CN112639868A - Image processing method and device and movable platform - Google Patents
Image processing method and device and movable platform Download PDFInfo
- Publication number
- CN112639868A CN112639868A CN202080004929.5A CN202080004929A CN112639868A CN 112639868 A CN112639868 A CN 112639868A CN 202080004929 A CN202080004929 A CN 202080004929A CN 112639868 A CN112639868 A CN 112639868A
- Authority
- CN
- China
- Prior art keywords
- image
- area
- interval
- processed
- flat
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000008859 change Effects 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
An image processing method, an image processing device and a movable platform are provided. The method comprises the following steps: determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value; histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area. Since the flat area is usually the corresponding image area including objects with less useful information, such as sky, lake, and ground, the tensile strength of the image area can be reduced as much as possible, and the tensile strength of the non-flat area can be increased, so that the non-flat area including more useful information can be stretched to a relatively large gray scale interval, and the contrast of the stretched non-flat area is clearer, and the detail information is richer.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image processing method, an image processing apparatus, and a movable platform.
Background
For some sensors, the resolution ratio of the acquired image is low, and the gray value distribution range of the image is small, so that the contrast ratio of the image is low, and the details in the image cannot be reflected. For example, the gray scale value of an infrared image collected by an infrared sensor is often distributed in a small range, resulting in low contrast of the image. Therefore, for such images, stretch enhancement processing is usually required to increase the gray value distribution range of the image to improve the contrast of the image and better embody the details of the image. However, for some images, a large area of flat regions, such as sky, lake, ground, etc., may be included, and these flat regions generally do not include useful information, but when the image is subjected to stretch enhancement processing, the image region occupies a larger gray scale interval, and the gray scale interval occupied by other image regions including useful information is compressed, so that the contrast of other image regions including useful information is still relatively low, and detailed information cannot be well shown. Therefore, it is necessary to provide a method for performing stretch enhancement processing on the image including the large-area flat region.
Disclosure of Invention
In view of the above, the present application provides an image processing method, an image processing apparatus and a movable platform.
According to a first aspect of the present application, there is provided an image processing method, the method comprising:
determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value;
histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
According to a second aspect of the present application, there is provided an image processing apparatus comprising: a processor, a memory, and a computer program stored on the memory, the processor, when executing the computer program, implementing the steps of:
determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value;
histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
According to a third aspect of the present application, there is provided a movable platform comprising an image sensor for capturing an image of a target and an image processing apparatus comprising: a processor, a memory, and a computer program stored on the memory, the processor, when executing the computer program, implementing the steps of:
determining a flat area in the target image, wherein the flat area is an area of which the gray scale change in the target image is less than or equal to a preset threshold value;
histogram stretching is carried out on the flat area and a non-flat area except the flat area in the target image respectively to obtain an image after stretching treatment, wherein the stretching strength of the non-flat area is higher than that of the flat area.
According to a fourth aspect of the present application, there is provided a computer readable storage medium storing a computer program, which when executed by a processor implements the method described in the first aspect above.
By applying the scheme provided by the application, when the image to be processed is subjected to the stretching enhancement processing, a flat area can be determined from the image to be processed according to the gray level change condition of the image to be processed, the flat area is an area with the gray level change smaller than or equal to a preset threshold value in the image to be processed, and the flat area is usually an image area corresponding to an object with less useful information, such as the sky, the lake, the ground and the like, so that the stretching strength of the image area can be reduced as much as possible when the image is subjected to the stretching enhancement processing, the stretching strength of the non-flat area is increased, the non-flat area with more useful information can be stretched to a larger gray level area, the contrast of the non-flat area after the stretching enhancement is clearer, and the detail information is richer.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a flowchart of an image processing method according to an embodiment of the present application.
FIG. 2 is a flowchart of an image processing method according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a logical structure of an image processing apparatus according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a logical structure of a movable platform according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Some sensors with lower resolution, such as infrared sensors and ultraviolet sensors, have a small gray value distribution range of the acquired image, resulting in a low contrast ratio of the image, and thus details in the image cannot be reflected. For example, it is assumed that the gray scale value ranges from 0 to 255, and the gray scale value of the image collected by the infrared sensor may only be distributed between 0 and 100, and the contrast is not clear, and the details in the image cannot be represented. Therefore, for such images, stretch enhancement processing is usually required to increase the gray value distribution range of the image to improve the contrast of the image and better embody the details of the image.
