Object detection apparatus and method

Patent metadata

Field	Value
Publication number	US-2016238703-A1
Application number	US-201615006239-A
Country	US
Kind code	A1
Filing date	Jan 26, 2016
Priority date	Feb 16, 2015
Publication date	Aug 18, 2016
Grant date	—

Abstract

A capture region calculation unit calculates a capture point having the local highest reflection intensity in power profile information and calculates a capture region surrounding the capture point. An edge calculation unit calculates the edges of one or more objects from image data. A marker calculation unit calculates a marker from the capture region. A component region calculation unit calculates component regions by extending the marker using the edges. A grouping unit groups component regions belonging to the same object, of the component regions. The object identification unit identifies the types of one or more objects (e.g., large vehicle, small vehicle, bicycle, pedestrian, flight object, bird) on the basis of a target object region resulting from the grouping.

First claim

What is claimed is:

1 . An object detection apparatus comprising:
an information generation circuitry which, in operation, calculates a reflection intensity with respect to each cell of cells, the cells being obtained by dividing a distance from a radar apparatus into predetermined intervals with respect to each transmission direction of a radar signal transmitted by the radar apparatus, the reflection intensity being a representative value of power of one or more received signals, the one or more received signals being the radar signal reflected by an object and being received by the radar apparatus, and generates power profile information for each cell of the cells by using the reflection intensities; a capture region calculation circuitry which, in operation, identifies a cell having a local highest reflection intensity in the power profile information, from among the cells as a capture point for capturing the object and identifies one or more cells surrounding the capture point as a capture region; an edge extraction circuitry which, in operation, extracts edges of the object included in an image captured by a camera apparatus; a marker calculation circuitry which, in operation, converts the capture region into a partial region of the image based on a coverage of the radar apparatus and a coverage of the camera apparatus and determines the partial region which is a region of the image corresponding to the capture region, as a marker; a component region calculation circuitry which, in operation, determines component regions corresponding to components of the object by extending the marker by using the edges as boundaries; a grouping circuitry which, in operation, groups the component regions into a target object region; and an object identification circuitry which, in operation, identifies the object from the target object region and outputs the identification result.

2 . The object detection apparatus according to claim 1 , wherein the marker calculation circuitry converts the capture region into the marker by using predetermined height information of the object.

3 . The object detection apparatus according to claim 1 , wherein the component region calculation circuitry superimposes the marker on the edges and divides the marker by an edge of the edges when the marker extends over the edge.

4 . The object detection apparatus according to claim 1 , wherein
the information generation circuitry calculates a Doppler speed for each cell of the cells based on a delay profile obtained from the one or more received signals by the radar apparatus and generates Doppler profile information indicating the Doppler speed for each cell of the cells, and the capture region calculation circuitry compares each Doppler speed of the cells included in the capture region and removes a cell having an inconsistent Doppler profile value from the capture region.

5 . The object detection apparatus according to claim 1 , further comprising a model frame identification circuitry that target object region supplements the target object region with a model frame which covers the target object region for groping the component regions.

6 . The object detection apparatus according to claim 1 , further comprising a region tracking circuitry which, in operation, tracks a change in a shape of the target object region associated with passage of time to detect information about a movement of the target object region.

7 . A radar apparatus for vehicles, comprising:
the object detection apparatus according to claim 1 ; and a radar apparatus connected to the object detection apparatus.

8 . A radar apparatus for road infrastructure systems, comprising:
the object detection apparatus according to claim 1 ; and a radar apparatus connected to the object detection apparatus.

9 . A radar apparatus for monitoring systems, comprising:
the object detection apparatus according to claim 1 ; and a radar apparatus connected to the object detection apparatus.

10 . An object detection method comprising:
calculating a reflection intensity with respect to each cell of cells, the cells being obtained by dividing a distance from a radar apparatus into predetermined intervals with respect to each transmission direction of a radar signal transmitted by the radar apparatus, the reflection intensity being a representative value of power of one or more received signals, the one or more received signals being the radar signal reflected by an object and being received by the radar apparatus, and generating power profile information for each cell of the cells by using the reflection intensities; identifying a cell having a local highest reflection intensity in the power profile information, from among the cells as a capture point for capturing the object and identifying one or more cells surrounding the capture point as a capture region; extracting edges of the object included in an image captured by a camera apparatus; converting the capture region into a partial region of the image based on a coverage of the radar apparatus and a coverage of the camera apparatus and determining the partial region which is a region of the image corresponding to the capture region, as a marker; determining component regions corresponding to components of the object by extending the marker by using the edges as boundaries; grouping the component regions into a target object region; and identifying the object from the target object region and outputting the identification result.

Assignees

• Panasonic Ip Man Co Ltd

Inventors

• Liu Weijie
• Nakagawa Yoichi

Classifications

• G01S13/91

  for traffic control (G01S13/93 takes precedence) · CPC title

• G01S13/867 Primary

  Combination of radar systems with cameras · CPC title

• G01S13/66

  Radar-tracking systems; Analogous systems · CPC title

• G01S13/52

  Discriminating between fixed and moving objects or between objects moving at different speeds · CPC title

• G01S13/886

  for alarm systems (alarms with electrical actuation G08B13/22) · CPC title