Systems and methods for detecting an object

Patent metadata

Field	Value
Publication number	US-10572744-B2
Application number	US-201515308292-A
Country	US
Kind code	B2
Filing date	Jun 3, 2015
Priority date	Jun 3, 2014
Publication date	Feb 25, 2020
Grant date	Feb 25, 2020

Abstract

Systems and methods are provided for detecting an object in front of a vehicle. In one implementation, an object detecting system includes an image capture device configured to acquire a plurality of images of an area, a data interface, and a processing device programmed to compare a first image to a second image to determine displacement vectors between pixels. The processing device is also programmed to search for a region of coherent expansion that is a set of pixels in at least one of the first image and the second image, for which there exists a common focus of expansion and a common scale magnitude such that the set of pixels satisfy a relationship between pixel positions, displacement vectors, the common focus of expansion, and the common scale magnitude. The processing device is further programmed to identify presence of a substantially upright object based on the set of pixels.

First claim

What is claimed is:

1. An object detecting system for a vehicle, comprising:
at least one image capture device configured to acquire a plurality of images of an area in front of the vehicle;
a data interface; and
at least one processing device programmed to:
receive the plurality of images via the data interface;
compare a first image to a second image to determine displacement vectors between pixels of the first image and pixels of the second image;
search for a region of coherent expansion that is a set of pixels in at least one of the first image and the second image, for which there exists a common focus of expansion and a common scale magnitude such that the set of pixels satisfy a relationship between pixel positions, displacement vectors, the common focus of expansion, and the common scale magnitude; and
identify presence of a substantially upright object in at least one of the first image and the second image based on the set of pixels.

2. The object detecting system of claim 1 , wherein the region of coherent expansion represents a substantially upright object that has a low time to collision with the vehicle.

3. The object detecting system of claim 1 , wherein the common focus of expansion represents a converging point for a plurality of displacement vectors associated with the set of pixels.

4. The object detecting system of claim 3 , wherein the scale magnitude associated with a pixel in the first image is defined as a magnitude of a displacement vector associated with the pixel divided by a distance from the pixel to the focus of expansion.

5. The object detecting system of claim 4 , wherein the at least one processing device is further programmed to:
calculate a plurality of combinations of scale magnitudes and focus of expansions for a plurality of pixels from at least one of the first image and the second image, the plurality of pixels including the set of pixels; and
determine the common focus of expansion and the common scale: magnitude based on a distribution of the plurality of combinations of scale magnitudes and focus of expansions.

6. The object detecting system of claim 5 , wherein determining the common focus of expansion and the common scale magnitude based on the distribution of the plurality of focuses of expansion includes:
determining the common focus of expansion and the common scale magnitude by determining that a density of distribution around the pair of common focus of expansion and the common scale magnitude is higher than a predetermined threshold.

7. A vehicle, comprising:
a body;
at least one image capture device configured to acquire a plurality of images of an area in front of the vehicle;
a data interface; and
at least one processing device programmed to:
receive the plurality of images via the data interface;
compare a first image to a second image to determine displacement vectors between pixels of the first image and pixels of the second image;
search for a region of coherent expansion that is a set of pixels in at least one of the first image and the second image, for which there exists a common focus of expansion and a common scale magnitude such that the set of pixels satisfy a relationship between pixel positions, displacement vectors, the common focus of expansion, and the common scale magnitude; and
identity presence of a substantially upright object in at least one of the first image and the second image based on the set of pixels.

8. A method for detecting an object in front of a vehicle, comprising:
acquiring, via at least one image capture device, a plurality of images of an area in front of the vehicle;
receiving, via a processing device, the plurality of images;
comparing, via the processing device, a first image to a second image to determine displacement vectors between pixels of the first image and pixels of the second image;
searching for, via the processing device, a region of coherent expansion that is a set of pixels in at least one of the first image and the second image, for which there exists a common focus of expansion and a common scale magnitude such that the set of pixels satisfy a relationship between pixel positions, displacement vectors, the common focus of expansion, and the common scale magnitude; and
identifying, via the processing device, presence of a substantially upright object in at least one of the first image and the second image based on the set of pixels.

9. The method of claim 8 , further comprising:
calculating a plurality of combinations of scale magnitudes and focus of expansions for a plurality of pixels from at least one of the first image and the second image, the plurality of pixels including the set of pixels; and
determining the common focus of expansion and the common scale magnitude based on a distribution of the plurality of combinations of scale magnitudes and focus of expansions.

10. The method of claim 8 , wherein determining the common focus of expansion and the common scale magnitude based on the distribution of the plurality of focuses of expansion includes:
determining the common focus of expansion and the common scale magnitude by determining that a density of distribution around the pair of common focus of expansion and the common scale magnitude is higher than a predetermined threshold.

11. The object detecting system of claim 1 , wherein the at least one processing device is further programmed to:
determine whether a horizontal coordinate of the common focus of expansion stays around a center in a horizontal dimension during a period of time; and
cause the vehicle to brake based on the determination that the horizontal coordinate of the focus of expansion stays around the center in the horizontal dimension during the period of time.

12. The object detecting system of claim 11 , wherein the at least one processing device is further programmed to:
determine whether the substantially upright object will impact the camera based on the determination that the horizontal coordinate of the focus of expansion stays around the center in the horizontal dimension.

13. The object detecting system of claim 1 , wherein determining the common focus of expansion comprises:
providing a three-dimensional array comprising a plurality of cells, individual ones of the plurality of cells comprising coordinates of a focus of expansion;
placing possible solutions to the coordinates into the individual ones of the plurality of cells; and
counting the number of solutions within the individual ones of the plurality of cells.

14. The vehicle of claim 7 , wherein the region of coherent expansion represents that the substantially upright object has a low time to collision with the vehicle.

15. The vehicle of claim 7 , wherein the common focus of expansion represents a converging point for a plurality of displacement vectors associated with the set of pixels.

16. The vehicle of claim 7 , wherein a scale magnitude associated with a pixel in the first image is defined as a magnitude of a displacement vector associated with the pixel divided by a distance from the pixel to the focus of expansion.

17. The vehicle of claim 7 , wherein the at least one processing device is further programmed to:
calculate a plurality of combinations of scale magnitudes and focus of expansions for a plurality of pixels from at least one of the first image and the second image, the plurality of pixels including the set of pixels; and
determine the common focus of expansion and the common scale: magnitude based on a distribution of the plurality of combinations of scale magnitud

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Shashua Amnon
• Dagan Erez
• Baba Tomer
• Myers Yoni
• Hollander Yossi

Classifications

• B60R2300/105

  using multiple cameras · CPC title

• B60R2300/202

  displaying a blind spot scene on the vehicle part responsible for the blind spot · CPC title

• B60R11/04

  Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle · CPC title

• B60R2300/303

  using joined images, e.g. multiple camera images · CPC title

• B60R2300/8026

  in addition to a rear-view mirror system · CPC title