The image enhancement method is a lot of methods, and a stretching enhancement treatment based on a histogram is commonly used, wherein the enhancement process is to count the number of pixel points corresponding to each gray level in an original image to obtain a gray level histogram of the image, and then map the gray level range of the pixel points in the image to a larger gray level range through a certain mapping relation, so that the histogram of the enhanced image is larger in gray level distribution range relative to the histogram of the original image, the contrast is more vivid, and the details are clearer.
However, for some images, a large area of flat areas may be included, such as sky, lake, ground, etc., which generally do not include useful information and are not objects that users need to pay attention to, but when performing stretch enhancement and equalization processing on an image, because the frequency of gray levels corresponding to the image area is large, the image area occupies a large gray scale interval during the enhancement processing, and the gray scale interval occupied by other image areas including useful information is compressed, so that the contrast of other image areas including useful information is still relatively low, and detailed information cannot be well shown.
For example, for some application scenarios, for example, when tasks such as power inspection and target detection are performed by using a thermal infrared imager, a shot picture often has a large-area sky (or lake, ground, and the like) area, and when infrared image stretching enhancement processing is performed, the large-area sky area occupies much image information, so that the information content of other effective scenes is compressed, and the temperature difference details of the effective scenes cannot be fully displayed.
Based on this, the present application provides an image processing method, a specific flow of which is shown in fig. 1, including the following steps:
s102, determining a flat area in an image to be processed, wherein the flat area is an area of which the gray change in the image to be processed is less than or equal to a preset threshold value;
s104, histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
The image processing method provided by the application can be executed by the image acquisition device, for example, after the image acquisition device acquires the image, the image processing method directly performs enhancement processing operation. Of course, the image enhancement processing may be performed by other devices with an image processing function besides the image capturing device, for example, a terminal such as a mobile phone, a notebook computer, a tablet, or the like, or a cloud server, and these devices may acquire an image captured by the image capturing device and then perform the image enhancement processing operation.
The image processing method provided by the application can be used for performing enhancement processing on an image containing some relatively flat objects, wherein the objects can be objects such as sky, lake and ground, generally, useful information contained in image areas corresponding to the flat objects is less, and a user does not need to pay attention to the areas, so that the areas are not expected to occupy too large gray scale areas in the enhancement processing process, so that the gray scale areas of other image areas are compressed, and detailed information in other image areas cannot be reflected. Therefore, the image regions corresponding to the objects can be determined from the image, and when the image histogram stretch enhancement processing is performed, the image regions corresponding to the objects can be subjected to stretch suppression, that is, the stretching strength of the partial region is reduced as much as possible, and the stretching strength of other image regions is improved, so that the contrast of the other image regions after stretch enhancement is higher, and the detailed information is richer.
The image to be processed in the present application may be any type of image with low contrast such as an infrared image and an ultraviolet image, which needs stretch enhancement processing, and the present application is not limited.
Because flat areas in the image correspond to flat objects such as sky, lake, ground and the like, and the areas are characterized in that the gray level change degree of pixel points is small, the flat areas in the image to be processed can be determined according to the gray level change degree, for example, the areas with the gray level change smaller than or equal to a preset threshold value in the image to be processed are determined as the flat areas. The gray level change of the image can be determined according to the gray level difference value between the pixel point and the adjacent pixel point, or the image can be divided into a plurality of image blocks and determined according to the difference between the mean value of the gray level values in the image blocks and the mean value of the gray level values of the adjacent image blocks.
After determining a flat region in the image to be processed, histogram stretch enhancement processing may be performed for the flat region and a non-flat region other than the flat region in the image, respectively, wherein, in order to improve the contrast of the non-flat region, the tensile strength of the non-flat region may be higher than that of the flat region. For example, assuming that the gray scale distribution range of the pixel point of the image to be processed is 0-60, wherein the gray scale distribution range of the pixel point of the flat area is 0-30, and the gray scale distribution range of the pixel point of the non-flat area is 30-60, the pixel value of the pixel point of the flat area can be mapped to the gray scale interval of 0-60 through one mapping equation, and the pixel value of the pixel point of the non-flat area can be mapped to the gray scale interval of 60-255 through another mapping equation, so that the contrast of the non-flat area can be greatly improved, and the detail information can be more clearly displayed.
Of course, since the flat regions in the image may not be all regions corresponding to objects that do not need to be focused, such as sky and lake, but may also be regions corresponding to other objects that need to be focused, it is also possible to further specify image regions corresponding to objects that do not need to be focused, such as sky and lake, from the flat regions, and then perform stretch enhancement processing on the partial regions and the remaining regions in the flat regions, respectively. Therefore, in some embodiments, when performing histogram stretching on a flat region, histogram stretching may be performed on a designated region and a non-designated region other than the designated region in the flat region, respectively, where the designated region may be an image region corresponding to an object that does not need to be focused, such as a sky, a lake, or the like, and for the designated region, the stretching strength may be smaller than that of the non-designated region, so that, in the stretching enhancement process, enhancement of the contrast of the designated region that is not focused may be suppressed as much as possible without affecting enhancement of the contrast of other regions, and thus, it is avoided that useful image details are not displayed clearly.
