CN111368865A - Method and device for detecting remote sensing image oil storage tank, readable storage medium and equipment - Google Patents
Method and device for detecting remote sensing image oil storage tank, readable storage medium and equipment Download PDFInfo
- Publication number
- CN111368865A CN111368865A CN201811600681.XA CN201811600681A CN111368865A CN 111368865 A CN111368865 A CN 111368865A CN 201811600681 A CN201811600681 A CN 201811600681A CN 111368865 A CN111368865 A CN 111368865A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- node
- classifier
- gray
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a method and a device for detecting an oil storage tank by using remote sensing images, a computer readable storage medium and equipment, belonging to the field of image processing and pattern recognition. The method comprises the following steps: unifying the remote sensing images into a single-channel grey-scale image; sliding a detection template on the single-channel gray-scale image by a certain step length to obtain a plurality of frames to be classified; extracting IPR characteristics of the frames to be classified, wherein the definition of the IPR characteristics is as the following formula 1/(1+ y/x), and x and y are gray values of any two pixels in one frame to be classified; classifying IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames; and performing nms operation on the target candidate box to obtain a final detection result. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
Description
Technical Field
The invention relates to the field of image processing and pattern recognition, in particular to a method and a device for detecting a remote sensing image oil storage tank, a computer readable storage medium and computer readable storage equipment.
Background
The remote sensing image is an image of a real object on the earth surface shot by a satellite from the space, is an important space information source at present, has a wide development prospect, and is particularly widely applied to various fields such as national defense safety, military deployment, economic production, environmental disaster monitoring and the like. With the development of high and new technologies, the spatial remote sensing technology has made a great deal of progress, and the improvement of the speed of remote sensing information transmission, the improvement of spatial resolution and the amplification of image information promote people to improve the requirements on the extraction, analysis and processing of remote sensing image information. The remote sensing image target detection and identification is an important branch in the remote sensing image processing technology and plays a role in the fields of national economy, national defense, military and the like. Due to the cross penetration of various technologies and knowledge, the remote sensing image target detection and identification technology develops towards the direction of more reliability, high efficiency and strong generalization.
The oil storage tank is a typical military target in remote sensing images, and the quantity, size, position distribution and other information of the oil storage tank have great significance in military affairs. The remote sensing image information is redundant, and how to efficiently detect the target of the oil storage tank has great influence on the subsequent extraction of the information of the oil storage tank.
Aiming at the characteristics of the oil storage tank on a remote sensing image, the detection method can be divided into the following three categories:
(1) morphological methods
The method mainly starts from the angle of the circular or nearly circular geometric characteristics of the oil storage tank, and achieves the aim of detecting the oil storage tank finally through circle detection. The method is based on Hough transformation or improved Hough transformation oil storage tank detection. The Hough transform is an effective circle detection method, and can still obtain ideal effects under the conditions of noise, deformation and incomplete target area, and the defects are that the calculation amount is large and the consumed time is long.
(2) Gray scale threshold segmentation method
When the gray level distribution in the oil storage tank target is uniform, the gray level difference between the target and the background is obvious, and the image noise is small, the oil storage tank and the surrounding background can be segmented by using a threshold segmentation technology, and a remote sensing image oil tank target segmentation method based on Ostu or improved Ostu threshold segmentation is commonly used.
(3) Template matching method
The method is suitable for the conditions of small deformation, uniform internal gray level change and the like of the oil storage tank, and the matching identification of the oil storage tank target is carried out in the image through the designed template. However, when the target form to be matched has large change and poor image quality, the matching process is easily affected, and how to design a template with strong general performance and stable effect is one of the difficult problems of using the template matching method.
The detection precision analysis, the morphological method and the template matching method are all started from the aspect of target morphological characteristics, and are easily influenced by deformation of the oil storage tank, and particularly, for the template matching method, the designed template is difficult to adapt to a target, so that the recognition rate is low; when the gray scale change of an image or a target is large, the internal gray scale is uneven, and the texture is complex, the method based on gray scale threshold segmentation is directly influenced, and in addition, when the gray scale distribution difference between images is large, the traditional method has poor self-adapting capability to the images, and the identification capability is reduced. In terms of detection time performance, although the detection method based on gray threshold segmentation is not stable enough, the time utility is good, and the method based on morphology and template matching has large calculation amount, large memory occupation amount and poor real-time performance. That is to say, the conventional methods have advantages but are not easy to achieve a detection effect with better time and precision balance due to their large limitations on applicable conditions.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a device for detecting a remote sensing image oil storage tank, a readable storage medium and equipment.
