WO2021179583A1

WO2021179583A1 - Detection method and detection device

Info

Publication number: WO2021179583A1
Application number: PCT/CN2020/118985
Authority: WO
Inventors: 雷述宇
Original assignee: 宁波飞芯电子科技有限公司
Priority date: 2020-03-10
Filing date: 2020-09-29
Publication date: 2021-09-16
Also published as: CN111308467A

Abstract

A detection method and a detection device, relating to the technical field of data detection. The method comprises: obtaining electric signals generated by multiple detection units (501) in the detection device on the basis of received echo signals, the echo signals being signals reflected by emitted radiation through a target object (S101); according to the electric signals generated by the detection units (501), obtaining first information of a target object corresponding to the detection units (501) (S102); according to the electric signals generated by the detection units (501) and the first information of the corresponding target object, obtaining second information of the target object corresponding to the detection units (501) (S103); and identifying the target object according to the second information of the target object corresponding to the detection units (501) (S104). According to the method and device, the echo signals are not only limited to distance calculation, the application range of the echo signals is effectively expanded, and the utilization rate of the echo signal is effectively improved.

Description

Detection method and detection equipment

Cross-references to related applications

This disclosure claims the priority of the Chinese patent application with the application number CN202010164772.4 and titled "Detection Method and Detection Equipment" filed with the Chinese Patent Office on March 10, 2020, the entire content of which is incorporated into this disclosure by reference.

Technical field

The present disclosure relates to the technical field of data detection, and in particular, to a detection method and detection equipment.

Background technique

Time-of-flight (TOF) sensors are generally considered to be the best distance sensors for automobiles, industries, and drones and robots. It can provide accurate distance measurement, is not affected by the size or color of the target object, nor is it disturbed by environmental noise, and can be used in direct sunlight. It mainly uses the round-trip flight time of the signal from the transmission to the reflection of the target object to be received to measure the distance of the target object.

In practical applications, in addition to obtaining object distance information, it is often necessary to make further judgments on the object, such as the shape and material of the object, so as to achieve the purpose of object recognition. The TOF sensor in the prior art mainly uses echo information to measure the distance of a target object, which has limitations in object recognition or other related applications.

Summary of the invention

The purpose of the present disclosure is to provide a detection method and detection equipment in view of the above-mentioned shortcomings in the prior art, so as to solve the problem of relatively limited application of echo information and low utilization rate in the prior art.

To achieve the foregoing objectives, the technical solutions adopted in the embodiments of the present application are as follows:

In the first aspect, an embodiment of the present application provides a detection method, and the method includes:

Acquiring electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected by the target object from the emitted radiation;

Obtaining the first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit;

Obtaining second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object, where the second information is used to reflect the attribute of the corresponding target object;

Identify the target object according to the second information of the target object corresponding to each detection unit.

Optionally, the obtaining the second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object includes:

Obtaining the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit;

According to the first information and the energy corresponding to each detection unit, the second information of the target object is obtained according to a preset function or preset parameter.

Optionally, the first information is distance, and the second information is reflectivity;

The preset parameters include: the emission energy of the emitted radiation, the fill factor of the detection device, the radiation attenuation coefficient corresponding to the distance of each detection unit, and the echo energy reflected by the target object enters each station. The ratio of the detection unit.

Optionally, before the obtaining the second information of the target object according to a preset function or a preset parameter according to the first information and the energy corresponding to each detection unit, the method further includes:

According to the distance corresponding to each detection unit, a preset distance attenuation model corresponding to the wavelength of the emitted radiation is used to obtain a radiation attenuation coefficient corresponding to the distance of each detection unit.

According to the distance corresponding to each detection unit and the diameter of the receiving lens in the detection device, the ratio of the echo energy reflected by the target object into each detection unit is obtained.

Optionally, the first information is distance, and the second information is reflectivity; the identifying the target object according to the second information of the target object corresponding to each detection unit includes:

Obtain a two-dimensional map of the reflectivity of the target object according to the reflectivity of the target object corresponding to each detection unit, and identify the target object according to the two-dimensional map of reflectivity; or,

Fuse the reflectivity of the target object corresponding to each detection unit with the distance corresponding to the corresponding detection unit to obtain a three-dimensional map of the reflectivity, and identify the target object according to the three-dimensional map of reflectivity; or,

The material of the target object is identified according to the reflectance of the target object corresponding to the plurality of detection units and the preset correspondence between the material of the object and the reflectance.