In some embodiments, the designated area may be an image area corresponding to a designated gray scale interval, or may be an image area corresponding to a designated temperature interval. The designated grayscale interval and the designated temperature interval may be grayscale intervals or temperature intervals corresponding to objects that do not need to be focused, such as sky and lake, and the designated grayscale intervals and the designated temperature intervals may be preset by a user or may be determined by the image processing apparatus. For example, if the user knows in advance the grayscale interval corresponding to an object such as a sky or a lake that is not focused on, that is, the grayscale interval corresponding to the designated area can be input in advance through the user interface, and when the image is processed, the user can specify the designated area corresponding to an object such as a sky or a lake that is not focused on, based on the grayscale interval input by the user. Of course, in some embodiments, if the image to be processed is an infrared image, the grayscale and the temperature in the infrared image are corresponding, and therefore, if the user knows in advance the temperature interval corresponding to an object that is not focused on, such as a sky, a lake, etc., the temperature interval corresponding to the designated area may also be input in advance through the user interface, so that when the image to be processed is subjected to enhancement processing, the area corresponding to the object that is not focused on, such as a sky, a lake, etc., may be determined according to the temperature interval input by the user.
In some embodiments, objects such as sky and lake that are not focused on may be things with the lowest temperature or things with the highest temperature in the image to be processed, and thus the designated area may be an area with the lowest temperature in the image to be processed or an area with the highest temperature in the image to be processed. Therefore, when the designated gray scale interval is determined, the designated gray scale interval can be determined not only according to the gray scale interval input by the user, but also according to the gray scale histogram of the flat area and the temperature level sequence of each image area in the image to be processed. For example, assuming that the designated area is an area corresponding to the sky, which is the lowest temperature object in the entire image, the gray level interval corresponding to the lowest temperature object may be determined according to the gray level histogram of the flat area, that is, the designated gray level interval.
In some embodiments, if the designated gray level interval is the gray level interval corresponding to the lowest temperature region in the image to be processed, histogram statistics may be performed on the flat region to obtain a gray level histogram corresponding to the flat region, and then the designated gray level interval is determined according to the gray level histogram of the flat region.
Similarly, in some embodiments, if the designated gray scale interval is the gray scale interval corresponding to the highest temperature region in the image to be processed, the gray scale histogram of the flat region may be determined first, and then the designated gray scale interval may be determined according to the gray scale histogram of the flat region. Of course, the present application is not limited to the region with the highest temperature or the region with the lowest temperature in the image to be processed, and for the remaining image regions, as long as the temperature sequence of each image region in the image to be processed is known, the corresponding gray level interval can be determined according to the gray level histogram.
Of course, in some embodiments, if the image to be processed is an infrared image, after determining the gray scale interval corresponding to the designated area, the designated area may be determined from the image to be processed directly according to the gray scale interval, and then the stretch enhancement processing is performed. However, for infrared images, the accuracy of temperature is generally higher than that of gray scale, so the accuracy of determining the image area of a certain object by gray scale is lower than that of determining the image area corresponding to the certain object by temperature. Therefore, in order to determine the specified area more accurately, the specified area may be determined according to the temperature, that is, a temperature interval corresponding to the specified area is determined, that is, the specified temperature interval, where the specified temperature interval may be determined according to the temperature interval input by the user, or may be determined according to the determined specified gray level interval, for example, the specified area is an area corresponding to the sky, and the sky is an object with the lowest temperature in the image to be processed, so that the gray level interval corresponding to the sky may be determined according to the gray level histogram of the flat area, the temperature interval of the sky may be determined according to the conversion relationship between the temperature and the gray level, and the stretch enhancement processing of the image to be processed may be guided by the temperature interval.
Of course, since the temperature of objects such as sky and lake, which do not need to be focused on, may change to some extent as time goes on, when the specified temperature interval is determined according to the specified gray scale interval, the temperature may be determined together with multiple frames of images collected before or after the image to be processed, so that the determined temperature is more accurate. Specifically, a first temperature interval corresponding to a specified gray scale interval corresponding to an object that does not need to be focused, such as a sky, a lake, etc., in the image to be processed may be determined first, then a second temperature interval corresponding to the specified gray scale interval in the specified image may be determined, and the specified temperature interval may be obtained according to the first temperature interval and the second temperature interval. Wherein the designated image may be a plurality of frames of images acquired before or after the image to be processed. When the designated temperature interval is determined according to the first temperature interval and the second temperature interval, the designated temperature interval may be obtained by taking an average value or a weighted average value of the temperature intervals of the respective frames of images.
