Back to results
US 11,999,316 B2Granted
Systems and methods of vehicle surveillance
AssigneeNio Technology (Anhui) Co., Ltd
InventorImama Ali
Life of this patent
Estimating the term…
Abstract
Disclosed systems and methods include receiving an image, processing the image with a depth estimation module to generate a first depth map, generating a foreground mask of the image, inpainting regions of the image, generating a second depth map based on the inpainted regions of the image, comparing histograms of the first and second depth maps, and generating proximity warnings based on the comparison of the histograms.
Claims20
A method of surveilling a vehicle, the method comprising:
- receiving, from an image sensor, an image;
- processing the received image to generate a first depth map;
- processing, with a background modeling algorithm, the received image to generate one or more of a foreground mask and a background mask;
- generating, with an image inpainting network, an inpainted image comprising the received image with an inpainted region associated with the one or more of the foreground mask and the background mask;
- processing the inpainted image to generate a second depth map;
- computing a histogram of the first depth map and a histogram of the second depth map;
- comparing the histogram of the first depth map with the histogram of the second depth map to determine one or more of a size and a relative depth range of one or more foreground objects;
- and
- generating an alert comprising data associated with the determined one or more of the size and the relative depth range of the one or more foreground objects.
6 more elements
A user device comprising:
- a processor;
- and
- a computer-readable storage medium storing computer-readable instructions which, when executed by the processor, cause the processor to execute a method of surveilling a vehicle, the method comprising:
- receiving, from an image sensor, an image;
- processing the received image to generate a first depth map;
- processing, with a background modeling algorithm, the received image to generate one or more of a foreground mask and a background mask;
- generating, with an image inpainting network, an inpainted image comprising the received image with an inpainted region associated with the one or more of the foreground mask and the background mask;
- processing the inpainted image to generate a second depth map;
- computing a histogram of the first depth map and a histogram of the second depth map;
- based on the histogram of the first depth map and the histogram of the second depth map, determining one or more of a size and a relative depth range of one or more foreground objects;
- and
- generating an alert comprising data associated with the determined one or more of the size and the relative depth range of the one or more foreground objects.
9 more elements
A computer program product comprising:
- a non-transitory computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code configured, when executed by a processor, to execute a method of surveilling a vehicle, the method comprising:
- receiving, from an image sensor, an image;
- processing the received image to generate a first depth map;
- processing, with a background modeling algorithm, the received image to generate one or more of a foreground mask and a background mask;
- generating, with an image inpainting network, an inpainted image comprising the received image with an inpainted region associated with the one or more of the foreground mask and the background mask;
- processing the inpainted image to generate a second depth map;
- computing a histogram of the first depth map and a histogram of the second depth map;
- based on the histogram of the first depth map and the histogram of the second depth map, determining one or more of a size and a relative depth range of one or more foreground objects;
- and
- generating an alert comprising data associated with the determined one or more of the size and the relative depth range of the one or more foreground objects.
7 more elements
Dependencies are inferred from the claim text.