Optionally, the first information is distance, and the second information is reflectivity; the recognizing the target object according to the two-dimensional reflectivity includes:

Performing image recognition on the two-dimensional map of reflectivity according to a pre-trained two-dimensional image recognition model to obtain the category and/or contour of the target object;

The two-dimensional image recognition model is a model obtained by training using preset two-dimensional maps of the reflectance of sample objects of different materials;

The recognizing the target object according to the three-dimensional map of reflectivity includes:

Performing image recognition on the three-dimensional map of reflectivity according to a pre-trained three-dimensional image recognition model to obtain the category and/or contour of the target object;

The three-dimensional image recognition model is a model obtained by training using preset three-dimensional maps of the reflectance of sample objects of different materials.

The recognizing the target object according to the second information of the target object corresponding to each detection unit includes:

Obtaining a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognizing the target object according to the three-dimensional image, and obtaining a first recognition result;

According to the reflectivity of the target object corresponding to each detection unit and the first recognition result, a second recognition result is obtained.

In a second aspect, an embodiment of the present application also provides a detection device, the detection device including: a detection unit, a first processing unit, a second processing unit, and an identification unit;

The detection unit is configured to obtain electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected from the target object by the emitted radiation;

The first processing unit is configured to obtain first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit;

The second processing unit is configured to obtain the second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object, and the second information is used for To reflect the attributes of the corresponding target object;

The recognition unit is configured to recognize the target object according to the second information of the target object corresponding to each detection unit.

Optionally, the second processing unit is specifically configured to obtain the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit; The first information and the energy obtain the second information of the target object according to a preset function or preset parameter.

Optionally, the device further includes a third processing unit;

The third processing unit is configured to use a preset distance attenuation model corresponding to the wavelength of the emitted radiation according to the distance corresponding to each detection unit to obtain a radiation attenuation coefficient corresponding to the distance of each detection unit; It is configured to obtain the ratio of echo energy reflected by the target object into each detection unit according to the distance corresponding to each detection unit and the diameter of the receiving lens in the detection device.

Optionally, the first information is the distance, and the second information is the reflectivity; the identification unit is specifically configured to obtain the reflectivity of the target object according to the reflectivity of the target object corresponding to each detection unit And identify the target object according to the two-dimensional map of reflectivity; alternatively, the reflectivity of the target object corresponding to each detection unit is merged with the distance corresponding to the corresponding detection unit, Obtain the three-dimensional map of the reflectivity, and identify the target object according to the three-dimensional map of the reflectivity; or, according to the reflectivity of the target object corresponding to the multiple detection units, and the preset material and reflection of the object The corresponding relationship of the rate is used to identify the material of the target object.

Optionally, the first information is the distance, and the second information is the reflectance;

The recognition unit is specifically configured to perform image recognition on the two-dimensional map of reflectivity according to a pre-trained two-dimensional image recognition model to obtain the category and/or contour of the target object; the two-dimensional image recognition model A model obtained by training using preset two-dimensional maps of the reflectance of sample objects of different materials; or,

The recognition unit is specifically configured to perform image recognition on a three-dimensional map of reflectance according to a pre-trained three-dimensional image recognition model to obtain the category and/or contour of the target object; the three-dimensional image recognition model is a preset The model obtained by training the three-dimensional map of the reflectance of the sample objects of a variety of different materials; or,

The recognition unit is configured to recognize the material of the target object according to the reflectance of the target object corresponding to the plurality of detection units and the preset correspondence between the object material and the reflectance.

The recognition unit is further configured to obtain a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognize the target object according to the three-dimensional image, and obtain a first recognition result; The reflectivity of the target object corresponding to the detection unit and the first recognition result obtain a second recognition result.

In a third aspect, an embodiment of the present application also provides a detection device, including a memory and a processor, the memory stores a computer program executable by the processor, and the detection device implements the foregoing when the computer program is executed. The detection method described in the first aspect.

In a fourth aspect, an embodiment of the present application also provides a storage medium on which a computer program is stored, and when the computer program is read and executed, the detection method described in the first aspect is implemented.

The beneficial effects of this application are:

The embodiments of the present application provide a detection method and a detection device. The detection method includes: acquiring electrical signals generated by multiple detection units in the detection device based on received echo signals, the echo signals being signals reflected by a target object from emitted radiation According to the electrical signal generated by each detection unit, obtain the first information of the target object corresponding to each detection unit; According to the electrical signal generated by each detection unit and the first information of the corresponding target object, obtain the target object corresponding to the detection unit The second information, the second information is configured to reflect the attribute of the corresponding target object; the target object is identified according to the second information of the target object corresponding to each detection unit. By calculating the distance information of the target object corresponding to the target detection unit based on the electrical signal generated by the echo signal, the echo energy information is determined, and the reflectivity of the target object is calculated according to the distance information and the echo energy in the echo information, Thus, based on the reflectivity, target object recognition is performed. This makes the echo signal not only limited to distance calculation, but effectively expands the application range of the echo signal, and effectively improves the utilization rate of the echo signal.

