Monitoring method and camera

• US 9,536,154 B2
• Filed: 05/08/2014
• Issued: 01/03/2017
• Est. Priority Date: 05/08/2013
• Status: Active Grant

• Current Assignee: Axis AB (Canon Inc.)
• Original Assignee: Axis AB (Canon Inc.)
• Inventors: Skans, Markus, Johannesson, Anders, Chen, Jiandan, Baltsen, Joakim
• Primary Examiner(s): Bitar, Nancy
• Application Number:
  US14/273,181
• Publication Number:
  US 20140334676A1
• Time in Patent Office: 971 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20112 Image segmentation details
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm
• CPC Class Codes: G08B 13/19686 Interfaces masking personal details for privacy, e.g. blurring faces, vehicle license plates

Abstract

A method of monitoring a scene by a camera (7) comprises marking a part (14) of the scene with light having a predefined spectral content and a spatial verification pattern. An analysis image is captured of the scene by a sensor sensitive to the predefined spectral content. The analysis image is segmented based on the predefined spectral content, to find a candidate image region. A spatial pattern is detected in the candidate image region, and a characteristic of the detected spatial pattern is compared to a corresponding characteristic of the spatial verification pattern. If the characteristics match, the candidate image region is identified as a verified image region corresponding to the marked part (14) of the scene. Image data representing the scene is obtained, and image data corresponding to the verified image region is processed in a first manner, and remaining image data is processed in a second manner.

Claims

1. A method of masking part of an image of a scene captured by a camera monitoring the scene, comprising:

mounting a light source and marking a part of the scene with light having a predefined spectral content and a spatial verification pattern,

capturing an analysis image of the scene by a sensor sensitive to the predefined spectral content,

segmenting the analysis image, based on the predefined spectral content, to find a candidate image region,

detecting a spatial pattern in the candidate image region,

comparing a characteristic of the detected spatial pattern to a corresponding characteristic of the spatial verification pattern, and, if the characteristic of the detected spatial pattern and the corresponding characteristic of the spatial verification pattern match,

identifying the candidate image region as a verified image region corresponding to the part of the scene which is illuminated by the light source,

obtaining image data representing the scene, and

hiding image data, corresponding to the verified image region, from being displayed, by blurring or substituting, and displaying remaining image data, thereby providing a privacy mask for the part of the scene which is illuminated by the light source, or displaying image data corresponding to the verified image region, and hiding remaining image data from being displayed, by blurring or substituting, thereby providing a privacy mask for a non-illuminated part of the scene,

modulating the spatial verification pattern between at least a first and a second spatial verification pattern according to a temporal modulation sequence, and

with a respective one of the first and the second spatial verification pattern, in accordance with the temporal modulation sequence, repeating said marking, said capturing, said segmenting, said detecting and said comparing.

2. The method of claim 1, further comprising capturing a monitoring image by a sensor insensitive to the predefined spectral content, and wherein the image data representing the scene is obtained from the monitoring image.

3. The method of claim 1, wherein the spatial verification pattern is a signature pattern associated with one or more cameras.

4. The method of claim 1, wherein the characteristic of the detected spatial pattern is a ratio between a spatial frequency of a detected pattern and a spatial frequency of a previously detected pattern, and the characteristic of the spatial verification pattern is a ratio between a spatial frequency of the first spatial verification pattern and a spatial frequency of the second spatial verification pattern.

5. The method of claim 1, wherein the temporal modulation sequence is generated based on a pseudo-random sequence.

6. The method of claim 4, wherein the temporal modulation sequence is generated based on a pseudo-random sequence.

7. The method of claim 1, wherein a prestored background image is used for the substituting.

8. The method of claim 1,

wherein the image data corresponding to the verified image region is included in input to motion detection circuitry, and the remaining image data is excluded from input to the motion detection circuitry, or

wherein the remaining image data is included in input to motion detection circuitry, and the image data corresponding to the verified image region is excluded from input to the motion detection circuitry.

9. The method of claim 1,

wherein the image data corresponding to the verified image region is included in input to object detection circuitry arranged to detect or identify a human, an animal, a vehicle, a license plate, text or visual information, or other object type, and wherein the remaining image data is excluded from input to the object detection circuitry, or,

wherein the remaining image data is included in input to object detection circuitry arranged to detect or identify a human, an animal, a vehicle, a license plate, text or visual information, or other object type, and wherein the image data corresponding to the verified image region is excluded from input to the object detection circuitry.

10. The method of claim 1, wherein the image data representing the verified image region is compressed at a first compression rate, wherein the remaining image data is compressed at a second compression rate, and wherein the first compression rate is different from the second compression rate.

11. A camera system for monitoring a scene, comprising:

a light source mounted to mark a part of the scene with light having a predefined spectral content and a spatial verification pattern; and

a camera arranged to monitor the scene, the camera comprising;

a sensor arranged to sense a predefined spectral content and capture an analysis image of the scene, and

image processing circuitry configured to;

segment the analysis image, based on the predefined spectral content, to find a candidate image region,

detect a spatial pattern in the candidate image region,

compare a characteristic of the detected spatial pattern to a corresponding characteristic of a spatial verification pattern, and, if the characteristic of the detected spatial pattern and the corresponding characteristic of the spatial verification pattern match,

identify the candidate region as a verified image region corresponding to a part of the scene illuminated by a light source with light having the predefined spectral content and the spatial verification pattern,

obtain image data representing the scene, and hide image data, corresponding to the verified image region, from being displayed, by blurring or substituting, and display remaining image data, to thereby provide a privacy mask for the part of the scene which is illuminated by the light source, or display image data corresponding to the verified image region, and hide remaining image data from being displayed, by blurring or substituting, to thereby provide a privacy mask for a non-illuminated part of the scene, wherein the spatial verification pattern between at least a first and a second spatial verification pattern is modulated according to a temporal modulation sequence, and the marking, capturing, segmenting, detecting, and comparing are repeated with a respective one of the first and the second spatial verification pattern, in accordance with the temporal modulation sequence.

12. The camera system of claim 11, wherein the sensor comprises a first group of sensor elements sensitive to light having the predefined spectral content and a second group of sensor elements insensitive to light having the predefined spectral content.

13. The camera system of claim 11, further comprising a temporal modulator configured to

generate the temporal modulation sequence, and

transmit the temporal modulation sequence to the light source and the camera in a synchronized manner.