CN112733853A - Method for detecting separation and associated mineral separation effect based on foreground and background - Google Patents
Method for detecting separation and associated mineral separation effect based on foreground and background Download PDFInfo
- Publication number
- CN112733853A CN112733853A CN202110074956.6A CN202110074956A CN112733853A CN 112733853 A CN112733853 A CN 112733853A CN 202110074956 A CN202110074956 A CN 202110074956A CN 112733853 A CN112733853 A CN 112733853A
- Authority
- CN
- China
- Prior art keywords
- feature map
- foreground
- classification
- feature
- background
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The application relates to intelligent quality detection in the field of intelligent manufacturing, and particularly discloses a method for detecting separation and associated mineral separation effects based on a foreground background.
Description
Technical Field
The present invention relates to intelligent quality detection in the field of smart manufacturing, and more particularly, to a method for detecting separation and associated mineral separation effects based on a foreground and a background, a system for detecting separation and associated mineral separation effects based on a foreground and a background, and an electronic device.
Background
In a coal-fired boiler of a thermal power plant, coal is combusted to generate flue gas, the flue gas contains a large amount of smoke dust, the flue gas passes through an electric dust remover, gas and dust in the flue gas are separated, and the separated dust is fly ash. The fly ash is usually further processed through a flotation column, which is short for a flotation column that separates minerals by a flotation process. Specifically, in the flotation column, the fly ash is treated by adding a medicament to form ore pulp, and after stirring and aeration, certain ore particles in the fly ash can be selectively fixed on bubbles and float to the surface of the ore pulp. Thus, mineral separation can be achieved by scraping the formed foam product away from the slurry.
However, if it is desired to test the mineral separation effectiveness of the flotation column, which requires separate testing of the froth product and the composition of the slurry, in practice, there have been many skilled workers who have roughly determined the mineral separation effectiveness of the flotation column by observing the froth product floating from the slurry.
At present, deep learning and neural networks have been widely applied in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks also exhibit a level close to or even exceeding that of humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like.
Based on this, the inventor of the present application expects a detection scheme to further obtain the mineral separation effect of the flotation column on a visual level by introducing a computer vision technology based on deep learning.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a detection method for separation and associated mineral separation effect based on a foreground background, a detection system for separation and associated mineral separation effect based on a foreground background and electronic equipment.
According to one aspect of the application, a method for detecting separation and associated mineral separation effect based on foreground and background is provided, which comprises the following steps:
acquiring an ore pulp image to be detected, wherein the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp;
enabling the ore pulp image to be detected to pass through a first convolutional neural network to obtain an initial characteristic diagram;
determining a first region of interest in the initial profile corresponding to the slurry portion and a second region of interest corresponding to the froth product;
extracting feature values in the first region of interest in the initial feature map and filling other parts with default values to obtain a background feature map;
extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map;
inputting the foreground feature map and the background feature map into a second convolutional neural network respectively to obtain a first feature map and a second feature map;
calculating a cosine distance between the first feature map and the second feature map to serve as a similarity coefficient between the first feature map and the second feature map;
fusing the first feature map and the second feature map based on the similarity coefficient to obtain a third feature map;
fusing the first feature map, the second feature map and the third feature map to obtain a classification feature map; and
and passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
In the above method for detecting separation based on foreground and background and associated mineral separation effect, determining a first region of interest corresponding to the pulp portion and a second region of interest corresponding to the foam product in the initial feature map includes: and determining a first interested area corresponding to the ore pulp part and a second interested area corresponding to the foam product in the initial characteristic map through image semantic segmentation.
In the method for detecting separation based on foreground and background and associated mineral separation effect, extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map, including: performing global mean pooling on the initial feature map to obtain a feature value; and extracting the characteristic value in the second region of interest in the initial characteristic map and filling other parts with the characteristic value as a default value to obtain a foreground characteristic map.
In the method for detecting separation based on foreground and background and associated mineral separation effect, based on the similarity coefficient, fusing the first feature map and the second feature map to obtain a third feature map, including: and calculating the weighted sum of the first feature map and the second feature map by taking the similarity coefficient as the weighting coefficient of the first feature map and subtracting the similarity coefficient by one as the weighting coefficient of the second feature map so as to obtain the third feature map.
In the method for detecting the separation and associated mineral separation effect based on the foreground and background, the step of passing the classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the mineral separation effect of the flotation column meets a preset standard or not, includes: passing the classification feature map through one or more fully connected layers to obtain a classification feature vector; and inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In the method for detecting the separation and associated mineral separation effect based on the foreground and background, the first convolutional neural network and the second convolutional neural network are depth residual error networks.
