Anti-interference target acquisition method based on machine vision technology measurement

Abstract

The invention discloses an anti-interference target acquisition method based on machine vision technology measurement. The method comprises the following steps: S1, performing multi-stage filtering preprocessing on an original image; s2, target feature extraction; s3, random forest construction: calling a historical data sample library to obtain an anti-interference target acquisition library, randomly selecting M data points from the anti-interference target acquisition library, creating decision trees for the selected data points, generating a result for each decision tree, comprehensively analyzing the results and outputting a majority vote or average; s4, obtaining a target feature reference set through a random forest; and S5, selecting the first N frames of the on-site detection picture as a training set, obtaining a proper vote counting weight through continuous training, and performing vote analysis from the (N + 1) th frame of image through the determined weight by using an Adaboost algorithm to determine a final target. According to the method, the interference problem in the target capturing process in a complex scene can be effectively solved, and the accuracy and robustness of target detection can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and in particular to an anti-interference target acquisition method based on machine vision technology measurement. Background Art

[0002] Machine vision is an important branch of the field of artificial intelligence. Machine vision is the use of machines to replace human eyes for measurement and judgment. The machine vision system uses machine vision products (i.e. image acquisition devices, such as industrial cameras) to convert the captured target into image signals, which are transmitted to a dedicated image processing system to obtain the morphological information of the captured target and convert it into digital signals based on pixel distribution, brightness, color and other information. The image system performs various operations on these signals to extract the characteristics of the target, and then controls the operation of the equipment on site based on the judgment results.

[0003] It should be pointed out that for machine vision systems, how to effectively process images obtained by machine vision instruments is of paramount importance; among them, the existing technologies mainly focus on the recognition and detection of target images, such as the Chinese invention patent with patent number: ZL202310712312.4, patent name: Fish swimming speed recognition method based on machine vision, and the Chinese invention patent with patent number: ZL202311312489.1, patent name: Goose house disinfection spray image detection method based on machine vision, and the Chinese invention patent with patent number: ZL202310124844.6, patent name: A Chinese invention patent for a seedling fertilization control system based on machine vision.

[0004] It should be emphasized that the existing technology has not yet taken into account the impact that external interference factors may have on the detection and recognition of image targets; in actual usage scenarios, the image acquisition process is often affected by external interference. If this problem is not solved, it may lead to target acquisition failure, making subsequent image processing useless.

[0005] Therefore, in order to solve the problem that target capture failure is easily caused by external interference factors with complex grayscale, shape and dynamic characteristics in the capture scene of machine vision instruments, it is necessary to provide an anti-interference target acquisition method based on machine vision technology measurement. Summary of the invention

[0006] The purpose of the present invention is to provide an interference-resistant target acquisition method based on machine vision technology measurement to address the deficiencies of the prior art. The interference-resistant target acquisition method based on machine vision technology measurement can effectively solve the interference problem in the target capture process in complex scenes and can effectively improve the accuracy and robustness of target detection.

[0007] To achieve the above object, the present invention is implemented through the following technical solutions.

[0008] A method for obtaining an anti-interference target based on machine vision technology measurement includes the following steps, specifically:

[0009] Step S1, image preprocessing: performing multi-stage filtering preprocessing on the captured original image;

[0010] Step S2, target feature extraction: extracting features of the target in the image preprocessed in step S1, and specifically including shape feature extraction, radiation feature extraction and motion feature extraction;

[0011] Step S3, random forest construction: call the historical data sample library to obtain the anti-interference target acquisition library, randomly select M data points from it, create a decision tree for the selected data points, each decision tree will produce a result, comprehensively analyze the results and output the majority vote or average;

[0012] In the process of creating a decision tree, the optimal feature among the extracted features is selected as the node splitting basis of the decision tree, and then the decision tree is recursively constructed using the training data until the samples contained in each leaf node belong to the same category or meet the stopping criteria, then the decision tree construction is completed;

[0013] Step S4, obtaining a target feature reference set through random forest;

[0014] Step S5, select the first N frames of the on-site detection image as the training set, obtain appropriate counting weights through continuous training, and then start from the N+1th frame image, use the determined weights and the Adaboost algorithm to perform voting analysis to determine the final target.

[0015] Among them, in the step S1, the multi-stage filtering preprocessing includes the following steps, specifically:

[0016] Step S1.1, using an adaptive median filter algorithm to filter the captured original image, during which a grayscale threshold is selected according to the maximum grayscale difference between the target and the background to reduce background noise and retain target details;

[0017] Adaptive median filtering algorithm formula:

[0018]

[0019] Step S1.2, further processing the image processed in step S1.1 using a mean filter to further reduce Gaussian noise in the image;

[0020] Step S1.3, using a 3×3 or 5x5 low-pass filter template to smooth the image processed in step S1.2 to remove irrelevant details in the image and blur the image to obtain a rough description of the target to be captured;

[0021] Low pass filter template:

[0022]

[0023] Step S1.4: Enhance the target edge clarity by using the edge extension function.

[0024] Wherein, in the step S2, when extracting shape features from an image, shape descriptors are used to describe the shape of the target in terms of edge, width, length, area, major axis, minor axis, major axis direction, and aspect ratio.

[0025] Wherein, in the step S2, when performing radiation feature extraction on the image, the specific steps include:

[0026] Step S2.1.1, analyzing the grayscale distribution of the target in the image, and extracting the maximum grayscale level, minimum grayscale level, and average grayscale level of the target;

[0027] Step S2.1.2, constructing a grayscale histogram of the target area and determining the grayscale distribution pattern;

[0028] Step S2.1.3: Calculate the signal-to-noise ratio of the regional target to measure the discrimination between the target and the background.

[0029] Wherein, in the step S2, when extracting motion features from the image, the motion characteristics of the target in the time series image are evaluated by multi-scale differential features in the time domain and the space domain, and the motion characteristics include speed, acceleration, motion direction and its changes;

[0030] The specific steps of motion feature extraction include:

[0031] Step S2.2.1, tracking the position or pixel intensity of the target in consecutive image frames to construct time series data of the target;

[0032] Step S2.2.2, analyze the movement of the target at different time intervals or window sizes, differentiate the time series data, extract feature information from the differentiation results, the feature information includes average velocity information, acceleration peak information, frequency and amplitude information of velocity changes, and determine the motion characteristics of the target based on the above feature information.

[0033] Compared with the prior art, the present invention has the following beneficial effects, specifically:

[0034] 1. Through deep learning and multi-feature analysis, it can effectively solve the problem of difficulty in distinguishing real targets from interference targets under the influence of external interference factors;

[0035] 2. By adopting the Adaboost algorithm and weighting the features to build an integrated classifier, the problem of being unable to accurately identify the real target in a multi-target scene with multiple suspected targets can be solved;

[0036] 3. By adopting the time domain and space domain feature change analysis, the problem of poor tracking stability for dynamic targets (especially targets that move quickly or change shape) can be solved;

[0037] 4. Therefore, the anti-interference target acquisition method based on machine vision technology measurement of the present invention can effectively solve the interference problem in the target capture process in complex scenes, and can effectively improve the accuracy and robustness of target detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention is further described below with the aid of the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention.

[0039] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0040] The present invention is described below in conjunction with specific implementation methods.

[0041] Embodiment 1, as Figure 1 As shown, an anti-interference target acquisition method based on machine vision technology measurement is based on a high-precision industrial camera, a computing server and a high-speed image acquisition card. The high-precision industrial camera is used to capture images of the scene in real time and ensure the clarity and continuity of the image. The computing server is a server that meets the requirements of running complex image processing algorithms and machine learning models. The high-speed image acquisition card is used to transmit the image data captured by the industrial camera to the computing device in real time.

[0042] Specifically, the anti-interference target acquisition method based on machine vision technology measurement includes the following steps:

[0043] Step S1, image preprocessing: performing multi-stage filtering preprocessing on the captured original image;

[0044] Step S2, target feature extraction: extracting features of the target in the image preprocessed in step S1, and specifically including shape feature extraction, radiation feature extraction and motion feature extraction;

[0045] When extracting shape features from an image, shape descriptors are used to describe the shape of the target, including its edge, width, length, area, major axis, minor axis, major axis direction, and aspect ratio.

[0046] Step S3, random forest construction: call the historical data sample library to obtain the anti-interference target acquisition library, randomly select M data points from it, create a decision tree for the selected data points, each decision tree will produce a result, comprehensively analyze the results and output the majority vote or average;

[0047] In the process of creating a decision tree, the optimal feature among the extracted features is selected as the node splitting basis of the decision tree, and then the decision tree is recursively constructed using the training data until the samples contained in each leaf node belong to the same category or meet the stopping criteria, then the decision tree construction is completed;

[0048] Step S4, obtaining a target feature reference set through random forest;

[0049] Step S5, select the first N frames of the on-site detection image as the training set, obtain the appropriate counting weights through continuous training, and then start from the N+1th frame image, use the determined weights and the Adaboost algorithm to perform voting analysis to determine the final target;

[0050] Specifically, the steps of the Adaboost algorithm are:

[0051] a. First, assign the same weight to each training sample Where N is the number of samples;

[0052] b. Then for each round t=1,2,...,T:

[0053] 1) Use weighted data to train a weak classifier;

[0054] 2) Calculate the error rate of the weak classifier Where I is the indicator function, yi is the actual label, and ht(xi) is the prediction of the classifier;

[0055] 3) Calculate the weight of the weak classifier

[0056] 4) Update sample weight ωi←ωiexp(-αtyiht(xi));

[0057] c. Finally, build the final classifier.

[0058] The anti-interference target acquisition method based on machine vision technology measurement of the first embodiment has the following advantages, specifically:

[0059] 1. Through deep learning and multi-feature analysis, it can effectively solve the problem of difficulty in distinguishing real targets from interference targets under the influence of external interference factors;

[0060] 2. By adopting the Adaboost algorithm and weighting the features to build an integrated classifier, the problem of being unable to accurately identify the real target in a multi-target scene with multiple suspected targets can be solved;

[0061] 3. By adopting the time domain and space domain feature change analysis, the problem of poor tracking stability for dynamic targets (especially targets that move quickly or change shape) can be solved;

[0062] Based on the above, it can be seen that the anti-interference target acquisition method based on machine vision technology measurement in the first embodiment can effectively solve the interference problem in the target capture process in complex scenes, and can effectively improve the accuracy and robustness of target detection.

[0063] Embodiment 2: The difference between the embodiment 2 and the embodiment 1 is that: in step S1, the multi-stage filtering preprocessing includes the following steps, specifically:

[0064] Step S1.1, using an adaptive median filter algorithm to filter the captured original image, during which a grayscale threshold is selected according to the maximum grayscale difference between the target and the background to reduce background noise and retain target details;

[0065] Adaptive median filtering algorithm formula:

[0066]

[0067] Step S1.2, further processing the image processed in step S1.1 using a mean filter to further reduce Gaussian noise in the image;

[0068] Step S1.3, using a 3×3 or 5x5 low-pass filter template to smooth the image processed in step S1.2 to remove irrelevant details in the image and blur the image to obtain a rough description of the target to be captured;

[0069] Low pass filter template:

[0070]

[0071] Step S1.4: Enhance the target edge clarity by using the edge extension function.

[0072] Embodiment 3: The difference between the embodiment 3 and the embodiment 1 is that: in step S2, when performing radiation feature extraction on the image, the specific steps include:

[0073] Step S2.1.1, analyzing the grayscale distribution of the target in the image, and extracting the maximum grayscale level, minimum grayscale level, and average grayscale level of the target;

[0074] Step S2.1.2, constructing a grayscale histogram of the target area and determining the grayscale distribution pattern;

[0075] Step S2.1.3: Calculate the signal-to-noise ratio of the regional target to measure the discrimination between the target and the background.

[0076] Embodiment 4: The difference between the embodiment 4 and the embodiment 1 is that: in the step S2, when extracting motion features from the image, the motion characteristics of the target in the time series image are evaluated by multi-scale differential features in the time domain and the space domain, and the motion characteristics include speed, acceleration, motion direction and changes thereof;

[0077] The specific steps of motion feature extraction include:

[0078] Step S2.2.1, tracking the position or pixel intensity of the target in consecutive image frames to construct time series data of the target;

[0079] Step S2.2.2, analyze the movement of the target at different time intervals or window sizes, differentiate the time series data, extract feature information from the differentiation results, the feature information includes average velocity information, acceleration peak information, frequency and amplitude information of velocity changes, and determine the motion characteristics of the target based on the above feature information.

[0080] The above contents are only preferred embodiments of the present invention. For ordinary technicians in this field, according to the concept of the present invention, there will be changes in the specific implementation methods and application scopes. The content of this specification should not be understood as limiting the present invention.

Claims

1. A method for obtaining an anti-interference target based on machine vision technology measurement, characterized in that: The following steps are included, specifically: Step S1, image preprocessing: performing multi-stage filtering preprocessing on the captured original image; Step S2, target feature extraction: extracting features of the target in the image preprocessed in step S1, and specifically including shape feature extraction, radiation feature extraction and motion feature extraction; Step S3, random forest construction: call the historical data sample library to obtain the anti-interference target acquisition library, randomly select M data points from it, create a decision tree for the selected data points, each decision tree will produce a result, comprehensively analyze the results and output the majority vote or average; In the process of creating a decision tree, the optimal feature among the extracted features is selected as the node splitting basis of the decision tree, and then the decision tree is recursively constructed using the training data until the samples contained in each leaf node belong to the same category or meet the stopping criteria, then the decision tree construction is completed; Step S4, obtaining a target feature reference set through random forest; Step S5, select the first N frames of the on-site detection image as the training set, obtain appropriate counting weights through continuous training, and then start from the N+1th frame image, use the determined weights and the Adaboost algorithm to perform voting analysis to determine the final target.

2. The method for obtaining an anti-interference target based on machine vision technology measurement according to claim 1, characterized in that: In step S1, the multi-stage filtering preprocessing includes the following steps, specifically: Step S1.1: Use the adaptive median filter algorithm to filter the captured original image. During this process, the grayscale threshold is selected according to the maximum grayscale difference between the target and the background to reduce background noise and retain target details: Adaptive median filtering algorithm formula: Step S1.2, further processing the image processed in step S1.1 using a mean filter to further reduce Gaussian noise in the image; Step S1.3, using a 3×3 or 5x5 low-pass filter template to smooth the image processed in step S1.2 to remove irrelevant details in the image and blur the image to obtain a rough description of the target to be captured; Low pass filter template: Step S1.4: Enhance the target edge clarity by using the edge extension function.

3. The method for obtaining an anti-interference target based on machine vision technology measurement according to claim 1, characterized in that: In step S2, when extracting shape features from an image, shape descriptors are used to describe the shape of the target using the edge, width, length, area, major axis, minor axis, major axis direction, and aspect ratio.

4. The method for obtaining an anti-interference target based on machine vision technology measurement according to claim 1, characterized in that: In step S2, when performing radiation feature extraction on an image, the specific steps include: Step S2.1.1, analyzing the grayscale distribution of the target in the image, and extracting the maximum grayscale level, minimum grayscale level, and average grayscale level of the target; Step S2.1.2, constructing a grayscale histogram of the target area and determining the grayscale distribution pattern; Step S2.1.3: Calculate the signal-to-noise ratio of the regional target to measure the discrimination between the target and the background.

5. The method for obtaining an anti-interference target based on machine vision technology measurement according to claim 1, characterized in that: In step S2, when extracting motion features from images, the motion characteristics of the target in the time series images are evaluated by multi-scale differential features in the time domain and the space domain, and the motion characteristics include speed, acceleration, motion direction and changes thereof; The specific steps of motion feature extraction include: Step S2.2.1, tracking the position or pixel intensity of the target in consecutive image frames to construct time series data of the target; Step S2.2.2, analyze the movement of the target at different time intervals or window sizes, differentiate the time series data, extract feature information from the differentiation results, the feature information includes average velocity information, acceleration peak information, frequency and amplitude information of velocity changes, and determine the motion characteristics of the target based on the above feature information.

Images