The technical scheme provided by the invention is as follows:
in a first aspect, the present invention provides a method for detecting an oil storage tank by using a remote sensing image, wherein the method comprises:
unifying the remote sensing images into a single-channel grey-scale image;
sliding a detection template on the single-channel gray-scale image by a certain step length to obtain a plurality of frames to be classified;
extracting IPR characteristics of the frames to be classified, wherein the IPR characteristics are defined as follows:
wherein, x and y are gray values of any two pixels in a frame to be classified;
classifying IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames;
and performing nms operation on the target candidate box to obtain a final detection result.
Further, the classifier is a RST classifier, the RST classifier is a tree classifier, and the RST classifier determines node characteristics according to the generated random numbers when constructing each node; if the generated random number is larger than a preset bias weight threshold value, selecting optimal characteristic information as node characteristics, otherwise, selecting suboptimal characteristic information as the node characteristics, wherein the optimal characteristic information is information of the current iteration, and the suboptimal characteristic information is information of the previous iteration.
Further, when the RST classifier learns, each attribute of the node learns a corresponding optimal threshold interval, the optimal threshold interval enables error loss of the left leaf node and the right leaf node to be minimum, when the sample characteristic value is within the optimal threshold interval, the sample is divided into the right leaf node, otherwise, the sample is divided into the left leaf node, and a fitting value is given by the leaf node; wherein the fitting value F (D) and the error loss L are calculated by the following formula:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is a positive sample in DThe sum of weights of W-Is the weighted sum of the negative samples in D.
Further, in the node splitting process of the RST classifier, if the sample sets in the nodes are of the same type, or the total number of samples does not meet the minimum number of samples required by the specified splitting, or the corresponding tree depth reaches the specified maximum tree depth, the node splitting is stopped.
Further, unifying the remote sensing images into a single-channel grayscale image includes:
if the remote sensing image is a panchromatic image, no processing is carried out, and if the remote sensing image is a multispectral color image, the remote sensing image is converted into a single-channel gray-scale image by the following method:
converting the multispectral color image into a gray level image by adopting a component weighted average mode;
calculating the global threshold value T of the gray level image by adopting an Ostu method*；
Performing power-law transformation on the gray image according to the global threshold to obtain the single-channel gray image, wherein the power-law transformation function is as follows:
wherein I is the pixel gray value of the gray image, I*The gray values of the pixels of the single-channel gray map are a and b, power law transformation coefficients are a < 1, b > 1, and α are set function segmentation threshold values.
In a second aspect, the present invention provides a device for detecting an oil storage tank by remote sensing images, the device comprising:
the single-channel gray-scale image acquisition module is used for unifying the remote sensing images into a single-channel gray-scale image;
the frame to be classified acquisition module is used for sliding the detection template on the single-channel gray-scale image in a certain step length to obtain a plurality of frames to be classified;
an IPR feature extraction module, configured to extract IPR features of the multiple frames to be classified, where the IPR features are defined as follows:
wherein, x and y are gray values of any two pixels in a frame to be classified;
the classification module is used for classifying the IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames;
and the nms module is used for performing nms operation on the target candidate box to obtain a final detection result.
Further, the classifier is a RST classifier, the RST classifier is a tree classifier, and the RST classifier determines node characteristics according to the generated random numbers when constructing each node; if the generated random number is larger than a preset bias weight threshold value, selecting optimal characteristic information as node characteristics, otherwise, selecting suboptimal characteristic information as the node characteristics, wherein the optimal characteristic information is information of the current iteration, and the suboptimal characteristic information is information of the previous iteration.
Further, when the RST classifier learns, each attribute of the node learns a corresponding optimal threshold interval, the optimal threshold interval enables error loss of the left leaf node and the right leaf node to be minimum, when the sample characteristic value is within the optimal threshold interval, the sample is divided into the right leaf node, otherwise, the sample is divided into the left leaf node, and a fitting value is given by the leaf node; wherein the fitting value F (D) and the error loss L are calculated by the following formula:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is the weighted sum of the positive samples in D, W-Is the weighted sum of the negative samples in D.
Further, in the node splitting process of the RST classifier, if the sample sets in the nodes are of the same type, or the total number of samples does not meet the minimum number of samples required by the specified splitting, or the corresponding tree depth reaches the specified maximum tree depth, the node splitting is stopped.
Further, the single-channel gray-scale map acquisition module includes:
if the remote sensing image is a panchromatic image, no processing is carried out, and if the remote sensing image is a multispectral color image, the remote sensing image is converted into a single-channel gray-scale image through the following units:
the weighted average unit is used for converting the multispectral color image into a gray image in a component weighted average mode;
an Ostu unit for calculating a global threshold T of the gray image by using an Ostu method*；
The power law transformation unit is used for performing power law transformation on the gray image according to the global threshold value to obtain the single-channel gray image, and the power law transformation function is as follows:
wherein I is the pixel gray value of the gray image, I*The gray values of the pixels of the single-channel gray map are a and b, power law transformation coefficients are a < 1, b > 1, and α are set function segmentation threshold values.