According to another aspect of the application, a detection system for separation based on foreground background and associated mineral separation effect comprises:
the system comprises an image acquisition unit, a data acquisition unit and a data processing unit, wherein the image acquisition unit is used for acquiring an ore pulp image to be detected, and the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp;
the initial characteristic map generating unit is used for enabling the ore pulp image to be detected obtained by the image obtaining unit to pass through a first convolutional neural network so as to obtain an initial characteristic map;
a region-of-interest determination unit for determining a first region of interest corresponding to the slurry portion and a second region of interest corresponding to the foam product in the initial feature map obtained by the initial feature map generation unit;
a background feature map generating unit, configured to extract feature values in the first region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and fill other portions with default values to obtain a background feature map;
a foreground feature map generating unit, configured to extract feature values in the second region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and fill other portions with default values to obtain a foreground feature map;
the feature map generating unit is used for inputting the foreground feature map obtained by the foreground feature map generating unit and the background feature map obtained by the background feature map generating unit into a second convolutional neural network respectively so as to obtain a first feature map and a second feature map;
a similarity coefficient calculation unit, configured to calculate a cosine distance between the first feature map and the second feature map obtained by the feature map generation unit, as a similarity coefficient between the first feature map and the second feature map;
a third feature map generation unit configured to fuse the first feature map and the second feature map obtained by the feature map generation unit based on the similarity coefficient obtained by the similarity coefficient calculation unit to obtain a third feature map;
a classification feature map generation unit, configured to fuse the first feature map, the second feature map, and the third feature map obtained by the feature map generation unit to obtain a classification feature map; and
and the classification result generating unit is used for enabling the classification characteristic diagram obtained by the classification characteristic diagram generating unit to pass through a classifier so as to obtain a classification result, and the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
In the above detection system based on separation of foreground and background and associated mineral separation effect, the region of interest determination unit is further configured to: and determining a first interested area corresponding to the ore pulp part and a second interested area corresponding to the foam product in the initial characteristic map through image semantic segmentation.
In the above detection system for separating and associated mineral separation effect based on foreground and background, the foreground feature map generation unit includes: the pooling processing subunit is used for performing global average pooling processing on the initial feature map to obtain a feature value; and the filling subunit is used for extracting the characteristic value in the second region of interest in the initial characteristic map and filling other parts with the characteristic value as a default value to obtain a foreground characteristic map.
In the above detection system based on separation of foreground and background and associated mineral separation effect, the third feature map generation unit is further configured to: and calculating the weighted sum of the first feature map and the second feature map by taking the similarity coefficient as the weighting coefficient of the first feature map and subtracting the similarity coefficient by one as the weighting coefficient of the second feature map so as to obtain the third feature map.
In the above system for detecting separation based on foreground and background and associated mineral separation effect, the classification result generating unit includes: the classification feature vector generation subunit is used for enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and the classification subunit is used for inputting the classification feature vector obtained by the classification feature vector generation subunit into a Softmax classification function so as to obtain the classification result.
In the above detection system based on foreground-background separation and associated mineral separation effect, the first convolutional neural network and the second convolutional neural network are depth residual error networks.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform a method of detection of foreground background based separation and associated mineral separation effects as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform a method of detection of a foreground background based separation and associated mineral separation effect as described above.
Compared with the prior art, the detection method based on the separation of the foreground background and the associated mineral separation effect, the detection system based on the separation of the foreground background and the associated mineral separation effect and the electronic equipment provided by the application extract higher-dimensional features in the background feature map and the foreground feature map through the convolutional neural network, represent the similarity between the background feature map and the foreground feature map according to the cosine distance of the background feature map and the foreground feature map in a higher-dimensional space, and fuse the feature maps according to the similarity to obtain a third feature map, so that the finally fused feature map contains the associated features which can fully represent the pulp part and the foam product part in the image, and the classification effect is improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 illustrates an application scenario of a method for detecting a separation based on a foreground and a background and an associated mineral separation effect according to an embodiment of the present application;
FIG. 2 illustrates a flow chart of a method of detection of foreground background based separation and associated mineral separation effects in accordance with an embodiment of the present application;
fig. 3 illustrates a system architecture diagram of a method of detection of foreground-background based separation and associated mineral separation effects in accordance with an embodiment of the present application;
fig. 4 illustrates a flowchart of extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map in the method for detecting separation based on foreground and background and associated mineral separation effects according to an embodiment of the present application;
fig. 5 illustrates a flow chart of passing the classification feature map through a classifier to obtain a classification result in a detection method of separation based on foreground and background and associated mineral separation effect according to an embodiment of the present application;
fig. 6 illustrates a block diagram of a detection system based on foreground-background separation and associated mineral separation effects in accordance with an embodiment of the present application.
Fig. 7 illustrates a block diagram of a foreground feature map generation unit in a detection system based on foreground-background separation and associated mineral separation effects according to an embodiment of the present application.
Fig. 8 illustrates a block diagram of a classification result generation unit in a detection system based on foreground-background separation and associated mineral separation effects according to an embodiment of the application.
