AUTOMATED VEHICLE RECOGNITION

• US 20150371109A1
• Filed: 01/17/2014
• Published: 12/24/2015
• Est. Priority Date: 01/17/2013
• Status: Abandoned Application

• Current Assignee: SenSen Networks Pty., Ltd. (SenSen Networks Ltd.)
• Original Assignee: SenSen Networks Pty., Ltd. (SenSen Networks Ltd.)
• Inventors: Challa, Subhash, Vo, Nhat Dinh Minh
• Application Number:
  US14/761,937
• Publication Number:
  US 20150371109A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

A system for identifying a vehicle. A camera obtains at least one image of a vehicle. An image processor derives from the image a first sub-image and a second sub-image distinct from the first sub-image, extracts from the first sub-image a first set of image features, and extracts from the second sub-image a second set of image features. The image processor matches the first set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a first matching score, and also matches the second set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a second matching score. The image processor then fuses the first matching score and the second matching score to produce a fused score which indicates whether the at least one image is of the same vehicle as the previously obtained image.

Claims

1. A method of identifying a vehicle, the method comprising:

obtaining from at least one camera at least one image of a vehicle;

using an image processor to derive from the at least one image a first sub-image and a second sub-image distinct from the first sub-image;

extracting from the first sub-image a first set of image features;

extracting from the second sub-image a second set of image features;

matching the first set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a first matching score;

matching the second set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a second matching score; and

fusing the first matching score and the second matching score to produce a fused score which indicates whether the at least one image is of the same vehicle as the previously obtained image.

2. The method of claim 1 wherein the first and second sub-images comprise two of:

a vehicle license plate sub-image, a vehicle logo sub-image, and a vehicle region of interest sub-image.

3. The method of claim 1 wherein the first and second sub-images, together with a third sub-image, comprise a vehicle license plate sub-image, a vehicle logo sub-image, and a vehicle region of interest sub-image.

4. The method of claim 1 wherein the sub-images comprise wholly distinct sub-areas of the at least one obtained image.

5. The method of claim 1 wherein the region of interest comprises one or more of:

a vehicle fender;

a vehicle panel and a license plate.

6. The method of claim 1 wherein each set of image features comprises image features which are tolerant to image translation, scaling, and rotation.

7. The method of claim 1 wherein extracting the first and/or second set of image features comprises a first step of coarse localisation of feature key points in the respective sub-image.

8. The method of claim 7 wherein the localised feature key points have a well-defined position in image space and have a local image structure which is rich in local information.

9. The method of claim 7 wherein the feature key points are localised by convolution with a box filter.

10. The method of claim 7 wherein the first and/or second set of image feature points are vetted in order to eliminate unqualified feature points.

11. The method of claim 7 wherein at least one descriptor of each key point is obtained.

12. The method of claim 11 wherein the or each descriptor is at least partly invariant to changes in scaling and rotation.

13. The method of claim 1 wherein matching the first set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a first matching score comprises applying distance matching and voting techniques in order to determine the match between the descriptors of one feature key point of the first set of image features to the descriptors of a corresponding feature key point in the previously obtained image.

14. The method of claim 1 further comprising assessing geometric alignment of feature points to reduce false matching of feature points.

15. The method of claim 1 wherein the vehicle is imaged while passing a toll booth, at a parking location or in motion on a road.

16. The method of claim 1 further comprising fusion of features identified in a plurality images obtained of the vehicle.

17. A system for identifying a vehicle, the system comprising:

at least one camera for obtaining at least one image of a vehicle; and

an image processor for

deriving from the at least one image a first sub-image and a second sub-image distinct from the first sub-image;

extracting from the first sub-image a first set of image features;

extracting from the second sub-image a second set of image features;

matching the first set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a first matching score;

matching the second set of image features to corresponding image features derived from a previously obtained image of a vehicle to produce a second matching score; and

fusing the first matching score and the second matching score to produce a fused score which indicates whether the at least one image is of the same vehicle as the previously obtained image.