In a third aspect, the present invention provides a computer readable storage medium for remote sensing image oil storage tank detection, comprising a processor and a memory for storing processor executable instructions, wherein the instructions, when executed by the processor, implement the steps of the remote sensing image oil storage tank detection method according to the first aspect.
In a fourth aspect, the present invention provides an apparatus for remote sensing image oil storage tank detection, including at least one processor and a memory storing computer executable instructions, where the processor executes the instructions to implement the steps of the remote sensing image oil storage tank detection method according to the first aspect.
The invention has the following beneficial effects:
the method comprises the steps of firstly unifying remote sensing images into a single-channel grey-scale image, then obtaining frames to be classified, extracting IPR characteristics of the frames to be classified, classifying the IPR characteristics by using a classifier, and finally performing non-maximum value inhibition to obtain a final detection frame. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
Drawings
FIG. 1 is a flow chart of the method for detecting an oil storage tank by remote sensing images according to the present invention;
FIG. 2 is a schematic view of an oil storage tank;
FIG. 3 is a schematic diagram of a visualization of an oil storage tank IPR feature matrix;
FIG. 4 is a schematic illustration of pretreatment;
FIG. 5 is a schematic illustration of a capped and uncapped oil storage tank test;
FIG. 6 is a schematic diagram of the detection of an oil storage tank with changes in size and gray scale;
FIG. 7 is a schematic view of a cylinder and sphere tank test;
FIG. 8 is a schematic view of the remote sensing image oil storage tank detection device of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
the embodiment of the invention provides a method for detecting an oil storage tank by using remote sensing images, which comprises the following steps of:
step S100: unifying the remote sensing images into a single-channel grey-scale image.
The remote sensing images are of various types, and the gray level images are processed by the method, so that the remote sensing images need to be unified into a single-channel gray level image.
Step S200: and sliding the detection template on the single-channel gray-scale image by a certain step length to obtain a plurality of frames to be classified.
The size of the detection template can be set according to the detection requirement, and the step length is determined according to the size of the detection template and the size of the remote sensing image during sliding.
Step S300: extracting IPR characteristics of a plurality of frames to be classified, wherein the IPR characteristics are defined as follows:
wherein x and y are gray values of any two pixels in one frame to be classified.
As shown in fig. 2, the oil tank shape and the internal gray level distribution are distinct, and the main gray level is generally greatly different from the background region, so that the pixel gray level size between the target and the background in the oil tank region can be compared to distinguish the two.
Based on this, the present invention designs an Improved Pixel Ratio (IPR) as a feature of an image, which is a variation of any two-Pixel gray scale Ratio and also describes the order relationship between two pixels, and its mathematical formula is defined as follows:
and x and y are more than or equal to 0 to represent the gray values of any two pixels, f (x and y) is the improved pixel ratio of x and y, and the IPR characteristics of the frame to be classified can be obtained by traversing each pixel in the frame to be classified by more than or equal to 0 x and y.
From the defined formula, the IPR feature has a bounded nature (f ∈ [0,1]), a gray scale invariant nature, and f (x, y) 1-f (y, x), i.e. one way of calculating the IPR feature value between two pixels can be represented linearly in another way, so the IPR feature dimension can be calculated as d p × (p-1)/2, where p represents the total number of pixels of the image, taking fig. 2 as an example, the IPR feature matrix visualization image of the oil tank is shown in fig. 3.
The invention adopts the original IPR characteristic as the image characteristic which is a deformation of the pixel gray scale ratio, inspects the sequence relation between any two pixels in the image, and the experiment proves that the characteristic is very effective for detecting a round object or a nearly round object, such as an oil storage tank. The method can adaptively detect the oil storage tank target with variable form and gray scale distribution in the remote sensing image, and has higher detection precision.
Step S400: and classifying IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames.
Step S500: and performing nms operation on the target candidate frame to obtain a final detection result.
Non-Maximum Suppression (nms), which is an element that suppresses a Maximum as the name implies, can be understood as a local Maximum search. After the classifier is used for identifying the IPR characteristics of a plurality of frames to be classified, each mania to be classified can obtain a score, however, the condition that the target candidate frame and other target candidate frames contain or are mostly crossed can be caused because the step length when the detection template slides is smaller than the length of the sliding template, and the target candidate frame with the crossed is processed by using nms to obtain the final detection frame.