FIG. 9 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of a scene
As mentioned above, in the coal-fired boiler of the thermal power plant, the fly ash is usually further processed by the flotation column, specifically, in the flotation column, the fly ash is processed by adding chemical agent to form slurry, and after being aerated by stirring, some ore particles in the slurry are selectively fixed on the air bubbles and float up to the surface of the slurry. Thus, mineral separation can be achieved by scraping the formed foam product away from the slurry.
However, at present, if it is required to detect the mineral separation effect of the flotation column, it is required to separately detect the components of the froth product and the slurry, and in fact, in practical applications, there have been many skilled workers who roughly judge the mineral separation effect of the flotation column by observing the froth product floating from the slurry.
Based on this, the inventor of the present application expects a detection scheme to further obtain the mineral separation effect of the flotation column on a visual level by introducing a computer vision technology based on deep learning. In this process, the inventors of the present application have found that a skilled worker can observe the foam product floating from the slurry by a comparative observation process of the slurry and the foam product, in addition to the observation of the slurry and the foam product separately.
Therefore, in the scheme of the application, in order to fully characterize the characteristics of the pulp part, the characteristics of the foam product part and the correlation characteristics between the pulp part and the foam product part in the image, the pulp part can be regarded as the background, the foam product part can be regarded as the foreground, and the correlation can be expressed by the similarity characteristics between the background and the foreground.
Specifically, a pulp image containing froth product floating from the pulp is first obtained and input into a first convolutional neural network to obtain an initial profile. Then, based on the division of the pulp part and the foam product part in the pulp image, a first region of interest and a second region of interest in the initial characteristic map, which respectively correspond to the pulp part and the foam product part, are respectively determined. Next, a background feature map and a foreground feature map are obtained by extracting a first region of interest and a second region of interest in the feature map, respectively, and filling the remaining portions with default values.
Then, the background feature map and the foreground feature map are respectively input into a second convolutional neural network to obtain a first feature map and a second feature map, and a cosine distance between the first feature map and the second feature map is calculated to represent the similarity between the first feature map and the second feature map. And respectively weighting and summing the first feature map and the second feature map by a and 1-a to obtain a third feature map for representing the similarity feature between the background and the foreground, wherein the cosine similarity is a.
And finally, fusing the first feature map, the second feature map and the third feature map to obtain a final feature map, and obtaining a classification result based on a classifier, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
Based on this, the application provides a method for detecting a separation and associated mineral separation effect based on a foreground and a background, which includes: acquiring an ore pulp image to be detected, wherein the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp; enabling the ore pulp image to be detected to pass through a first convolutional neural network to obtain an initial characteristic diagram; determining a first region of interest in the initial profile corresponding to the slurry portion and a second region of interest corresponding to the froth product; extracting feature values in the first region of interest in the initial feature map and filling other parts with default values to obtain a background feature map; extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map; inputting the foreground feature map and the background feature map into a second convolutional neural network respectively to obtain a first feature map and a second feature map; calculating a cosine distance between the first feature map and the second feature map to serve as a similarity coefficient between the first feature map and the second feature map; fusing the first feature map and the second feature map based on the similarity coefficient to obtain a third feature map; fusing the first feature map, the second feature map and the third feature map to obtain a classification feature map; and enabling the classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
Fig. 1 illustrates an application scenario diagram of a method for detecting a separation based on a foreground and a background and an associated mineral separation effect according to an embodiment of the present application.
As shown in fig. 1, in the application scenario, a pulp image to be detected is obtained through a camera (for example, as indicated by C in fig. 1), wherein the pulp image includes a pulp portion and a foam product floating from the pulp; then, the image is input into a server (for example, S as illustrated in fig. 1) deployed with a detection algorithm for separation and associated mineral separation effect based on foreground and background, wherein the server can process the image based on the detection algorithm for separation and associated mineral separation effect of foreground and background to generate a detection result whether the mineral separation effect of the flotation column to be detected meets a preset standard.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 2 illustrates a flow chart of a method of detection of separation based on foreground background and associated mineral separation effects. As shown in fig. 2, a method for detecting a separation based on a foreground and a background and an associated mineral separation effect according to an embodiment of the present application includes: s110, acquiring an ore pulp image to be detected, wherein the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp; s120, enabling the ore pulp image to be detected to pass through a first convolutional neural network to obtain an initial characteristic diagram; s130, determining a first region of interest corresponding to the ore pulp part and a second region of interest corresponding to the foam product in the initial characteristic diagram; s140, extracting feature values in the first region of interest in the initial feature map and filling other parts with default values to obtain a background feature map; s150, extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map; s160, inputting the foreground feature map and the background feature map into a second convolutional neural network respectively to obtain a first feature map and a second feature map; s170, calculating a cosine distance between the first feature map and the second feature map to serve as a similarity coefficient between the first feature map and the second feature map; s180, fusing the first feature map and the second feature map based on the similarity coefficient to obtain a third feature map; s190, fusing the first feature map, the second feature map and the third feature map to obtain a classification feature map; and S200, passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
Fig. 3 illustrates an architectural diagram of a method for detecting a separation based on foreground and background and associated mineral separation effects according to an embodiment of the present application. As shown IN fig. 3, IN the network architecture of the detection method of separation and associated mineral separation effect based on foreground and background, first, a pulp image to be detected (for example, IN1 as illustrated IN fig. 3) acquired by a camera is input into a first convolution neural network (for example, CNN1 as illustrated IN fig. 3) to obtain an initial characteristic map (for example, Fi as illustrated IN fig. 3), wherein the pulp image includes a pulp part and foam products floating from the pulp; then, determining a first region of interest (e.g., Fa1 as illustrated in figure 3) corresponding to the slurry portion and a second region of interest (e.g., Fa2 as illustrated in figure 3) corresponding to the foam product in the initial profile; then, extracting feature values in the first region of interest in the initial feature map and filling other parts with default values to obtain a background feature map (e.g., Fb as illustrated in fig. 3); then, extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map (e.g., Fp as illustrated in fig. 3); then, inputting the foreground feature map and the background feature map into a second convolutional neural network (e.g., CNN2 as illustrated in fig. 3) respectively to obtain a first feature map (e.g., F1 as illustrated in fig. 3) and a second feature map (e.g., F2 as illustrated in fig. 3); then, calculating a cosine distance between the first feature map and the second feature map as a similarity coefficient between the first feature map and the second feature map (for example, as indicated by a circle K1 in fig. 3); then, based on the similarity coefficient, fusing the first feature map and the second feature map to obtain a third feature map (e.g., F3 as illustrated in fig. 3); then, fusing the first feature map, the second feature map and the third feature map to obtain a classification feature map (e.g., Fc as illustrated in fig. 3); the classification signature is then passed through a classifier (e.g., as illustrated in fig. 3) to obtain a classification result indicative of whether the mineral separation performance of the flotation column meets a predetermined criterion.
In step S110, a pulp image to be detected is obtained, wherein the pulp image includes a pulp portion and a foam product floating from the pulp. As mentioned above, in the flotation column, the fly ash is treated by adding a chemical agent to form a slurry, and after stirring and aeration, some ore particles in the slurry are selectively fixed on bubbles and float to the surface of the slurry. Thus, mineral separation can be achieved by scraping the formed foam product away from the slurry. Thus, the mineral separation effect of the flotation column can be roughly judged by observing the froth product floating from the slurry.
Specifically, in this application embodiment, the pulp image that awaits measuring can be acquireed through the camera, that is, in this application scheme, through computer vision technique, further detect the mineral separation effect of flotation column on the visual layer.
In step S120, the pulp image to be detected is passed through a first convolutional neural network to obtain an initial feature map. Namely, extracting each high-dimensional feature in the pulp image to be detected by using the first convolution neural network.
In particular, in the embodiment of the present application, the first convolutional neural network may employ a deep residual neural network, for example, ResNet 50. It should be known to those skilled in the art that, compared to the conventional convolutional neural network, the deep residual network is an optimized network structure proposed on the basis of the conventional convolutional neural network, which mainly solves the problem of gradient disappearance during the training process. The depth residual error network introduces a residual error network structure, the network layer can be made deeper through the residual error network structure, and the problem of gradient disappearance can not occur. The residual error network uses the cross-layer link thought of a high-speed network for reference, breaks through the convention that the traditional neural network only can provide N layers as input from the input layer of the N-1 layer, enables the output of a certain layer to directly cross several layers as the input of the later layer, and has the significance of providing a new direction for the difficult problem that the error rate of the whole learning model is not reduced and inversely increased by superposing multiple layers of networks.
In step S130, a first region of interest in the initial profile corresponding to the slurry portion and a second region of interest corresponding to the foam product are determined. Those skilled in the art will appreciate that in the field of image processing, a region of interest (ROI) is an image region selected from an image, which is the focus of your image analysis. The area is delineated for further processing. The ROI is used for delineating the target which the user wants to read, so that the processing time can be reduced, and the precision can be increased.
Specifically, in the embodiment of the present application, the process of determining a first region of interest corresponding to the slurry portion and a second region of interest corresponding to the foam product in the initial characteristic map includes: and determining a first interested area corresponding to the ore pulp part and a second interested area corresponding to the foam product in the initial characteristic map through image semantic segmentation. It should be understood that the high-dimensional features of the feature map positions corresponding to the edges of the pulp part and the foam product are directly extracted in the high-dimensional space through image semantic segmentation, so that the error influence caused by the deviation between the positions of the pulp part and the foam product in the image frames on the source image domain and the positions of the pulp part and the foam product on the feature map can be reduced, and the accuracy of edge extraction is improved.
In step S140, feature values in the first region of interest in the initial feature map are extracted and other portions are filled with default values to obtain a background feature map. That is, the background feature map is obtained by extracting the first region of interest in the feature map and filling the rest with default values. It will be appreciated that in order to be able to fully characterize the pulp fraction and the froth product fraction in the image, the pulp fraction may be considered as background and the froth product fraction as foreground.
In step S150, feature values in the second region of interest in the initial feature map are extracted and other parts are filled with default values to obtain a foreground feature map. That is, the foreground feature map is obtained by extracting the second region of interest in the feature map and filling the remaining portion with default values.
Specifically, in this embodiment of the present application, the process of extracting feature values in the second region of interest in the initial feature map and filling other portions with default values to obtain a foreground feature map includes: first, global mean pooling is performed on the initial feature map to obtain a feature value. Then, feature values in the second region of interest in the initial feature map are extracted and other parts are filled with the feature values as default values to obtain a foreground feature map. It should be understood that, by pooling the global average of the initial feature maps, the extracted feature values more represent the background portion of the image, and therefore, with the feature values as default values, the calculation accuracy of the similarity between the background feature map and the foreground feature map can be improved, so as to improve the classification effect.
Fig. 4 illustrates a flowchart of extracting feature values in the second region of interest in the initial feature map and filling other portions with default values to obtain a foreground feature map in the method for detecting separation based on foreground and background and associated mineral separation effects according to an embodiment of the present application. As shown in fig. 4, extracting feature values in the second region of interest in the initial feature map and filling other portions with default values to obtain a foreground feature map, including: s310, performing global average pooling on the initial feature map to obtain a feature value; and S320, extracting the characteristic value in the second region of interest in the initial characteristic diagram and filling other parts with the characteristic value as a default value to obtain a foreground characteristic diagram.
In step S160, the foreground feature map and the background feature map are respectively input into a second convolutional neural network to obtain a first feature map and a second feature map. Namely, extracting higher-dimensional features in the foreground feature map and the background feature map by using a second convolutional neural network. In particular, in embodiments of the present application, the second convolutional neural network may employ a deep residual neural network, e.g., ResNet 50.
In step S170, a cosine distance between the first feature map and the second feature map is calculated as a similarity coefficient between the first feature map and the second feature map. It will be appreciated by those skilled in the art that cosine similarity is often used to represent similarity between two feature maps when analyzing the similarity. The range of cosine similarity is [ -1,1], and if a distance-like representation is desired, the cosine distance is obtained by subtracting the cosine similarity from 1. The cosine distance thus takes on a value range of [0,2 ].
In step S180, based on the similarity coefficient, the first feature map and the second feature map are fused to obtain a third feature map. It should be understood that the first characteristic diagram and the second characteristic diagram are fused, and the obtained third characteristic diagram can fully represent the correlation characteristics between the ore pulp part and the foam product part.
Specifically, in this embodiment of the present application, a process of fusing the first feature map and the second feature map based on the similarity coefficient to obtain a third feature map includes: and calculating the weighted sum of the first feature map and the second feature map by taking the similarity coefficient as the weighting coefficient of the first feature map and subtracting the similarity coefficient by one as the weighting coefficient of the second feature map so as to obtain the third feature map. That is, assuming that the cosine similarity is a, the first feature map and the second feature map are weighted and summed by a and 1-a, respectively, to obtain a third feature map representing the similarity feature between the background and the foreground.
In step S190, the first feature map, the second feature map and the third feature map are fused to obtain a classification feature map. It should be appreciated that the first, second and third profiles are fused such that the classification profile obtained is capable of adequately characterizing the pulp fraction, the froth product fraction, and the correlation between the pulp fraction and the froth product fraction.
In step S200, the classification feature map is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard. That is, the classifier includes an encoder, which may be a convolutional layer, a pooling layer, or a fully-connected layer.
Specifically, in the embodiment of the present application, the process of passing the classification feature map through a classifier to obtain a classification result includes: firstly, the classification feature map is passed through one or more fully-connected layers to obtain a classification feature vector, that is, the classification feature map is passed through the fully-connected layers to encode the classification feature map through the fully-connected layers so as to fully utilize each position information in the classification feature map to generate the classification feature vector. And then inputting the classification feature vector into a Softmax classification function to obtain a classification result, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
Fig. 5 illustrates a flowchart of passing the classification feature map through a classifier to obtain a classification result in a method for detecting a separation based on a foreground and a background and an associated mineral separation effect according to an embodiment of the present application. As shown in fig. 5, passing the classification feature map through a classifier to obtain a classification result includes: s410, enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and S420, inputting the classification feature vector into a Softmax classification function to obtain the classification result.
