Claims:WE CLAIM
1. A method for detecting objects from scene images, the method comprising:
segmenting, by an image processing device, a scene image captured by at least one camera into a plurality of image segments, wherein each of the plurality of image segments comprise a plurality of pixels;
detecting, by the image processing device, at least one object in each of the plurality of image segments;
finding, by the image processing device, a plurality of similar images from an online database based on the at least one object identified in each of the plurality of image segments;
identifying using a knowledge base engine, by the image processing device, at least one similar object in the plurality of similar images based on associated description and image characteristics;
updating, by the image processing device, the knowledge base engine based on the at least one similar object identified from the plurality of similar images; and
training, by the image processing device, a neural network to detect objects from scene images captured by the at least one camera, based on the updated knowledge base engine.
2. The method of claim 1, wherein segmenting comprises:
grouping pixels in the scene image to generate the plurality of image segments, wherein pixels in each image segment comprises same image characteristics, and wherein the image characteristics comprises at least one of color, intensity, texture, or shape; and
creating vector features for each of the plurality of image segments based on associated image characteristics.
3. The method of claim 2 further comprising assigning a label to each of the plurality of image segments based on associated image characteristics.
4. The method of claim 2, wherein the at least one object in an image segment is identified based on vector features created for the image segment.
5. The method of claim 4, wherein finding the plurality of similar images from an online database comprises:
generating a search query based on the vector features created for the image segment; and
retrieving similar images from the online database based on execution of the search query, wherein each of the similar images are retrieved along with an associated description.
6. The method of claim 1, wherein identifying the at least one similar object comprises:
assigning confidence scores to terms in description associated with the plurality of similar images;
ranking the terms based on the assigned confidence score; and
selecting at least one term as at least one class for the knowledge base engine, based on the ranking, wherein the at least one term is ranked above a threshold rank.
7. The method of claim 6, wherein updating the knowledge base engine comprises assigning each of the at least one class as a main class or a sub class based on the ranking.
8. The method of claim 1, wherein the neural network is a convolutional neural network that is trained using the updated knowledge based engine.
9. The method of claim 1 further comprising communicating, by the image processing device, information related to the detected objects to a navigation control system in an autonomous vehicle for navigation.
10. An image processing device for detecting objects from scene images, the image processing device comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
segment a scene image captured by at least one camera into a plurality of image segments, wherein each of the plurality of image segments comprise a plurality of pixels;
detect at least one object in each of the plurality of image segments;
find a plurality of similar images from an online database based on the at least one object identified in each of the plurality of image segments;
identify using a knowledge base engine, at least one similar object in the plurality of similar images based on associated description and image characteristics;
update the knowledge base engine based on the at least one similar object identified from the plurality of similar images; and
train a neural network to detect objects from scene images captured by the at least one camera, based on the updated knowledge base engine.
11. The image processing device of claim 10 further comprising the at least one camera to capture the scene image.
12. The image processing device of claim 10, wherein to segment the scene image, the processor instructions cause the processor to:
group pixels in the scene image to generate the plurality of image segments, wherein pixels in each image segment comprises same image characteristics, and wherein the image characteristics comprises at least one of color, intensity, texture, or shape; and
create vector features for each of the plurality of image segments based on associated image characteristics.
13. The image processing device of claim 12, the processor instructions cause the processor to assign a label to each of the plurality of image segments based on associated image characteristics.
14. The image processing device of claim 12, wherein the at least one object in an image segment is identified based on vector features created for the image segment.
15. The image processing device of claim 14, wherein to find the plurality of similar images from an online database, the processor instructions cause the processor to:
generate a search query based on the vector features created for the image segment; and
retrieve similar images from the online database based on execution of the search query, wherein each of the similar images are retrieved along with an associated description.
16. The image processing device of claim 10, wherein to identify the at least one similar object, the processor instructions cause the processor to:
assign confidence scores to terms in description associated with the plurality of similar images;
rank the terms based on the assigned confidence score; and
select at least one term as at least one class for the knowledge base engine, based on the ranking, wherein the at least one term is ranked above a threshold rank.
17. The image processing device of claim 16, wherein to update the knowledge base engine, the processor instructions cause the processor to assign each of the at least one class as a main class or a sub class based on the ranking.
18. The image processing device of claim 10, wherein the neural network is a convolutional neural network that is trained using the updated knowledge based engine.
19. The image processing device of claim 10, wherein the processor instructions cause the processor to communicate information related to the detected objects to a navigation control system in an autonomous vehicle for navigation.

Dated this 30th day of December, 2017

Madhusudan S.T
IN/PA-1297
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
This disclosure relates generally to detecting objects from images and more particularly to method and device for detecting objects from scene images by using dynamic knowledge base.