Ultrasound image processing method, and automotive parts processing apparatus and medium program

Abstract

The application provides an ultrasonic image processing method, an automobile part processing device and a medium program, and is applied to the automobile part processing device. The automobile part processing device comprises an ultrasonic sensor. The method comprises the following steps: determining a target relative position parameter between the automobile part processing device and a target object through the ultrasonic sensor; determining a first working parameter corresponding to the target relative position parameter; and controlling the ultrasonic sensor to work at the first working parameter, so as to obtain a first image of the target object. The ultrasonic imaging effect of the automobile part processing device can be improved by adopting the application, so as to improve the accuracy of welding point identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile parts processing and the technical field of image processing, in particular to an ultrasonic image processing method, an automobile parts processing device and a medium program. BACKGROUND

[0002] In practical applications, ultrasonic waves can be used not only for positioning but also for ultrasonic imaging. At present, ultrasonic imaging technology is also widely used in life. However, the ultrasonic imaging effect is poor, especially in the aspect of automobile parts processing. The poor ultrasonic imaging effect often leads to a low yield of automobile parts. For example, when identifying a welding point, the identification accuracy is low, which leads to poor processing precision, and thus the yield of automobile parts is low. Therefore, how to improve the ultrasonic imaging effect of the automobile parts processing device to improve the welding point identification accuracy is an urgent problem to be solved. SUMMARY

[0003] The present application provides an ultrasonic image processing method, an automobile parts processing device and a medium program, which can improve the ultrasonic imaging effect of the automobile parts processing device to improve the welding point identification accuracy.

[0004] In a first aspect, an ultrasonic image processing method is provided, which is applied to an automobile parts processing device. The automobile parts processing device includes an ultrasonic sensor. The method includes the following steps.

[0005] Determining a target relative position parameter between the automobile parts processing device and a target object by using the ultrasonic sensor. The target object includes a suspected welding point or a user-specified position or region.

[0006] Determining a first working parameter corresponding to the target relative position parameter.

[0007] Controlling the ultrasonic sensor to work at the first working parameter to obtain a first image of the target object.

[0008] Determining a first low-frequency component part and a first high-frequency component part of the first image.

[0009] Determining a first energy value of the first low-frequency component part and a second energy value of the first image.

[0010] Determining a target ratio between the first energy value and the second energy value.

[0011] When the target ratio is not in a preset range, determining a first deviation between the target ratio and the preset range.

[0012] adjust the first working parameter according to the first deviation, to obtain a second working parameter;

[0013] control the ultrasonic sensor to work at the second working parameter, to obtain a second image of the target object;

[0014] determine a first feature distribution density according to the first high-frequency component part;

[0015] determine a first image enhancement processing parameter corresponding to the first feature distribution density;

[0016] perform image enhancement processing on the second image according to the first image enhancement processing parameter, to obtain a target image;

[0017] perform image segmentation on a region where the target object is located in the target image, to obtain a target region;

[0018] obtain a feature set of the target region, and perform welding spot identification according to the feature set.

[0019] In a second aspect, an embodiment of the present application provides an ultrasonic image processing apparatus applied to an automobile part processing device, the automobile part processing device comprising an ultrasonic sensor, and the apparatus comprising a determination unit, a control unit, an adjustment unit and an enhancement unit, wherein

[0020] the determination unit is configured to determine a target relative position parameter between the automobile part processing device and a target object by using the ultrasonic sensor, and determine a first working parameter corresponding to the target relative position parameter;

[0021] the control unit is configured to control the ultrasonic sensor to work at the first working parameter, to obtain a first image of the target object;

[0022] the determination unit is further configured to determine a first low-frequency component part and a first high-frequency component part of the first image, determine a first energy value of the first low-frequency component part and a second energy value of the first image, determine a target ratio value between the first energy value and the second energy value, and when the target ratio value is not in a preset range, determine a first deviation between the target ratio value and the preset range;

[0023] the adjustment unit is further configured to adjust the first working parameter according to the first deviation, to obtain a second working parameter;

[0024] the control unit is further configured to control the ultrasonic sensor to work at the second working parameter, to obtain a second image of the target object;

[0025] The determining unit is further configured to determine a first feature distribution density according to the first high-frequency component part; and determine a first image enhancement processing parameter corresponding to the first feature distribution density.

[0026] The enhancing unit is configured to perform image enhancement processing on the second image according to the first image enhancement processing parameter to obtain a target image.

[0027] The segmenting unit is configured to perform image segmentation on a region in which the target object is located in the target image to obtain a target region.

[0028] The recognizing unit is configured to obtain a feature set of the target region, and perform welding spot recognition according to the feature set.

[0029] In a third aspect, an embodiment of the present application provides a vehicle part processing device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the present application.

[0030] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of the present application.

[0031] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the present application. The computer program product can be a software installation package.

[0032] By implementing the embodiments of the present application, the following beneficial effects are achieved:

[0033] It can be seen that the ultrasonic image processing method and related device described in the embodiments of the present application are applied to the automobile part processing equipment, the automobile part processing equipment includes an ultrasonic sensor, the target relative position parameter between the automobile part processing equipment and a target object is determined through the ultrasonic sensor; the target object includes a suspected welding point or a user-specified position or region; a first working parameter corresponding to the target relative position parameter is determined; the ultrasonic sensor is controlled to work at the first working parameter, and a first image of the target object is obtained; a first low-frequency component part and a first high-frequency component part of the first image are determined; a first energy value of the first low-frequency component part and a second energy value of the first image are determined; a target ratio between the first energy value and the second energy value is determined; when the target ratio is not in a preset range, a first deviation between the target ratio and the preset range is determined; the first working parameter is adjusted according to the first deviation, and a second working parameter is obtained; the ultrasonic sensor is controlled to work at the second working parameter, and a second image of the target object is obtained; a first feature distribution density is determined according to the first high-frequency component part; a first image enhancement processing parameter corresponding to the first feature distribution density is determined;The second image is subjected to image enhancement processing according to first image enhancement processing parameters, to obtain a target image, the target object region in the target image is subjected to image segmentation, to obtain a target region, a feature set of the target region is acquired, and welding point recognition is performed according to the feature set, first, the corresponding first working parameters can be configured based on the target relative position parameters between the ultrasonic sensor and the target object, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment, second, ultrasonic imaging is performed by using the first working parameters, the first low-frequency component part thereof reflects the basic structure of the image, and the first high-frequency component part thereof reflects the detail information of the image, if the energy proportion of the first low-frequency component part is too high, more details will be covered, and if the energy proportion of the first low-frequency component part is too low, the basic structure of the image will not be clear, therefore, it is necessary to ensure that the first low-frequency component part is within a reasonable range, if the energy proportion of the first low-frequency component part is not within the reasonable range, the first working parameters need to be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image returns to the reasonable range, and third, ultrasonic imaging is performed by using the second working parameters, to obtain a second image, since the working parameters are adjusted, the high-frequency and low-frequency parts in the image are influenced to a certain extent, in order to inhibit image over-adjustment or image under-enhancement, the second image is dynamically feedback adjusted based on the feature distribution in the first high-frequency component part of the first image, to obtain a final target image, so that the depth of the final ultrasonic imaging conforms to the actual situation, and the image over-enhancement or under-enhancement is prevented, and fourth, since the depth of the ultrasonic imaging conforms to the actual situation, the region image of the target object can also conform to the actual situation, which helps to ensure the welding point recognition accuracy, in this way, the ultrasonic imaging effect of the automobile part processing equipment can be improved, to improve the welding point recognition accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0035] Figure 1 is a flow diagram of an ultrasonic image processing method provided by an embodiment of the present application;

[0036] Figure 2 is a structural schematic diagram of an automobile part processing equipment provided by an embodiment of the present application;

[0037] Figure 3 is a functional unit composition block diagram of an ultrasonic image processing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0038] The terms "first", "second", and the like in the description and in the claims of the present application and above drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units is not limited to the listed steps or units, but in one possible example also includes steps or units not listed, or in one possible example also includes other steps or units inherent to the process, method, product, or device.

[0039] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearance of the phrase in various places in the specification does not necessarily all refer to the same embodiment, nor does it necessarily refer to a separate or alternative embodiment, which is independent of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0040] In order to make the person skilled in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0041] The automobile parts processing equipment related to the embodiments of the present application can include but is not limited to automobile parts processing machine tools, ultrasonic welding guns, etc., without limitation.

[0042] For example, taking an automobile parts processing machine tool as an example, in actual application, ultrasonic technology imaging is often used for welding spot detection, for example, whether there is a welding spot at a certain position or, when there is a welding spot, whether the welding spot is a false welding, the precision of welding spot identification determines the machining precision of the automobile parts processing machine tool, the embodiments of the present application provide an ultrasonic image processing method, applied to an automobile parts processing equipment, the automobile parts processing equipment includes an ultrasonic sensor, and the method comprises:

[0043] Determining a target relative position parameter between the automobile parts processing equipment and a target object through the ultrasonic sensor; the target object includes a suspected welding spot or a user-specified position or region;

[0044] Determining a first working parameter corresponding to the target relative position parameter;

[0045] controlling the ultrasonic sensor to work at the first working parameter to obtain a first image of the target object;

[0046] determining a first low-frequency component part and a first high-frequency component part of the first image;

[0047] determining a first energy value of the first low-frequency component part and a second energy value of the first image;

[0048] determining a target ratio value between the first energy value and the second energy value;

[0049] when the target ratio value is not in a preset range, determining a first deviation between the target ratio value and the preset range;

[0050] adjusting the first working parameter according to the first deviation to obtain a second working parameter;

[0051] controlling the ultrasonic sensor to work at the second working parameter to obtain a second image of the target object;

[0052] determining a first feature distribution density according to the first high-frequency component part;

[0053] determining a first image enhancement processing parameter corresponding to the first feature distribution density;

[0054] performing image enhancement processing on the second image according to the first image enhancement processing parameter to obtain a target image;

[0055] performing image segmentation on a region where the target object is located in the target image to obtain a target region;

[0056] obtaining a feature set of the target region, and performing welding spot recognition according to the feature set.

[0057] By the embodiments of the present application, firstly, the corresponding first working parameter can be configured based on the target relative position parameter between the ultrasonic sensor and the target object, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment, secondly, the first image is obtained by ultrasonic imaging using the first working parameter, the first low-frequency component part of which reflects the basic structure of the image, and the first high-frequency component part of which reflects the detail information of the image, if the energy proportion of the first low-frequency component part is too high, it will cover more details, and if the energy proportion of the first low-frequency component part is too low, it will result in that the basic structure of the image is not clear, therefore, it is necessary to ensure the first low-frequency component part within a reasonable range, if the energy proportion of the first low-frequency component part is not within a reasonable range, the first working parameter needs to be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image returns to a reasonable range, and then, the second working parameter is obtained after adjustment, thirdly, the second image is obtained by ultrasonic imaging using the second working parameter, since the working parameter is adjusted, it has a certain degree of influence on the high-frequency and low-frequency parts in the image, in order to suppress excessive image adjustment or insufficient image enhancement, the second image is dynamically feedback adjusted based on the feature distribution in the first high-frequency component part of the first image, to obtain the final target image, so that the depth of the final ultrasonic imaging conforms to the actual situation, and also prevents the image from being over-enhanced or under-enhanced, fourthly, since the depth of the ultrasonic imaging conforms to the actual situation, it can ensure that the regional image of the target object also conforms to the actual situation in depth, which helps to ensure the accuracy of the weld point identification, in this way, the ultrasonic imaging effect of the automobile part processing equipment can be improved, so as to improve the accuracy of the weld point identification.

[0058] Please refer to Figure 1 , Figure 1 is a flow diagram of an ultrasonic image processing method provided by an embodiment of the present application, as shown in the figure, applied to an automobile part processing equipment, the automobile part processing equipment comprising an ultrasonic sensor, the ultrasonic image processing method comprising:

[0059] 101, determining a target relative position parameter between the automobile part processing equipment and the target object by the ultrasonic sensor; the target object comprising a suspected weld point or a user-specified position or region.

[0060] In the embodiments of the present application, the target relative position parameter can include a target relative distance and / or a target relative angle.

[0061] In specific implementation, the target relative position parameter between the automobile part processing equipment and the target object can be determined by the ultrasonic sensor, that is, the environment can be preliminarily identified to determine the relative position relationship between the ultrasonic sensor and the target object.

[0062] The target object can include a suspected solder joint or a user-specified position or region. For example, a user can select a position or region for solder joint identification.

[0063] 102. Determine a first working parameter corresponding to the target relative position parameter.

[0064] In an embodiment of the present application, the first working parameter can include at least one of the following: a transmission power of the ultrasonic sensor, a transmission direction of the ultrasonic sensor, a working current of the ultrasonic sensor, a working voltage of the ultrasonic sensor, a working power of the ultrasonic sensor, and the like, without limitation.

[0065] In a specific implementation, a mapping relationship between a preset relative position parameter and a working parameter of the ultrasonic sensor can be pre-stored, the first working parameter corresponding to the target relative position parameter can be determined based on the mapping relationship, and the corresponding first working parameter can be configured based on the target relative position parameter between the ultrasonic sensor and the target object, so that the working parameter of the ultrasonic sensor is deeply consistent with the actual environment.

[0066] 103. Control the ultrasonic sensor to work at the first working parameter to obtain a first image of the target object.

[0067] The first image can include the entire image, i.e., the background region part and the target region part, or the first image can only include the target region part. The target region part can be understood as a partial image of the region where the target object is located.

[0068] In a specific implementation, the ultrasonic sensor can be controlled to work at the first working parameter to obtain the first image of the target object, i.e., the ultrasonic sensor is controlled to collect an image of the target object at the first working parameter to obtain the first image of the target object. Since the corresponding first working parameter is configured based on the target relative position parameter between the ultrasonic sensor and the target object, the working parameter of the ultrasonic sensor is deeply consistent with the actual environment, and the ultrasonic imaging effect is also preliminarily ensured.

[0069] 104. Determine a first low-frequency component part and a first high-frequency component part of the first image.

[0070] In an embodiment of the present application, the first image can be subjected to multi-scale decomposition to obtain the first low-frequency component part and the first high-frequency component part of the first image. The multi-scale decomposition algorithm can include at least one of the following: a wavelet transform algorithm, a pyramid transform algorithm, a neural network algorithm, a contourlet transform algorithm, a non-subsampled contourlet transform algorithm, and the like, without limitation. The first low-frequency component part thereof reflects the basic structure of the image, and the first high-frequency component part thereof reflects the detailed information of the image.

[0071] 105、determine a first energy value of the first low-frequency component part and a second energy value of the first image.

[0072] In a specific implementation, the first energy value of the first low-frequency component part and the second energy value of the first image can be determined, and then an energy ratio between the two can be calculated. If the energy ratio of the first low-frequency component part is too high, more details will be covered, and if the energy ratio of the first low-frequency component part is too low, the basic structure of the image will not be clear. Therefore, the first low-frequency component part needs to be ensured within a reasonable range.

[0073] 106、determine a target ratio between the first energy value and the second energy value.

[0074] In a specific implementation, the target ratio = the first energy value / the second energy value. If the energy ratio of the first low-frequency component part is too high, more details will be covered, and if the energy ratio of the first low-frequency component part is too low, the basic structure of the image will not be clear. Therefore, the first low-frequency component part needs to be ensured within a reasonable range, i.e., the target ratio needs to be ensured within a reasonable range.

[0075] 107、when the target ratio is not in a preset range, determine a first deviation between the target ratio and the preset range.

[0076] In a specific implementation, the preset range can be pre-set or system default. The preset range can include an upper threshold and a lower threshold, and the upper threshold is greater than the lower threshold.

[0077] In a specific implementation, the target ratio can be compared with the upper threshold and the lower threshold to determine the deviation direction. The deviation direction is either that the target ratio is less than the lower threshold or that the target ratio is greater than the upper threshold. The target ratio less than the lower threshold can be defined as a first deviation direction, and the target ratio greater than the upper threshold can be defined as a second deviation direction. If the first deviation direction, the first working parameter needs to be increased, and if the second deviation direction, the first working parameter needs to be decreased.

[0078] For the first deviation direction, the first deviation = (the lower threshold-the target ratio) / the lower threshold, and for the second deviation direction, the first deviation = (the upper threshold-the target ratio) / the upper threshold.

[0079] 108、adjust the first working parameter according to the first deviation to obtain a second working parameter.

[0080] In a specific implementation, the second working parameter = (1 + the first deviation degree) * the first working parameter. In this way, when the energy proportion of the first low-frequency component part is not within a reasonable range, the first working parameter can be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image is returned to the reasonable range. Then, the second working parameter is obtained after adjustment.

[0081] 109. Control the ultrasonic sensor to work at the second working parameter to obtain a second image of the target object.

[0082] In the embodiments of the present application, the first working parameter is configured based on the target relative position parameter between the ultrasonic sensor and the target object, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment. Then, the first working parameter is dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image is returned to the reasonable range. Then, the second working parameter is obtained after adjustment, so as to further ensure the basic structure of the image and help to ensure the ultrasonic imaging effect. That is, the ultrasonic sensor is controlled to collect an image of the target object at the second working parameter, and a second image of the target object is obtained.

[0083] 110. Determine a first feature distribution density according to the first high-frequency component part.

[0084] The first feature distribution density can be a feature point distribution density. In a specific implementation, the first high-frequency component part can be subjected to feature extraction to obtain at least one feature point. The number of the at least one feature point is determined, and the area of the first high-frequency component part is also determined. The first feature distribution density = number / area.

[0085] 111. Determine a first image enhancement processing parameter corresponding to the first feature distribution density.

[0086] The first image enhancement processing parameter can include an image enhancement processing algorithm and a corresponding algorithm control parameter. The algorithm control parameter is used to control the image enhancement degree, algorithm speed, image enhancement region, image enhancement position, etc. of the image enhancement processing algorithm, which is not limited herein.

[0087] 112. Perform image enhancement processing on the second image according to the first image enhancement processing parameter to obtain a target image.

[0088] In the embodiments of the present application, the second image can be subjected to image enhancement processing according to the first image enhancement processing parameters to obtain a target image. Since the working parameters are adjusted, the high-frequency and low-frequency parts in the image are affected to a certain extent. In order to prevent the image from being over-adjusted or under-enhanced, the second image is dynamically adjusted based on the feature distribution in the first high-frequency component part of the first image to obtain the final target image, so that the final ultrasonic imaging depth conforms to the actual situation, and the image is prevented from being over-enhanced or under-enhanced. In this way, the ultrasonic imaging effect can be improved.

[0089] Optionally, the first image enhancement processing parameters include a first image enhancement processing algorithm and a first algorithm control parameter.

[0090] The step 111 of determining the first image enhancement processing parameters corresponding to the first feature distribution density can include the following steps:

[0091] The first image enhancement processing algorithm corresponding to the first feature distribution density is determined.

[0092] The initial algorithm control parameter of the first image enhancement processing algorithm is obtained.

[0093] The second high-frequency component part of the second image is determined.

[0094] The second feature distribution density is determined according to the second high-frequency component part.

[0095] The second deviation between the second feature distribution density and the first feature distribution density is determined.

[0096] The target feedback adjustment parameter corresponding to the second deviation is determined.

[0097] The initial algorithm control parameter is subjected to feedback adjustment according to the target feedback adjustment parameter to obtain the first algorithm control parameter.

[0098] The first feature distribution density reflects the feature sparsity degree, and different feature sparsity degrees will have a certain influence on the accuracy of subsequent image recognition. Therefore, the mapping relationship between the preset first feature distribution density and the image enhancement processing algorithm can be stored in advance, and then the first image enhancement processing algorithm corresponding to the first feature distribution density can be determined based on the mapping relationship. The initial algorithm control parameter of the first image enhancement processing algorithm can also be obtained. Different image enhancement processing algorithms can correspond to different algorithm control parameters, and the initial algorithm control parameters can be configured based on experience in general cases.

[0099] Further, the second image can be subjected to multi-scale decomposition to obtain a second low-frequency component part and a second high-frequency component part of the second image. The multi-scale decomposition algorithm can include at least one of a wavelet transform algorithm, a pyramid transform algorithm, a neural network algorithm, a contourlet transform algorithm, a non-subsampled contourlet transform algorithm, etc., without limitation. The second low-frequency component part thereof reflects the basic structure of the image, and the second high-frequency component part thereof reflects the detailed information of the image.

[0100] Further, the second feature distribution density can be determined according to the second high-frequency component part. The second feature distribution density can refer to a feature point distribution density. In a specific implementation, feature extraction can be performed on the second high-frequency component part to obtain at least one feature point, the number of the at least one feature point is determined, and the area of the second high-frequency component part is also determined. The first feature distribution density = number / area. Then, the second deviation between the second feature distribution density and the first feature distribution density can be determined. The second deviation = (second feature distribution density-first feature distribution density) / (first feature distribution density+second feature distribution density). Further, a mapping relationship between a preset deviation and a feedback adjustment parameter can be pre-stored. Then, the target feedback adjustment parameter corresponding to the second deviation can be determined based on the mapping relationship. Further, part or all of the initial algorithm control parameters can be feedback adjusted according to the target feedback adjustment parameter to obtain the first algorithm control parameter. Specifically, the first algorithm control parameter = (1+target feedback adjustment parameter)*initial algorithm control parameter. Since the working parameter is adjusted, it has a certain degree of influence on the high-frequency and low-frequency parts in the image. In order to suppress over-adjustment of the image or under-enhancement of the image, the initial algorithm control parameter is feedback adjusted based on the feature distribution in the first high-frequency component part of the first image and the feature distribution in the second high-frequency component part, so that the final ultrasonic imaging effect depth conforms to the actual situation, and over-enhancement or under-enhancement of the image is prevented. In this way, the ultrasonic imaging effect can be improved.

[0101] Optionally, the step of feedback adjusting the initial algorithm control parameter according to the target feedback adjustment parameter to obtain the first algorithm control parameter includes:

[0102] feedback adjusting the initial algorithm control parameter according to the target feedback adjustment parameter to obtain a reference algorithm control parameter;

[0103] determining a second low-frequency component part of the second image;

[0104] determining a third deviation according to the second low-frequency component part and the first low-frequency component part;

[0105] determining a target fine adjustment parameter corresponding to the third deviation;

[0106] fine-tune the reference algorithm control parameter according to the target fine-tuning parameter, to obtain the first algorithm control parameter.

[0107] The reference algorithm control parameter is obtained by feedback adjustment of part or all of the initial algorithm control parameter according to a target feedback adjustment parameter, specifically, reference algorithm control parameter = (1 + target feedback adjustment parameter) * initial algorithm control parameter. Since the working parameter adjustment has a certain degree of influence on the high-frequency and low-frequency parts in the image, in order to suppress over-adjustment of the image or under-enhancement of the image, the initial algorithm control parameter is feedback adjusted based on the feature distribution in the first high-frequency component part of the first image and the feature distribution in the second high-frequency component part, so that the final ultrasonic imaging effect is deep and consistent with the actual situation, and over-enhancement or under-enhancement of the image is prevented.

[0108] Next, the second low-frequency component part of the second image can be determined, and the third deviation degree can be determined according to the second low-frequency component part and the first low-frequency component part, that is, the third energy value of the second low-frequency component part can be determined, the first energy value of the first low-frequency component part is obtained, and the third deviation degree = (third energy value - first energy value) / (third energy value + first energy value). The mapping relationship between the preset deviation degree and the fine-tuning parameter can also be pre-stored, and then the target fine-tuning parameter corresponding to the third deviation degree can be determined based on the mapping relationship. The energy of the low-frequency component part to some extent reflects the stability of the basic structure of the image, that is, the stability change of the basic structure of the image can be determined again from the basic structure of the image. The stability change is used to further optimize the algorithm control parameter, and then the first algorithm control parameter can be obtained by fine-tuning the reference algorithm control parameter according to the target fine-tuning parameter, specifically, first algorithm control parameter = (1 + target fine-tuning parameter) * reference algorithm control parameter. In this way, on the one hand, the initial algorithm control parameter is feedback adjusted based on the feature distribution in the first high-frequency component part of the first image and the feature distribution in the second high-frequency component part, so that the final ultrasonic imaging effect is deep and consistent with the actual situation, and over-enhancement or under-enhancement of the image is prevented. On the other hand, the energy of the first low-frequency component part of the first image and the energy of the second low-frequency component part of the second image are used to determine the stability change of the basic structure of the image, that is, the algorithm control parameter is fine-tuned in depth, which can suppress over-adjustment of the image or prevent under-enhancement of the image, and thus the ultrasonic imaging effect is improved in depth.

[0109] Optionally, the target relative position parameter includes a target relative distance and a target relative angle.

[0110] The first working parameter comprises a first transmission power of the ultrasonic sensor and a first transmission direction of the ultrasonic sensor.

[0111] The step 102 of determining the first working parameter corresponding to the target relative position parameter can comprise the following steps:

[0112] determining a reference transmission power according to the target relative distance;

[0113] determining a reference transmission direction according to the target relative angle; the reference transmission direction is a direction in which the ultrasonic sensor points to the target object;

[0114] constructing a target vector according to the reference transmission power, the reference transmission direction and the target relative distance;

[0115] determining a first position of the target object, and determining a second position, a second transmission power and a second transmission direction of a target interference source; and

[0116] constructing a first vector according to the first position, the second position, the second transmission power and the second transmission direction;

[0117] determining a second vector according to the first vector and the target vector; a resultant vector of the first vector and the second vector is the target vector;

[0118] determining the first working parameter according to the second vector.

[0119] The target relative position parameter can comprise a target relative distance and a target relative angle. The first working parameter comprises a first transmission power of the ultrasonic sensor and a first transmission direction of the ultrasonic sensor.

[0120] In a specific implementation, a preset mapping relationship between a distance and a transmission power can be stored in advance, and then the reference transmission power corresponding to the target relative distance can be determined based on the mapping relationship, and the reference transmission direction can be determined according to the target relative angle; the reference transmission direction is a direction in which the ultrasonic sensor points to the target object.

[0121] Next, a target vector can be constructed according to the reference transmission power, the reference transmission direction and the target relative distance; specifically, a size of the target vector = the reference transmission power / the target relative distance, and a direction of the target vector is the reference transmission direction.

[0122] Furthermore, the first position of the target object can be determined, as well as the second position, second transmission power and second transmission direction of the target interference source, and then a first vector can be constructed based on the first position, the second position, the second transmission power and the second transmission direction, wherein the reference distance between the first position and the second position is determined, the size of the first vector = the second transmission power / reference distance, and the direction of the first vector is the second transmission direction.

[0123] Furthermore, the second vector can be determined based on the first vector and the target vector, and the resultant vector of the first vector and the second vector is the target vector. Since the resultant vector and its corresponding component vector are known, the other corresponding component vector, i.e., the second vector, can be quickly determined, and then the first working parameter is determined based on the second vector, wherein the vector direction of the second vector is the first transmission direction, and the first transmission power = the vector size of the second vector * the relative distance to the target. In this way, in the presence of an interference source, the working parameters of the ultrasonic sensor can be dynamically adjusted based on the relative position relationship between the interference source and the target object and the influence of the interference source on the ultrasonic imaging, so that the adjusted working parameters of the ultrasonic sensor can suppress the influence of the interference source, thereby ensuring the ultrasonic imaging effect.

[0124] Optionally, the following steps may also be included:

[0125] When the target ratio is within the preset range, determining an image quality evaluation value of the first image;

[0126] When the image quality evaluation value is greater than a first preset threshold, saving the first image;

[0127] When the image quality evaluation value is less than or equal to the first preset threshold, determining a target difference between the preset threshold and the image quality evaluation value;

[0128] When the target difference is greater than a second preset threshold, executing the step of controlling the ultrasonic sensor to operate with the first operating parameter;

[0129] When the target difference is less than or equal to the second preset threshold, determining a target signal-to-noise ratio of the first image;

[0130] Obtain the target magnetic field interference intensity parameters of the current environment;

[0131] Determining a second image enhancement processing algorithm corresponding to the target magnetic field interference intensity parameter;

[0132] Acquiring default algorithm control parameters corresponding to the second image enhancement processing algorithm;

[0133] determining a target optimization coefficient corresponding to the target signal-to-noise ratio;

[0134] optimizing the default algorithm control parameter according to the target optimization coefficient, to obtain a second algorithm control parameter;

[0135] performing image enhancement processing on the first image according to the second image enhancement processing algorithm and the second algorithm control parameter, to obtain a third image.

[0136] In the embodiment, when the target ratio is in the preset range, the image quality evaluation value of the first image can be determined. Specifically, at least one image quality evaluation index can be used to evaluate the image quality of the first image, to obtain the image quality evaluation value of the first image. The image quality evaluation index can include at least one of the following: average gray level, sharpness, signal-to-noise ratio, edge preservation, average gradient, etc., without limitation.

[0137] In a specific implementation, when the image quality evaluation value is greater than a first preset threshold, it indicates that the image quality is good, and the first image can be saved. When the image quality evaluation value is less than or equal to the first preset threshold, it indicates that the image quality is general, and a target difference value between the preset threshold and the image quality evaluation value can be determined, i.e., target difference value = preset threshold - image quality evaluation value. The greater the target difference value, the worse the image quality. When the target difference value is greater than a second preset threshold, it indicates that the image quality is too poor, and the image needs to be reacquired, i.e., the step of controlling the ultrasonic sensor to work at the first working parameter can be performed. When the target difference value is less than or equal to the second preset threshold, it indicates that the image quality is not too poor, and the image quality can be improved through certain image enhancement means, i.e., the target signal-to-noise ratio of the first image can be determined, the target magnetic field interference intensity parameter of the current environment can be obtained, the target magnetic field interference intensity parameter reflects the influence degree of the environmental magnetic field on ultrasonic imaging, a mapping relationship between the preset magnetic field interference intensity parameter and the image enhancement processing algorithm can be pre-stored, and then a second image enhancement processing algorithm corresponding to the target magnetic field interference intensity parameter can be determined based on the mapping relationship. The default algorithm control parameter corresponding to the second image enhancement processing algorithm can be obtained. Different image enhancement processing algorithms correspond to different algorithm control parameters. The algorithm control parameter is used to control the image enhancement degree, algorithm speed, image enhancement region, image enhancement position, etc. of the image enhancement processing algorithm, without limitation. That is, the corresponding image enhancement processing algorithm can be dynamically selected based on different magnetic field interference, which helps to adapt the image enhancement effect to the current magnetic field environment, and to a certain extent, overcome the interference of the external magnetic field on the image itself, and thus deeply improve the ultrasonic imaging effect.

[0138] Further, different signal-to-noise ratios indicate that the degree of image enhancement processing required is also different, therefore, the mapping relationship between the preset signal-to-noise ratio and the optimization coefficient can be stored in advance, and then the target optimization coefficient corresponding to the target signal-to-noise ratio can be determined based on the mapping relationship, and then part or all of the parameters in the default algorithm control parameter are optimized according to the target optimization coefficient to obtain the second algorithm control parameter, that is, the second algorithm control parameter=(1+target optimization coefficient)*default algorithm control parameter, and then the first image is subjected to image enhancement processing according to the second image enhancement processing algorithm and the second algorithm control parameter to obtain the third image, in this way, when the image quality of the ultrasonic imaging is good, the image can be directly saved, when it is poor, it is reacquired, and when it is general, the image is dynamically enhanced based on the magnetic field interference and the signal-to-noise ratio of the image itself, which helps to improve the efficiency of ultrasonic imaging.

[0139] Optionally, the step of obtaining the target magnetic field interference intensity parameter of the current environment can include the following steps:

[0140] determining a first magnetic field interference intensity parameter of a position where the ultrasonic sensor is located;

[0141] determining a second magnetic field interference intensity parameter of a position where the target object is located;

[0142] determining a target weight pair according to the target relative position parameter, the target weight pair including a first weight and a second weight, the first weight corresponding to the first magnetic field interference intensity parameter, and the second weight corresponding to the second magnetic field interference intensity parameter;

[0143] performing weighted operation according to the first magnetic field interference intensity parameter, the second magnetic field interference intensity parameter, and the target weight pair to obtain the target magnetic field interference intensity parameter.

[0144] In the embodiments of the present application, the first magnetic field interference intensity parameter of the position where the ultrasonic sensor is located can be determined when the ultrasonic sensor is turned off, and the second magnetic field interference intensity parameter of the position where the target object is located can be determined.

[0145] Further, a target weight pair can also be determined according to the target relative position parameter, the target weight pair including a first weight and a second weight, the first weight corresponding to the first magnetic field interference intensity parameter, and the second weight corresponding to the second magnetic field interference intensity parameter, that is, the target relative position parameter can include a target relative distance, that is, according to a preset mapping relationship between the distance and the weight pair, a target weight pair corresponding to the target relative distance can be determined based on the mapping relationship. The first weight+the second weight=1.

[0146] Further, the first magnetic field interference strength parameter, the second magnetic field interference strength parameter and the target weight value can be subjected to a weighted operation to obtain a target magnetic field interference strength parameter, specifically as follows: target magnetic field interference strength parameter = first weight value * first magnetic field interference strength parameter + second weight value * second magnetic field interference strength parameter. In this way, the magnetic field interference conditions of the position where the ultrasonic sensor is located and the position where the target object is located can be comprehensively considered, the influence of the two on ultrasonic imaging can be dynamically evaluated, and the final magnetic field interference condition can be determined based on the two magnetic field interference conditions, so that the final magnetic field interference strength parameter is in deep accordance with the actual environment, which helps to improve the ultrasonic imaging effect.

[0147] 113. performing image segmentation on the region where the target object in the target image is located to obtain a target region.

[0148] In the embodiments of the present application, image segmentation can be performed on the region where the target object in the target image is located to obtain a target region related to the target object. Since the ultrasonic imaging depth is in accordance with the actual situation, the region image of the target object can also be in deep accordance with the actual situation, thereby helping to ensure the accuracy of the weld point recognition.

[0149] 114. obtaining a feature set of the target region, and performing weld point recognition based on the feature set.

[0150] In specific implementations, the feature set can include at least one feature, and the feature can include at least one of the following: feature points, feature vectors, feature values, areas, widths, thicknesses, perimeters, shapes, etc., without limitation.

[0151] Specifically, the feature set of the target region can be obtained, and then weld point recognition is performed based on the feature set, i.e., whether the target object is a weld point or not, or whether the target object is a false weld, etc., without limitation.

[0152] Optionally, the step 114 of performing weld point recognition based on the feature set can include the following steps:

[0153] comparing the feature set with a preset feature set to obtain a target comparison result;

[0154] determining a weld point recognition result based on the target comparison result.

[0155] The preset feature set can include at least one feature, and the feature can include at least one of the following: feature points, feature vectors, feature values, areas, widths, thicknesses, perimeters, shapes, etc., without limitation. The preset feature set can be a feature set of a normal weld point, or a feature set of a false weld, etc., without limitation.

[0156] In specific implementation, the feature set can be compared with the preset feature set to obtain a target comparison result, and then the welding point recognition result can be determined according to the target comparison result. For example, a mapping relationship between a preset comparison result and a welding point recognition result can be stored in advance, and then the target comparison result can be determined to determine the welding point recognition result according to the mapping relationship. In this way, whether the different comparison results are welding points or false welding, and even in the case of identifying welding points, the welding point quality can also be identified. For example, the greater the comparison result is, the better the welding point quality is. Since the ultrasonic imaging depth conforms to the actual situation, the area image of the target object also conforms to the actual situation in depth, which helps to ensure the accuracy of welding point recognition. In this way, the ultrasonic imaging effect of the automobile part processing equipment can be improved to improve the accuracy of welding point recognition.

[0157] It can be seen that the ultrasonic image processing method described in the embodiments of the present application is applied to the automobile part processing equipment, the automobile part processing equipment includes an ultrasonic sensor, the target relative position parameter between the automobile part processing equipment and a target object is determined through the ultrasonic sensor; the target object includes a suspected welding point or a user-specified position or region; a first working parameter corresponding to the target relative position parameter is determined; the ultrasonic sensor is controlled to work at the first working parameter to obtain a first image of the target object; a first low-frequency component part and a first high-frequency component part of the first image are determined; a first energy value of the first low-frequency component part and a second energy value of the first image are determined; a target ratio between the first energy value and the second energy value is determined; when the target ratio is not in a preset range, a first deviation between the target ratio and the preset range is determined; the first working parameter is adjusted according to the first deviation to obtain a second working parameter; the ultrasonic sensor is controlled to work at the second working parameter to obtain a second image of the target object; a first feature distribution density is determined according to the first high-frequency component part; a first image enhancement processing parameter corresponding to the first feature distribution density is determined;According to the first image enhancement processing parameter, the second image is subjected to image enhancement processing to obtain a target image, the target object region in the target image is subjected to image segmentation to obtain a target region, a feature set of the target region is acquired, and welding point recognition is performed according to the feature set. Firstly, the corresponding first working parameter can be configured based on the target relative position parameter between the ultrasonic sensor and the target object, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment. Secondly, ultrasonic imaging is performed by using the first working parameter to obtain a first image. The first low-frequency component part of the first image reflects the basic structure of the image, and the first high-frequency component part of the first image reflects the detail information of the image. If the energy proportion of the first low-frequency component part is too high, more details will be covered. If the energy proportion of the first low-frequency component part is too low, the basic structure of the image will not be clear. Therefore, it is necessary to ensure that the first low-frequency component part is within a reasonable range. If the energy proportion of the first low-frequency component part is not within the reasonable range, the first working parameter needs to be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image returns to the reasonable range. Thirdly, ultrasonic imaging is performed by using the second working parameter to obtain a second image. Since the working parameter is adjusted, the high-frequency and low-frequency parts of the image are affected to a certain extent. In order to prevent the image from being over-adjusted or under-enhanced, the second image is dynamically adjusted and fed back based on the feature distribution in the first high-frequency component part of the first image to obtain a final target image. The depth of the final ultrasonic imaging conforms to the actual situation, and the image is prevented from being over-enhanced or under-enhanced. Fourthly, since the depth of the ultrasonic imaging conforms to the actual situation, the region image of the target object can also conform to the actual situation, which helps to ensure the accuracy of welding point recognition. In this way, the ultrasonic imaging effect of the automobile part processing equipment can be improved to improve the accuracy of welding point recognition.

[0158] Consistent with the above embodiments, please refer to Figure 2 , Figure 2 is a structural schematic diagram of an automobile part processing equipment provided by the embodiment of the present application, as shown in the figure, which includes a processor, a memory, a communication interface and one or more programs. The above one or more programs are stored in the above memory and are configured to be executed by the above processor. In the embodiment of the present application, the automobile part processing equipment further includes an ultrasonic sensor. The program includes instructions for performing the following steps:

[0159] Determine the target relative position parameter between the automobile part processing equipment and the target object by the ultrasonic sensor;

[0160] Determine the first working parameter corresponding to the target relative position parameter;

[0161] control the ultrasonic sensor to work at the first working parameter to obtain a first image of the target object;

[0162] determine a first low-frequency component part and a first high-frequency component part of the first image;

[0163] determine a first energy value of the first low-frequency component part and a second energy value of the first image;

[0164] determine a target ratio value between the first energy value and the second energy value;

[0165] when the target ratio value is not in a preset range, determine a first deviation between the target ratio value and the preset range;

[0166] adjust the first working parameter according to the first deviation to obtain a second working parameter;

[0167] control the ultrasonic sensor to work at the second working parameter to obtain a second image of the target object;

[0168] determine a first feature distribution density according to the first high-frequency component part;

[0169] determine a first image enhancement processing parameter corresponding to the first feature distribution density;

[0170] perform image enhancement processing on the second image according to the first image enhancement processing parameter to obtain a target image.

[0171] Optionally, the first image enhancement processing parameter includes a first image enhancement processing algorithm and a first algorithm control parameter;

[0172] In the aspect of determining the first image enhancement processing parameter corresponding to the first feature distribution density, the above program includes instructions for performing the following steps:

[0173] determine a first image enhancement processing algorithm corresponding to the first feature distribution density;

[0174] obtain an initial algorithm control parameter of the first image enhancement processing algorithm;

[0175] determine a second high-frequency component part of the second image;

[0176] determine a second feature distribution density according to the second high-frequency component part;

[0177] determine a second deviation between the second feature distribution density and the first feature distribution density;

[0178] determine a target feedback adjustment parameter corresponding to the second deviation;

[0179] feedback adjust the initial algorithm control parameter according to the target feedback adjustment parameter to obtain a first algorithm control parameter.

[0180] Optionally, the target relative position parameter comprises a target relative distance and a target relative angle.

[0181] The first working parameter comprises a first transmission power of the ultrasonic sensor and a first transmission direction of the ultrasonic sensor.

[0182] In the aspect of determining the first working parameter corresponding to the target relative position parameter, the program comprises instructions for performing the following steps:

[0183] determining a reference transmission power according to the target relative distance;

[0184] determining a reference transmission direction according to the target relative angle; the reference transmission direction is a direction in which the ultrasonic sensor points to the target object;

[0185] constructing a target vector according to the reference transmission power, the reference transmission direction and the target relative distance;

[0186] determining a first position of the target object and determining a second position, a second transmission power and a second transmission direction of a target interference source;

[0187] constructing a first vector according to the first position, the second position, the second transmission power and the second transmission direction;

[0188] determining a second vector according to the first vector and the target vector; a resultant vector of the first vector and the second vector is the target vector;

[0189] determining the first working parameter according to the second vector.

[0190] Optionally, the program further comprises instructions for performing the following steps:

[0191] when the target ratio is in the preset range, determining an image quality evaluation value of the first image;

[0192] when the image quality evaluation value is greater than a first preset threshold, saving the first image;

[0193] when the image quality evaluation value is less than or equal to the first preset threshold, determining a target difference value between the preset threshold and the image quality evaluation value;

[0194] when the target difference is greater than a second preset threshold, performing the step of controlling the ultrasonic sensor to work at the first working parameter;

[0195] when the target difference is less than or equal to the second preset threshold, determining a target signal-to-noise ratio of the first image;

[0196] obtaining a target magnetic field interference intensity parameter of a current environment;

[0197] determining a second image enhancement processing algorithm corresponding to the target magnetic field interference intensity parameter;

[0198] obtaining a default algorithm control parameter corresponding to the second image enhancement processing algorithm;

[0199] determining a target optimization coefficient corresponding to the target signal-to-noise ratio;

[0200] optimizing the default algorithm control parameter according to the target optimization coefficient to obtain a second algorithm control parameter;

[0201] performing image enhancement processing on the first image according to the second image enhancement processing algorithm and the second algorithm control parameter to obtain a third image.

[0202] Optionally, in the aspect of obtaining the target magnetic field interference intensity parameter of the current environment, the above program includes instructions for performing the following steps:

[0203] determining a first magnetic field interference intensity parameter of a position where the ultrasonic sensor is located;

[0204] determining a second magnetic field interference intensity parameter of a position where the target object is located;

[0205] determining a target weight pair according to the target relative position parameter, the target weight pair including a first weight and a second weight, the first weight corresponding to the first magnetic field interference intensity parameter, and the second weight corresponding to the second magnetic field interference intensity parameter;

[0206] performing weighted operation according to the first magnetic field interference intensity parameter, the second magnetic field interference intensity parameter and the target weight pair to obtain the target magnetic field interference intensity parameter.

[0207] Optionally, in the aspect of identifying the welding spot according to the feature set, the above program includes instructions for performing the following steps:

[0208] comparing the feature set with a preset feature set to obtain a target comparison result;

[0209] determining a welding spot identification result according to the target comparison result.

[0210] It can be seen that the automobile part processing equipment described in the embodiment of the application, the automobile part processing equipment includes an ultrasonic sensor, first, based on the target relative position parameter between the ultrasonic sensor and the target object, the corresponding first working parameter is configured, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment, second, ultrasonic imaging is carried out by using the first working parameter to obtain a first image, the first low-frequency component part of which reflects the basic structure of the image, and the first high-frequency component part reflects the detail information of the image, if the energy proportion of the first low-frequency component part is too high, it will cover more details, and if the energy proportion of the first low-frequency component part is too low, it will cause the basic structure of the image to be unclear, therefore, it is necessary to ensure that the first low-frequency component part is within a reasonable range, if the energy proportion of the first low-frequency component part is not within a reasonable range, the first working parameter needs to be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image returns to a reasonable range, and then, the second working parameter is obtained after adjustment, third, ultrasonic imaging is carried out by using the second working parameter to obtain a second image, since the working parameter is adjusted, it has a certain degree of influence on the high-frequency and low-frequency parts in the image, in order to suppress excessive image adjustment or image under-enhancement, the second image is dynamically feedback adjusted based on the feature distribution in the first high-frequency component part of the first image to obtain the final target image, so that the depth of the final ultrasonic imaging conforms to the actual situation, and also prevents image over-enhancement or under-enhancement, fourth, since the depth of ultrasonic imaging conforms to the actual situation, it can ensure that the regional image of the target object also conforms to the actual situation in depth, which helps to ensure the accuracy of weld point identification, in this way, the ultrasonic imaging effect of the automobile part processing equipment can be improved to improve the accuracy of weld point identification.

[0211] Figure 3 is a functional unit composition block diagram of an ultrasonic image processing device 300 involved in the embodiment of the application, applied to an automobile part processing equipment, the automobile part processing equipment includes an ultrasonic sensor, the ultrasonic image processing device 300 includes: a determination unit 301, a control unit 302, an adjustment unit 303, an enhancement unit 304, a segmentation unit 305 and an identification unit 306, wherein,

[0212] The determination unit 301 is configured to determine the target relative position parameter between the automobile part processing equipment and the target object by the ultrasonic sensor; the target object includes a suspected weld point or a user-specified position or region;

[0213] The control unit 302 is configured to control the ultrasonic sensor to work with the first working parameter to obtain a first image of the target object;

[0214] The determining unit 301 is further configured to determine a first low-frequency component part and a first high-frequency component part of the first image, determine a first energy value of the first low-frequency component part and a second energy value of the first image, determine a target ratio value between the first energy value and the second energy value, and determine a first deviation degree between the target ratio value and a preset range when the target ratio value is not in the preset range.

[0215] The adjusting unit 303 is further configured to adjust the first working parameter according to the first deviation degree to obtain a second working parameter.

[0216] The control unit 302 is further configured to control the ultrasonic sensor to work in the second working parameter to obtain a second image of the target object.

[0217] The determining unit 301 is further configured to determine a first feature distribution density according to the first high-frequency component part, and determine a first image enhancement processing parameter corresponding to the first feature distribution density.

[0218] The enhancing unit 304 is configured to perform image enhancement processing on the second image according to the first image enhancement processing parameter to obtain a target image.

[0219] The segmenting unit 305 is configured to perform image segmentation on a region where the target object is located in the target image to obtain a target region.

[0220] The recognizing unit 306 is configured to acquire a feature set of the target region, and perform weld point recognition according to the feature set.

[0221] Optionally, the first image enhancement processing parameter includes a first image enhancement processing algorithm and a first algorithm control parameter.

[0222] In the aspect of determining the first image enhancement processing parameter corresponding to the first feature distribution density, the determining unit 301 is specifically configured to:

[0223] determine a first image enhancement processing algorithm corresponding to the first feature distribution density.

[0224] acquire an initial algorithm control parameter of the first image enhancement processing algorithm.

[0225] determine a second high-frequency component part of the second image.

[0226] determine a second feature distribution density according to the second high-frequency component part.

[0227] determine a second deviation degree between the second feature distribution density and the first feature distribution density.

[0228] determine a target feedback adjustment parameter corresponding to the second deviation degree;

[0229] perform feedback adjustment on the initial algorithm control parameter according to the target feedback adjustment parameter to obtain a first algorithm control parameter.

[0230] Optionally, the target relative position parameter comprises a target relative distance and a target relative angle.

[0231] The first working parameter comprises a first transmission power of the ultrasonic sensor and a first transmission direction of the ultrasonic sensor.

[0232] In the determination of the first working parameter corresponding to the target relative position parameter, the determination unit 301 is specifically configured to:

[0233] determine a reference transmission power according to the target relative distance;

[0234] determine a reference transmission direction according to the target relative angle; the reference transmission direction is a direction in which the ultrasonic sensor points to the target object.

[0235] construct a target vector according to the reference transmission power, the reference transmission direction and the target relative distance;

[0236] determine a first position of the target object and a second position, a second transmission power and a second transmission direction of a target interference source;

[0237] construct a first vector according to the first position, the second position, the second transmission power and the second transmission direction;

[0238] determine a second vector according to the first vector and the target vector; a resultant vector of the first vector and the second vector is the target vector.

[0239] determine the first working parameter according to the second vector.

[0240] Optionally, the ultrasonic image processing apparatus 300 is further specifically configured to:

[0241] when the target ratio is in the preset range, determine an image quality evaluation value of the first image;

[0242] when the image quality evaluation value is greater than a first preset threshold, save the first image;

[0243] when the image quality evaluation value is less than or equal to the first preset threshold, determine a target difference value between the preset threshold and the image quality evaluation value.

[0244] when the target difference is greater than a second preset threshold, performing the step of controlling the ultrasonic sensor to work at the first working parameter;

[0245] when the target difference is less than or equal to the second preset threshold, determining a target signal-to-noise ratio of the first image;

[0246] obtaining a target magnetic field interference intensity parameter of a current environment;

[0247] determining a second image enhancement processing algorithm corresponding to the target magnetic field interference intensity parameter;

[0248] obtaining a default algorithm control parameter corresponding to the second image enhancement processing algorithm;

[0249] determining a target optimization coefficient corresponding to the target signal-to-noise ratio;

[0250] optimizing the default algorithm control parameter according to the target optimization coefficient to obtain a second algorithm control parameter;

[0251] performing image enhancement processing on the first image according to the second image enhancement processing algorithm and the second algorithm control parameter to obtain a third image.

[0252] Optionally, in the aspect of obtaining the target magnetic field interference intensity parameter of the current environment, the ultrasonic image processing apparatus 300 is specifically configured to:

[0253] determining a first magnetic field interference intensity parameter of a position where the ultrasonic sensor is located;

[0254] determining a second magnetic field interference intensity parameter of a position where the target object is located;

[0255] determining a target weight pair according to the target relative position parameter, the target weight pair including a first weight and a second weight, the first weight corresponding to the first magnetic field interference intensity parameter, and the second weight corresponding to the second magnetic field interference intensity parameter;

[0256] performing weighted operation according to the first magnetic field interference intensity parameter, the second magnetic field interference intensity parameter and the target weight pair to obtain the target magnetic field interference intensity parameter.

[0257] Optionally, in the aspect of identifying the welding point according to the feature set, the identification unit 306 is specifically configured to:

[0258] comparing the feature set with a preset feature set to obtain a target comparison result;

[0259] determining a welding point identification result according to the target comparison result.

[0260] It can be seen that the ultrasonic image processing device described in the embodiment of the application,

[0261] The application is applied to an automobile part processing device. The automobile part processing device includes an ultrasonic sensor. Firstly, a corresponding first working parameter is configured based on a target relative position parameter between the ultrasonic sensor and a target object, so that the working parameter depth of the ultrasonic sensor conforms to the actual environment. Secondly, ultrasonic imaging is performed by using the first working parameter to obtain a first image. The first low-frequency component part of the first image reflects the basic structure of the image, and the first high-frequency component part of the first image reflects the detail information of the image. If the energy proportion of the first low-frequency component part is too high, more details will be covered. If the energy proportion of the first low-frequency component part is too low, the basic structure of the image will not be clear. Therefore, it is necessary to ensure that the first low-frequency component part is within a reasonable range. If the energy proportion of the first low-frequency component part is not within the reasonable range, the first working parameter needs to be dynamically adjusted based on the deviation degree, so that the energy proportion of the low-frequency component part of the image returns to the reasonable range. Thirdly, ultrasonic imaging is performed by using the second working parameter to obtain a second image. Since the working parameter is adjusted, the high-frequency and low-frequency parts in the image are affected to a certain extent. In order to prevent the image from being adjusted too much or the image from being under-enhanced, the second image is dynamically feedback adjusted based on the feature distribution in the first high-frequency component part of the first image to obtain a final target image. The depth of the final ultrasonic imaging conforms to the actual situation, and the image is prevented from being over-enhanced or under-enhanced. Fourthly, since the depth of the ultrasonic imaging conforms to the actual situation, the area image of the target object also conforms to the actual situation, which helps to ensure the accuracy of the welding point identification. In this way, the ultrasonic imaging effect of the automobile part processing device can be improved, and the accuracy of the welding point identification can be improved.

[0262] It can be understood that the functions of each program module of the ultrasonic image processing device of the embodiment can be specifically implemented according to the methods in the above method embodiments, and the specific implementation process can be referred to the related description of the above method embodiments, which will not be described here.

[0263] The embodiment of the application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any method described in the above method embodiments. The above computer includes an automobile part processing device.

[0264] The embodiment of the present application further provides a computer program product, which comprises a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform some or all of the steps of any method described in the above method embodiments. The computer program product can be a software installation package, and the computer comprises an automobile part processing device.

[0265] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0266] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0267] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented by other means. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical or other forms.

[0268] The units described above as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0269] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0270] If the above integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the above-mentioned method of each embodiment of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0271] A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by programs instructing relevant hardware, and the programs can be stored in a computer readable memory, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0272] The embodiments of the present application are described in detail above, and the specific examples are applied to the principles and implementation modes of the present application. The above embodiment description is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed; in summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An ultrasonic image processing method, characterized in that: Applied to automobile parts processing equipment, the automobile parts processing equipment includes an ultrasonic sensor, and the method includes: Determining target relative position parameters between the automotive parts processing equipment and a target object by using the ultrasonic sensor; the target object includes a suspected welding point or a user-specified position; Determining a first operating parameter corresponding to the target relative position parameter, wherein a mapping relationship between preset relative position parameters and operating parameters of the ultrasonic sensor is pre-stored, and the first operating parameter corresponding to the target relative position parameter can be determined based on the mapping relationship; controlling the ultrasonic sensor to operate with the first operating parameters to obtain a first image of the target object; determining a first low-frequency component portion and a first high-frequency component portion of the first image; determining a first energy value of the first low-frequency component portion and a second energy value of the first image; determining a target ratio between the first energy value and the second energy value; When the target ratio is not within a preset range, determining a first deviation between the target ratio and the preset range; wherein the preset range includes an upper threshold and a lower threshold; a target ratio less than the lower threshold is a first deviation direction, and a target ratio greater than the upper threshold is a second deviation direction; for the first deviation direction, the first deviation = (lower threshold - target ratio) / lower threshold; for the second deviation direction, the first deviation = (upper threshold - target ratio) / upper threshold; Adjust the first operating parameter according to the first deviation to obtain a second operating parameter; the second operating parameter = (1 + first deviation) × first operating parameter; controlling the ultrasonic sensor to operate at the second operating parameter to obtain a second image of the target object; determining a first characteristic distribution density according to the first high-frequency component portion; determining a first image enhancement processing parameter corresponding to the first feature distribution density; performing image enhancement processing on the second image according to the first image enhancement processing parameters to obtain a target image; Performing image segmentation on the area where the target object is located in the target image to obtain a target area; Acquire a feature set of the target area, and perform solder joint recognition based on the feature set; Wherein, the first image enhancement processing parameters include: a first image enhancement processing algorithm and a first algorithm control parameter; The determining of the first image enhancement processing parameter corresponding to the first feature distribution density includes: determining a first image enhancement processing algorithm corresponding to the first feature distribution density; Acquiring initial algorithm control parameters of the first image enhancement processing algorithm; determining a second high frequency component portion of the second image; determining a second characteristic distribution density according to the second high frequency component portion; Determine a second deviation between the second characteristic distribution density and the first characteristic distribution density; second deviation=(second characteristic distribution density-first characteristic distribution density) / (first characteristic distribution density+second characteristic distribution density); determining a target feedback adjustment parameter corresponding to the second deviation; Feedback adjustment is performed on the initial algorithm control parameter according to the target feedback adjustment parameter to obtain the first algorithm control parameter; the first algorithm control parameter = (1 + target feedback adjustment parameter) × initial algorithm control parameter; Wherein, the target relative position parameters include target relative distance and target relative angle; The first operating parameter includes a first transmitting power of the ultrasonic sensor and a first transmitting direction of the ultrasonic sensor; The determining of the first operating parameter corresponding to the target relative position parameter includes: determining a reference transmit power according to the relative distance to the target; Determine a reference emission direction according to the target relative angle; the reference emission direction is the direction in which the ultrasonic sensor points to the target object; Constructing a target vector according to the reference transmit power, the reference transmit direction, and the target relative distance; Determining a first position of the target object, and determining a second position, a second transmission power, and a second transmission direction of a target interference source; constructing a first vector according to the first position, the second position, the second transmission power, and the second transmission direction; Determine a second vector according to the first vector and the target vector, wherein a resultant vector of the first vector and the second vector is the target vector; The first operating parameter is determined according to the second vector; wherein, the vector direction of the second vector is the first transmission direction, and the first transmission power=the vector size of the second vector*the relative distance to the target.

2. The method according to claim 1, characterized in that The method further comprises: When the target ratio is within the preset range, determining an image quality evaluation value of the first image; When the image quality evaluation value is greater than a first preset threshold, saving the first image; When the image quality evaluation value is less than or equal to the first preset threshold, determining a target difference between the preset threshold and the image quality evaluation value; When the target difference is greater than a second preset threshold, executing the step of controlling the ultrasonic sensor to operate with the first operating parameter; When the target difference is less than or equal to the second preset threshold, determining a target signal-to-noise ratio of the first image; Obtain the target magnetic field interference intensity parameters of the current environment; Determining a second image enhancement processing algorithm corresponding to the target magnetic field interference intensity parameter; Acquiring default algorithm control parameters corresponding to the second image enhancement processing algorithm; determining a target optimization coefficient corresponding to the target signal-to-noise ratio; Optimizing the default algorithm control parameters according to the target optimization coefficient to obtain second algorithm control parameters; Perform image enhancement processing on the first image according to the second image enhancement processing algorithm and the second algorithm control parameters to obtain a third image.

3. The method according to claim 2, characterized in that The obtaining of the target magnetic field interference intensity parameter of the current environment includes: Determining a first magnetic field interference intensity parameter at a location of the ultrasonic sensor; Determining a second magnetic field interference intensity parameter at a location of the target object; Determining a target weight pair according to the target relative position parameter, the target weight pair including a first weight and a second weight, the first weight corresponding to the first magnetic field interference intensity parameter, and the second weight corresponding to the second magnetic field interference intensity parameter; A weighted operation is performed on the first magnetic field interference intensity parameter, the second magnetic field interference intensity parameter, and the target weight value to obtain the target magnetic field interference intensity parameter.

4. The method according to claim 1, wherein The identifying of solder joints according to the feature set includes: Comparing the feature set with a preset feature set to obtain a target comparison result; A solder joint recognition result is determined according to the target comparison result.

5. An ultrasonic image processing device, characterized in that: Applied to automobile parts processing equipment, the automobile parts processing equipment includes an ultrasonic sensor, the device includes: a determination unit, a control unit, an adjustment unit, an enhancement unit, a segmentation unit and an identification unit, wherein, The determining unit is configured to determine target relative position parameters between the automobile parts processing equipment and a target object using the ultrasonic sensor; the target object includes a suspected welding point or a user-specified position; The control unit is configured to control the ultrasonic sensor to operate at a first operating parameter corresponding to the target relative position parameter to obtain a first image of the target object; a mapping relationship between a preset relative position parameter and the operating parameter of the ultrasonic sensor is pre-stored, and the first operating parameter corresponding to the target relative position parameter can be determined based on the mapping relationship; The determining unit is further configured to determine a first low-frequency component portion and a first high-frequency component portion of the first image; determine a first energy value of the first low-frequency component portion and a second energy value of the first image; determine a target ratio between the first energy value and the second energy value; and when the target ratio is not within a preset range, determine a first deviation between the target ratio and the preset range; wherein the preset range includes an upper threshold and a lower threshold; a target ratio less than the lower threshold is a first deviation direction, and a target ratio greater than the upper threshold is a second deviation direction; for the first deviation direction, the first deviation = (lower threshold - target ratio) / lower threshold; and for the second deviation direction, the first deviation = (upper threshold - target ratio) / upper threshold; The adjustment unit is further configured to adjust the first operating parameter according to the first deviation to obtain a second operating parameter; the second operating parameter = (1 + first deviation) × first operating parameter; The control unit is further configured to control the ultrasonic sensor to operate with the second operating parameters to obtain a second image of the target object; The determining unit is further configured to determine a first characteristic distribution density based on the first high-frequency component portion; and determine a first image enhancement processing parameter corresponding to the first characteristic distribution density; The enhancement unit is configured to perform image enhancement processing on the second image according to the first image enhancement processing parameters to obtain a target image; The segmentation unit is configured to perform image segmentation on the region where the target object is located in the target image to obtain a target region; The recognition unit is used to obtain a feature set of the target area and perform welding spot recognition based on the feature set; Wherein, the first image enhancement processing parameters include: a first image enhancement processing algorithm and a first algorithm control parameter; The determining of the first image enhancement processing parameter corresponding to the first feature distribution density includes: determining a first image enhancement processing algorithm corresponding to the first feature distribution density; Acquiring initial algorithm control parameters of the first image enhancement processing algorithm; determining a second high frequency component portion of the second image; determining a second characteristic distribution density according to the second high frequency component portion; Determine a second deviation between the second characteristic distribution density and the first characteristic distribution density; second deviation=(second characteristic distribution density-first characteristic distribution density) / (first characteristic distribution density+second characteristic distribution density); determining a target feedback adjustment parameter corresponding to the second deviation; Feedback adjustment is performed on the initial algorithm control parameter according to the target feedback adjustment parameter to obtain the first algorithm control parameter; the first algorithm control parameter = (1 + target feedback adjustment parameter) × initial algorithm control parameter; in, The target relative position parameters include target relative distance and target relative angle; The first operating parameter includes a first transmitting power of the ultrasonic sensor and a first transmitting direction of the ultrasonic sensor; The determining of the first operating parameter corresponding to the target relative position parameter includes: determining a reference transmit power according to the relative distance to the target; Determine a reference emission direction according to the target relative angle; the reference emission direction is the direction in which the ultrasonic sensor points to the target object; Constructing a target vector according to the reference transmit power, the reference transmit direction, and the target relative distance; Determining a first position of the target object, and determining a second position, a second transmission power, and a second transmission direction of a target interference source; constructing a first vector according to the first position, the second position, the second transmission power, and the second transmission direction; Determine a second vector according to the first vector and the target vector, wherein a resultant vector of the first vector and the second vector is the target vector; The first operating parameter is determined according to the second vector; wherein, the vector direction of the second vector is the first transmission direction, and the first transmission power=the vector size of the second vector*the relative distance to the target.

6. An automobile parts processing equipment, characterized in that: The automobile parts processing equipment includes a processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the programs include instructions for executing the steps in the method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that The computer storage medium is used to store one or more programs and is configured to be executed by a processor, wherein the programs include instructions for executing the steps of the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that The computer program product comprises instructions for executing the steps of the method according to any one of claims 1-4.

Images