In summary, the method for detecting the separation and associated mineral separation effect based on the foreground and background according to the embodiment of the present application is elucidated, which extracts higher dimensional features in the background feature map and the foreground feature map through the convolutional neural network, and represents the similarity between the background feature map and the foreground feature map according to the cosine distance of the background feature map and the foreground feature map in a higher dimensional space, and fuses the feature maps according to the similarity to obtain a third feature map, so that the finally fused feature map contains associated features capable of sufficiently representing the pulp part and the foam product part in the image, thereby improving the classification effect.
Exemplary System
Fig. 6 illustrates a block diagram of a detection system based on foreground-background separation and associated mineral separation effects in accordance with an embodiment of the present application.
As shown in fig. 6, a detection system 600 for separating and associated mineral separation effect based on foreground and background according to an embodiment of the present application includes: an image obtaining unit 610, configured to obtain an ore pulp image to be detected, where the ore pulp image includes an ore pulp portion and a foam product floating from the ore pulp; an initial characteristic map generating unit 620, configured to pass the pulp image to be detected obtained by the image obtaining unit 610 through a first convolutional neural network to obtain an initial characteristic map; a region-of-interest determining unit 630 for determining a first region of interest corresponding to the slurry portion and a second region of interest corresponding to the foam product in the initial characteristic map obtained by the initial characteristic map generating unit 620; a background feature map generating unit 640, configured to extract feature values in the first region of interest obtained by the region of interest determining unit 630 in the initial feature map obtained by the initial feature map generating unit 620 and fill other portions with default values to obtain a background feature map; a foreground feature map generating unit 650, configured to extract feature values in the second region of interest obtained by the region of interest determining unit 630 in the initial feature map obtained by the initial feature map generating unit 620 and fill other portions with default values to obtain a foreground feature map; a feature map generating unit 660, configured to input the foreground feature map obtained by the foreground feature map generating unit 650 and the background feature map obtained by the background feature map generating unit 640 into a second convolutional neural network, respectively, so as to obtain a first feature map and a second feature map; a similarity coefficient calculation unit 670, configured to calculate a cosine distance between the first feature map and the second feature map obtained by the feature map generation unit 660, so as to serve as a similarity coefficient between the first feature map and the second feature map; a third feature map generating unit 680, configured to fuse the first feature map and the second feature map obtained by the feature map generating unit 660 based on the similarity coefficient obtained by the similarity coefficient calculating unit 670 to obtain a third feature map; a classification feature map generating unit 690, configured to fuse the first feature map, the second feature map, and the third feature map obtained by the feature map generating unit 660, and the third feature map obtained by the third feature map generating unit 680, so as to obtain a classification feature map; and a classification result generating unit 700, configured to pass the classification feature map obtained by the classification feature map generating unit 690 through a classifier to obtain a classification result, where the classification result is used to indicate whether the mineral separation effect of the flotation column meets a preset standard.
In an example, in the above detection system 600 based on foreground-background separation and associated mineral separation effect, the region of interest determination unit 630 is further configured to: and determining a first interested area corresponding to the ore pulp part and a second interested area corresponding to the foam product in the initial characteristic map through image semantic segmentation.
In one example, in the above detection system 600 based on the separation of the foreground and background and the associated mineral separation effect, as shown in fig. 7, the foreground feature map generating unit 650 includes: a pooling processing subunit 651, configured to perform global mean pooling on the initial feature map to obtain a feature value; and a filling subunit 652, configured to extract feature values in the second region of interest in the initial feature map and fill other portions with the feature values as default values to obtain a foreground feature map.
In an example, in the above detection system 600 based on separation of foreground and background and associated mineral separation effect, the third feature map generation unit 680 is further configured to: and calculating the weighted sum of the first feature map and the second feature map by taking the similarity coefficient as the weighting coefficient of the first feature map and subtracting the similarity coefficient by one as the weighting coefficient of the second feature map so as to obtain the third feature map.
In an example, in the above detection system 600 based on the separation of the foreground and the background and the associated mineral separation effect, as shown in fig. 8, the classification result generating unit 700 includes: a classification feature vector generation subunit 710, configured to pass the classification feature map through one or more fully connected layers to obtain a classification feature vector; and a classification subunit 720, configured to input the classification feature vector obtained by the classification feature vector generation subunit 710 into a Softmax classification function, so as to obtain the classification result.
In one example, in the detection system 600 for foreground-background based separation and associated mineral separation effects described above, the first convolutional neural network and the second convolutional neural network are deep residual error networks.
Here, it will be understood by those skilled in the art that the specific functions and operations of the various units and modules in the above-described detection system 600 have been described in detail in the above description of the detection method based on foreground-background separation and associated mineral separation effect with reference to fig. 1 to 5, and therefore, a repeated description thereof will be omitted.
As described above, the detection system 600 according to the embodiment of the present application may be implemented in various terminal devices, such as a server for detection of mineral separation effect and the like. In one example, the detection system 600 according to the embodiments of the present application may be integrated into the terminal device as a software module and/or a hardware module. For example, the detection system 600 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the detection system 600 may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the detection system 600 and the terminal device may be separate devices, and the detection system 600 may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 9.
FIG. 9 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
As shown in fig. 9, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input system 13 and an output system 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input system 13 may comprise, for example, a keyboard, a mouse, etc.
The output system 14 may output various information including classification results and the like to the outside. The output system 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 9, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the functions of the method of detection of separation based on foreground background and associated mineral separation effects according to various embodiments of the present application described in the "exemplary methods" section above of this specification.
The computer program product may be written with program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps in the method for detection of a foreground background based separation and associated mineral separation effect described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. A method for detecting separation and associated mineral separation effect based on foreground and background is characterized by comprising the following steps:
acquiring an ore pulp image to be detected, wherein the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp;
enabling the ore pulp image to be detected to pass through a first convolutional neural network to obtain an initial characteristic diagram;
determining a first region of interest in the initial profile corresponding to the slurry portion and a second region of interest corresponding to the froth product;
extracting feature values in the first region of interest in the initial feature map and filling other parts with default values to obtain a background feature map;
extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain a foreground feature map;
inputting the foreground feature map and the background feature map into a second convolutional neural network respectively to obtain a first feature map and a second feature map;
calculating a cosine distance between the first feature map and the second feature map to serve as a similarity coefficient between the first feature map and the second feature map;
fusing the first feature map and the second feature map based on the similarity coefficient to obtain a third feature map;
fusing the first feature map, the second feature map and the third feature map to obtain a classification feature map; and
and passing the classification characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
2. The method of detecting a foreground background based separation and associated mineral separation effect of claim 1, wherein determining a first region of interest in the initial signature corresponding to the pulp portion and a second region of interest corresponding to the froth product includes:
and determining a first interested area corresponding to the ore pulp part and a second interested area corresponding to the foam product in the initial characteristic map through image semantic segmentation.
3. The method for detecting mineral separation effect based on foreground and background as claimed in claim 1, wherein extracting feature values in the second region of interest in the initial feature map and filling other parts with default values to obtain foreground feature map comprises:
performing global mean pooling on the initial feature map to obtain a feature value; and
and extracting the characteristic value in the second region of interest in the initial characteristic map and filling other parts with the characteristic value as a default value to obtain a foreground characteristic map.
4. The method for detecting separation and associated mineral separation effects based on foreground background as claimed in claim 1, wherein fusing the first feature map and the second feature map to obtain a third feature map based on the similarity coefficient comprises:
and calculating the weighted sum of the first feature map and the second feature map by taking the similarity coefficient as the weighting coefficient of the first feature map and subtracting the similarity coefficient by one as the weighting coefficient of the second feature map so as to obtain the third feature map.
5. The method for detecting separation and associated mineral separation effect based on foreground and background as claimed in claim 1, wherein passing the classification feature map through a classifier to obtain a classification result, the classification result being used to indicate whether the mineral separation effect of the flotation column meets a preset standard, comprising:
passing the classification feature map through one or more fully connected layers to obtain a classification feature vector; and
inputting the classification feature vector into a Softmax classification function to obtain the classification result.
6. The method of detecting a foreground background based separation and associated mineral separation effect of claim 1, wherein said first convolutional neural network and said second convolutional neural network are deep residual networks.
7. A system for detecting separation and associated mineral separation effects based on a foreground background, comprising:
the system comprises an image acquisition unit, a data acquisition unit and a data processing unit, wherein the image acquisition unit is used for acquiring an ore pulp image to be detected, and the ore pulp image comprises an ore pulp part and a foam product floating from the ore pulp;
the initial characteristic map generating unit is used for enabling the ore pulp image to be detected obtained by the image obtaining unit to pass through a first convolutional neural network so as to obtain an initial characteristic map;
a region-of-interest determination unit for determining a first region of interest corresponding to the slurry portion and a second region of interest corresponding to the foam product in the initial feature map obtained by the initial feature map generation unit;
a background feature map generating unit, configured to extract feature values in the first region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and fill other portions with default values to obtain a background feature map;
a foreground feature map generating unit, configured to extract feature values in the second region of interest obtained by the region of interest determining unit in the initial feature map obtained by the initial feature map generating unit and fill other portions with default values to obtain a foreground feature map;
the feature map generating unit is used for inputting the foreground feature map obtained by the foreground feature map generating unit and the background feature map obtained by the background feature map generating unit into a second convolutional neural network respectively so as to obtain a first feature map and a second feature map;
a similarity coefficient calculation unit, configured to calculate a cosine distance between the first feature map and the second feature map obtained by the feature map generation unit, as a similarity coefficient between the first feature map and the second feature map;
a third feature map generation unit configured to fuse the first feature map and the second feature map obtained by the feature map generation unit based on the similarity coefficient obtained by the similarity coefficient calculation unit to obtain a third feature map;
a classification feature map generation unit, configured to fuse the first feature map, the second feature map, and the third feature map obtained by the feature map generation unit to obtain a classification feature map; and
and the classification result generating unit is used for enabling the classification characteristic diagram obtained by the classification characteristic diagram generating unit to pass through a classifier so as to obtain a classification result, and the classification result is used for indicating whether the mineral separation effect of the flotation column meets a preset standard or not.
8. The system for detecting mineral separation effect based on foreground-background separation and correlation according to claim 7, wherein the foreground feature map generating unit comprises:
the pooling processing subunit is used for performing global average pooling processing on the initial feature map to obtain a feature value; and
and the filling subunit is used for extracting the characteristic value in the second region of interest in the initial characteristic map and filling other parts with the characteristic value as a default value to obtain a foreground characteristic map.
9. The system for detecting mineral separation effect based on foreground and background of claim 7, wherein the classification result generating unit comprises:
the classification feature vector generation subunit is used for enabling the classification feature map to pass through one or more full-connection layers to obtain a classification feature vector; and
a classification subunit, configured to input the classification feature vector obtained by the classification feature vector generation subunit into a Softmax classification function to obtain the classification result.
10. An electronic device, comprising:
a processor; and
memory in which computer program instructions are stored, which, when executed by the processor, cause the processor to carry out a method of detection of foreground background based separation and associated mineral separation effects according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110074956.6A CN112733853A (en) | 2021-01-20 | 2021-01-20 | Method for detecting separation and associated mineral separation effect based on foreground and background |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110074956.6A CN112733853A (en) | 2021-01-20 | 2021-01-20 | Method for detecting separation and associated mineral separation effect based on foreground and background |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112733853A true CN112733853A (en) | 2021-04-30 |
Family
ID=75592659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110074956.6A Withdrawn CN112733853A (en) | 2021-01-20 | 2021-01-20 | Method for detecting separation and associated mineral separation effect based on foreground and background |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112733853A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115239515A (en) * | 2022-07-28 | 2022-10-25 | 德玛克(长兴)精密机械有限公司 | Precise intelligent processing and manufacturing system for mechanical parts and manufacturing method thereof |
| CN115423805A (en) * | 2022-11-03 | 2022-12-02 | 河南洋荣服饰有限公司 | Automatic trousers piece clamping device |
-
2021
- 2021-01-20 CN CN202110074956.6A patent/CN112733853A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115239515A (en) * | 2022-07-28 | 2022-10-25 | 德玛克(长兴)精密机械有限公司 | Precise intelligent processing and manufacturing system for mechanical parts and manufacturing method thereof |
| CN115423805A (en) * | 2022-11-03 | 2022-12-02 | 河南洋荣服饰有限公司 | Automatic trousers piece clamping device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dodge et al. | Parsing floor plan images | |
| CN109684803B (en) | Man-machine verification method based on gesture sliding | |
| CN112733853A (en) | Method for detecting separation and associated mineral separation effect based on foreground and background | |
| CN115797706B (en) | Target detection method, target detection model training method and related device | |
| CN115564766B (en) | Preparation method and system of water turbine volute seat ring | |
| TW200529093A (en) | Face image detection method, face image detection system, and face image detection program | |
| CN111260666A (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN112418351A (en) | Zero sample learning image classification method based on global and local context sensing | |
| CN114580515A (en) | Neural network training method for intelligent detection of semiconductor desoldering | |
| KR20230038086A (en) | Method for de-identifying face and body contained in video data, and device performing the same | |
| CN115128663A (en) | Mine safety production detection system based on Internet of things and detection method thereof | |
| CN116030018A (en) | Incoming material qualification inspection system and method for door processing | |
| CN116797814A (en) | Intelligent building site safety management system | |
| CN105469099B (en) | Pavement crack detection and identification method based on sparse representation classification | |
| CN112767342A (en) | Intelligent gas detection method based on double-branch inference mechanism | |
| CN112960213A (en) | Intelligent package quality detection method using characteristic probability distribution representation | |
| Kwaśnicka et al. | Bridging the semantic gap in image and video analysis | |
| CN116467485B (en) | Video image retrieval construction system and method thereof | |
| CN114839466B (en) | EMC electromagnetic compatibility test system for water pump and test method thereof | |
| CN112418353A (en) | Neural network training method for battery diaphragm abnormity detection | |
| CN116955991A (en) | Intelligent indoor environment detection system and method thereof | |
| CN116797586A (en) | Automatic paper cup defect detection method and system | |
| CN111488776A (en) | Object detection method, object detection device and electronic equipment | |
| CN113269171B (en) | Lane line detection method, electronic device and vehicle | |
| CN112560857B (en) | Character area boundary detection method, equipment, storage medium and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210430 |