Since the designated gray scale interval or the image area corresponding to the designated temperature interval in the flat area is often an object that the user does not need to pay attention to, and needs to be suppressed during the stretching enhancement processing, similarly, for the non-flat area, the designated temperature interval or the image area corresponding to the designated gray scale interval is also a part that the user does not need to pay attention to, so that the suppression processing can be performed also when histogram stretching is performed on the part of the area, that is, the stretching intensity of the part can be reduced, so that the contrast of other important areas in the non-flat area can be clearer. Therefore, in some embodiments, when histogram stretching is performed on the non-flat region, a target region may also be determined from the non-flat region according to the specified gray scale interval or the specified temperature interval, where the target region is an image region corresponding to the specified temperature interval or the specified gray scale interval, and then image stretching enhancement processing may be performed on the target region and the non-target region in the non-flat region, respectively, where the stretching strength of the non-target region may be higher than that of the target region. Therefore, after the stretching enhancement processing, the image area outside the designated gray scale interval or the designated temperature interval can obtain higher contrast, and the details can be more clearly shown.
In some implementations, the enhancement process may be performed on the image to be processed before determining the flat region and the non-flat region of the image to be processed and then performing the stretch enhancement process on the flat region and the non-flat region, respectively.
In some embodiments, before determining a flat region and a non-flat region of an image to be processed and then performing stretch enhancement on the flat region and the non-flat region, respectively, preprocessing such as image rectification, dead pixel removal, noise removal and the like may be performed on the image to be processed, where the image rectification may be performing sensor response rate rectification and bias rectification on the image so as to obtain a relatively clean image with less noise, and then performing stretch enhancement operation.
In some embodiments, after determining a flat region and a non-flat region of an image to be processed, and then performing stretch enhancement processing on the flat region and the non-flat region respectively, one or more of local enhancement processing and pseudo-color mapping processing may be further performed on the image after the stretch enhancement processing, so as to obtain an image with richer details, which is convenient for subsequent research.
To further explain the image processing method of the present application, the above-described image processing method is explained below with reference to a specific embodiment.
Unmanned aerial vehicle can be used for electric power to patrol and examine usually, for example install infrared sensor on unmanned aerial vehicle, go to gather the infrared image of outdoor power equipment or electric wire, whether circuit fault appears through infrared image detection. For example, if the circuit is short-circuited, the local temperature is very high, and whether the temperature is abnormal or not and whether the fault occurs can be judged through an infrared image. However, the acquired infrared image has narrow gray scale distribution and low image contrast, so that details in the infrared image cannot be seen clearly. Therefore, the infrared image is usually enhanced, but the background of the infrared image, such as a photographed electric wire and an electric power device, often includes a large sky area, and when the enhancement processing and the image equalization processing are performed, the sky area occupies a large number of gray scale sections, and the gray scale sections of the electric power device area are compressed, so that the contrast of the electric power device area is still not high enough, and details cannot be well embodied. Therefore, the embodiment provides an image processing method, when the image is subjected to stretch enhancement processing, the stretching strength of the sky area can be suppressed, so that the detail information of the power equipment area can be better presented.
Wherein, unmanned aerial vehicle can carry out enhancement processing to the infrared image of gathering by oneself, also can send for appointed image processing equipment to handle. The specific processing procedure may refer to the processing flow chart in fig. 2.
