Method and apparatus for determining abnormal object
First Claim
Patent Images
1. A method of determining an abnormal object, the method comprising:
- selecting a candidate object from target objects extracted from a two-dimensional (2D) image of a front view captured from a host vehicle;
estimating a three-dimensional (3D) information of the candidate object from the 2D image;
generating a 3D model based on the estimated 3D information;
determining, based on the 3D model, whether the candidate object corresponds to an abnormal object that interferes with driving of the host vehicle; and
outputting the abnormal object, in response to the candidate object corresponding to the abnormal object,wherein the selecting the candidate object comprises selecting a first target object from among the target objects as the candidate object in response to a difference being greater than or equal to a threshold, the difference being between a size of a portion of the first target object not occluded by another vehicle in the 2D image to be used to generate the 3D model and a size of a portion of a second target object of the target objects that is not occluded by another vehicles in the 2D image to be used to generate the 3D model.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed is a method and apparatus for determining an abnormal object, the method including selecting a candidate object from target objects extracted from a two-dimensional (2D) image of a front view captured from a host vehicle, generating a three-dimensional (3D) model of the candidate object, determining, based on the 3D model, whether the candidate object corresponds to an abnormal object that interferes with driving of the host vehicle, and outputting the abnormal object, in response to the candidate object corresponding to the abnormal object.
24 Citations
18 Claims
-
1. A method of determining an abnormal object, the method comprising:
-
selecting a candidate object from target objects extracted from a two-dimensional (2D) image of a front view captured from a host vehicle; estimating a three-dimensional (3D) information of the candidate object from the 2D image; generating a 3D model based on the estimated 3D information; determining, based on the 3D model, whether the candidate object corresponds to an abnormal object that interferes with driving of the host vehicle; and outputting the abnormal object, in response to the candidate object corresponding to the abnormal object, wherein the selecting the candidate object comprises selecting a first target object from among the target objects as the candidate object in response to a difference being greater than or equal to a threshold, the difference being between a size of a portion of the first target object not occluded by another vehicle in the 2D image to be used to generate the 3D model and a size of a portion of a second target object of the target objects that is not occluded by another vehicles in the 2D image to be used to generate the 3D model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. An apparatus for determining an abnormal object, the apparatus comprising:
-
an image sensor configured to capture a front image from a host vehicle and to generate a two-dimensional (2D) image; and a processor configured to select a candidate object from target objects extracted from the 2D image, estimate a 3D information of the candidate object from the 2D image, generate a 3D model based on the estimated 3D information, determine, based on the 3D model, whether the candidate object corresponds to an abnormal object that interferes with driving of the host vehicle, and output the abnormal object, in response to the candidate object corresponding to the abnormal object, wherein the processor is further configured to select a first target object from among the target objects as the candidate object in response to a difference being greater than or equal to a threshold, the difference being between a size of a portion of the first target object not occluded by another vehicle in the 2D image to be used to generate the 3D model and a size of a portion of a second target object of the target objects that is not occluded by another vehicles in the 2D image to be used to generate the 3D model. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification