Vehicle bottom flying spot scanning method
阅读说明：本技术 一种车底飞点扫描方法 (Vehicle bottom flying spot scanning method ) 是由 熊凯 韩畅 沈海平 于 2020-06-10 设计创作，主要内容包括：本发明公开了一种车底飞点扫描方法,包括：扫描待扫描车辆底部,并获取所述待扫描车辆底部在二维方向上X射线背散射的多段二维强度分布信息；通过重构图像算法模块将多段二维强度分布信息重构得到所述待扫描车辆的整体图像信息。本发明中可通过斩波轮产生飞点,对待扫描车辆底部进行Y轴方向的一维扫描,同时待扫描车辆以正常速度从飞点扫描装置上方驶过,从而产生X轴方向的一维扫描,通过重构图像算法模块将二维强度分布信息重构得到该待扫描车辆的整体图像信息。本发明中将飞点扫描和待扫描车辆的运动相结合以降低扫描的耗时,从而提高扫描的效率,并且通过图像处理算法,对原始图像进行增强处理,提高图像的分辨率,进而提升扫描的准确率。(The invention discloses a vehicle bottom flying spot scanning method, which comprises the following steps: scanning the bottom of a vehicle to be scanned, and acquiring a plurality of sections of two-dimensional intensity distribution information of X-ray backscattering of the bottom of the vehicle to be scanned in a two-dimensional direction; and reconstructing the multi-section two-dimensional intensity distribution information through a reconstructed image algorithm module to obtain the integral image information of the vehicle to be scanned. In the invention, flying spots can be generated through the chopper wheel, one-dimensional scanning in the Y-axis direction is carried out on the bottom of the vehicle to be scanned, meanwhile, the vehicle to be scanned passes through the flying spot scanning device at a normal speed, so that one-dimensional scanning in the X-axis direction is generated, and the overall image information of the vehicle to be scanned is obtained by reconstructing the two-dimensional intensity distribution information through the reconstructed image algorithm module. According to the invention, flying spot scanning and the motion of a vehicle to be scanned are combined to reduce the time consumption of scanning, so that the scanning efficiency is improved, and the original image is enhanced through an image processing algorithm, so that the resolution of the image is improved, and the scanning accuracy is further improved.)
1. A method for scanning flying spots at the bottom of a vehicle is characterized by comprising the following steps:
scanning the bottom of a vehicle to be scanned, and acquiring a plurality of sections of two-dimensional intensity distribution information of X-ray backscattering of the bottom of the vehicle to be scanned in a two-dimensional direction;
and reconstructing the multi-section two-dimensional intensity distribution information through a reconstructed image algorithm module to obtain the integral image information of the vehicle to be scanned.
2. The vehicle bottom flying spot scanning method according to claim 1, wherein the two-dimensional directions of the plurality of pieces of two-dimensional intensity distribution information include an X direction and a Y direction, the X direction is a traveling direction of the vehicle to be scanned, and the Y direction is a direction perpendicular to the traveling direction of the vehicle to be scanned.
3. The vehicle bottom flying spot scanning method of claim 2, wherein the obtaining of the multi-segment two-dimensional intensity distribution information comprises:
generating scanning flying spots through a rotating chopper wheel, and performing one-dimensional scanning on the bottom of a vehicle to be scanned in the Y-axis direction; and
meanwhile, when the vehicle to be scanned runs through the chopper wheel, one-dimensional scanning in the X-axis direction is generated.
4. The vehicle bottom flying spot scanning method according to claim 3, wherein the obtaining of the scanning flying spot comprises:
the X-ray source emits an X-ray beam;
the X-ray beam passes through a pre-collimating slit arranged between the X-ray source and the chopper wheel and then passes through the rotary chopper wheel, thereby generating scanning flying spots.
5. The vehicle bottom flying spot scanning method according to any one of claims 1 to 4, wherein if the moving speed of the vehicle to be scanned is large, interpolation reconstruction calculation is performed through direct correlation of pixel points, the direct interval of scanning lines is shortened, and the resolution of an image is increased.
6. The vehicle bottom flying spot scanning method according to claim 5, wherein after obtaining the overall image information of the vehicle to be scanned, the method further comprises:
and performing enhancement processing on the image, and displaying the whole image information.
7. The vehicle bottom flying spot scanning method according to claim 6, wherein after obtaining the overall image information of the object to be scanned, the method further comprises:
and identifying contraband image information in the whole image information.
