Method and arrangement for recording regions of interest of moving objects

• US 20050212913A1
• Filed: 03/29/2005
• Published: 09/29/2005
• Est. Priority Date: 03/29/2004
• Status: Abandoned Application

• Current Assignee: Cross Match Technologies GmbH (Assa Abloy AB)
• Original Assignee: Smiths Heimann Biometrics GmbH (Assa Abloy AB)
• Inventors: Richter, Uwe
• Application Number:
  US11/092,002
• Publication Number:
  US 20050212913A1
• Time in Patent Office: Days
• US Class Current: 348/170
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

The invention is directed to a method and an arrangement for recording regions of interest in moving objects, preferably of persons. The object of the invention, to find a novel possibility for recording high-resolution electronic images of the faces of persons which achieves high-quality portraits quickly and without manual intervention on the part of the operator with optimal settings of the camera, is met according to the invention in that the image sensor is switchable to a full-image mode and a partial-image mode. An overview recording (such as full image 51) is recorded by a wide-angle objective in the full-image mode and the region of interest (such as face 11) of a person object is recorded in the partial-image mode. The full image is analyzed by an image evaluating unit with regard to the presence and position of object features of a person, a circumscribing rectangle is determined therefrom, and the determined circumscribing rectangle is used as a boundary of a programmable readout window of the image sensor in order to read out a sequence of partial images in the partial-image mode which contain the face of the person so as to fill the image area.

Claims

1. A method for recording regions of interest in moving or changing objects, preferably of persons, comprising the steps of:

tracking a region of interest of an object with an image that is read out of an image sensor for the output image so as to fill the image area; and

further comprising the steps of;

operating the image sensor in such a way that it can be switched sequentially to a full-image mode and a partial-image mode, wherein a full image is recorded by a wide-angle objective as a stationary overview recording in the full-image mode and the region of interest of the object is recorded in the partial-image mode;

analyzing the full image acquired in the full-image mode by an image evaluating unit with regard to the presence and position of given object features, such as the face of a person, and determining a circumscribing rectangle around the region of interest of the object defined by the object features that are found from the position of the object features that are found;

using the currently determined circumscribing rectangle as a boundary of a programmable readout window of the image sensor; and

reading out, in partial-image mode, a sequence of partial images in which the region of interest of the object is contained so as to fill the image area at a high image rate based on the currently adjusted readout window of the image sensor.

2. The method according to claim 1, wherein partial images that are read out in partial-image mode are analyzed to determine whether there is any movement of given object features in successively read out partial images and, when it is determined that there has been a displacement of the object features, the position of the circumscribing rectangle is displaced in a matching manner in order to keep the region of interest of the object completely within the partial image (54) that is read out subsequently.

3. The method according to claim 2, wherein a switching back to the full-image mode is carried out when a border of the rectangle circumscribing the displaced partial image reaches or goes beyond the edge of the full-image recording, and the presence and position of the given object features are determined anew.

4. The method according to claim 2, wherein a switching back to the full-image mode is carried out when at least one object feature that is used to determine the circumscribing rectangle disappears from the partial image, and the presence and position of the given object features are determined anew.

5. The method according to claim 1, wherein the brightness of the object feature in the image is determined in addition to its position, a comparison is made to a reference brightness defined as optimal and, when there is a divergence from the reference brightness, adaptation is carried out by changing the sensitivity adjustments of the image sensor.

6. The method according to claim 5, wherein the gain of the A-D conversion of the image sensor signal is increased when a deficient brightness is determined in the read out partial image compared to the reference brightness.

7. The method according to claim 5, wherein the electronic shutter speed of the image sensor is changed when a deficient brightness is determined in the read out partial image compared to the reference brightness.

8. The method according to claim 5, wherein the electronic shutter speed of the image sensor is regulated and the gain of the A-D conversion of the image sensor signal is increased when a deficient brightness is determined in the read out partial image compared to the reference brightness.

12. An arrangement for carrying out the method according to claim 1, comprising:

a camera arrangement with an objective;

an image sensor;

an image sensor control unit;

an image storage unit; and

an image output unit;

said objective being a wide-angle objective;

said image sensor being a sensor with a variably programmable readout windows which has the full spatial resolution but a substantially shorter readout time compared to the full-image readout mode and can be switched selectively between the full-image mode and partial-image mode;

an image evaluating unit being provided for evaluating the full images recorded in the full-image mode;

wherein the presence and the position of given defined object features can be determined from the full images and regions of interest around the object features are defined from the position of found object features in the form of circumscribing rectangles; and

said image evaluating unit communicating with the image sensor by a sensor control unit in order to use the calculated circumscribing rectangles for variable control of the readout window in the partial-image mode of the image sensor.

13. The arrangement according to claim 12, wherein the wide-angle objective is a fixed-focus objective.

14. The arrangement according to claim 13, wherein the wide-angle objective (24) is a fixed-focus objective, wherein the focus is less than 1.5 m in front of the camera.

