comprising data about said image or part thereof that comprises the at least one selected object; andsend said command to the sensing unit, wherein said command further comprises an indication whether the at least one selected object is a moving object or a stationary object;wherein the sensing unit is further configured to:responsive to said command received from said control unit indicative of at least one selected object, identify a location of the at least one selected object in a latest available captured image, the identification comprising: determining whether the at least one selected object is a moving object or a stationary object based on said indication of said received command; in the case the at least one selected object is a moving object: using the object-tag, obtained from the received first type of command, corresponding to the at least one selected object, for identifying the at least one selected object in the latest available captured image without first identifying the selected object in another previously captured image responsive to the command; andin the case the at least one selected object is a stationary object: using the image or piece thereof, obtained from the received second type of command, comprising the at least one selected object, for identifying the at least one selected object in the latest available captured image. 2. The tracking system according to claim 1, wherein said object-tag is associated with a respective moving object to yield said respective tagged object based on information indicative of a location of said moving object in said succession of images. 3. The tracking system according to claim 1, wherein said sensing unit is configured to continuously send a flow of images from said succession of images to said control unit. 4. The tracking system according to claim 1, wherein said sensing unit is further configured to: in the case the at least one selected object is a stationary object, match said image or piece thereof to said latest available captured image; andidentify the at least one selected object in said image or piece thereof. 5. The tracking system according to claim 1, wherein said sensing unit is configured to identify said one or more moving objects with the help of a Video Motion Detection algorithm. 6. The tracking system according to claim 1, further comprising an object locating module configured to: in case said selected object is not located in a field of view of said image sensor, estimate a real-time location of the selected object; andgenerate direction commands to said image sensor, such that said selected object is located in a real-time image of the scene generated by the image sensor. 7. The tracking system according to claim 1, wherein said command is a tracking command for instructing said sensing unit to track the selected object. 8. The tracking system according to claim 1, wherein said control unit is further configured to: receive a captured image from said sensing unit; anddisplay said image on a display operatively connected to the control unit; andwherein said selection is made by an operator interacting with the control unit. 9. The tracking system according to claim 1, further configured to execute said command with respect to the selected object notwithstanding a time-delay between a time when the sensing unit captures the image with the selected object, to a time when a corresponding command is received at the sensing unit with respect to the selected object. 10. The tracking system according to claim 1, being further configured to: store information with respect to said one or more objects and respective object-tags in a data-repository associated with the sensing unit;determine that a given tagged object is no longer moving;maintain in the data repository information with respect to the given tagged object and a respective object-tag for a time period which is equal or greater than a communication time-delay between the sensing unit and the control unit; anddiscard the information once the time period lapses. 11. A method of tracking objects, the method comprising: in a sensing unit comprising an image sensor, perform at least the following with the help of at least one computer processor: capturing two or more images of a scene;generating a succession of images;identifying one or more moving objects in said succession of images;assigning an object-tag to at least one of said moving objects to yield a respective tagged object;sending, to a control unit communicating with said sensing unit, data including at least: an image of the succession of images; andthe tagged object;tracing the tagged object, from an earlier image in said succession of images to a later image in said succession of images, thereby maintaining a given object-tag continuously associated with a respective moving object along said succession of images;in the control unit: receiving input indicative of a selection of at least one in an image received from the sensing unit;responsive to the selection of the object in said image, determining whether the at least one selected object is a moving object or a stationary object; in the case the at least one selected object is a moving object: identifying an object-tag assigned to the at least one selected object; andgenerating a first type of command comprising said object-tag;in the case the at least one selected object is a stationary object: generating a second type of command comprising data about said image or part thereof that comprises the at least one selected object; andsending said command to the sensing unit, wherein said command further comprises an indication whether the at least one selected object is a moving object or a stationary object;in the sensing unit: identifying, responsive to said command received from said control unit indicative of at least one selected object, a location of the at least one selected object in a latest available captured image, the identification comprising: determining whether the at least one selected object is a moving object or a stationary object based on said indication of said received command; in the case the at least one selected object is a moving object, using the object-tag, obtained from the received first type of command, corresponding to the at least one selected object, for identifying the at least one selected object in the latest available captured image without first identifying the selected object in another previously captured image responsive to the command; andin the case the at least one selected object is a stationary object, using the image or piece thereof, obtained from the received second type of command, comprising the at least one selected object, for identifying the at least one selected object in the latest available captured image. 12. The method according to claim 11, wherein said object-tag is associated with a respective moving object to yield said respective tagged object, based on information indicative of a location of said moving object in said succession of images. 13. The method according to claim 11, further comprising continuously sending a flow of images from said succession of images to said control unit. 14. The method according to claim 11, further comprising: in case the at least one selected object is a stationary object, matching said image or piece thereof to said latest available captured image; andidentifying the at least one selected object in said image or piece thereof, in order to identify the at least one selected object in the latest available captured image. 15. The method according to claim 11, further comprising selecting at least one moving object from among said one or more moving objects, based on a predetermined criterion. 