The method comprises the steps of firstly unifying remote sensing images into a single-channel grey-scale image, then obtaining frames to be classified, extracting IPR characteristics of the frames to be classified, classifying the IPR characteristics by using a classifier, and finally performing non-maximum value inhibition to obtain a final detection frame. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
The remote sensing image comprises a multispectral color image and a panchromatic image, wherein the panchromatic image is a black-and-white image in the whole visible light wave band range (blue light wave bands are usually abandoned to avoid atmospheric scattering influence), the panchromatic image is a single-channel gray-scale image and is not processed, the multispectral color image has three channels of RGB, and the multispectral color image is converted into the single-channel gray-scale image by the following method:
step S110: the original R, G, B three-channel multispectral color image is converted into a gray level image Grayimage by adopting a component weighted average mode, and the mathematical formula is as follows:
Grayimage＝0.2989R+0.5870G+0.1140B
compared with a full-color image, the gray level image converted in the step still has a larger difference in image gray level distribution. Aiming at the problem, the invention provides a processing method based on power law transformation by taking a panchromatic image as a template, so that the gray distribution of the processed image is similar to the gray distribution of the panchromatic image, and the experimental image is standardized by the gray distribution, and the specific operation steps are as follows:
step S120: calculating global threshold T of gray level image by Ostu method*。
The Otsu algorithm is an efficient algorithm for carrying out binarization on an image, a gray level image is divided into a foreground image and a background image by using a global threshold value, and when the optimal global threshold value is adopted, the difference between the background and the foreground is the largest.
Step S130: performing power law transformation on the gray image according to the global threshold value to obtain a single-channel gray image, wherein the power law transformation function is as follows:
wherein I is the pixel gray value of the gray image, I*In the pixel gray scale value of the single-channel gray scale map, a and b are power law transformation coefficients, a < 1, b > 1, and α are set function segmentation threshold values, and as a preferred example, a is 0.63, b is 1.37, α is 0.3, and β is 0.4.
Fig. 4 illustrates two exemplary preprocessing processes, wherein (a) and (d) are panchromatic images, (b) and (e) are general grayscale images gray images converted from multispectral color images, and (c) and (f) are single-channel grayscale images after gray-scale power-law transformation. Compared with the common gray-scale image, the gray-scale distribution of the single-channel gray-scale image obtained by the embodiment of the invention through power-law transformation is more similar to that of a full-color image.
The classifier of the invention is preferably a RST classifier (Random sub-optimal Tree), which is a Tree classifier, wherein the Tree RST classifier determines node characteristics according to generated Random numbers when constructing each node; and if the generated random number is larger than a preset bias weight threshold value rho, selecting optimal characteristic information as the node characteristic, otherwise, selecting suboptimal characteristic information as the node characteristic, wherein the optimal characteristic information is the information of the current iteration, and the suboptimal characteristic information is the information of the previous iteration.
The optimal feature information (information of the current iteration) and the suboptimal feature information (information of the previous iteration) of the embodiment of the present invention may be features, threshold interval parameters, left and right leaf node fitting scores, and the like used when the node error loss is minimum (see the RST classifier learning algorithm example below for details).
The random sub-optimal tree is a classification tree which randomly selects suboptimal characteristic information as the name suggests, and is the original classifier of the invention. The invention selects the node characteristics according to the random perturbation factors (i.e. random numbers). When each node of the RST is constructed, a random disturbance factor is introduced, the selection of the optimal characteristic of each node is interfered (random numbers are randomly given by a system during learning and are subjected to uniform distribution), when the random number is larger than a given threshold value rho, the optimal characteristic is selected at the node, otherwise, the suboptimal characteristic is selected (in experiments, preferably, rho is 0.3).
The optimal characteristic information is information of the iteration and is also the characteristic with the minimum error loss, the suboptimal characteristic information is information of the previous iteration and is also the characteristic with the minimum error loss, and random disturbance factors are introduced to improve the generalization capability of the model and prevent the over-fitting phenomenon. The RST classifier is combined with the IPR characteristics, so that the stability and the generalization of the oil storage tank detection method are superior to those of the traditional oil storage tank detection method.
When the RST classifier learns, each attribute of the node learns a corresponding optimal threshold interval, and the optimal threshold interval enables error loss of the left leaf sub-node and the right leaf sub-node to be minimum.
The tree classifier is a classification method, a sample set is given, each sample of the sample set has a group of attributes and a category, the attributes and the categories are determined in advance, the attributes are classification standards of the samples, the samples can be classified into different categories according to different attributes, and all the attributes form a candidate attribute set. The RST classifier is obtained through sample set learning, when learning, a node learns a corresponding optimal threshold interval on each attribute, the attribute of the node is namely the attribute in the candidate attribute set, the node is used as a splitting (classifying) standard according to the attribute, and the node divides the sample set into left and right leaf nodes according to the attribute.
