Method, device, and computer program for reducing the resolution of an input image

Patent metadata

Field	Value
Publication number	US-9576335-B2
Application number	US-41870609-A
Country	US
Kind code	B2
Filing date	Apr 6, 2009
Priority date	Apr 9, 2008
Publication date	Feb 21, 2017
Grant date	Feb 21, 2017

Abstract

In a method, a device, and a computer program for reducing the resolution of an input image, wherein input image shows a three-dimensional scene that was recorded by a surveillance camera, the distance between surveillance camera and objects in the three-dimensional scene is referred to as the object distance, and the resolution reduction is adjusted with consideration for the object distance in the three-dimensional scene and/or the perspective distortion of the three-dimensional scene.

First claim

The invention claimed is:

1. A computer-implemented method for processing an input image recorded by a surveillance camera, in which the input image shows a three-dimensional scene in which a distance between the surveillance camera and objects in the three-dimensional scene is referred to as an object distance, and in which a resolution of the input image is reduced to realize a resolution-reduced image of the three-dimensional scene, the method comprising the steps of:
in an off-line process, generating reduction parameters in advance that include information about perspective distortion of the three-dimensional scene; and
using a computer, processing the input image and the off-line generated reduction parameters to implement a resolution reduction in the input image with consideration of the perspective distortion information of the three-dimensional scene; and
wherein said resolution reduction in the resolution reduced image includes reducing resolution of regions in the input image that represent regions in the three-dimensional scene having great object distance to a lesser extent than that of regions in the input image that represent regions in the three-dimensional scene having a small object distance, thereby realizing the resolution-reduced image.

2. The method as defined in claim 1 , further comprising adjusting the resolution reduction via an evaluation of camera parameters.

3. The method as defined in claim 1 , further comprising adjusting the resolution reduction via modeling of a scene reference model and/or a base plane.

4. The method as defined in claim 1 , further comprising combining the resolution reduction with other pre-rectifications of the input image.

5. The method as defined in claim 1 , further comprising using a resulting distorted and resolution-reduced input image for image analysis.

6. The method as defined in claim 5 , further comprising generating object-describing metadata by the image analysis.

7. The method as defined in claim 6 , further comprising rectifying object-describing metadata in accordance with the resolution reduction that was carried out.

8. A computer program comprising program code means for carrying out the steps of the method as defined in claim 1 when the program is run on a computer.

9. The method as defined by claim 1 , further comprising a step of providing access to the input image with the adjusted resolution reduction.

10. The computer-implemented method according to claim 1 , further including using a camera parameter in the reduction parameter.

11. The computer-implemented method according to claim 1 , further including using a predefined resolution reduction to image regions to which an actual object distance is unassignable.

12. A video surveillance system for reducing resolution of an input image of a three-dimensional scene to realize a resolution reduced image, comprising
an input module configured to receive the input image from a surveillance camera, a recorder or both;
a parameter module for providing resolution reduction parameters that include information about perspective distortion of the three-dimensional scene; and
a reduction module configured to receive the reduction parameters, to reduce a resolution of the input image with consideration for an object distance in the three-dimensional scene, the perspective distortion of the three-dimensional scene or both;
wherein the reduction module reduces resolution of regions in the input image that represent regions in the three-dimensional scene having great object distance to a lesser extent than that of regions in the input image that represent regions in the three-dimensional scene having a small object distance, on a basis of the reduction parameters, thereby realizing the resolution-reduced image.

13. The video surveillance system as defined in claim 12 , further comprising a parameter module which is configured to provide parameters for the resolution reduction, the parameters including or being based on information about the object distances in the three-dimensional scene and/or about the perspective distortion of the three-dimensional scene.

14. A computer program comprising program code means for carrying out the steps of the method as recited in claim 1 when the program is run on the video surveillance system of claim 12 .

15. The video surveillance system of claim 12 , further comprising an image processing module configured to process the reduced resolution input image to detect, segment or track objects therein.

16. A computer-implemented method for processing an input image recorded by a surveillance camera, in which the input image shows a three-dimensional scene in which a distance between the surveillance camera and objects in the three-dimensional scene is referred to as an object distance, and in which a resolution of the input image is reduced to realize a resolution-reduced image of the three-dimensional scene, the method comprising the steps of:
in an off-line process, generating reduction parameters in advance that comprise information about perspective distortion of the three-dimensional scene; and
using a computer, processing the input image and the off-line generated reduction parameters comprising the perspective distortion information to adjust a resolution reduction in the input image via modeling of a scene reference model and with consideration of a perspective distortion information of the three-dimensional scene;
wherein said resolution reduction includes reducing resolution of regions in the input image that represent regions in the three-dimensional scene having great object distance to a lesser extent than that of regions in the input image that represent regions in the three-dimensional scene having a small object distance thereby realizing the resolution reduced image.

Assignees

• Niem Wolfgang
• Bosch Gmbh Robert

Inventors

• Niem Wolfgang
• Anhaeupl Bernd

Classifications

• G06T3/0012 Primary

  Physics · mapped topic

• G06T3/00

  Geometric image transformations in the plane of the image · CPC title

• G06T3/4023

  based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels · CPC title

• G06T3/04 Primary

  Context-preserving transformations, e.g. by using an importance map (panospheric to cylindrical image transformations G06T3/12) · CPC title

• G06T7/207 Primary

  for motion estimation over a hierarchy of resolutions (multi-resolution motion estimation or hierarchical motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/53) · CPC title