US 12,243,323 B2
Analysis of dynamic spatial scenarios
Halil Beglerovic, Graz (AT); Jonas Rübsam, Graz (AT); and Steffen Metzner, Weiz (AT)
Assigned to AVL List GmbH, Graz (AT)
Appl. No. 17/275,810
Filed by AVL LIST GMBH, Graz (AT)
PCT Filed Sep. 13, 2019, PCT No. PCT/AT2019/060301
§ 371(c)(1), (2) Date Feb. 7, 2022,
PCT Pub. No. WO2020/051618, PCT Pub. Date Mar. 19, 2020.
Claims priority of application No. A 50788/2018 (AT), filed on Sep. 14, 2018.
Prior Publication US 2022/0237889 A1, Jul. 28, 2022
Int. Cl. G06V 20/58 (2022.01); G06T 11/20 (2006.01); G06V 10/426 (2022.01); G06V 10/62 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/58 (2022.01) [G06T 11/203 (2013.01); G06V 10/426 (2022.01); G06V 10/62 (2022.01); G06V 10/82 (2022.01); G06V 2201/08 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A method for preparing data from dynamic spatial scenarios for processing by an artificial neural network, the method comprising:
acquiring sensor data, wherein the sensor data characterizes a dynamic spatial scenario with respect to an ego object and at least one other object; and
generating a representation on the basis of a progression over time of an angular sector ascertained from the sensor data, wherein the progression over time of the angular sector, from the perspective of the ego object, is covered by the at least one other object.