Vision system and method for a motor vehicle
AssigneeQualcomm Auto Ltd.
InventorsGustav Lars Henrik Jagbrant, Per Cronvall
Life of this patent
Estimating the term…
Abstract
A vision system for a motor vehicle comprises an imaging apparatus (11) adapted to capture images (30) from a surrounding of the motor vehicle, and a data processing unit (14) adapted to perform image processing on images (30) captured by said imaging apparatus (11). The data processing unit (14) comprises a traffic sign detector (31) adapted to detect traffic signs in images (30) captured by said imaging apparatus (11) through image processing, a decision section (35) and a traffic sign estimator (36) that is adapted to estimate validity information (37) of one or more traffic signs in an image (30) captured by said imaging apparatus (11).
Claims20
A system comprising:
- an imaging apparatus configured to capture images from a surrounding of a motor vehicle;
- and
- at least one processor configured to:
- detect one or more traffic signs in each of the images captured by the imaging apparatus;
- generate, using a first classifier, traffic sign classifier information based on a first portion of each of the images including the detected one or more traffic signs;
- generate, using a second classifier, validity information of the detected one or more traffic signs based on a second portion of each of the images excluding that masks the detected one or more traffic signs in each of the images captured by the imaging apparatus;
- compare the traffic sign classifier information and the validity information;
- and
- output a control signal based in part on comparing the traffic sign classifier information and the validity information.
A computer-implemented method comprising:
- capturing, using an imaging apparatus, images from a surrounding of a motor vehicle;
- detecting one or more traffic signs in each of the images captured using the imaging apparatus;
- generating, using a first classifier, traffic sign classifier information based on a first portion of each of the images including the detected one or more traffic signs;
- generating, using a second classifier, validity information of the detected one or more traffic signs based on a second portion of each of the images that masks the detected one or more traffic signs in each of the images captured by the imaging apparatus;
- comparing the traffic sign classifier information and the validity information;
- and
- outputting a control signal based in part on comparing the traffic sign classifier information and the validity information.
A non-transitory, machine-readable medium having stored thereon a plurality of executable instructions, that when executed by a processor, the plurality of executable instructions comprising instructions to:
- obtain images captured by an imaging apparatus from a surrounding of a motor vehicle;
- detecting one or more traffic signs in each of the images captured using the imaging apparatus;
- generating, using a first classifier, traffic sign classifier information based on a first portion of each of the images including the detected one or more traffic signs;
- generating, using a second classifier, validity information of the detected one or more traffic signs based on a second portion of each of the images excluding that masks the detected one or more traffic signs in each of the images captured by the imaging apparatus;
- comparing the traffic sign classifier information and the validity information;
- and
- outputting a control signal based in part on comparing the traffic sign classifier information and the validity information.
Dependencies are inferred from the claim text.