16. The method according to claim 11, further comprising: in case said selected object is not located in a field of view of said image sensor, estimating a real-time location of the selected object; andgenerating direction commands to said image sensor, such that said selected object is located in a real-time image of the scene generated by the image sensor. 17. The method according to claim 11, further comprising storing information with respect to said one or more objects and respective object-tags in a data-repository operatively connected to the sensing unit. 18. The method according to claim 11, further comprising: in said control unit: receiving a captured image from said sensing unit;displaying said image on a display operatively connected to the control unit; andwherein said selection is made by an operator interacting with the control unit. 19. The method according to claim 11, further comprising: executing said command with respect to the selected object notwithstanding a time-delay between a time when the sensing unit acquires the image with the selected object, to a time when a corresponding command is received at the sensing unit with respect to the selected object. 20. The method according to claim 17, further comprising: determining that a given tagged object is no longer moving;maintaining in the data repository information with respect to the given tagged object and a respective object-tag for a time period which is equal or greater than a communication time-delay between the sensing unit and the control unit; anddiscarding the information once the time period lapses. 21. A non-transitory computer storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform a method of tracking objects, the method comprising: generating a succession of images;identifying one or more moving objects in said succession of images;assigning an object-tag to at least one of said moving objects to yield a respective tagged object;sending, to a control unit, data including at least: an image of the succession of images; andthe tagged object;tracing the tagged object, from an earlier image in said succession of images to a later image in said succession of images, thereby maintaining a given object-tag continuously associated with a respective moving object along said succession of images;receiving a command from the control unit;wherein the command is generated at the control unit upon receipt of input indicative of a selection of at least one object in an image received from the sensing unit; wherein in the case the at least one selected object is a moving object, an object-tag assigned to the at least one selected object is incorporated in the generated first type of command;in the case the at least one selected object is a stationary object, data about said image or part thereof that comprises the at least one selected object is incorporated in the generated second type of command; andwherein said command further comprises an indication whether the at least one selected object is a moving object or a stationary object;identifying, responsive to said command, a location of the at least one selected object in a latest available captured image, the identification comprising: determining whether the at least one selected object is a moving object or a stationary object based on said indication of said received command;in the case the at least one selected object is a moving object: using the object-tag, obtained from the received first type of command, corresponding to the at least one selected object, for identifying the at least one selected object in the latest available captured image without first identifying the selected object in another previously captured image responsive to the command; andin the case the at least one selected object is a stationary object: using the image or piece thereof, obtained from the received second type of command, comprising the at least one selected object, for identifying the at least one selected object in the latest available captured image. 22. A tracking system, comprising: a sensing unit comprising an image sensor;the sensing unit configured to:communicate over a communication link with a control unit;capture, with the help of the image sensor, two or more images of a scene and generate a succession of images;identify one or more moving objects in said succession of images;assign an object-tag to at least one of said moving objects to yield a respective tagged object;send, to the control unit, data including at least: an image of the succession of images; andthe tagged object;trace the tagged object, from an earlier image in said succession of images to a later image in said succession of images, thereby maintaining a given object-tag continuously associated with a respective moving object along said succession of images;receive a command from the control unit;wherein the command is generated at the control unit upon receipt of input indicative of a selection of at least one object in an image received from the sensing unit; wherein in the case the at least one selected object is a moving object, an object-tag assigned to the at least one selected object is incorporated in the generated first type of command;in the case the at least one selected object is a stationary object, data about said image or part thereof that comprises the at least one selected object is incorporated in the generated second type of command; andwherein said command further comprises an indication whether the at least one selected object is a moving object or a stationary object;responsive to said command received from said control unit indicative of at least one selected object, identify a location of the at least one selected object in a latest available captured image, the identification comprising: determining whether the at least one selected object is a moving object or a stationary object based on said indication of said received command; in the case the at least one selected object is a moving object: using the object-tag, obtained from the received first type of command, corresponding to the at least one selected object, for identifying the at least one selected object in the latest available captured image without first identifying the selected object in another previously captured image responsive to the command; andin the case the at least one selected object is a stationary object: using the image or piece thereof, obtained from the received second type command, comprising the at least one selected object, for identifying the at least one selected object in the latest available captured image. 23. The tracking system according to claim 1, wherein said step of tracing further comprises, in case a position of the tagged object is changed from a first position in the earlier image to a second updated position in the later image, updating a stored position of the tagged object from the first position to the second updated position, and the step of identifying a selected moving object further comprises using the received object-tag to identify the selected object based on the updated position. 24. The method according to claim 11, wherein said step of tracing further comprises, in case a position of the tagged object is changed from a first position in the earlier image to a second updated position in the later image, updating a stored position of the tagged object from the first position to the second updated position, and the step of identifying a selected moving object further comprises using the received object-tag to identify the selected object based on the updated position.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (89)
Khani Dara T., Adaptive filter selection for optimal feature extraction.