Description of the drawings

In order to explain the technical solutions of the embodiments of the present disclosure more clearly, the following will briefly introduce the drawings that need to be used in the embodiments. It should be understood that the following drawings only show certain embodiments of the present disclosure, and therefore do not It should be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a detection method provided by an embodiment of this application;

2 is a schematic diagram of an echo signal waveform provided by an embodiment of the application;

FIG. 3 is a schematic flowchart of another detection method provided by an embodiment of the application;

4 is a schematic flowchart of another detection method provided by an embodiment of this application;

FIG. 5 is a schematic flowchart of another detection method provided by an embodiment of this application;

FIG. 6 is a schematic diagram of a detection device provided by an embodiment of the application;

FIG. 7 is a schematic diagram of another detection device provided by an embodiment of the application;

FIG. 8 is a schematic diagram of another detection device provided by an embodiment of the application;

FIG. 9 is a schematic diagram of another detection device provided by an embodiment of this application;

FIG. 10 is a schematic diagram of a detection device provided by an embodiment of this application.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments These are a part of the embodiments of the present disclosure, but not all of the embodiments.

It should be noted that the solution of this application mainly focuses on TOF (Time of Flight, time of flight ranging) detection equipment. The current TOF equipment uses echo information to measure distance. In fact, the echo information has more uses, not just for distance measurement. The solution of this application makes full use of the echo signal on the basis of the existing technology, mainly using the strength of the obtained echo to perform Feature extraction, and then complete a series of targets such as target object recognition and material recognition. The improvement scheme of the present application will be described in detail below through a number of embodiments.

FIG. 1 is a schematic flowchart of a detection method provided by an embodiment of the application; the execution subject of the method may be a laser detection device such as a detector. As shown in Figure 1, the method may include:

S101. Acquire electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected by the target object from the emitted radiation.

Optionally, the emitted radiation may be a point light source or a surface light source, a plurality of detection units in the detection device emit light source signals to the target object, and the echo signal generated by the light source after being reflected on the surface of the target object is received by the detection device. Among them, the received echo signal may include: a background light signal and an effective signal. Optionally, the background light signal may include energy mean and variance, color information, etc.; the effective signal may include: energy and signal return time.

S102. Obtain first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit.

Optionally, according to the echo signal obtained above, the electrical signal generated by the detection unit based on the received echo signal can be obtained, and based on the signal transmission and the electrical signal generated by the detection unit, and the distance calculation formula, it can be further obtained The first information of the target object, where the first information includes distance information, thereby obtaining the distance information of the detection device from the target object.

Optionally, using the TOF principle, the distance between the target object and the detection device can be measured, and the distance calculation formula is: D=(△t·c)/2. Among them, Δt is the time difference from when the signal is transmitted to being received after being reflected by the target object, and c is the speed of light. This application is applicable to both ITOF and DTOF distance calculation methods.

S103: Obtain second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object, where the second information is used to reflect the attribute of the corresponding target object.

In an embodiment of the present application, according to the magnitude of the electrical signal generated by each detection unit, the echo energy generated by each detection unit can be further obtained. Combining the echo energy with the first information is used to obtain the second information. The following uses the ITOF distance calculation method as an example to illustrate the acquisition of echo energy.

Figure 2 is a schematic diagram of an echo signal waveform provided by an embodiment of this application. As shown in Figure 2, Q0°, Q90°, Q180°, Q270° are respectively used to modulate and demodulate laser echo energy in ITOF ranging The number of photogenerated electrons received by each of the four-phase demodulation signal after integration. It can be obtained by converting laser echo photons into electrons by photodiode devices and integrating them. When the echo signal falls within the 0～T/4 period, as shown in Figure 2,

Among them, z(t) is the power of the echo signal. According to the above calculation formula, the electrical signal generated by each detection unit can be calculated.

Thus, the signal energy accumulation of the complementary phase of the pixel in each detection unit can be obtained, such as Q0°, Q180°. Let QB be the cumulative sum of the energy of the background light in the two phases, QB can be obtained by multiplying the number of photogenerated electrons collected by the demodulation signal of any phase after the emitting light source is turned off. The total energy of such an echo signal can be calculated using formula 1: Q0°+Q180°-QB.

In some embodiments, based on the acquired echo energy and the first information (distance), the second information corresponding to the target object of each detection unit may be calculated. In this embodiment, the second information may be reflectance.