Because the IPR characteristic function is a continuous function and the characteristic has the invariance of gray scale proportion, the classification method of the threshold interval shape is softer and more delicate than the single threshold shape, and the corresponding range of the characteristic is more accurate, thereby belonging to soft division. When the sample characteristic value is within the optimal threshold interval, the sample is divided into right leaf nodes, otherwise, the sample is divided into left leaf nodes, and a fitting value is given by the leaf nodes; the fitting value of the node is determined according to the distribution condition of the positive and negative sample weights contained in the current node, the node loss function is calculated based on a weighted least square method, and specifically, the calculation formulas of the fitting value F (D) and the error loss L are as follows:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is the weighted sum of the positive samples in D, W-Is the weighted sum of the negative samples in D.
The RST classifier follows a tree building process of depth first and then breadth second from top to bottom, and in the node splitting process, if the sample sets in the nodes are of the same type, or the total number of samples does not meet the minimum number of samples required by the designated splitting, or the corresponding tree depth reaches the designated maximum tree depth, the node splitting is stopped.
Here, a specific RST classifier learning algorithm example is given:
the oil storage tank detection classifier is mainly used for learning by using a Gentle AdaBoost algorithm framework, and meanwhile, a soft cascade structure can be introduced to further strengthen the performance of a plurality of weak RST classifiers obtained by learning to construct a strong classifier. In the above RST classifier, during learning, when the sample feature value is within the threshold interval, the sample is divided into the right leaf node and the left leaf node, but no matter which leaf node the sample is divided into, the sample is not directly determined to be a positive type sample or a negative type sample, but the leaf node gives a fitting value as an empirical reference value for subsequent strong classifier classification.
According to the empirical reference value output by the RST classifier, a threshold value is learned at each stage of the soft cascade, when the score of the sample at the stage is larger than the threshold value, the sample is judged to be a positive sample, and because the soft cascade stage function is in an accumulated sum form, the judgment at the current stage can refer to the score at the previous stage, so that the model acceptance capability can be effectively improved, and the possibility of false rejection is reduced.
In order to adapt to targets of various sizes, the invention designs a multi-scale detection template by taking 15 × 15 pixels as a basic template, and the difference between the sizes of two adjacent scales is 1.2 times.
The invention is illustrated below in a specific test example:
the effectiveness of the experiment is verified on a remote sensing image library GED (Google earth database), the detection result is shown in fig. 5-7, fig. 5 is an example of detection of an oil storage tank with a cover and without a cover, fig. 6 is an example of detection of an oil storage tank with size and gray level changes, and fig. 7 is an example of detection of an oil storage tank with a cylinder and a sphere. Experiments prove that the method has good performance for image detection of the oil storage tank in an unrestricted state, has stronger robustness and generalization capability, higher detection precision and good time utility, and can be effectively applied to target detection of the oil storage tank in a visible light remote sensing image.
Example 2:
the embodiment of the invention provides a remote sensing image oil storage tank detection device, as shown in fig. 8, the device comprises:
the single-channel gray-scale image acquisition module 10 is used for unifying the remote sensing images into a single-channel gray-scale image;
a frame to be classified acquisition module 20, configured to slide the detection template on the single-channel grayscale map by a certain step length to obtain a plurality of frames to be classified;
an IPR feature extraction module 30, configured to extract IPR features of multiple frames to be classified, where the IPR features are defined as follows:
wherein, x and y are gray values of any two pixels in a frame to be classified;
the classification module 40 is configured to classify IPR features of a plurality of frames to be classified by using a classifier to obtain target candidate frames;
and the nms operation module 50 is configured to perform nms operation on the target candidate box to obtain a final detection result.
The method comprises the steps of firstly unifying remote sensing images into a single-channel grey-scale image, then obtaining frames to be classified, extracting IPR characteristics of the frames to be classified, classifying the IPR characteristics by using a classifier, and finally performing non-maximum value inhibition to obtain a final detection frame. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
The classifier is a RST classifier, the RST classifier is a tree classifier, and the RST classifier determines the node characteristics according to the generated random number when constructing each node; if the generated random number is larger than a preset bias weight threshold value, selecting optimal characteristic information as node characteristics, otherwise, selecting suboptimal characteristic information as the node characteristics, wherein the optimal characteristic information is information of the current iteration, and the suboptimal characteristic information is information of the previous iteration.
When the RST classifier learns, each attribute of a node learns a corresponding optimal threshold interval, the optimal threshold interval enables error loss of a left leaf sub-node and a right leaf sub-node to be minimum, when a sample characteristic value is within the optimal threshold interval, a sample is divided into the right leaf sub-node, otherwise, the sample is divided into the left leaf sub-node, and a fitting value is given by a leaf node; wherein, the calculation formula of the fitting value F (D) and the error loss L is as follows:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is the weighted sum of the positive samples in D, W-Is the weighted sum of the negative samples in D.
