US 12,333,810 B2
Object detection
Yun Li, Lund (SE); Alexander Hunt, Tygelsjö (SE); Hector Caltenco, Oxie (SE); and Saeed Bastani, Lund (SE)
Assigned to Telefonaktiebolaget LM Ericsson (Publ), Stockholm (SE)
Appl. No. 17/761,482
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Oct. 2, 2019, PCT No. PCT/EP2019/076765
§ 371(c)(1), (2) Date Mar. 17, 2022,
PCT Pub. No. WO2021/063505, PCT Pub. Date Apr. 8, 2021.
Prior Publication US 2022/0366691 A1, Nov. 17, 2022
Int. Cl. G06V 20/40 (2022.01); G06T 7/20 (2017.01); G06V 10/82 (2022.01); H04N 23/65 (2023.01)
CPC G06V 20/46 (2022.01) [G06T 7/20 (2013.01); G06V 10/82 (2022.01); H04N 23/65 (2023.01)] 21 Claims
OG exemplary drawing
 
1. A method of detecting objects in a video, the method comprising, for each image in a sequence of images of the video:
determining a degree of correlation between the image and at least one preceding image in the sequence of images based on a correlation between frames based on a deviation of a number of matched features between the image and the at least one preceding image;
obtaining a first measure of energy consumption required for performing an object detection process on the image, obtaining a second measure of energy consumption required for performing an object tracking process for tracking at least one object from a previous image;
when the degree of correlation is below a threshold value, performing an object detection process on the image;
when the degree of correlation is above a threshold value, comparing the first measure of energy and the second measure of energy and performing the object detection process on the image if
the first measure of energy consumption is lower than the second measure of energy consumption; and
performing the object tracking process on the image if the first measure of energy consumption is larger than the second measure of energy consumption.