Vehicle inspection methods and systems

• US 10,289,699 B2
• Filed: 09/30/2016
• Issued: 05/14/2019
• 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, Zhao, Ziran, Liu, Yaohong, Gu, Jianping, Hu, Zheng, Li, Qiang
• Primary Examiner(s): Liu, Li
• Application Number:
  US15/282,134
• Publication Number:
  US 20170017667A1
• Time in Patent Office: 956 Days
• CPC Class Codes: G01N 2223/401 image processing
• CPC Class Codes: G01N 2223/631 large structures, walls
• CPC Class Codes: G01N 23/04 and forming images of the material
• 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: G06F 16/54 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/10116 X-ray image
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06V 2201/05 Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

A vehicle inspection method and system are disclosed. In one aspect, the method includes acquiring a transmission image of an inspected vehicle. The method further includes acquiring a transmission image template of a vehicle model corresponding to the model of the inspected vehicle from a database. The method further includes performing registration on the transmission image of the inspected vehicle and the transmission image template. The method further includes determining a difference between a transmission image after the registration and a transmission image template after the registration, to obtain a difference area of the transmission image of the vehicle relative to the transmission image template. The method further includes processing the difference area to determine whether the vehicle carries a suspicious object or not. In some embodiments, this solution can avoid the problems of a detection loophole and a poor effect of manually determining an image in a conventional manner, and is important to assist the security inspection for small vehicles.

Claims

1. A vehicle inspection method comprising:

acquiring a transmission image of vehicle;

removing parts of the transmission image that are outside an inspected vehicle in the transmission image to obtain a transmission image of the inspected vehicle;

acquiring from a database a transmission image template of a vehicle model that is the same as that of the inspected vehicle;

performing registration on the transmission image of the inspected vehicle with the transmission image template to obtain a registered transmission image;

determining a difference between the registered transmission image and the transmission image template, to obtain a change area of the transmission image of the vehicle relative to the transmission image template; and

processing the change area to determine whether the vehicle carries a suspected object;

wherein the removing parts of the transmission image comprises;

removing strip in the transmission image of the vehicle to obtain an image having a changing background;

obtaining a gradient map for the image having the changing background and quantizing the gradient map to obtain a binary quantized gradient map;

obtaining a largest continuous region in a horizontal projection and a vertical projection in the binary quantized gradient map; and

removing parts outside the largest continuous region in the transmission image of the vehicle to obtain the transmission image of the inspected vehicle, and

wherein the method is performed by at least one processor.

2. The vehicle inspection method according to claim 1, wherein said acquiring from a database a transmission image template of a vehicle model that is the same as that of the inspected vehicle comprises:

retrieving the transmission image template of the vehicle model from the database based on a unique identifier of the inspected vehicle.

3. The vehicle inspection method according to claim 1, wherein said acquiring from a database a transmission image template of a vehicle model that is the same as that of the inspected vehicle comprises:

extracting information on an internal structure of the vehicle from the transmission image, and retrieving the transmission image template of the vehicle model from the database based on the information on the internal structure as well as information on external features of the vehicle.

4. The vehicle inspection method according to claim 1, wherein said performing rigid registration comprises:

performing feature extraction on the transmission image and the transmission image template to obtain feature points;

finding a pair of matched feature points through similarity measurement;

obtaining image spatial coordinate transformation parameters based on the pair of matched feature points; and

performing image registration on the image spatial coordinate transformation parameters,

and wherein said performing elastic registration comprises;

performing non-linear registration on the transmission image and the transmission image template so as to reduce the effects of three dimensional deformation by removing local deformation, wherein the elastic registration is pixel based and feature based.

5. The vehicle inspection method according to claim 1, further comprising:

marking the suspected object in the change area.

8. The vehicle inspection method according to claim 1, wherein said performing registration on the transmission image of the inspected vehicle with the transmission image template comprises:

performing rigid registration on the transmission image of the inspected vehicle with the transmission image template to obtain a transmission image performed rigid registration;

wherein the transmission image performed rigid registration is aligned with the transmission image template by a global transformation;

performing normalization on gray levels of the transmission image performed rigid registration; and

performing elastic registration on the normalized transmission image performed rigid registration to obtain the registered transmission image without local deformation after the registration.

6. A vehicle inspection system, comprising a processor configured to:

acquire a transmission image of an inspected vehicle;

remove parts of the transmission image that are outside the inspected vehicle in the transmission image to obtain a transmission image of the inspected vehicle;

acquire a transmission image template of a vehicle model the same as that of the inspected vehicle from a database,

perform registration on the transmission image of the inspected vehicle with the transmission image template to obtain a registered transmission image,

determine a difference between the registered transmission image and the transmission image template to obtain a change area of the transmission image of the inspected vehicle relative to the transmission image template, and

process the change area to determine whether the inspected vehicle carries a suspected object or not;

wherein the processor is further configured to;

remove strip in the transmission image of the inspected vehicle to obtain an image having a changing background;

obtain a gradient map for the image having the changing background and quantize the gradient map to obtain a binary quantized gradient map;

obtain a largest continuous region in a horizontal projection and a vertical projection in the binary quantized gradient map; and

remove parts outside the largest continuous region in the transmission image of the vehicle to obtain the transmission image of inspected vehicle.

7. The vehicle inspection system according to claim 6, wherein the processor is further configured to:

extract information on an internal structure of the vehicle from the transmission image; and

retrieve the transmission image template of the vehicle model from the database based on the information on the internal structure as well as information on external features of the vehicle.