VEHICLE IDENTIFICATION METHODS AND SYSTEMS

• US 20170294118A1
• Filed: 12/23/2015
• Published: 10/12/2017
• Est. Priority Date: 12/30/2014
• Status: Active Grant

• Current Assignee: Nuctech Company Limited (Tsinghua Tongfang Co., Ltd.), Tsinghua University
• Original Assignee: Nuctech Company Limited (Tsinghua Tongfang Co., Ltd.), Tsinghua University
• Inventors: Chen, Zhiqiang, Zhang, Li, Li, Jianmin, Zhao, Ziran, Liu, Yaohong, Li, Qiang, Hu, Zheng, Gu, Jianping, Li, Ying
• Granted Patent: US 10,607,483 B2
• Time in Patent Office: Days
• CPC Class Codes: G01V 5/20 Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
• CPC Class Codes: G01V 5/22 Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G08G 1/015 with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
• CPC Class Codes: G08G 1/017 identifying vehicles G08G1/015, G08G1/054 take precedence
• CPC Class Codes: G08G 1/054 photographing overspeeding vehicles

Abstract

Disclosed is a vehicle identification method and system. The method includes: acquiring appearance information of an inspected vehicle; obtaining external features of the vehicle based on the appearance information; acquiring a transmission image of the vehicle and obtaining internal features of the vehicle from the transmission image; forming descriptions on the vehicle at least based on the external features and the internal features; and determining a vehicle model of the vehicle from a vehicle model databased by utilizing the descriptions. This method merges various types of modality information, especially introducing the transmission image, and combines the internal structure information with the appearance information, so that the present disclosure can identify a vehicle model more practically.

Claims

1. A vehicle identification method comprising:

acquiring appearance information of an inspected vehicle and obtaining external features of the vehicle based on the appearance information;

acquiring a transmission image of the vehicle and obtaining internal features of the vehicle from the transmission image;

forming descriptions on the vehicle at least based on the external features and the internal features; and

determining a vehicle model of the vehicle from a vehicle model database by utilizing the descriptions.

2. The method according to claim 1, wherein said obtaining internal features of the vehicle from the transmission image comprises:

dividing the transmission image into a plurality of sub-image blocks;

performing feature extraction on the plurality of sub-image blocks; and

performing significance weighting on features of each sub-image block to form the internal features of the vehicle.

3. The method according to claim 2, wherein the vehicle'"'"'s head has significance larger than that of the vehicle'"'"'s side.

4. The method according to claim 1, wherein said appearance information includes contour information obtained by using an infrared sensor and face information and chassis information of the vehicle obtained using a visible light sensor, and the external features include contour features based on the contour information, face features based on the face information and chassis features based on the chassis information.

5. The method according to claim 4, wherein the vehicle is identified by using the contour features, the face features and the chassis features in sequence.

6. The method according to claim 2, wherein a bag-of-word model based feature extraction is performed on the plurality of sub-image blocks, and local significance weighting is performed on the extracted bag-of-word model features to form perspective features by means of concatenation or direct summation.

7. The method according to claim 4, wherein a gradient operation is applied on the chassis image to form a gradient image, and then local projection features of the gradient image are used as the chassis features.

8. The method according to claim 7, wherein the gradient image is divided into a plurality of sub-image blocks, and a horizontal projection, a vertical projection and/or a slanting projection of the sub-image blocks are calculated, respectively, to form feature vectors as the chassis features.

9. A vehicle identification system comprising:

a sensor configured to sense appearance information of an inspected vehicle;

a ray scanning device configured to perform ray scanning on the inspected vehicle to acquire a transmission image of the vehicle; and

an information processing device configured to obtain external features of the vehicle based on the appearance information, to obtain internal features of the vehicle from the transmission image, to form descriptions on the vehicle at least based on the external features and the internal features, and to determine a vehicle model of the vehicle from a vehicle model database by utilizing the descriptions.

10. The vehicle identification system according to claim 9, wherein the information processing device is further configured to divide the transmission image into a plurality of sub-image blocks, perform feature extraction on the plurality of sub-image blocks, and perform significance weighting on features of each sub-image block to form the internal features of the vehicle.

11. The vehicle identification system according to claim 10, wherein the vehicle'"'"'s head has significance larger than that of the vehicle'"'"'s side.

12. The vehicle identification system according to claim 9, wherein said appearance information includes contour information obtained by using an infrared sensor and face information and chassis information of the vehicle obtained using a visible light sensor, and the external features include contour features based on the contour information, face features based on the face information and chassis features based on the chassis information.

13. A vehicle identification method comprising:

acquiring appearance information of an inspected vehicle and obtaining external features of the vehicle based on the appearance information;

acquiring a transmission image of the vehicle and obtaining internal features of the vehicle from the transmission image;

forming descriptions on the vehicle at least based on the external features and the internal features;

determining a vehicle model of the vehicle from a vehicle model database by utilizing the descriptions;

determining a standard transmission image of the model from a database by utilizing the determined model; and

determining whether there is an entrainment in the vehicle by comparing the transmission image of the inspected vehicle with the standard transmission image.

14. The method according to claim 13, further comprising:

determining a change region of the transmission image of the inspected vehicle relative to the standard transmission image; and

presenting the change region to the user.

15. The method according to claim 14, wherein said determining a change region of the transmission image of the inspected vehicle relative to the standard transmission image comprises:

performing a registration on the transmission image of the inspected vehicle and the standard transmission image; and

calculating a difference between the transmission image of the inspected vehicle and the standard transmission image.

16. The method according to claim 15, wherein said presenting the change region to the user comprises:

highlighting the change region on the transmission image.