Palantir Technologies Inc. patent applications on September 5th, 2024
Patent Applications by Palantir Technologies Inc. on September 5th, 2024
Palantir Technologies Inc.: 1 patent applications
Palantir Technologies Inc. has applied for patents in the areas of G06V10/98 (1), G06V10/74 (1), G06V10/94 (1) G06V10/987 (1)
With keywords such as: object, detected, objects, level, confidence, input, including, based, template, and metric in patent application abstracts.
Patent Applications by Palantir Technologies Inc.
Inventor(s): Aleksandr Patsekin of Foster City CA (US) for palantir technologies inc., Ben Radford of Denver CO (US) for palantir technologies inc., Cameron Derwin of Seattle WA (US) for palantir technologies inc., Daniel Marasco of Washington DC (US) for palantir technologies inc., Di Wang of Sammamish WA (US) for palantir technologies inc., Dimitrios Lymperopoulos of Kirkland WA (US) for palantir technologies inc., Keun Jae Kim of Kirkland WA (US) for palantir technologies inc., Michel Goraczko of Seattle WA (US) for palantir technologies inc., Peng Lei of Bellevue WA (US) for palantir technologies inc., Prasanna Srikhanta of Seattle WA (US) for palantir technologies inc., Rodney LaLonde of Arlington VA (US) for palantir technologies inc., Tong Shen of Redmond WA (US) for palantir technologies inc., Xin Li of San Jose CA (US) for palantir technologies inc., Yue Wu of Lynnwood WA (US) for palantir technologies inc.
IPC Code(s): G06V10/98, G06V10/74, G06V10/94
CPC Code(s): G06V10/987
Abstract: in some examples, systems and methods for user-assisted object detection are provided. for example, a method includes: receiving an input image, and performing object detection by a software detector to identify a set of detected objects. the software detector includes a machine-learning model. the method further includes outputting one or more indicators of the set of detected objects. each detected object in the set of detected objects is associated with a confidence level. the method further includes receiving a user input; identifying a template including an image portion associated with the user input; determining a similarity metric between the template and an object in the set of detected objects; modifying a confidence level of the object based at least in part on the determined similarity metric; and generating an output including an indicator of the object based at least in part on the modified confidence level.
Palantir Technologies Inc. patent applications on September 5th, 2024