After the infrared image acquired by the infrared sensor on the unmanned aerial vehicle is acquired, the infrared image may be preprocessed, for example, the infrared image is corrected, dead pixels, noise and the like in the infrared image are removed, and of course, the infrared image may be enhanced. The method comprises the steps of preprocessing an infrared image to obtain a preprocessed infrared image, then determining a flat area and a non-flat area in the image according to gray level change of the preprocessed infrared image, wherein the flat area is an area of which the gray level change in the image is smaller than or equal to a preset threshold value. Then histogram statistics is carried out on the flat area and the non-flat area respectively to obtain the gray level histograms of the flat area and the non-flat area. Since the sky is usually the object with the lowest temperature in the infrared image, the gray level interval of the sky area can be determined according to the gray level histogram of the flat area. Of course, since the grayscale fluctuation corresponding to the same object is large, the accuracy of determining the sky image region according to the grayscale is lower than that of determining the sky image region according to the temperature, so that the grayscale interval corresponding to the sky can be converted into the temperature interval corresponding to the sky according to the conversion relationship between the grayscale and the temperature. In addition, due to the lapse of time, the temperature of the sky may change to some extent, and in order to obtain a more accurate temperature interval of the sky, the temperature interval of the sky determined according to the multiframe infrared images acquired by the unmanned aerial vehicle before may be acquired, and then an average value may be obtained according to the temperature interval determined according to the current infrared image to be enhanced and the temperature interval of the sky in the multiframe images acquired before, and the average value may be used as the temperature interval corresponding to the sky area of the current infrared image to be enhanced. After the temperature interval of the sky is determined, an image area corresponding to the sky temperature interval and an image area outside the sky temperature interval can be determined from a flat area according to the temperature interval of the sky, an image area corresponding to the sky temperature interval and an image area outside the sky temperature interval can be determined from a non-flat area, and then histogram stretching processing is carried out on the four areas respectively. The sky area has no information to be focused on, so the tensile strength of the sky area can be as small as possible, and the non-flat area and the area with higher temperature in the flat area contain the information to be focused on, so the tensile strength of the sky area is as large as possible. Therefore, the image after the stretch processing may be obtained by stretch-enhancing the region corresponding to the sky temperature section in the flat region with the first stretch strength, stretch-enhancing the region other than the sky temperature section in the flat region with the second stretch strength, stretch-enhancing the region other than the sky temperature section in the non-flat region with the third stretch strength, and stretch-enhancing the region other than the sky temperature section in the non-flat region with the fourth stretch strength. Wherein the first tensile strength < the third tensile strength ≦ the second tensile strength ≦ the fourth tensile strength, and wherein the second tensile strength may be the same as or different from the fourth tensile strength. Of course, the image after the stretch processing may be obtained by simply performing stretch enhancement on the region corresponding to the sky temperature section in the flat region with the first stretch strength, performing stretch enhancement on the region other than the sky temperature section in the flat region with the second stretch strength, and performing stretch enhancement on the non-flat region with the fourth stretch strength. Or, performing stretch enhancement on the flat area by using the first tensile strength, and performing stretch enhancement on the non-flat area by using the fourth tensile strength to obtain an image after the stretch processing.
After the infrared image after stretching processing is obtained, local enhancement processing or pseudo-color mapping processing can be further carried out on the image, so that observation and aiming are facilitated, and subsequent fault analysis is carried out.
With the image processing method of the present embodiment, when performing stretch enhancement processing on an infrared image, a flat area including sky can be determined first, then, the temperature interval of the sky is determined according to the low-temperature characteristic of the sky and the gray histogram of the flat area, and during the stretching enhancement treatment, the region corresponding to the sky temperature section in the flat region is suppressed, and similarly, the region corresponding to the sky temperature section in the non-flat region is also a low temperature portion and does not contain information to be paid attention to, therefore, the portion may be weakly suppressed so that the tensile strength of the region corresponding to the sky temperature section in the flat region and the region corresponding to the sky temperature section in the non-flat region is smaller than that of the other image regions, therefore, the area needing to be focused in the infrared image is distributed in a larger gray scale interval after being stretched, the contrast can be greatly improved, and the subsequent fault analysis is facilitated.
Furthermore, the present application also provides an image processing apparatus, as shown in fig. 3, the image processing apparatus 30 includes: a processor 31, a memory 32 and a computer program stored on said memory, said processor 31, when executing said computer program, implementing the steps of:
determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value;
histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
In some embodiments, the processor, when configured to histogram stretch the flat region, comprises:
respectively performing histogram stretching on a designated area in the flat area and a non-designated area except the designated area; wherein the tensile strength of the non-designated area is higher than the tensile strength of the designated area.
In some embodiments, the designated area is an area corresponding to a designated gray scale interval;
or the specified area is an area corresponding to the specified temperature interval.
In some embodiments, the designated area is an area with the lowest temperature in the image to be processed or an area with the highest temperature in the image to be processed.
In some embodiments, the specified gray scale interval is determined based on a gray scale interval input by a user, or
The appointed gray level interval is determined based on the gray level histogram of the flat area and the temperature sequence of each image area in the image to be processed.
In some embodiments of the present invention, the,
and the appointed gray scale interval is a gray scale interval corresponding to the area with the lowest temperature in the image to be processed.
In some embodiments of the present invention, the,
and the appointed gray scale interval is a gray scale interval corresponding to the area with the highest temperature in the image to be processed.
In some embodiments, the specified temperature interval is determined based on a user-entered temperature interval, or
The specified temperature interval is determined based on the specified gray scale interval.