S104: Identify the target object according to the second information of the target object corresponding to each detection unit.

Optionally, based on the reflectance information corresponding to the target obtained by the above calculation, a preset method may be further used to identify the target object based on the reflectance information, which may include the material, contour, and image of the target object, etc. The identification and specific identification methods can be understood with reference to the following specific embodiments.

In summary, the detection method provided by this embodiment includes: acquiring electrical signals generated by multiple detection units in the detection device based on received echo signals, the echo signals being signals reflected by the target object from the emitted radiation; according to each detection unit The generated electrical signal obtains the first information of the target object corresponding to each detection unit; according to the electrical signal generated by each detection unit and the corresponding first information of the target object, the second information of the target object corresponding to the detection unit is obtained. The second information is configured to reflect the attributes of the corresponding target object; the target object is identified according to the second information of the target object corresponding to each detection unit. By calculating the distance information of the target object corresponding to the target detection unit based on the electrical signal generated by the echo signal, the echo energy information is determined, and the reflectivity of the target object is calculated according to the distance information and the echo energy in the echo information, Thus, based on the reflectivity, target object recognition is performed. This makes the echo signal not only limited to distance calculation, but effectively expands the application range of the echo signal, and effectively improves the utilization rate of the echo signal.

FIG. 3 is a schematic flowchart of another detection method provided by an embodiment of the application; optionally, as shown in FIG. 3, in step S103, according to the electrical signals generated by each detection unit and the corresponding first Information, obtaining second information of the target object corresponding to the detection unit, may include:

S201: Obtain the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit.

S202: Obtain second information of the target object according to the preset function or preset parameter according to the first information and energy corresponding to each detection unit.

Optionally, the method for calculating the energy of the echo signal has been described in the above embodiment, that is, through the above formula 1: Q0°+Q180°-QB, the value of the echo signal received by each detection unit can be calculated Energy Q _R.

Optionally, the first information is the distance, and the second information is the reflectivity; the preset parameters may include: the emission energy of the emitted radiation, the fill factor of the detection device, the radiation attenuation coefficient corresponding to the distance of each detection unit, or the reflection of the target object The ratio of echo energy into each detection unit.

Alternatively, the energy Q _R of the first information signal and an echo of the target object obtained by the above calculation, using the equation 3:

Calculate the second information of the target object, that is, calculate the reflectance of the target object. Among them, Q _R is the energy of the echo signal, Q _T is the emission energy of the light source, γ is the fill factor, α is the attenuation coefficient of the light propagation distance L, and β is the energy reflected by the target object that can enter the detection unit (pixel) The ratio.

Assuming that the calculated first information of the target object, that is, the distance information, is L, it should be noted that in the above formula 3, the parameters α and β are both related to the distance information as L. You can refer to the following specific embodiments to calculate Radiation attenuation coefficient α and ratio β.

FIG. 4 is a schematic flowchart of another detection method provided by an embodiment of the application; optionally, in step S202, the target object is obtained according to a preset function or preset parameter according to the first information and energy corresponding to each detection unit Before the second information, the method of this application may also include:

S301: According to the distance corresponding to each detection unit, a preset distance attenuation model corresponding to the wavelength of emitted radiation is used to obtain a radiation attenuation coefficient corresponding to the distance of each detection unit.

Optionally, the calculation of the attenuation coefficient α is explained: for the wavelength of the light emitted by the light source and specific weather conditions, we can obtain a model of α changing with distance under different conditions through testing. In the actual use process, the weather conditions can be obtained by fusion of multiple information, and then the corresponding model is selected and brought into the formula for calculation. In addition, for some light, such as infrared light, if the farthest distance to be measured is not long, for example, when the farthest distance to be measured is 200 meters, under common weather conditions (rain, snow or moderate haze, etc.), it is different. The proportion of attenuation caused by atmospheric scattering of light propagating in the atmosphere at distance is not large, which can be considered as 1.

S302: According to the distance corresponding to each detection unit or the diameter of the receiving lens in the detection device, obtain the ratio of the echo energy reflected by the target object into each detection unit.

Optionally, the calculation of the ratio β at which the echo energy reflected by the target object enters each detection unit depends on the diameter of the lens and the first information (distance L) of the target object. Formula 4:

Calculate the ratio β. Among them, d is the lens diameter, and L is the first information, that is, the distance.

In some embodiments, the first information is distance, and the second information is reflectivity; optionally, in step S104, identifying the target object according to the second information of the target object corresponding to each detection unit may include: According to the reflectivity of the target object corresponding to each detection unit, a two-dimensional map of the reflectivity of the target object is obtained, and the target object is identified according to the two-dimensional map of reflectivity.