Chodos Steven L. (Los Angeles CA) Groves Gillian K. (Lawndale CA) Stephan Larisa (Hawthorne CA), Adaptive track loop bandwidth reduction in cluttered scenes.
Lo Thomas K. (Temple City CA) Banh Nam D. (Canoga Park CA) Bohn Timothy T. (Simi Valley CA) Sacks Jack M. (Thousand Oaks CA), Apparatus and method for tracking a target.
Rankin David B. (Lowell MA) Roberts ; Jr. Edgar P. (Winston-Salem NC) Kluttz James W. (Winston-Salem NC), Apparatus and method for tracking the flight of a golf ball.
Fagarasan John T. (Brea CA) Alland Stephen W. (Pomona CA) Jakaub Ronald J. (Hacienda Heights CA), Automatic global radar/IR/ESM track association based on ranked candidate pairings and measures of their proximity.
Fagarasan John T. (Brea CA) Alland Stephen W. (Pomona CA) Jakaub Ronald J. (Hacienda Heights CA), Automatic global radar/IR/Esm track association based on ranked candidate pairings and measures of their proximity.
Petajan Eric D. (25 Cypress St. Millburn NJ 07041), Electronic facial tracking and detection system and method and apparatus for automated speech recognition.
Chacon Kim M. (Arcadia CA) Groves Gillian K. (Lawndale CA) Prager Kenneth E. (Los Angeles CA), Image-based detection and tracking system and processing method employing clutter measurements and signal-to-clutter rat.
Kara Atsushi (#145 The Village at Vanderbilt Nashville TN 37212) Kawamura Kazuhiko (5908 Robert E. Lee Dr. Nashville TN 37215), Method and apparatus for automatically tracking an object.
Ono Shuji,JPX ; Osawa Akira,JPX, Method for learning by a neural network including extracting a target object image for which learning operations are to be carried out.
Bassman Robert G ; Bhatt Bhavesh B. ; Call Bill J. ; Hansen Michael W. ; Hsu Stephen C. ; van der Wal Gooitzen S. ; Wixson Lambert E., Parallel-pipelined image processing system.
Schlossers Christophe (Chatillon FRX) Burzawa Stephane (Versailles FRX) Megel Franois (Chaville FRX) Le Gouzouguec Anne (Vanves FRX), Process and device for determining the location of a target.
Krueger Myron W. (55 Edith Rd. Vernon CT 06066) Hinrichsen Katrin (81 Willington Oaks Storrs CT 06268) Gionfriddo Thomas S. (81 Willington Oaks Storrs CT 06268), Real time perception of and response to the actions of an unencumbered participant/user.
Lo Thomas K. (Temple City CA) Sacks Jack M. (Thousand Oaks CA) Simoni Wayne P. (Canoga Park CA), Segmentation method for terminal aimpoint determination on moving objects and apparatus therefor.
Ertel John (Portola Valley CA) Holland William D. (Palo Alto CA) Vincent Kent D. (Cupertino CA) Jamp Rueiming (Los Altos CA) Baldwin Richard R. (Saratoga CA), Substrate advance measurement system using cross-correlation of light sensor array signals.
Nishimura Shigeru (Tokyo JPX) Kuroda Toshihisa (Kanagawa JPX) Aoki Shin-ichiro (Kanagawa JPX), Video signal processing apparatus for separating an image of a moving object from video signals.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.