In some embodiments, the processor is configured to determine the specified temperature interval based on the specified gray scale interval, including:
determining a first temperature interval corresponding to the appointed gray level interval in the image to be processed;
determining a second temperature interval corresponding to the appointed gray interval in an appointed image, wherein the appointed image comprises a plurality of frames of images collected before or after the image to be processed;
and obtaining the specified temperature interval according to the first temperature interval and the second temperature interval.
In some embodiments, the processor for histogram stretching the non-flat region comprises:
histogram stretching is carried out on a target area in the non-flat area and a non-target area except the target area, wherein the target area is an image area corresponding to the specified temperature interval or the specified gray level interval, and the stretching strength of the non-target area is higher than that of the target area.
In some embodiments, the image to be processed is an enhanced processed image.
In certain embodiments, the image to be processed comprises an infrared image.
In certain embodiments, the image to be processed is a pre-processed image, the pre-processing including one or more of: image rectification, dead pixel removal and noise removal.
In certain embodiments, the processor is further configured to:
performing the following operations on the image after the stretching treatment: a local enhancement process and/or a pseudo-color mapping process.
For specific details of processing the image to be processed by the image processing apparatus, reference may be made to the description of each embodiment of the image processing method, and details are not repeated here.
Further, the present application also provides a movable platform, as shown in fig. 4, the movable platform 40 includes an image sensor 41 and an image processing device 42, the image sensor 41 is used for capturing a target image, and the image processing device 42 includes: a processor 421, a memory 422, and a computer program stored on the memory, wherein the processor 421 executes the computer program to implement the following steps:
determining a flat area in the target image, wherein the flat area is an area with gray level change smaller than or equal to a preset threshold value in the image to be processed;
histogram stretching is carried out on the flat area and a non-flat area except the flat area in the target image respectively to obtain an image after stretching treatment, wherein the stretching strength of the non-flat area is higher than that of the flat area.
In addition, the image processing apparatus in the movable platform may further complete any image processing method in the foregoing embodiments, and specific details may refer to descriptions of various embodiments in the image processing methods, which are not described herein again.
In certain embodiments, the movable platform in this application can be unmanned aerial vehicle, installs infrared sensor on the unmanned aerial vehicle for gather infrared image. For example, use the unmanned aerial vehicle who installs infrared sensor to carry out electric power and patrol and examine, judge whether electric power trouble appears through the infrared image of gathering. Of course, the movable platform of the application can be other movable intelligent equipment provided with an image sensor, such as an unmanned vehicle, an unmanned ship and the like
Accordingly, the embodiments of the present specification further provide a computer storage medium, in which a program is stored, and the program, when executed by a processor, implements the image processing method in any of the above embodiments.
Embodiments of the present description may take the form of a computer program product embodied on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having program code embodied therein. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of the storage medium of the computer include, but are not limited to: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. 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 identical elements in a process, method, article, or apparatus that comprises the element.
The method and apparatus provided by the embodiments of the present invention are described in detail above, and the principle and the embodiments of the present invention are explained in detail herein by using specific examples, and the description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (31)
1. An image processing method, characterized in that the method comprises:
determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value;
histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
2. The image processing method of claim 1, wherein histogram stretching the flat region comprises:
respectively performing histogram stretching on a designated area in the flat area and a non-designated area except the designated area; wherein the tensile strength of the non-designated area is higher than the tensile strength of the designated area.
3. The image processing method according to claim 2, wherein the designated area is an area corresponding to a designated gray scale interval;
or the specified area is an area corresponding to the specified temperature interval.
4. The image processing method according to claim 3, wherein the designated area is an area with the lowest temperature in the image to be processed or an area with the highest temperature in the image to be processed.
5. The image processing method according to claim 4,
the specified gray scale interval is determined based on a gray scale interval input by a user, or
The appointed gray level interval is determined based on the gray level histogram of the flat area and the temperature sequence of each image area in the image to be processed.
6. The image processing method according to claim 5, wherein the designated gray scale interval is a gray scale interval corresponding to a region with the lowest temperature in the image to be processed.
7. The image processing method according to claim 5, wherein the designated gray scale interval is a gray scale interval corresponding to a region with the highest temperature in the image to be processed.
8. The image processing method according to any one of claims 3 to 7, wherein the specified temperature zone is determined based on a temperature zone input by a user, or
The specified temperature interval is determined based on the specified gray scale interval.
9. The image processing method of claim 8, wherein determining the specified temperature interval based on the specified gray scale interval comprises:
determining a first temperature interval corresponding to the appointed gray level interval in the image to be processed;
determining a second temperature interval corresponding to the appointed gray interval in an appointed image, wherein the appointed image comprises a plurality of frames of images collected before or after the image to be processed;
and obtaining the specified temperature interval according to the first temperature interval and the second temperature interval.
10. The image processing method according to any one of claims 3 to 9, wherein histogram stretching the non-flat region comprises:
histogram stretching is carried out on a target area in the non-flat area and a non-target area except the target area, wherein the target area is an image area corresponding to the specified temperature interval or the specified gray level interval, and the stretching strength of the non-target area is higher than that of the target area.
11. The image processing method according to claim 1, wherein the image to be processed is an enhanced image.
12. The image processing method according to claim 1, wherein the image to be processed includes an infrared image.
13. The image processing method according to claim 1, wherein the image to be processed is a preprocessed image, and the preprocessing comprises one or more of: image rectification, dead pixel removal and noise removal.
14. The image processing method according to claim 1, characterized in that the method further comprises:
performing the following operations on the image after the stretching treatment: a local enhancement process and/or a pseudo-color mapping process.
15. An image processing apparatus characterized by comprising: a processor, a memory, and a computer program stored on the memory, the processor, when executing the computer program, implementing the steps of:
determining a flat area in an image to be processed, wherein the flat area is an area of which the gray level change in the image to be processed is less than or equal to a preset threshold value;
histogram stretching is respectively carried out on the flat area and a non-flat area except the flat area in the image to be processed, and an image after stretching processing is obtained, wherein the stretching strength of the non-flat area is higher than that of the flat area.
16. The image processing apparatus of claim 15, wherein the processor, when performing histogram stretching on the flat region, comprises:
respectively performing histogram stretching on a designated area in the flat area and a non-designated area except the designated area; wherein the tensile strength of the non-designated area is higher than the tensile strength of the designated area.
17. The image processing apparatus according to claim 16, wherein the designated region is a region corresponding to a designated gray scale section;
or the specified area is an area corresponding to the specified temperature interval.
18. The apparatus according to claim 17, wherein said specified area is an area with a lowest temperature in said image to be processed or an area with a highest temperature in said image to be processed.
19. The image processing apparatus according to claim 18,
the specified gray scale interval is determined based on a gray scale interval input by a user, or
The appointed gray level interval is determined based on the gray level histogram of the flat area and the temperature sequence of each image area in the image to be processed.
20. The image processing apparatus according to claim 19,
and the appointed gray scale interval is a gray scale interval corresponding to the area with the lowest temperature in the image to be processed.
21. The image processing apparatus according to claim 19,
and the appointed gray scale interval is a gray scale interval corresponding to the area with the highest temperature in the image to be processed.
22. The apparatus according to any one of claims 17 to 21, wherein the specified temperature zone is determined based on a temperature zone input by a user, or
The specified temperature interval is determined based on the specified gray scale interval.
23. The image processing apparatus of claim 22, wherein the processor is configured to determine the specified temperature interval based on the specified gray scale interval, and comprises:
determining a first temperature interval corresponding to the appointed gray level interval in the image to be processed;
determining a second temperature interval corresponding to the appointed gray interval in an appointed image, wherein the appointed image comprises a plurality of frames of images collected before or after the image to be processed;
and obtaining the specified temperature interval according to the first temperature interval and the second temperature interval.
24. The image processing apparatus according to any of claims 17-23, wherein the processor configured to histogram stretch the non-flat region comprises:
histogram stretching is carried out on a target area in the non-flat area and a non-target area except the target area, wherein the target area is an image area corresponding to the specified temperature interval or the specified gray level interval, and the stretching strength of the non-target area is higher than that of the target area.
25. The image processing apparatus according to claim 15, wherein the image to be processed is an enhanced image.
26. The image processing apparatus according to claim 15, wherein the image to be processed includes an infrared image.
27. The image processing apparatus according to claim 15, wherein the image to be processed is a preprocessed image, the preprocessing including one or more of: image rectification, dead pixel removal and noise removal.
28. The image processing apparatus of claim 15, wherein the processor is further configured to:
performing the following operations on the image after the stretching treatment: a local enhancement process and/or a pseudo-color mapping process.
29. A movable platform comprising an image sensor for capturing an image of a target and an image processing device comprising: a processor, a memory, and a computer program stored on the memory, the processor, when executing the computer program, implementing the steps of:
determining a flat area in the target image, wherein the flat area is an area of which the gray scale change in the target image is less than or equal to a preset threshold value;
histogram stretching is carried out on the flat area and a non-flat area except the flat area in the target image respectively to obtain an image after stretching treatment, wherein the stretching strength of the non-flat area is higher than that of the flat area.