It should be noted that, due to the different structure or surface material of the common objects, the reflectance maps of these objects also show different characteristics. For example, for the back of the car, the car lights and the middle license plate have high reflectivity and reflection. The gray-scale image of the high rate will show a reverse smile; the high reflectivity of the marking line on the road will show a regular band.

In this embodiment, according to the calculated reflectivity of the target object, a two-dimensional map of the reflectance of the target object, that is, the grayscale map of the reflectance of the target object, can be obtained, and based on the above characteristics of the reflectivity grayscale map, the The target object is identified.

Optionally, according to a pre-trained two-dimensional image recognition model, the reflectance gray map can be image recognized to obtain the category and/or contour of the target object; wherein, the two-dimensional image recognition model can be a variety of presets. The model obtained by training the gray-scale reflectivity of sample objects of different materials.

For example: Obtain a variety of different materials and different types of sample objects, calculate the reflectance of multiple sample objects, obtain the reflectance grayscale map of all sample objects, and input the reflectance grayscale map of all sample objects as samples into the recognition model Perform sample training in the process to obtain a trained two-dimensional image recognition model, and then use the trained two-dimensional image recognition model to identify the reflectance grayscale map of any target object, so that the reflectance grayscale map can be compared with the target object Recognize the target object based on the corresponding relationship. Among them, include: image recognition: for common objects, we can analyze their materials, and substitute the reflectance index of each material as the gray value to get the gray image of the surface of the object. The grayscale images of these common objects are the training set and test set for object recognition, and then image recognition. Contour recognition: Use the gray image obtained after the material analysis to perform contour recognition to identify the object.

In some embodiments, in the above step S104, identifying the target object according to the second information of the target object corresponding to each detection unit may include: corresponding the reflectivity of the target object corresponding to each detection unit to the corresponding detection unit Fusion of distances to obtain a three-dimensional map of reflectivity, and identify the target object based on the three-dimensional map of reflectivity.

Optionally, according to the reflectance of the target object calculated above and the distance corresponding to the corresponding detection unit, the TOF method is used to obtain a three-dimensional image of the target object with distance information and reflectance information, that is, a three-dimensional image of reflectance. , So as to identify the target object based on the three-dimensional map of reflectivity.

Optionally, according to a pre-trained three-dimensional image recognition model, image recognition of the three-dimensional reflectivity map can be performed to obtain the category and/or contour of the target object; wherein, the three-dimensional image recognition model adopts a preset variety of different materials. The model obtained by training the three-dimensional map of the reflectivity of the sample object.

In some embodiments, because different surfaces of the target object have different distances from the detection device, the contour of the target object can be restored according to multiple distance information of the detection device from the target object, that is, the contour of the target object can be restored. Recognition. Further, the material of the target object can be judged more accurately based on the recognized contour information and the reflectivity of the object material. For example, when we have determined that the target object corresponding to a certain detection unit belongs to a part of the car body, then we can narrow the material classification scope, according to the material classification of the car, more accurately determine the material of the object corresponding to the detection unit, and further Determine the material of the object corresponding to the detection device.

In some embodiments, in the foregoing step S104, identifying the target object according to the second information of the target object corresponding to each detection unit may also include: according to the reflectivity of the target object corresponding to the multiple detection units, and a preset The corresponding relationship between the material of the object and the reflectivity is used to identify the material of the target object.

Optionally, the reflectance can be used to determine the material of the target object according to the corresponding relationship of the reflectance of different objects at the current light source wavelength. The following Table 1 shows the corresponding relationship between the reflectance value of normal incidence and the material of the object under a certain light source wavelength. Among them, the wavelength of the light source is in the 589.3nm band.

Table 1

物体材质Object material	反射率Reflectivity
银silver	0.950.95
金gold	0.850.85
铝aluminum	0.830.83
铜copper	0.700.70

According to the corresponding relationship between the reflectivity and the material of the object, the material of the target object can be determined. For example, if the reflectance of the target object is 0.95 obtained through the above calculation, then according to the corresponding relationship, it can be determined that the material of the target object is silver.

It should be noted that because the target object will be affected by various external factors such as the environment or the air, the calculated reflectance of the target object may have errors, which does not conform to the above corresponding relationship. In this case, it can be considered as reflection. When the difference between the standard reflectivity and the standard reflectivity meets the preset difference, it can be considered that the material of the target object corresponds to the object material corresponding to the standard reflectivity. For example: assuming that the preset difference is 0.05, when the calculated reflectivity of the target object is 0.9 or 1.0, it can be considered that the material of the target object is silver. Specifically, the preset difference value can be determined according to actual empirical values, and is not limited to the above 0.05, which is only an example value.