In the node splitting process of the RST classifier, if the sample sets in the nodes are of the same type, or the total number of samples does not meet the minimum sample number required by the designated splitting, or the corresponding tree depth reaches the designated maximum tree depth, the node splitting is stopped.
The single-channel gray-scale image acquisition module of the invention comprises:
if the remote sensing image is a panchromatic image, no processing is carried out, and if the remote sensing image is a multispectral color image, the remote sensing image is converted into a single-channel gray-scale image through the following units:
the weighted average unit is used for converting the multispectral color image into a gray image in a component weighted average mode;
an Ostu unit for calculating a global threshold T of the gray image by using an Ostu method*；
The power law transformation unit is used for performing power law transformation on the gray image according to the global threshold value to obtain a single-channel gray image, and the power law transformation function is as follows:
wherein I is the pixel gray value of the gray image, I*The gray values of the pixels of the single-channel gray map are a and b, power law transformation coefficients are a < 1, b > 1, and α are set function segmentation threshold values.
The device provided by the embodiment of the present invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, reference may be made to the corresponding contents in the method embodiments without reference to the device embodiments. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the apparatus and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Example 3:
the method or apparatus provided by the present specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, so as to implement the effect of the solution described in the embodiments of the present specification. Accordingly, the present invention also provides a computer readable storage medium for remote sensing image oil tank testing, comprising a processor and a memory for storing processor executable instructions, which when executed by the processor, implement the steps comprising the remote sensing image oil tank testing method of embodiment 1.
The method comprises the steps of firstly unifying remote sensing images into a single-channel grey-scale image, then obtaining frames to be classified, extracting IPR characteristics of the frames to be classified, classifying the IPR characteristics by using a classifier, and finally performing non-maximum value inhibition to obtain a final detection frame. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.
The above description of the apparatus according to the method embodiment may also include other embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.
Example 4:
the invention also provides equipment for detecting the remote sensing image oil storage tank, which can be a single computer, and can also comprise an actual operation device and the like using one or more methods or devices of one or more embodiments of the specification. The apparatus for remote sensing image oil storage tank detection may comprise at least one processor and a memory storing computer executable instructions, wherein the processor executes the instructions to implement the steps of the remote sensing image oil storage tank detection method in any one or more of the embodiments.
The method comprises the steps of firstly unifying remote sensing images into a single-channel grey-scale image, then obtaining frames to be classified, extracting IPR characteristics of the frames to be classified, classifying the IPR characteristics by using a classifier, and finally performing non-maximum value inhibition to obtain a final detection frame. The method can adaptively detect the oil storage tank target with various forms and gray scale distribution in the remote sensing image, has higher detection precision, and has simple data processing and good time utility.
The above description of the device according to the method or apparatus embodiment may also include other embodiments, and specific implementation may refer to the description of the related method embodiment, which is not described herein in detail.
It should be noted that, the above-mentioned apparatus or system in this specification may also include other implementation manners according to the description of the related method embodiment, and a specific implementation manner may refer to the description of the method embodiment, which is not described herein in detail. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class, storage medium + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element.
As will be appreciated by one skilled in the art, one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description of the specification, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A remote sensing image oil storage tank detection method is characterized by comprising the following steps:
unifying the remote sensing images into a single-channel grey-scale image;
sliding a detection template on the single-channel gray-scale image by a certain step length to obtain a plurality of frames to be classified;
extracting IPR characteristics of the frames to be classified, wherein the IPR characteristics are defined as follows:
wherein, x and y are gray values of any two pixels in a frame to be classified;
classifying IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames;
and performing nms operation on the target candidate box to obtain a final detection result.
2. The remote sensing image oil storage tank detection method according to claim 1, wherein the classifier is a RST classifier, the RST classifier is a tree classifier, and the RST classifier determines node characteristics according to generated random numbers when constructing each node; if the generated random number is larger than a preset bias weight threshold value, selecting optimal characteristic information as node characteristics, otherwise, selecting suboptimal characteristic information as the node characteristics, wherein the optimal characteristic information is information of the current iteration, and the suboptimal characteristic information is information of the previous iteration.
3. The remote sensing image oil storage tank detection method according to claim 2, wherein each attribute of a node learns a corresponding optimal threshold interval when the RST classifier learns, the optimal threshold interval enables error loss of a left leaf node and a right leaf node to be minimum, when a sample characteristic value is within the optimal threshold interval, a sample is divided into the right leaf node, otherwise, the sample is divided into the left leaf node, and a fitting value is given by the leaf node; wherein the fitting value F (D) and the error loss L are calculated by the following formula:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is the weighted sum of the positive samples in D, W-Is the weighted sum of the negative samples in D.