8. The vehicle bottom flying spot scanning method according to claim 7, wherein said identifying the contraband image information in the whole image information comprises:
and inputting the whole image information into a neural network model, and obtaining contraband image information in the whole image information through the neural network model.
9. The vehicle bottom flying spot scanning method of claim 8, wherein the training method of the neural network model comprises the following steps:
and taking the whole image sample and the contraband standard image contained in the whole image sample as training samples to train the neural network model.
10. The vehicle bottom flying spot scanning method according to claim 9, wherein after obtaining the contraband image information in the overall image information through the neural network model, the method further comprises:
third-party review is carried out on the contraband image information to obtain a review result;
when the rechecking result shows that the contraband image information is error information, correcting the contraband image information to obtain correct contraband image information; and
and taking the whole image information and the correct contraband image information as training samples to train the neural network model again.
Technical Field
The invention belongs to the technical field of security inspection, and particularly relates to a scanning method for flying spots at the bottom of a vehicle.
Background
In recent years, the electronic commerce development of China is witnessed rapidly, the rapid and efficient development of the logistics express industry is promoted, and the combination of the network and the express brings brand-new convenient life to people. In 2017, the total express delivery amount in China exceeds 400 hundred million, and occupies half of the total amount of the whole world. However, with the development of blowout type in logistics express industry, and many express enterprises adopt franchised operation mode, it is difficult for enterprises to check all network points for receiving and distributing. The logistics express industry increases the supervision on the package and the potential safety hazard investigation, and is very urgent. As the countries with the first fast quantity in the world nowadays, the system has extremely important significance for the fast, comprehensive and accurate security inspection technology of logistics express delivery.
On the other hand, border areas are often accompanied by a large number of inbound and outbound people streams and import and export goods transportation, and it is very important for accompanying luggage of inbound and outbound personnel, mailed inbound and outbound letters, packages, even imported and outbound containers and goods, and introduction of security check related equipment.
The X-ray has strong penetrating power, and the detection technology of the X-ray has important application in the fields of security inspection and nondestructive detection. The traditional security inspection and nondestructive detection technology is X-ray fluoroscopy, and is based on the attenuation principle of substances to X-rays. In the field of security inspection, drugs and explosives are low-atomic-number and low-density organic matters, and are attenuated very weakly to X-rays and are almost transparent, so that the detection effect of the perspective technology is very poor. In the field of nondestructive testing, perspective has a good testing effect on small parts, but large metal parts have poor imaging contrast due to strong attenuation effect, such as testing cracks, damages and the like on the surface layer of aviation parts. Therefore, it is necessary to develop a new detection technology to enrich the means of contraband pursuit and nondestructive detection and improve the accuracy and precision of detection.
Therefore, it is necessary to develop a new detection technology to enrich the means of contraband pursuit and nondestructive detection and improve the accuracy and precision of detection.
Disclosure of Invention
The invention provides a scanning method for flying spots at the bottom of a vehicle, which improves the security inspection efficiency and accuracy.
The technical scheme of the invention is as follows: a vehicle bottom flying spot scanning method comprises the following steps:
scanning the bottom of a vehicle to be scanned, and acquiring a plurality of sections of two-dimensional intensity distribution information of X-ray backscattering of the bottom of the vehicle to be scanned in a two-dimensional direction;
and reconstructing the multi-section two-dimensional intensity distribution information through a reconstructed image algorithm module to obtain the integral image information of the vehicle to be scanned.
Preferably, the two-dimensional directions of the plurality of pieces of two-dimensional intensity distribution information include an X direction and a Y direction, the X direction is a traveling direction of the vehicle to be scanned, and the Y direction is a direction perpendicular to the traveling direction of the vehicle to be scanned.
Preferably, the acquiring the plurality of pieces of two-dimensional intensity distribution information includes:
generating scanning flying spots through a rotating chopper wheel, and performing one-dimensional scanning on the bottom of a vehicle to be scanned in the Y-axis direction; and
meanwhile, when the vehicle to be scanned runs through the chopper wheel, one-dimensional scanning in the X-axis direction is generated.
Preferably, the acquiring of the scanning flying spot comprises:
the X-ray source emits an X-ray beam;
the X-ray beam passes through a pre-collimation slit arranged between the X-ray source and the chopper wheel and then passes through the rotary chopper wheel, thereby generating scanning flying spots.
