首页|Researchers Submit Patent Application, 'Tracking Objects With Changing Appearances', for Approval (USPTO 20240054776)
Researchers Submit Patent Application, 'Tracking Objects With Changing Appearances', for Approval (USPTO 20240054776)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
From Washington, D.C., NewsRx journalists report that a patent application by the inventors Rao, Jinmeng (Sunnyvale, CA, US); Silva, Daniel Ribeiro (San Jose, CA, US), filed on October 27, 2023, was made available online on February 15, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: "Objects may be tracked across multiple images (or frames) in various ways. In some cases, techniques such as bipartite graph matching may be employed to match one or more objects depicted in a first image with the same object(s) depicted in another image. Object tracking is often employed to track objects that either themselves move as multiple images are captured, or that are viewed from different perspectives across multiple images. While these objects may vary spatially across images, the objects themselves are usually relatively static in appearance." As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors' summary information for this patent application: "Implementations are described herein for tracking objects with changing appearances across temporally-disparate images. More particularly, but not exclusively, techniques are described herein for tracking biological objects that evolve, grow, or otherwise transition among different visual appearances between acquisition of images depicting those biological objects. Techniques described herein allow for the same biological object, such as a fruit, nut, berry, flower, or other plant-part-of-interest, to be tracked across two or more digital images that are captured days or even weeks apart, regardless of the object's changing appearance. Consequently, it is possible to localize that biological object over a relatively long period of time for purposes such as monitoring and/or predicting the biological object's growth, health, yield, etc.
NETL
NSTL