4. The remote sensing image oil storage tank detection method of claim 3, wherein in the node splitting process of the RST classifier, if a sample set in a node is of the same type, or the total number of samples does not meet the minimum number of samples required by the designated splitting, or the corresponding tree depth reaches the designated maximum tree depth, the node splitting is stopped.
5. The method for detecting an oil storage tank by remote sensing images as claimed in any one of claims 1 to 4, wherein unifying the remote sensing images into a single-channel gray-scale map comprises:
if the remote sensing image is a panchromatic image, no processing is carried out, and if the remote sensing image is a multispectral color image, the remote sensing image is converted into a single-channel gray-scale image by the following method:
converting the multispectral color image into a gray level image by adopting a component weighted average mode;
calculating the global threshold value T of the gray level image by adopting an Ostu method*；
Performing power-law transformation on the gray image according to the global threshold to obtain the single-channel gray image, wherein the power-law transformation function is as follows:
wherein I is the pixel gray value of the gray image, I*The gray values of the pixels of the single-channel gray map are a and b, power law transformation coefficients are a < 1, b > 1, and α are set function segmentation threshold values.
6. The utility model provides a remote sensing image oil storage tank detection device which characterized in that, the device includes:
the single-channel gray-scale image acquisition module is used for unifying the remote sensing images into a single-channel gray-scale image;
the frame to be classified acquisition module is used for sliding the detection template on the single-channel gray-scale image in a certain step length to obtain a plurality of frames to be classified;
an IPR feature extraction module, configured to extract IPR features of the multiple frames to be classified, where the IPR features are defined as follows:
wherein, x and y are gray values of any two pixels in a frame to be classified;
the classification module is used for classifying the IPR characteristics of the frames to be classified by using a classifier to obtain target candidate frames;
and the nms operation module is used for performing nms operation on the target candidate frame to obtain a final detection result.
7. The remote sensing image oil storage tank detection device according to claim 6, wherein the classifier is a RST classifier, the RST classifier is a tree classifier, and the RST classifier determines node characteristics according to generated random numbers when constructing each node; if the generated random number is larger than a preset bias weight threshold value, selecting optimal characteristic information as node characteristics, otherwise, selecting suboptimal characteristic information as the node characteristics, wherein the optimal characteristic information is information of the current iteration, and the suboptimal characteristic information is information of the previous iteration.
8. The remote sensing image oil storage tank detection device of claim 7, wherein when the RST classifier learns, each attribute of a node learns a corresponding optimal threshold interval, the optimal threshold interval minimizes error loss of left and right leaf nodes, when a sample characteristic value is within the optimal threshold interval, the sample is divided into the right leaf nodes, otherwise, the sample is divided into the left leaf nodes, and a fitting value is given by the leaf nodes; wherein the fitting value F (D) and the error loss L are calculated by the following formula:
L＝W+·(F(D)-1)·(F(D)-1)+W-·(F(D)+1)·(F(D)+1)
d is the sample set in the node, W+Is the weighted sum of the positive samples in D, W-Is the weighted sum of the negative samples in D.
9. A computer readable storage medium for remote sensing image oil storage tank detection, comprising a processor and a memory for storing processor executable instructions, which when executed by the processor, implement steps comprising the remote sensing image oil storage tank detection method of any one of claims 1-5.
10. An apparatus for remote sensing image oil storage tank detection, comprising at least one processor and a memory storing computer executable instructions, wherein the processor executes the instructions to implement the steps of the remote sensing image oil storage tank detection method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811600681.XA CN111368865B (en) | 2018-12-26 | 2018-12-26 | Remote sensing image oil storage tank detection method and device, readable storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811600681.XA CN111368865B (en) | 2018-12-26 | 2018-12-26 | Remote sensing image oil storage tank detection method and device, readable storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111368865A true CN111368865A (en) | 2020-07-03 |
| CN111368865B CN111368865B (en) | 2023-08-22 |
Family
ID=71206014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811600681.XA Active CN111368865B (en) | 2018-12-26 | 2018-12-26 | Remote sensing image oil storage tank detection method and device, readable storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368865B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749673A (en) * | 2021-01-20 | 2021-05-04 | 西安中科星图空间数据技术有限公司 | Method and device for intelligently extracting stock of oil storage tank based on remote sensing image |