Preferably, if the motion speed of the vehicle to be scanned is large, interpolation reconstruction calculation is performed through direct correlation of pixel points, the direct interval of scanning lines is shortened, and the resolution of the image is increased.
Preferably, after obtaining the overall image information of the vehicle to be scanned, the method further includes:
and performing enhancement processing on the image, and displaying the whole image information.
Preferably, after obtaining the overall image information of the object to be scanned, the method further includes:
and identifying contraband image information in the whole image information.
Preferably, the identifying the contraband image information in the whole image information includes:
and inputting the whole image information into a neural network model, and obtaining contraband image information in the whole image information through the neural network model.
Preferably, the training method of the neural network model includes:
and taking the whole image sample and the contraband standard image contained in the whole image sample as training samples to train the neural network model.
Preferably, after obtaining the contraband image information in the whole image information through the neural network model, the method further includes:
third-party review is carried out on the contraband image information to obtain a review result;
when the rechecking result shows that the contraband image information is error information, correcting the contraband image information to obtain correct contraband image information; and
and taking the whole image information and the correct contraband image information as training samples to train the neural network model again.
Compared with the prior art, the invention has the beneficial effects that:
in the invention, flying spots can be generated through the chopper wheel, one-dimensional scanning in the Y-axis direction is carried out on the bottom of the vehicle to be scanned, and meanwhile, the vehicle to be scanned passes through the flying spot scanning device at a normal speed, so that one-dimensional scanning in the X-axis direction is generated. And finally, acquiring the data information of the back scattering intensity of the X-ray of the vehicle to be scanned, and then reconstructing the two-dimensional intensity distribution information through a reconstruction image algorithm module to obtain the whole image information of the vehicle to be scanned. According to the invention, flying spot scanning and the motion of a vehicle to be scanned are combined to reduce the time consumption of scanning, so that the scanning efficiency is improved, and the original image is enhanced through an image processing algorithm, so that the resolution of the image is improved, and the scanning accuracy is further improved.
Drawings
Fig. 1 is a flowchart illustrating a vehicle bottom flying spot scanning method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a vehicle bottom flying spot scanning device according to an embodiment of the present invention.
Fig. 3 is a schematic view illustrating a distribution of scan lines according to an embodiment of the invention.
Fig. 4 is a flowchart of a vehicle bottom flying spot scanning method according to another embodiment of the present invention.
Fig. 5 is a flowchart of a vehicle bottom flying spot scanning method according to another embodiment of the present invention.
Fig. 6 is a flowchart of a vehicle bottom flying spot scanning method according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Further, in the exemplary embodiments, since the same reference numerals denote the same components having the same structure or the same steps of the same method, if an embodiment is exemplarily described, only a structure or a method different from the already described embodiment is described in other exemplary embodiments.
Throughout the specification and claims, when an element is referred to as being "connected" to another element, the element may be "directly connected" to the other element or "electrically connected" to the other element through a third element. Furthermore, unless explicitly described to the contrary, the term "comprising" and its corresponding terms should only be taken as including the stated features, but should not be taken as excluding any other features.
Fig. 1 is a flowchart of a vehicle bottom flying spot scanning method according to an embodiment of the present disclosure. As shown in fig. 1, the scanning method for the flying spots at the bottom of the train comprises the following steps:
step 110: scanning a vehicle to be scanned and acquiring data information of the back scattering intensity of X-rays at the bottom of the vehicle to be scanned.
As shown in fig. 2, which is a schematic structural diagram of a vehicle bottom flying spot scanning device provided in an embodiment of the present application, the vehicle bottom flying spot scanning device includes: the X-ray detector comprises a
In an embodiment, the
In one embodiment, as shown in fig. 2, the
In one embodiment, as shown in fig. 2, a driving device 14 may be disposed on the supporting side plate 13, the driving device 14 is connected to the
In an embodiment, as shown in fig. 2, the drive means 14 and the
In one embodiment, as shown in fig. 2, the
In one embodiment, the
In an embodiment, as shown in fig. 2, the flying spot scanning apparatus may include at least two X-ray detectors 6, and the two X-ray detectors 6 are arranged on the upper end of the
Step 120: and reconstructing the two-dimensional intensity distribution information through a reconstructed image algorithm module to obtain the whole image information of the vehicle to be scanned.
