MACHINE VISION BASED OBSTACLE AVOIDANCE SYSTEM

• US 20110050883A1
• Filed: 12/21/2009
• Published: 03/03/2011
• Est. Priority Date: 08/28/2009
• Status: Active Grant

• Current Assignee: Indian Institute of Science
• Original Assignee: Indian Institute of Science
• Inventors: Kompella, Varun Raj, Ghose, Debasish
• Granted Patent: US 8,675,060 B2
• Time in Patent Office: Days
• US Class Current: 348/113
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

Machine vision based obstacle avoidance system is provided. The system utilizes a CCD camera to capture an image. A normalized image and dynamic masking is used in object detection

Claims

1. A method of detecting an obstacle in a field of view of a mobile platform having a base structure, a drive mechanism and a machine vision system, comprising:

capturing an image in the form of a signal;

converting the signal into a digital image having a plurality of pixels and inverting the digital image;

normalizing the digital image by setting pixels in the plurality of pixels having an intensity value away from a histogram global maximum to a first predetermined intensity and setting pixels in the plurality of pixels having intensity values close to the global maximum to a second predetermined intensity;

performing edge detection on the normalized digital image, thereby outputting a bounding graph indicating edges of detected objects in the image; and

determining local maximums and zeros in the graph, and determining a dynamic mask based on said maximums and zeros, wherein the dynamic mask is applied to a second digital image to determine the presence of an object, wherein pixels having intensity value away from the global maximum of the histogram are assigned a first intensity value I₁, and pixels which have intensity values close to the global maximum, are assigned a second intensity value I₂.

2. The method of claim 1 further comprising filtering noise peaks in the bounding graph.

3. The method of claim 2 further removing a portion of the bounding graph corresponding to additional noise in the bounding graph and replacing said removed portion with a smoothed portion.

4. The method of claim 1 wherein the dynamic mask indicates an object detected in a field of view of said machine vision system, and wherein a width and a height of the dynamic mask indicate a travesability of an area corresponding to the mask.

5. The method of claim 1 further comprising partitioning the digital image into a plurality of sections and determining a location of the object by determining a section of the plurality of sections having the dynamic mask located therein.

6. The method of claim 5 further comprising sending an object avoidance signal to the drive mechanism thereby causing said base structure to avoid the detected object, wherein the object avoidance signal is based on the determined location of the object.

7. The method of claim 1 further comprising receiving the input image and generating a histogram indicating frequencies of pixel intensities of the plurality of pixels ranging from 0 to 255, wherein said histogram is used to generate a binary image by assigning pixels with predetermined intensities, and said image is used to determine an existence of an object

8. The method of claim 1 further comprising applying a second mask to the digital binary image to determine a presence of objects that are in close proximity to the base platform by looking for an intensity switch, wherein said second mask corresponds to a bottom portion of said image.

9. The method of claim 1, further comprising converting the digital image into grayscale.

10. A mobile platform comprising:

a base structure;

a drive mechanism coupled to the base structure;

a machine vision system including

an optical input module that captures an image in the form of a signal;

a pre-processing module that receives said signal from the optical input module, that converts the signal into a digital image having a plurality of pixels and that inverts the digital image;

an image normalizing module that normalizes the digital image by setting pixels in the plurality of pixels having an intensity less than a predetermined threshold to a first predetermined intensity and setting pixels in the plurality of pixels having an intensity greater than or equal to the predetermined threshold to a second predetermined intensity;

an edge detection module that receives the normalized digital image and performs edge detection the normalized digital image, thereby outputting a bounding graph indicating edges of detected objects in the image; and

a detection module that receives the bounding graph and determines local maximums and zeros in the graph, and determines a dynamic mask based on said maximums and zeros, wherein the dynamic mask is applied to a second digital image to determine the presence of an object.

11. The mobile platform of claim 10 further comprising an image filtering module that receives the bounding graph from the edge detection module and filters noise peaks in the bounding graph.

12. The mobile platform of claim 11 further comprising a clipping module that receives the bounding graph from the image filtering module and removes a portion of the bounding graph corresponding to additional noise in the bounding graph and replaces said removed portion with a smoothed portion.

13. The mobile platform of claim 10 wherein the dynamic mask indicates an object detected in a field of view of said optical input module, and wherein a width and a height of the dynamic mask indicate a travesability of an area corresponding to the mask.

14. The mobile platform of claim 10 further comprising an object detection module that partitions the digital image into a plurality of sections and determines a location of the object by determining a section of the plurality of sections having the dynamic mask located therein.

15. The mobile platform of claim 14 wherein the object detection module sends a object avoidance signal to the drive mechanism thereby causing said base structure to avoid the detected object, wherein the object avoidance signal is based on the determined location of the object.

16. The mobile platform of claim 10 further comprising a histogram generation module that receives the input image and generates a histogram indicating frequencies of pixel intensities of the plurality of pixels ranging from 0 to 255, wherein said histogram is used to generate a binary image by assigning pixels with predetermined intensities, and said image is used to determine an existence of an object

17. The mobile platform of claim 10 wherein a second mask is applied to the digital image to determine a presence of objects that are in close proximity to the optical input module, wherein said second mask corresponds to a bottom portion of said image.

18. The mobile platform of claim 10, wherein the preprocessing module converts the digital image into grayscale.

19. The mobile platform of claim 10 wherein said base structure is one of a motorized wheel chair, a wheel chair, a robotic cleaner, a robotic vacuum, and a cane.

20. A mobile platform comprising:

a base structure that is one of a motorized wheel chair, a wheel chair, a robotic cleaner, a robotic vacuum, and a cane;

a drive mechanism coupled to the base structure;

a machine vision system including;

an optical input module that captures an image in the form of a signal;

a pre-processing module that receives said signal from the optical input module, that converts the signal into a grayscale digital image having a plurality of pixels and that inverts the digital image;

an image normalizing module that normalizes the digital image by setting pixels in the plurality of pixels having an intensity less than a predetermined threshold to a first predetermined intensity and setting pixels in the plurality of pixels having an intensity greater than or equal to the predetermined threshold to a second predetermined intensity;

an edge detection module that receives the normalized digital image and performs edge detection the normalized digital image, thereby outputting a bounding graph indicating edges of detected objects in the image;

an image filtering module that receives the bounding graph from the edge detection module and filters noise peaks in the bounding graph;

a clipping module that receives the filtered bounding graph from the image filtering module and removes a portion of the filtered bounding graph corresponding to additional noise in the filtered bounding graph and replaces said removed portion with a smoothed portion;

a detection module that receives the clipped and filtered bounding graph and determines local maximums and zeros in the graph, and determines a dynamic mask based on said maximums and zeros, wherein the dynamic mask is applied to a second digital image to determine the presence of an object; and

an object detection module that partitions the second digital image into a plurality of sections and determines a location of the object by determining a section of the plurality of sections having the dynamic mask located therein.