15. The arrangement according to claim 12, wherein the wide-angle objective is an autofocus objective.

16. The arrangement according to claim 12, wherein the image sensor is a high-resolution CMOS array.

17. The arrangement according to claim 12, wherein the image sensor (25) has a low image rate in the full-image readout of all pixels.

18. The arrangement according to claim 12, wherein the image evaluating unit contains means for detecting faces of persons.

19. The arrangement according to claim 18, wherein the image evaluating unit has additional means for assessing the quality of found faces.

20. The arrangement according to claim 19, wherein the image evaluating unit has means for assessing the brightness of the read out partial image in relation to basic facial features.

21. The arrangement according to claim 19, wherein the image evaluating unit has means for assessing the size ratios of given object features.

22. The arrangement according to claim 19, wherein an additional operation control unit is provided for influencing the image evaluating unit, wherein the operation control unit has a clock cycle for cyclical switching of the image evaluating unit between full-image evaluations and partial-image evaluations.

9. A method for recording regions of interests of moving or changing objects, preferably of persons, comprising the steps of:

tracking a region of interest of an object so as to fill the image area for the output format with an image that is read out from an image sensor, and further comprising the steps of;

operating the image sensor so as to be switchable sequentially to a full-image mode and a partial-image mode, wherein a full image is made as a stationary overview recording in the full-image mode and the region of interest of the object is recorded in the partial-image recording mode;

analyzing the full image acquired in the full-image recording mode by an image evaluating unit for the presence and position of given defined object features, such as faces of persons, and circumscribing rectangles around the regions of interest of all found objects which are defined by the given object features are determined from the position of the given found object features;

using the currently determined circumscribing rectangles as boundaries of different programmable readout windows of the image sensor for all objects, such as a plurality of persons, that were acquired with the image sensor in full-image mode; and

switching the image sensor is switched to a repeating multiple partial-image recording mode with the determined circumscribing rectangles in the partial-image recording mode based on the currently adjusted plurality of readout windows, and image sequences of partial images having regions of interest of the objects that are read out successively so as to fill the image area are outputted.

10. The method according to claim 9, wherein the repeating multiple partial-image recording mode ends and the image sensor is switched back to the full-image recording mode when at least one given object feature in one of the partial images has disappeared, and the presence and position of the regions of interest of objects are determined once again in the full image in order that current regions of interest are outputted in a new repeating multiple partial-image mode so as to fill the image area.

11. The method according to claim 9, wherein the repeating multiple partial-image recording mode is ended after a predetermined time and the image sensor is switched back to the full-image recording mode, the presence and position of the regions of interest of objects are determined anew in the full image in order to output current regions of interest in a new repeating multiple partial-image mode such that they fill the image area.

23. An arrangement for carrying out the method according to claim 9, comprising:

a camera arrangement with an objective;

an image sensor;

an image sensor control unit;

an image storage unit; and

an image output unit;

said objective being a wide-angle objective;

said image sensor being a sensor with a variably programmable readout windows which has the full spatial resolution but a substantially shorter readout time compared to the full-image readout mode and can be switched selectively between the full-image mode and partial-image mode;

an image evaluating unit being provided for evaluating the full images recorded in the full-image mode;

wherein the presence and the position of given defined object features can be determined from the full images and regions of interest around the object features are defined from the position of found object features in the form of circumscribing rectangles; and

said image evaluating unit communicating with the image sensor by a sensor control unit in order to use the calculated circumscribing rectangles for variable control of the readout window in the partial-image mode of the image sensor.

24. The arrangement according to claim 23, wherein the wide-angle objective is a fixed-focus objective.

25. The arrangement according to claim 24, wherein the wide-angle objective (24) is a fixed-focus objective, wherein the focus is less than 1.5 m in front of the camera.

26. The arrangement according to claim 23, wherein the wide-angle objective is an autofocus objective.

27. The arrangement according to claim 23, wherein the image sensor is a high-resolution CMOS array.

28. The arrangement according to claim 23, wherein the image sensor (25) has a low image rate in the full-image readout of all pixels.

29. The arrangement according to claim 23, wherein the image evaluating unit contains means for detecting faces of persons.

30. The arrangement according to claim 29, wherein the image evaluating unit has additional means for assessing the quality of found faces.

31. The arrangement according to claim 30, wherein the image evaluating unit has means for assessing the brightness of the read out partial image in relation to basic facial features.

32. The arrangement according to claim 30, wherein the image evaluating unit has means for assessing the size ratios of given object features.

33. The arrangement according to claim 30, wherein an additional operation control unit is provided for influencing the image evaluating unit, wherein the operation control unit has a clock cycle for cyclical switching of the image evaluating unit between full-image evaluations and partial-image evaluations.