Figure 5 is a schematic flow chart of another detection method provided by an embodiment of the application; optionally, the first information is the distance, and the second information is the reflectivity; The second information, to identify the target object, can include:

S401: Obtain a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognize the target object according to the three-dimensional image, and obtain a first recognition result.

In some embodiments, a three-dimensional image of the target object can be obtained according to the distance of the target object. The three-dimensional image of the target object can be a three-dimensional image with distance information. According to the three-dimensional image, a preset three-dimensional image recognition model is used for recognition. , The first recognition result can be obtained, and the first recognition result can be contour recognition, that is, the three-dimensional contour figure of the target object is obtained.

S402: Obtain a second recognition result according to the reflectivity of the target object corresponding to each detection unit and the first recognition result.

Optionally, based on the three-dimensional contour graphics of the target object, different parts of the target object can be determined, and further, combined with the reflectivity of the target object, that is, according to the reflectivity of the different parts of the target object, the material of the different parts can be determined, Thus, according to the material of different parts and the contour information of the target object, the target object can be recognized, and the second recognition result can be obtained.

For example: Suppose that the first recognition result of the target object is: car, according to the reflectivity of different parts of the car, the material of different parts can be determined, and for the car, the material corresponding to each part is basically fixed, then according to the determined The material of different parts can determine whether the part is the part corresponding to the car. If each different part corresponds to it, then it can be determined that the target object is the car.

In summary, the detection method provided by the embodiment of the present application includes: acquiring electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected from the target object by the emitted radiation; The electrical signal generated by each detection unit obtains the first information of the target object corresponding to each detection unit; according to the electrical signal generated by each detection unit and the corresponding first information of the target object, the second information of the target object corresponding to the detection unit is obtained. The second information is configured to reflect the attribute of the corresponding target object; the target object is identified according to the second information of the target object corresponding to each detection unit. By calculating the distance information of the target object corresponding to the target detection unit based on the electrical signal generated by the echo signal, the echo energy information is determined, and the reflectivity of the target object is calculated according to the distance information and the echo energy in the echo information, Thus, based on the reflectivity, target object recognition is performed. This makes the echo signal not only limited to distance calculation, but effectively expands the application range of the echo signal, and effectively improves the utilization rate of the echo signal.

6 is a schematic diagram of a detection device provided by an embodiment of the application; as shown in FIG. 6, the detection device includes: a detection unit 501, a first processing unit 502, a second processing unit 503, and an identification unit 504;

The detection unit 501 is configured to obtain electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected by the target object from the emitted radiation;

The first processing unit 502 is configured to obtain the first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit;

The second processing unit 503 is configured to obtain second information of the target object corresponding to the detection unit according to the electrical signals generated by each detection unit and the corresponding first information of the target object, and the second information is configured to reflect the attributes of the corresponding target object ；

The recognition unit 504 is configured to recognize the target object according to the second information of the target object corresponding to each detection unit.

Optionally, the second processing unit 503 is specifically configured to obtain the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit; according to the first information and energy corresponding to each detection unit, according to a preset The function or preset parameter obtains the second information of the target object.

The preset parameters include: the emission energy of the emitted radiation, the fill factor of the detection device, the radiation attenuation coefficient corresponding to the distance of each detection unit, and the ratio of the echo energy reflected by the target object into each detection unit.

FIG. 7 is a schematic diagram of another detection device provided by an embodiment of the application; optionally, as shown in FIG. 7, the device further includes a third processing unit 505;

The third processing unit 505 is configured to use a preset distance attenuation model corresponding to the wavelength of the emitted radiation according to the distance corresponding to each detection unit to obtain the radiation attenuation coefficient corresponding to the distance of each detection unit; it is configured to be based on the distance corresponding to each detection unit Or the diameter of the receiving lens in the detection device to obtain the ratio of the echo energy reflected by the target object into each detection unit.

FIG. 8 is a schematic diagram of another detection device provided by an embodiment of this application; FIG. 9 is a schematic diagram of another detection device provided by an embodiment of this application; optionally, as shown in FIG. 8 and FIG. 9, the identification The unit 504 is specifically configured to obtain a two-dimensional map of the reflectivity of the target object according to the reflectivity of the target object corresponding to each detection unit, and to identify the target object according to the two-dimensional map of the reflectivity; or, to correspond to each detection unit The reflectivity of the target object is fused with the distance corresponding to the corresponding detection unit to obtain a three-dimensional map of reflectivity, and the target object is identified according to the three-dimensional map of reflectivity; or, according to the reflectivity of multiple detection units corresponding to the target object , And the corresponding relationship between the preset object material and reflectivity to identify the material of the target object.

