Method for monitoring a detection region of a working element

• US 7,065,241 B2
• Filed: 01/08/2001
• Issued: 06/20/2006
• Est. Priority Date: 01/07/2000
• Status: Expired due to Fees

• Current Assignee: Leuze electronic GmbH & Co. KG
• Original Assignee: Leuze Lumiflex GmbH & Co. KG
• Inventors: Kummert, Anton, Lehner, Werner, Velten, Jörg
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): STREGE, JOHN B
• Application Number:
  US09/755,197
• Publication Number:
  US 20010041077A1
• Time in Patent Office: 1,989 Days
• Field of Search: 382/152, 382/165, 382/103, 382110-112
• US Class Current: 382/152
• CPC Class Codes: F16P 3/142 using image capturing devices
• CPC Class Codes: G01V 8/10 Detecting, e.g. by using light barriers by reflection from the object G01S17/00
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/254 involving subtraction of images

Abstract

The invention relates to an apparatus and a method for monitoring a detection region of a working element (100). The apparatus has at least one camera for continuously monitoring the detection region, and an evaluation unit (53), into which image information generated by the camera is read. In the evaluation unit (53), a comparison of the image information to reference images, and/or a color-feature analysis, allows the detection of endangered objects within at least one protection zone in the detection region. If at least one endangered object is detected inside the protection zone, the evaluation unit (53) disables the working element (100). In contrast, if no endangered object (54) is located inside the protection zone, the evaluation unit (53) enables the working element (100).

Claims

1. A method for monitoring a detection region of a working element, the method comprising the following steps:

monitoring continuously a detection region with at least one camera;

reading image information, in the form of color values, generated in the camera during the monitoring into an evaluation unit wherein the image generated by the camera is read into the evaluation unit in the form of a pixel matrix with different color values;

distinguishing endangered objects from non-endangered objects with the evaluation unit based on the color values;

disabling the working element with the evaluation unit, if at least one endangered object is detected within at least one protection zone in the detection region; and

enabling the working element with the evaluation unit if no endangered object is located in the protection zone,

wherein the distinguishing step includes assessing the color values with a threshold-value unit; and

creating binary images based on the assessment with the threshold-value unit and wherein the assessing step comprises;

associating three color values of the base colors of red, green and blue with each pixel of the image read into the evaluation unit;

assigning the color values predetermined weight factors;

creating a linear combination from the color values using the weight factors; and

assessing the linear combination of color values with the threshold-value unit using a threshold value.

2. The method according to claim 1, wherein the threshold-value unit is a component of a neural network.

3. The method according to claim 1, further comprising, determining at least one of the threshold value and the weight factors through a learning process, in which colors of the endangered objects are established.

4. The method according to claim 1, wherein the endangered object are of a predetermined color, with the threshold value being adapted to the predetermined color.

5. A method for monitoring a detection region of a working element, the method comprising the following steps:

monitoring continuously a detection region with at least one camera;

reading image information, in the form of color values, generated in the camera during the monitoring into an evaluation unit wherein the image generated by the camera is read into the evaluation unit in the form of a pixel matrix with different color values;

distinguishing endangered objects from non-endangered objects with the evaluation unit based on the color values;

disabling the working element with the evaluation unit, if at least one endangered object is detected within at least one protection zone in the detection region;

enabling the working element with the evaluation unit if no endangered object is located in the protection zone;

forming a connected region of foreground pixels in the binary images generated by the threshold-value unit to represent the endangered objects; and

eliminating individual foreground pixels in a background around the connected region using morphological operators, wherein the distinguishing step includes assessing the color values with a threshold-value unit; and

creating binary images based on the assessment with the threshold-value unit.