Dual sensor system and related data manipulation methods and uses

• US 9,685,065 B2
• Filed: 01/02/2014
• Issued: 06/20/2017
• Est. Priority Date: 01/03/2013
• Status: Expired due to Fees

• Current Assignee: Sensolid BVBA
• Original Assignee: Sensolid BVBA
• Inventors: Diels, Roger
• Primary Examiner(s): FILE, ERIN M
• Application Number:
  US14/759,221
• Publication Number:
  US 20150379851A1
• Time in Patent Office: 1,265 Days
• 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 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors

Abstract

The invention relates to sensor systems and related data manipulation methods and software and use thereof, for instance amongst others, in surveillance systems, e.g. fall detection, more in particular systems and methods for capturing data of a scene is provided, comprising a first sensor, providing a first data set; a second sensor, spatially arranged with respect to the first sensor in a predetermined arrangement, the second sensor providing a second data set; and data manipulation means using said first and/or second data set to support enhanced data computations on one or both of said data sets to generate said scene data.

Claims

1. A system for capturing data of a scene, the system comprising:

a. a first sensor, measuring temperature, providing a first data set provided in an array format;

b. a second sensor, measuring distance, providing a second data set provided in an array format; and

c. data manipulation means using at least said second data set to support enhanced data computations performed on the first data set to adapt the first data set by filtering or averaging first data set pixels to generate said scene data;

wherein said adapting of part of said first data set is based on recalculating part of said data set by filtering first data set pixels, wherein as part of said adapting of part of said first data set the original pixel temperature data in said first data set is split in a plurality of depth neighborhood class temperatures, based on said second data set.

2. The system of claim 1, further comprising determining confidence information of the temperature of pixels within said depth neighborhood classes;

and use of said confidence information for said adapting of part of said first data set.

3. The system of claim 1, wherein one or more of said adapted first data set pixels of which one or more is part of said depth neighborhood class temperatures, is adapted based on recalculating part of said data set by an inverse weighted averaging, the inverse weighting being based on the distance as seen in the second data set, in combination with filtering first data set pixels.

4. The system of claim 1, wherein said first sensor is an absolute DC temperature device.

5. The system of claim 1, wherein said first sensor is based on an array of IR thermopiles and/or said first sensor is based on an array of a bolometer.

6. The system of claim 1, wherein said second sensor is an active sensor.

7. The system of claim 1, wherein said second sensor is an array of Time-of Flight device.

8. A system for capturing data of a scene, the system comprising:

a. a first sensor, measuring temperature, providing a first data set provided in an array format;

b. a second sensor, measuring distance, providing a second data set provided in an array format; and

c. data manipulation means using at least said second data set to support enhanced data computations performed on the first data set to adapt the first data set by filtering or averaging first data set pixels to generate said scene data;

wherein said adapting of part of said first data set is based on recalculating part of said data set by filtering first data set pixels;

wherein said adapting of part, or whole, of said first data set is based on recalculating part of said data set by weighted averaging first data set pixels, whereby the weight factors are based on said second data set;

wherein the data manipulation means is capable to distinguish a plurality of objects, based on said second data set;

wherein said adapting of part of said first data set is based on recalculating part of said data set by assigning energy contributions in the first data set to objects, said assigning being based on said second data set.

9. The system of claim 8, wherein said recalculating takes into account past data.

10. The system of claim 8 wherein said recalculating takes into account temperature dynamic properties of objects.

11. The system of claim 8, wherein said first sensor is an absolute DC temperature device.

12. The system of claim 8, wherein said first sensor is based on an array of a IR thermopiles and/or said first sensor is based on an array of a bolometer.

13. The system of claim 8, wherein said second sensor is an active sensor.

14. The system of claim 8, wherein said second sensor is an array of Time-of Flight device.