Optionally, the first information is the distance and the second information is the reflectance; the recognition unit 504 is specifically configured to perform image recognition on the two-dimensional map of reflectance according to a pre-trained two-dimensional image recognition model to obtain the target object category and / Or contour; the two-dimensional image recognition model is a model obtained by training using preset two-dimensional maps of the reflectance of sample objects of different materials; or,

The recognition unit 504 is specifically configured to perform image recognition on the three-dimensional map of reflectivity according to the pre-trained three-dimensional image recognition model to obtain the category and/or contour of the target object; the three-dimensional image recognition model is made of preset multiple different materials The model obtained by training the three-dimensional map of the reflectance of the sample object; or,

The recognition unit 504 is configured to recognize the material of the target object according to the reflectance of the target object corresponding to the multiple detection units and the preset correspondence between the material of the object and the reflectance.

The recognition unit 504 is further configured to obtain a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognize the target object according to the three-dimensional image, and obtain a first recognition result; according to the reflection of the target object corresponding to each detection unit Rate and the first recognition result to obtain the second recognition result.

The foregoing detection device is used to execute the method provided in the foregoing embodiment, and its implementation principle and technical effect are similar, and will not be repeated here.

The above modules may be one or more integrated circuits configured to implement the above methods, for example: one or more specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), or one or more microprocessors (digital singnal processor, DSP for short), or, one or more Field Programmable Gate Array (FPGA for short), etc. For another example, when one of the above modules is implemented in the form of processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU for short) or other processors that can call program codes. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC for short).

10 is a schematic diagram of a detection device provided by an embodiment of the application; the detection device may be a detector, and the detection device includes a processor 701 and a memory 702.

The memory 702 is configured to store a program, and the processor 701 calls the program stored in the memory 702 to execute the foregoing method embodiment. The specific implementation method is similar to the technical effect, and will not be repeated here.

Optionally, the present disclosure also provides a program product, such as a computer-readable storage medium, including a program, which is used to execute the foregoing method embodiments when executed by a processor.

In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware, or may be implemented in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (English: processor) execute the various embodiments of the present disclosure Part of the method. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated as: ROM), random access memory (English: Random Access Memory, abbreviated as: RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

Claims

A detection method, characterized in that the method includes:

Acquiring electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected by the target object from the emitted radiation;

Obtaining the first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit;

Obtaining second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object, where the second information is used to reflect the attribute of the corresponding target object;

Identify the target object according to the second information of the target object corresponding to each detection unit.
The method according to claim 1, wherein the second information of the target object corresponding to the detection unit is obtained based on the electrical signal generated by each detection unit and the corresponding first information of the target object, include:

Obtaining the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit;

According to the first information and the energy corresponding to each detection unit, the second information of the target object is obtained according to a preset function or preset parameter.
The method according to claim 2, wherein the first information is distance, and the second information is reflectivity;

The preset parameters include: the emission energy of the emitted radiation, the fill factor of the detection device, the radiation attenuation coefficient corresponding to the distance of each detection unit, and the echo energy reflected by the target object enters each station. The ratio of the detection unit.
The method according to claim 3, wherein the second information of the target object is obtained according to the first information and the energy corresponding to each of the detection units and according to a preset function or preset parameter Previously, the method also included:

According to the distance corresponding to each detection unit, a preset distance attenuation model corresponding to the wavelength of the emitted radiation is used to obtain a radiation attenuation coefficient corresponding to the distance of each detection unit.
The method according to claim 3, wherein the second information of the target object is obtained according to the first information and the energy corresponding to each of the detection units and according to a preset function or preset parameter Previously, the method also included:

According to the distance corresponding to each detection unit and the diameter of the receiving lens in the detection device, the ratio of the echo energy reflected by the target object into each detection unit is obtained.
The method according to claim 1, wherein the first information is distance, and the second information is reflectance; and the second information of the target object corresponding to each detection unit is Recognition of target objects, including:

Obtain a two-dimensional map of the reflectivity of the target object according to the reflectivity of the target object corresponding to each detection unit, and identify the target object according to the two-dimensional map of reflectivity; or,

Fuse the reflectivity of the target object corresponding to each detection unit with the distance corresponding to the corresponding detection unit to obtain a three-dimensional map of the reflectivity, and identify the target object according to the three-dimensional map of reflectivity; or,

The material of the target object is identified according to the reflectance of the target object corresponding to the plurality of detection units and the preset correspondence between the material of the object and the reflectance.
The method according to claim 6, wherein the first information is distance and the second information is reflectivity; and the recognizing the target object according to the two-dimensional map of reflectivity includes :

Performing image recognition on the two-dimensional map of reflectivity according to a pre-trained two-dimensional image recognition model to obtain the category and/or contour of the target object;

The two-dimensional image recognition model is a model obtained by training using preset two-dimensional maps of the reflectance of sample objects of different materials;

The recognizing the target object according to the three-dimensional map of reflectivity includes:

Performing image recognition on the three-dimensional map of reflectivity according to a pre-trained three-dimensional image recognition model to obtain the category and/or contour of the target object;

The three-dimensional image recognition model is a model obtained by training using preset three-dimensional maps of the reflectance of sample objects of different materials.
The method according to claim 1, wherein the first information is distance, and the second information is reflectivity;

The recognizing the target object according to the second information of the target object corresponding to each detection unit includes:

Obtaining a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognizing the target object according to the three-dimensional image, and obtaining a first recognition result;

According to the reflectivity of the target object corresponding to each detection unit and the first recognition result, a second recognition result is obtained.
A detection device, characterized in that the detection device includes: a detection unit, a first processing unit, a second processing unit, and an identification unit;

The detection unit is configured to obtain electrical signals generated by multiple detection units in the detection device based on received echo signals, where the echo signals are signals reflected from the target object by the emitted radiation;

The first processing unit is configured to obtain first information of the target object corresponding to each detection unit according to the electrical signal generated by each detection unit;

The second processing unit is configured to obtain the second information of the target object corresponding to the detection unit according to the electrical signal generated by each detection unit and the corresponding first information of the target object, and the second information configuration To reflect the attributes of the corresponding target object;

The recognition unit is configured to recognize the target object according to the second information of the target object corresponding to each detection unit.
The device according to claim 9, wherein the second processing unit is specifically configured to obtain the energy of the echo signal received by each detection unit according to the electrical signal generated by each detection unit; The first information and the energy corresponding to each detection unit obtain the second information of the target object according to a preset function or preset parameter.
The device according to claim 10, wherein the first information is distance, and the second information is reflectivity;

The preset parameters include: the emission energy of the emitted radiation, the fill factor of the detection device, the radiation attenuation coefficient corresponding to the distance of each detection unit, and the echo energy reflected by the target object enters each station. The ratio of the detection unit.
The device according to claim 11, further comprising a third processing unit;

The third processing unit is configured to use a preset distance attenuation model corresponding to the wavelength of the emitted radiation according to the distance corresponding to each detection unit to obtain a radiation attenuation coefficient corresponding to the distance of each detection unit; It is configured to obtain the ratio of echo energy reflected by the target object into each detection unit according to the distance corresponding to each detection unit and the diameter of the receiving lens in the detection device.
The device according to claim 9, wherein the first information is distance, and the second information is reflectivity; and the identification unit is specifically configured to be based on the reflection of the target object corresponding to each detection unit Obtain a two-dimensional map of the reflectivity of the target object, and identify the target object according to the two-dimensional map of reflectivity; or, compare the reflectivity of the target object corresponding to each detection unit with the corresponding The distances corresponding to the detection units are merged to obtain the three-dimensional map of reflectivity, and the target object is identified according to the three-dimensional map of reflectivity; or, according to the reflectivity of the target object corresponding to the multiple detection units , And the preset corresponding relationship between the object material and the reflectivity, to identify the material of the target object.
The device according to claim 13, wherein the first information is distance and the second information is reflectivity;

The recognition unit is specifically configured to perform image recognition on the two-dimensional map of reflectivity according to a pre-trained two-dimensional image recognition model to obtain the category and/or contour of the target object; the two-dimensional image recognition model A model obtained by training using preset two-dimensional maps of the reflectance of sample objects of different materials; or,

The recognition unit is specifically configured to perform image recognition on a three-dimensional map of reflectance according to a pre-trained three-dimensional image recognition model to obtain the category and/or contour of the target object; the three-dimensional image recognition model is a preset The model obtained by training the three-dimensional map of the reflectance of the sample objects of a variety of different materials; or,

The recognition unit is configured to recognize the material of the target object according to the reflectance of the target object corresponding to the plurality of detection units and the preset correspondence between the object material and the reflectance.
The device according to claim 9, wherein the first information is distance, and the second information is reflectivity;

The recognition unit is further configured to obtain a three-dimensional image of the target object according to the distance of the target object corresponding to each detection unit, recognize the target object according to the three-dimensional image, and obtain a first recognition result; The reflectivity of the target object corresponding to the detection unit and the first recognition result obtain a second recognition result.