公开(公告)号：US11321851B2

公开(公告)日：2022-05-03

申请号：US16031092

申请日：2018-07-10

Applicant: Aptiv Technologies Limited

Inventor： Jan Siegemund ,  Daniel Schugk

IPC: G06T7/00 ,  G06T7/246 ,  G06T7/40 ,  G06K9/62 ,  G06T7/277 ,  G06V10/25 ,  G06V10/75

Abstract: A method of tracking an object of interest between temporally successive images taken from a vehicle based camera system comprising: a) from an initial image, determining an initial patch with a respective boundary box encapsulating an identified object of interest; b) using a search template in Kanade Lucas Tomasi (KLT) methodology to track said object of interest in a temporally successive image from said camera system; so as to determine therein a new patch having a respective new boundary box or portion thereof, with respect to said object of interest, characterized in; and c) performing a check on the robustness of the tracking step in step b) by analyzing one or more parameters output from step b).

公开(公告)号：US20220261670A1

公开(公告)日：2022-08-18

申请号：US17661913

申请日：2022-05-03

Applicant: Aptiv Technologies Limited

Inventor： Farzin G. Rajabizadeh ,  Narges Milani ,  Daniel Schugk ,  Lutz Roese-Koerner ,  Yu Su ,  Dennis Mueller

IPC: G06N7/00 ,  G06N3/08 ,  G06N3/04 ,  G06V10/44 ,  G06V20/58 ,  G06N20/00

Abstract: A method of processing image data in a connectionist network comprises a plurality of units, wherein the method implements a multi-channel unit forming a respective one of the plurality of units, and wherein the method comprises: receiving, at the data input, a plurality of input picture elements representing an image acquired by means of a multi-channel image sensor, wherein the plurality of input picture elements comprise a first and at least a second portion of input picture elements, wherein the first portion of input picture elements represents a first channel of the image sensor and the second portion of input picture elements represents a second channel of the image sensor; processing of the first and at least second portion of input picture elements separately from each other; and outputting, at the data output, the processed first and second portions of input picture elements.

公开(公告)号：US20190188586A1

公开(公告)日：2019-06-20

申请号：US16203124

申请日：2018-11-28

Applicant: Aptiv Technologies Limited

Inventor： Farzin G. Rajabizadeh ,  Narges Milani ,  Daniel Schugk ,  Lutz Roese-Koerner ,  Yu Su ,  Dennis Mueller

IPC: G06N7/00 ,  G06N3/08 ,  G06K9/00 ,  G06N3/04

CPC classification number: G06N7/00 ,  G06K9/00818 ,  G06K9/00825 ,  G06K9/4628 ,  G06N3/0454 ,  G06N3/08

Abstract: A method of processing image data in a connectionist network comprises a plurality of units, wherein the method implements a multi-channel unit forming a respective one of the plurality of units, and wherein the method comprises: receiving, at the data input, a plurality of input picture elements representing an image acquired by means of a multi-channel image sensor, wherein the plurality of input picture elements comprise a first and at least a second portion of input picture elements, wherein the first portion of input picture elements represents a first channel of the image sensor and the second portion of input picture elements represents a second channel of the image sensor; processing of the first and at least second portion of input picture elements separately from each other; and outputting, at the data output, the processed first and second portions of input picture elements.

公开(公告)号：US11379746B2

公开(公告)日：2022-07-05

申请号：US16203124

申请日：2018-11-28

Applicant: Aptiv Technologies Limited

Inventor： Farzin G. Rajabizadeh ,  Narges Milani ,  Daniel Schugk ,  Lutz Roese-Koerner ,  Yu Su ,  Dennis Mueller

IPC: G06N7/00 ,  G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06V10/44 ,  G06V20/58

Abstract: A method of processing image data in a connectionist network comprises a plurality of units, wherein the method implements a multi-channel unit forming a respective one of the plurality of units, and wherein the method comprises: receiving, at the data input, a plurality of input picture elements representing an image acquired by means of a multi-channel image sensor, wherein the plurality of input picture elements comprise a first and at least a second portion of input picture elements, wherein the first portion of input picture elements represents a first channel of the image sensor and the second portion of input picture elements represents a second channel of the image sensor; processing of the first and at least second portion of input picture elements separately from each other; and outputting, at the data output, the processed first and second portions of input picture elements.