30. The movable platform of claim 29, wherein the movable platform comprises a drone.
31. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the image processing method according to any one of claims 1 to 14.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/081813 WO2021189460A1 (en) | 2020-03-27 | 2020-03-27 | Image processing method and apparatus, and movable platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112639868A true CN112639868A (en) | 2021-04-09 |
Family
ID=75291265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080004929.5A Pending CN112639868A (en) | 2020-03-27 | 2020-03-27 | Image processing method and device and movable platform |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112639868A (en) |
| WO (1) | WO2021189460A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511120B (en) * | 2022-04-21 | 2022-07-19 | 浙江天铂云科光电股份有限公司 | Power equipment fault diagnosis method based on temperature vision electric wire |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100085361A1 (en) * | 2008-10-08 | 2010-04-08 | Korea Advanced Institute Of Science And Technology | Apparatus and method for enhancing images in consideration of region characteristics |
| CN106934782A (en) * | 2017-01-16 | 2017-07-07 | 中国计量大学 | A kind of infrared image enhancing method |
| CN107067385A (en) * | 2017-01-23 | 2017-08-18 | 上海兴芯微电子科技有限公司 | A kind of image enchancing method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100900678B1 (en) * | 2008-02-15 | 2009-06-01 | 한양대학교 산학협력단 | Image quality enhancement method using dynamic range segmentation |
| CN110400260B (en) * | 2018-04-25 | 2022-07-29 | 展讯通信（上海）有限公司 | Image processing method and device |
-
2020
- 2020-03-27 WO PCT/CN2020/081813 patent/WO2021189460A1/en active Application Filing
- 2020-03-27 CN CN202080004929.5A patent/CN112639868A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100085361A1 (en) * | 2008-10-08 | 2010-04-08 | Korea Advanced Institute Of Science And Technology | Apparatus and method for enhancing images in consideration of region characteristics |
| CN106934782A (en) * | 2017-01-16 | 2017-07-07 | 中国计量大学 | A kind of infrared image enhancing method |
| CN107067385A (en) * | 2017-01-23 | 2017-08-18 | 上海兴芯微电子科技有限公司 | A kind of image enchancing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 唐圣凯: "基于Otsu可控灰度拉伸的直方均衡化算法", 中国优秀硕士学位论文全文数据库 信息科技辑, 15 September 2019 (2019-09-15), pages 1 - 3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021189460A1 (en) | 2021-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20110267507A1 (en) | Range measurement using a zoom camera | |
| US20110267485A1 (en) | Range measurement using a coded aperture | |
| US20110267477A1 (en) | Range measurement using symmetric coded apertures | |
| CN112560619B (en) | Multi-focus image fusion-based multi-distance bird accurate identification method | |
| CN112164086A (en) | Refined image edge information determining method and system and electronic equipment | |
| CN113962859B (en) | Panorama generation method, device, equipment and medium | |
| Feng et al. | A novel saliency detection method for wild animal monitoring images with WMSN | |
| CN110490196A (en) | Subject detection method and apparatus, electronic equipment, computer readable storage medium | |
| CN111311562B (en) | Ambiguity detection method and device for virtual focus image | |
| CN117274759A (en) | Infrared and visible light image fusion system based on distillation-fusion-semantic joint driving | |
| CN113688830B (en) | Deep learning target detection method based on center point regression | |
| CN114140481A (en) | Edge detection method and device based on infrared image | |
| CN112639868A (en) | Image processing method and device and movable platform | |
| CN110392211A (en) | Image processing method and device, electronic equipment, computer readable storage medium | |
| CN111753775B (en) | Fish growth assessment method, device, equipment and storage medium | |
| CN111179245B (en) | Image quality detection method, device, electronic equipment and storage medium | |
| CN110399868B (en) | Coastal wetland bird detection method | |
| CN116543022A (en) | Gas infrared image processing method, gas leak detector and storage medium | |
| WO2022247684A1 (en) | Detection method and system for base-station feeder line, and related apparatus | |
| CN115205793A (en) | Electric power machine room smoke detection method and device based on deep learning secondary confirmation | |
| Wang et al. | Spatio-temporal ssim index for video quality assessment | |
| CN114066794A (en) | Image processing method, device and equipment and storage medium | |
| CN110717441B (en) | Video target detection method, device, equipment and medium | |
| Anitha et al. | Quality assessment of resultant images after processing | |
| van Zwanenberg et al. | Analysis of natural scene derived spatial frequency responses for estimating camera ISO12233 slanted-edge performance (JIST-first) |
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 |