| CN114550009A (en) * | 2022-04-01 | 2022-05-27 | 中国科学院空天信息创新研究院 | Lightweight target detection method, device, equipment and medium for satellite-borne remote sensing image |
| CN116681699A (en) * | 2023-07-31 | 2023-09-01 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346434A (en) * | 2017-05-03 | 2017-11-14 | 上海大学 | A kind of plant pest detection method based on multiple features and SVMs |
| CN107358239A (en) * | 2017-06-07 | 2017-11-17 | 南京航空航天大学 | Image invariant feature extraction method based on circular track conversion |
| CN108304873A (en) * | 2018-01-30 | 2018-07-20 | 深圳市国脉畅行科技股份有限公司 | Object detection method based on high-resolution optical satellite remote-sensing image and its system |
| WO2018214195A1 (en) * | 2017-05-25 | 2018-11-29 | 中国矿业大学 | Remote sensing imaging bridge detection method based on convolutional neural network |
-
2018
- 2018-12-26 CN CN201811600681.XA patent/CN111368865B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346434A (en) * | 2017-05-03 | 2017-11-14 | 上海大学 | A kind of plant pest detection method based on multiple features and SVMs |
| WO2018214195A1 (en) * | 2017-05-25 | 2018-11-29 | 中国矿业大学 | Remote sensing imaging bridge detection method based on convolutional neural network |
| CN107358239A (en) * | 2017-06-07 | 2017-11-17 | 南京航空航天大学 | Image invariant feature extraction method based on circular track conversion |
| CN108304873A (en) * | 2018-01-30 | 2018-07-20 | 深圳市国脉畅行科技股份有限公司 | Object detection method based on high-resolution optical satellite remote-sensing image and its system |
Non-Patent Citations (3)
| Title |
|---|
| LI CHAO-KUI, ET AL: "A new kind of Combination Classifier and its application in Classification of Remote Sensing Image", 2018 FIFTH INTERNATIONAL WORKSHOP ON EARTH OBSERVATION AND REMOTE SENSING APPLICATIONS (EORSA) * |
| 余健;: "联合纹理和光谱特征的高光谱图像分类方法", no. 06 * |
| 马兰;陈筱勇;郭建星;: "基于SVM和变形模板的热红外油罐目标检测", no. 02 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749673A (en) * | 2021-01-20 | 2021-05-04 | 西安中科星图空间数据技术有限公司 | Method and device for intelligently extracting stock of oil storage tank based on remote sensing image |
| CN114550009A (en) * | 2022-04-01 | 2022-05-27 | 中国科学院空天信息创新研究院 | Lightweight target detection method, device, equipment and medium for satellite-borne remote sensing image |
| CN114550009B (en) * | 2022-04-01 | 2022-12-06 | 中国科学院空天信息创新研究院 | Lightweight target detection method, device, equipment and medium for satellite-borne remote sensing image |
| CN116681699A (en) * | 2023-07-31 | 2023-09-01 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
| CN116681699B (en) * | 2023-07-31 | 2023-12-15 | 国网浙江省电力有限公司宁波供电公司 | Intelligent storage method and device for transformer substation oil samples |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111368865B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | Multilevel cloud detection in remote sensing images based on deep learning | |
| Byeon et al. | Scene labeling with lstm recurrent neural networks | |
| CN109255344B (en) | Machine vision-based digital display type instrument positioning and reading identification method | |
| CN108121991B (en) | Deep learning ship target detection method based on edge candidate region extraction | |
| Attari et al. | Nazr-CNN: Fine-grained classification of UAV imagery for damage assessment | |
| US20140270489A1 (en) | Learned mid-level representation for contour and object detection | |
| CN109002755B (en) | Age estimation model construction method and estimation method based on face image | |
| Huang et al. | Local binary patterns and superpixel-based multiple kernels for hyperspectral image classification | |
| Alsmadi et al. | Fish recognition based on robust features extraction from color texture measurements using back-propagation classifier | |
| Fan et al. | A novel automatic dam crack detection algorithm based on local-global clustering | |
| Agarwal et al. | Image understanding using decision tree based machine learning | |
| CN106815323A (en) | A kind of cross-domain vision search method based on conspicuousness detection | |
| Xiang et al. | Moving object detection and shadow removing under changing illumination condition | |
| CN111368865B (en) | Remote sensing image oil storage tank detection method and device, readable storage medium and equipment | |
| CN113762138A (en) | Method and device for identifying forged face picture, computer equipment and storage medium | |
| Jiang et al. | Focal-test-based spatial decision tree learning: A summary of results | |
| CN112381030B (en) | Satellite optical remote sensing image target detection method based on feature fusion | |
| CN110852327A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN111814852A (en) | Image detection method, image detection device, electronic equipment and computer-readable storage medium | |
| CN111382638B (en) | Image detection method, device, equipment and storage medium | |
| Yang et al. | An improved algorithm for the detection of fastening targets based on machine vision | |
| Ouadiay et al. | Simultaneous object detection and localization using convolutional neural networks | |
| CN111353577B (en) | Multi-task-based cascade combination model optimization method and device and terminal equipment | |
| Liang et al. | Salient object detection based on regions | |
| Bianchi et al. | An interpretable graph-based image classifier |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |