Auto-setup of a video safety curtain system

• US 6,829,371 B1
• Filed: 11/30/2000
• Issued: 12/07/2004
• Est. Priority Date: 04/29/2000
• Status: Expired due to Fees

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Schatz, David A., Silver, William, Nichani, Sanjay
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US09/728,503
• Time in Patent Office: 1,468 Days
• Field of Search: 382/103, 382/107, 382/146, 382/242, 382/243, 348/196, 348/143, 348/150, 348/151, 348/159, 348/153, 348/154, 348/155, 348/625, 348/630, 348/675, 348/708, 348/718, 348/719, 348/720, 348/721, 348/180, 348/184, 348/185, 348/211.8, 348/211.13, 348/399.1, 348/339.1, 348/252, 340/541, 340/565, 725/9, 725/10, 725/14, 725/17
• US Class Current: 382/103
• CPC Class Codes: F16P 3/142 using image capturing devices

Abstract

A two-dimensional (2-D) machine-vision safety method and apparatus performs high-integrity, high efficiency machine vision. The system digitally filters a configurable number of time-sequenced camera images of a viewed area to create a filtered image. Objects within view in a training phase are detected and compared to objects detected in a runtime phase. Each new image is then compared to the previously created model and a pixel-oriented difference image is calculated. The difference image is then processed for segmentation features attributable to an intruder object. Alarm conditions are determined from threshold parameters related to location of the intruder objects. For segmentation results that exceed a predetermined threshold, an alarm condition is set. Setup parameters are automatically generated by analysis of distinctively marked physical boundaries in an image. Automatic tools assist in optimization of setup configurations, based on size and speed of intruding objects, system response time, and camera geometry.

Claims

1. A method of determining setup parameters for a video monitoring system comprising the steps of:

installing a border pattern at a perimeter of a protection zone;

acquiring an image of a target area including at least part of said border pattern;

detecting said border pattern in said image; and

computing said setup parameters relative to said border pattern in said image.

2. The method according to claim 1 wherein the border pattern is disposed on marking tape.

3. The method according to claim 1 wherein said video monitoring system comprises a video safety curtain.

4. The method according to claim 1 further comprising the steps of:

communicating said setup parameters to a video safety curtain system; and

operating said video safety curtain system using said parameters.

5. The method according to claim 4 further comprising the step of automatically setting up said video safety curtain using said setup parameters.

6. The method according to claim 1 wherein said step of detecting said border pattern in said image is performed by a segmenting-filtering-pattern finding algorithm.

7. The method according to claim 1 wherein said step of detecting said border pattern in said image further comprises the steps of:

smoothing said image;

enhancing said pattern;

subtracting a resultant image from an original image;

binarizing said image using segmentation algorithm; and

performing a post processing routine to generate a perimeter descriptor that is suitable for use by said video monitoring system.

8. The method according to claim 7 wherein said step of smoothing said image is performed using a gaussian filter.

9. The method according to claim 7 wherein said step of enhancing said pattern is performed using a morphological open filter.

10. The method according to claim 7 wherein said step of segmentation algorithm comprises a blob filter.

11. The method according to claim 1 wherein said step of detecting said border pattern in sad image further comprises the steps of:

training a pattern finder with a synthetic model of said pattern;

finding instances of said pattern in said image using a pattern finding algorithm;

providing said instances and said pattern width to a post processor component; and

generating a perimeter descriptor suitable for use by said video monitoring system using said post processing component.

12. The method according to claim 11 wherein said pattern comprises marking tape.

13. A method of calibrating a video monitoring system comprising the steps of:

providing a calibration pattern within a field of view of camera components of said video monitoring system;

acquiring an image of said calibration pattern; and

constructing a transformation object that relates objects in physical space to locations in said image wherein the transformation object is defined by the following equations;

$C_x<br><br>\left(I_x,I_y\right)=\underset{i,j\ge <br><br>0}{\overset{i+j\le <br><br>n}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>a_{\mathrm{ij}}<br><br>I_x^i<br><br>I_y^j$$C_y<br><br>\left(I_x,I_y\right)=\underset{i,j\ge <br><br>0}{\overset{i+j\le <br><br>n}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>b_{\mathrm{ij}}<br><br>I_x^i<br><br>I_y^j$

 

wherein a_v and b_v are polynomial coefficients;

n is the degree of a polynomial transformation;

(I_x,I_y) are the image coordinates of said calibration pattern; and

(C_x,C_y) are physical coordinates of said calibration pattern.

14. The method according to claim 13 wherein said step of constructing a transformation object is performed using a CVL non-linear calibration tool.

15. A method of determining operating parameters for a video safety curtain comprising the steps of:

constraining said operation parameters to depend on a 3 dimensional shape of said protection zone;

determining a maximum distance (r_max) over which an object is capable of traveling within a protection zone prior to detection; and

providing a buffer zone distance within a protection zone perimeter and contiguous to said perimeter wherein said buffer zone distance is greater than r_max.

16. A method according to claim 15 wherein said maximum distance, r_max, depends on a speed of said object, a size of said object and a system response time.

17. A method according to claim 15 further comprising the step of:

constraining said buffer zone distance to be less than a maximum distance over which a perimeter marking pattern may be occluded to a camera by said object.

18. The method according to claim 17 wherein said maximum distance over which a perimeter marking pattern may be occluded to a camera by an object is determined by the steps of:

calculating a ratio of camera height versus minimum object height; and

multiplying said ratio by a distance between said perimeter marking pattern and a center point below said camera.

19. The method according to claim 15 further comprising the step of:

constraining a distance between a danger zone and a center point below said camera to be greater than the minimum distance between said perimeter marking pattern minus said maximum distance over which an object is capable of traveling within a protection zone prior to detection.