Method and apparatus for detecting 3D object from 2D image
AssigneeSamsung Electronics Co., Ltd.
InventorsHee-min Choi, Hyo-a Kang, Yoon-suk Hyun
Life of this patent
Estimating the term…
Loading patent…
AssigneeSamsung Electronics Co., Ltd.
InventorsHee-min Choi, Hyo-a Kang, Yoon-suk Hyun
Estimating the term…
A method of detecting a 3D object from a 2D image includes receiving a 2D image including an object, acquiring an object detection region from the 2D image, iteratively searching for candidates for a direction of a volume including the object of the 2D image in a 3D coordinate system based on the object detection region, and detecting the volume from the 3D coordinate system based on results of the iterative searching.
A method of detecting a 3D object from a 2D image, the method comprising:
An apparatus for detecting a 3D object from a 2D image, the apparatus comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
Analysis of geometric attributes: of area, perimeter, diameter or volume
Image analysis: determining position or orientation of objects or cameras
Image acquisition modality: video; Image sequence
Special algorithmic details: artificial neural networks [ANN]
About 13 years of term left · ends 6 Nov 2039 (estimated)
Korean Patent Application No. 10-2018-0133044, filed on Nov. 1, 2018, in the Korean Intellectual Property Office, and entitled: “Method and Apparatus for Detecting 3D Object from 2D Image,” is incorporated by reference herein in its entirety.
Embodiments relate to a method and apparatus for detecting a 3D object from a 2D image.
Object detection techniques are for detecting a region containing an object from an image. For example, a two-dimensional (2D) bounding box that surrounds an object may be detected from a 2D image using an object detection technique. A 2D bounding box may be specified by the location and size of the 2D bounding box in an image. Object detection techniques may be performed through image processing based on a neural network. In addition, a three-dimensional (3D) bounding box refers to a volume surrounding an object in a 3D coordinate system and may be, e.g., specified by the location, size, and direction of the 3D bounding box in the 3D coordinate system. Applications requiring 3D bounding boxes may include, e.g., driving applications.
Features will become apparent to those of skill in the art by describing in detail exemplary embodiments with reference to the attached drawings, in which:
FIG. 1 illustrates a view of an object detection method according to an embodiment;
FIG. 2 illustrates an operational flowchart of an object detection method according to an embodiment;
Specific structural or functional descriptions presented in the present specification are example descriptions for describing embodiments according to technical concepts, and the embodiments may be implemented in various other forms without being limited to the forms described in the present specification.
Although the terms “first” and “second” are used to describe various elements, these terms are only used to distinguish one element from another element. For example, a first element may be referred to a second element, and similarly a second element may be referred to as a first element.
It should be understood that when an element is referred to as being “coupled” or “connected” to another element, the element may be coupled or connected directly to the other element or any other element may be between the two elements. In contrast, it may be understood that when an element is referred to as being “directly coupled” or “directly connected” to another element, there is no element interposed between the two elements. Expressions used to describe a relationship between elements, e.g., “on,” “directly on,” “between,” “directly between,” “neighboring,” or “directly neighboring” should be interpreted in the same manner.