Patents by Inventor Sandhya Sridhar
Sandhya Sridhar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12233912Abstract: A location of a first object can be determined in an image. A line can be drawn on the first image based on the location of the first object. A deep neural network can be trained to determine a relative location between the first object in the image and a second object in the image based on the line. The deep neural network can be optimized by determining a fitness score that divides a number of deep neural network parameters by a performance score. The deep neural network can be output.Type: GrantFiled: January 10, 2022Date of Patent: February 25, 2025Assignee: Ford Global Technologies, LLCInventors: Nikhil Nagraj Rao, Francois Charette, Shruthi Venkat, Sandhya Sridhar, Vidya Nariyambut Murali
-
Publication number: 20240362793Abstract: A computer that includes a processor and a memory, the memory including instructions executable by the processor to generate background pixels and object pixels and generate background pixel ray data based on the background pixels and object ray pixel data based on the object pixels. The background pixel ray data can be input to a first neural network to generate background neural radiance fields (NeRFs) and the object pixel ray data can be input to a second neural network to generate object NeRFs. An output image can be rendered based on the background NeRFs and the object NeRFs.Type: ApplicationFiled: April 27, 2023Publication date: October 31, 2024Applicants: Ford Global Technologies, LLC, GEORGIA TECH RESEARCH CORPORATIONInventors: Amit Raj, Akshay Krishnan, James Hays, Xianling Zhang, Alexandra Carlson, Nikita Jaipuria, Sandhya Sridhar, Nathan Tseng
-
Publication number: 20230219601Abstract: A location of a first object can be determined in an image. A line can be drawn on the first image based on the location of the first object. A deep neural network can be trained to determine a relative location between the first object in the image and a second object in the image based on the line. The deep neural network can be optimized by determining a fitness score that divides a number of deep neural network parameters by a performance score. The deep neural network can be output.Type: ApplicationFiled: January 10, 2022Publication date: July 13, 2023Applicant: Ford Global Technologies, LLCInventors: Nikhil Nagraj Rao, Francois Charette, Shruthi Venkat, Sandhya Sridhar, Vidya Nariyambut Murali
-
Publication number: 20140314924Abstract: Flavored dairy beverages having stabilizing systems and methods of making the flavored dairy beverages are disclosed herein. The flavored dairy beverages can have a reduced amount of sugar and be shelf-stable and aseptic. In a general embodiment, the dairy beverages comprise milk, a flavoring component, and a stabilizing system comprising a cellulose and carrageenan. The weight ratio of the cellulose to the carrageenan ranges from about 17:1 to about 1.5:1.Type: ApplicationFiled: November 2, 2012Publication date: October 23, 2014Inventors: Alexander A. Sher, Sandhya Sridhar, Stephen Mark, Ying Zheng, Jun-Tse Ray Fu
-
Patent number: 8475855Abstract: A confectionery product comprises first and second confectionery mass layers arranged in contact with each other as a laminate. At least one of the inner surfaces of the first and second confectionery mass layers is provided with at least one depression, and preferably a plurality of depressions arranged in a regular two-dimensional array. The inner surfaces of the confectionery mass layers define at least one pocket in the confectionery product, the or each pocket being located in an area corresponding to a respective depression. The pockets may provide aeration on a macro scale, and they may be at least partially filled with a liquid, semi-solid or solid material.Type: GrantFiled: December 29, 2008Date of Patent: July 2, 2013Assignee: Nestec S.A.Inventors: Monica C. Valdez, Adrienne D. Holmes, John David Wood, Marcel Aebi, Sandhya Sridhar
-
Publication number: 20130129900Abstract: The present invention relates to a non dairy beverage products including products manufactured with superior creaminess. In particular, the invention is concerned with a partially denatured protein system induced by controlled denaturation of protein which imparts outstanding sensory attributes RTD beverage. A method for producing such beverage and product obtainable from the method are also part of the invention.Type: ApplicationFiled: August 4, 2011Publication date: May 23, 2013Applicant: NESTEC S.A.Inventors: Sandhya Sridhar, Stephen Mark, Christian Milo, Alexander A. Sher, Madhavi Ummadi, Madansinh Nathusinh Vaghela, Aaron Beth Butterworth, Nirav Chandrakant Pandya, Bridgett Lynn McCune, Christophe Joseph Etienne Schmitt
-
Publication number: 20130129899Abstract: The present invention relates to beverage products. In particular, the invention is concerned with a partially denaturated protein system induced by controlled denaturation of milk protein which imparts outstanding sensory attributes on beverage product, in particular when containing low fat. A method of producing such beverage and the products obtainable from the method are also part of the present invention.Type: ApplicationFiled: August 4, 2011Publication date: May 23, 2013Applicant: NESTEC S.A.Inventors: Madhavi Ummadi, Madansinh Nathusinh Vaghela, Aaron Beth Butterworth, Nirav Chandrakant Pandya, Bridgett Lynn McCune, Christophe Joseph Etienne Schmitt, Sandhya Sridhar, Stephen Mark, Christian Milo, Alexander A. Sher
-
Publication number: 20120141635Abstract: A confectionery product comprises first and second confectionery mass layers arranged in contact with each other as a laminate. At least one of the inner surfaces of the first and second confectionery mass layers is provided with at least one depression, and preferably a plurality of depressions arranged in a regular two-dimensional array. The inner surfaces of the confectionery mass layers define at least one pocket in the confectionery product, the or each pocket being located in an area corresponding to a respective depression. The pockets may provide aeration on a macro scale, and they may be at least partially filled with a liquid, semi-solid or solid material.Type: ApplicationFiled: December 21, 2009Publication date: June 7, 2012Applicant: NESTEC S.A.Inventors: Monica Christina Valdez, Adrienne Holmes, John David Wood, Marcel Aebi, Sandhya Sridhar
-
Publication number: 20100166922Abstract: A confectionery product comprises first and second confectionery mass layers arranged in contact with each other as a laminate. At least one of the inner surfaces of the first and second confectionery mass layers is provided with at least one depression, and preferably a plurality of depressions arranged in a regular two-dimensional array. The inner surfaces of the confectionery mass layers define at least one pocket in the confectionery product, the or each pocket being located in an area corresponding to a respective depression. The pockets may provide aeration on a macro scale, and they may be at least partially filled with a liquid, semi-solid or solid material.Type: ApplicationFiled: December 29, 2008Publication date: July 1, 2010Applicant: NESTEC S.A.Inventors: Monica C. Valdez, Adrienne D. Holmes, John David Wood, Marcel Aebi, Sandhya Sridhar