Fig. 3 is a schematic view illustrating a distribution of scan lines according to an embodiment of the present application. In this embodiment, flying spots are generated by chopper wheels, and one-dimensional scanning in the Y-axis direction is performed on the bottom of the vehicle to be scanned, while the vehicle to be scanned passes over the flying spot scanning device at a normal speed, thereby generating one-dimensional scanning in the X-axis direction. The two act together to produce a scan line profile as shown in figure 3. By sampling the scan lines at an appropriate frequency, the distribution of pixel points at corresponding positions can be obtained. If the vehicle movement speed is large, interpolation reconstruction calculation can be carried out through direct correlation of pixel points, the direct interval of scanning lines can be shortened, and the resolution of images is increased. It should be understood that, in the embodiment of the present application, different reconstruction algorithms may also be selected according to different actual application scenes, as long as the selected reconstruction algorithm can meet the image reconstruction requirement, and the specific algorithm for image reconstruction is not limited in the embodiment of the present application.
Fig. 4 is a flowchart illustrating a vehicle bottom flying spot scanning method according to another embodiment of the present disclosure. As shown in fig. 4, after
step 130: the original scanned image obtained in
After the information of the whole image of the vehicle to be scanned is obtained through combination, the whole image of the vehicle to be scanned can be displayed through the display device, and therefore whether the vehicle to be scanned carries contraband or not is judged according to the whole image. In an embodiment, step 130 may specifically include: the original image is denoised by a Gaussian filtering algorithm, the image is enhanced by a self-adaptive contrast enhancement algorithm, and the visibility of the X-ray backscatter image is improved by pseudo-color enhancement.
Fig. 5 is a flowchart illustrating a vehicle bottom flying spot scanning method according to another embodiment of the present disclosure. As shown in fig. 5, after
step 140: and identifying contraband image information in the overall image information.
The dangerous goods contained in the vehicle to be scanned can be automatically identified by providing an automatic identification device to assist the manual inspection. In an embodiment, the automatic identification device may include a neural network model, specifically, the neural network model may include a deep learning neural network model, and the specific implementation manner of
Fig. 6 is a flowchart illustrating a vehicle flying spot scanning method according to another embodiment of the present application. As shown in fig. 6, after
step 150: and carrying out third-party review on the contraband image information to obtain a review result.
When the neural network model identifies that the contraband image information exists, particularly at the initial stage of the neural network model identification, the identification precision and reliability of the neural network model are still to be determined, third-party review, such as manual review, can be performed on the contraband image information, and a review result is given.
Step 160: and when the rechecking result shows that the contraband image information is error information, correcting the contraband image information to obtain correct contraband image information.
And when the rechecking result shows that the contraband image information is the error information, the third party corrects the error contraband image information to obtain correct contraband image information, for example, when the position of the contraband marked by the neural network model is deviated, the correct position of the contraband is marked, and for example, when the position of the contraband marked by the neural network model does not have the contraband, the corresponding mark can be deleted.
Step 170: and taking the whole image information and the correct contraband image information as training samples to train the neural network model again.
And (4) retraining the neural network model by taking the correct contraband image information and the corresponding overall image information corrected by the third party as training samples so as to further improve the identification precision of the neural network model. It should be understood that, in the embodiment of the present application, a specific method for automatic identification may be selected according to requirements of an actual application scenario, for example, an article to be automatically identified may also be extracted in an image identification manner and compared with a standard image of a dangerous good or a contraband, so as to obtain the dangerous good or the contraband in a vehicle to be scanned.
The vehicle bottom flying spot scanning method and the scanning device provided by the embodiment of the invention can be applied to security check equipment, flying spots are generated by the chopper wheel, one-dimensional scanning in the Y-axis direction is carried out on the bottom of a vehicle to be scanned, and the vehicle to be scanned passes over the flying spot scanning device at a normal speed, so that one-dimensional scanning in the X-axis direction is generated. And finally, acquiring the data information of the X-ray back scattering intensity of the vehicle to be scanned, and then reconstructing the two-dimensional intensity distribution information through a reconstructed image algorithm module to obtain the whole image information of the vehicle to be scanned. The flying spot scanning and the motion of the vehicle to be scanned are combined to reduce the time consumption of scanning, so that the scanning efficiency is improved, and the original image is enhanced through an image processing algorithm, so that the resolution of the image is improved, and the scanning accuracy is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, but rather as the subject matter of the invention is intended to cover all modifications, equivalents and alternatives falling within the spirit and scope of the invention.
- 上一篇：一种医用注射器针头装配设备
- 下一篇：一种高通量合金制备、表征及成分设计方法