US 11,875,450 B2
Surround view
Shashank Dabral, Allen, TX (US); Vikram Appia, Dallas, TX (US); Hemant Hariyani, Plano, TX (US); and Lucas Weaver, Dallas, TX (US)
Assigned to Texas Instruments Incorporated, Dallas, TX (US)
Filed by TEXAS INSTRUMENTS INCORPORATED, Dallas, TX (US)
Filed on Jun. 29, 2022, as Appl. No. 17/853,220.
Application 17/853,220 is a continuation of application No. 16/519,099, filed on Jul. 23, 2019, granted, now 11,380,046.
Prior Publication US 2022/0335680 A1, Oct. 20, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 15/20 (2011.01); G06T 7/40 (2017.01); G06T 1/20 (2006.01); G06T 15/00 (2011.01); G06T 15/04 (2011.01); H04N 13/111 (2018.01); G06T 5/00 (2006.01); B60R 1/00 (2022.01)
CPC G06T 15/20 (2013.01) [G06T 1/20 (2013.01); G06T 5/006 (2013.01); G06T 7/40 (2013.01); G06T 15/04 (2013.01); H04N 13/111 (2018.05); B60R 1/00 (2013.01); B60R 2300/105 (2013.01); B60R 2300/30 (2013.01); B60R 2300/306 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system on a chip (SoC) comprising:
a graphics processing unit (GPU); and
a digital signal processor (DSP) coupled to the GPU,
wherein the DSP is configured to:
compare a first depth of a previously flagged object with a second depth of a flagged object;
based on a result of comparing the first and second depths, update a virtual bowl surface to generate an updated virtual bowl surface; and
generate a bowl to physical camera mapping based on the updated virtual bowl surface, and
wherein the GPU is configured to:
perform a physical camera to virtual camera transformation based on the bowl to physical camera mapping to generate an output image.