Systems and methods for detecting motion based on a video pattern

Patent metadata

Field	Value
Publication number	US-10311690-B2
Application number	US-201615220996-A
Country	US
Kind code	B2
Filing date	Jul 27, 2016
Priority date	Jul 27, 2016
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

Some systems and methods for detecting motion based on a video pattern can include creating a motion image from a sequence of raw images, masking the motion image with a lens pattern associated with a PIR sensor and an associated Fresnel lens, splitting each of a plurality of blocks of the lens pattern into first and second negative areas, identifying a positive area pixel value as a sum of all pixels in the motion image aligned with the first positive area in the plurality of blocks, identifying a negative area pixel value as a sum of all pixels in the motion image aligned with the second negative area in the plurality of blocks, identifying a motion image response value as a difference between the positive and negative area pixel values, and identifying a presence of motion when the motion image response value exceeds a predetermined value.

First claim

What is claimed is:

1. A method comprising:
creating a motion image from a sequence of raw images of a region by differentiating the sequence of raw images so that the motion image includes pixels representing only portions of the sequence of raw images where there is a difference between at least one of the sequence of raw images and any subsequent ones of the sequence of raw images;
masking the motion image with a lens pattern associated with a PIR sensor and an associated Fresnel lens monitoring the region by overlaying the motion image with the lens pattern;
splitting each of a plurality of blocks of the lens pattern as overlaid on the motion image into a respective first section and a respective second section, wherein the respective first section of each of the plurality of blocks is a respective positive area associated with a first slot of the PIR sensor and the respective second section of each of the plurality of blocks is a respective negative area associated with a second slot of the PIR sensor;
identifying a positive area pixel value as a sum of all of the pixels in the motion image that are aligned with the respective positive area of each of the plurality of blocks;
identifying a negative area pixel value as a sum of all of the pixels in the motion image that are aligned with the respective negative area of each of the plurality of blocks;
subtracting the positive area pixel value and the negative area pixel value as identified from the respective positive area of each of the plurality of blocks and the respective negative area of each of the plurality of blocks of the motion image to identify a motion image response value; and
identifying a presence of motion in the region when the motion image response value exceeds a predetermined value.

2. The method of claim 1 further comprising receiving the sequence of raw images from a video imager monitoring the region.

3. The method of claim 1 further comprising receiving the lens pattern from the PIR sensor.

4. The method of claim 1 further comprising retrieving the lens pattern from a memory device.

5. The method of claim 1 further comprising identifying the presence of the motion in the region when the motion image response value exceeds the predetermined value within a predetermined period of time.

6. The method of claim 1 further comprising transmitting a signal indicative of the presence of the motion when the motion image response value exceeds the predetermined value.

7. The method of claim 1 further comprising causing activation of an alarm when the motion image response value exceeds the predetermined value.

8. A system comprising:
a programmable processor; and
executable control software stored on a non-transitory computer readable medium,
wherein the programmable processor and the executable control software create a motion image from a sequence of raw images of a region by differentiating the sequence of raw images so that the motion image includes pixels representing only portions of the sequence of raw images where there is a difference between at least one of the sequence of raw images and any subsequent ones of the sequence of raw images,
wherein the programmable processor and the executable control software mask the motion image with a lens pattern associated with a PIR sensor and an associated Fresnel lens monitoring the region by overlaying the motion image with the lens pattern,
wherein the programmable processor and the executable control software split each of a plurality of blocks of the lens pattern as overlaid on the motion image into a respective first section and a respective second section,
wherein the respective first section of each of the plurality of blocks is a respective positive area associated with a first slot of the PIR sensor and the respective second section of each of the plurality of blocks is a respective negative area associated with a second slot of the PIR sensor,
wherein the programmable processor and the executable control software identify a positive area pixel value as a sum of all of the pixels in the motion image that are aligned with the respective positive area of each of the plurality of blocks,
wherein the programmable processor and the executable control software identify a negative area pixel value as a sum of all of the pixels in the motion image that are aligned with the respective negative area of each of the plurality of blocks,
wherein the programmable processor and the executable control software subtract the positive area pixel value and the negative area pixel value as identified from the respective positive area of each of the plurality of blocks and the respective negative area of each of the plurality of blocks of the motion image to identify a motion image response value, and
wherein the programmable processor and the executable control software identify a presence of motion in the region when the motion image response value exceeds a predetermined value.

9. The system of claim 8 further comprising a transceiver device, wherein the programmable processor and the executable control software receive the sequence of images, via the transceiver device, from a video imager monitoring the region.

10. The system of claim 8 further comprising a transceiver device, wherein the programmable processor and the executable control software receive the lens pattern, via the transceiver device, from the PIR sensor.

11. The system of claim 8 further comprising a memory device, wherein the programmable processor and the executable control software retrieve the lens pattern from the memory device.

12. The system of claim 8 wherein the programmable processor and the executable control software identify the presence of the motion in the region when the motion image response value exceeds the predetermined value within a predetermined period of time.

13. The system of claim 8 further comprising a transceiver device, wherein the programmable processor and the executable control software transmit, via the transceiver device, a signal indicative of the presence of the motion when the motion image response value exceeds the predetermined value.

14. The system of claim 8 further comprising an alarm device, wherein the programmable processor and the executable control software cause the alarm device to be activated when the motion image response value exceeds the predetermined value.

Assignees

• Honeywell Int Inc
• Ademco Inc

Inventors

• Xia Xiaomin
• Wu Di
• Liu Chao
• Zhao Tianfeng

Classifications

• G08B13/19602 Primary

  Image analysis to detect motion of the intruder, e.g. by frame subtraction · CPC title

• G06V10/806

  of extracted features · CPC title

• G06V10/811

  the classifiers operating on different input data, e.g. multi-modal recognition · CPC title

• G06V20/52 Primary

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06F18/256

  of results relating to different input data, e.g. multimodal recognition · CPC title