Infrared image processing and hot spot tracking method, system and device for bird repelling in airport

Abstract

The invention provides an infrared image processing and hot spot tracking method, system and device for bird repelling in an airport, and the method comprises the steps: firstly carrying out the infrared image preprocessing operation after an infrared image is obtained through detection, and carrying out the non-uniformity correction, image noise reduction and image enhancement processing; and then, aiming at the image subjected to image noise reduction, performing hot spot detection operation, determining the highest temperature point in the image, and displaying the position of the highest temperature point in real time on the 8-bit image subjected to image enhancement by a visual square frame to realize hot spot tracking operation, so that real-time display and online monitoring functions of infrared image processing and hot spot tracking are realized. According to the infrared image processing and hot spot tracking method for airport bird repelling, the position of the highest temperature point in the infrared image can be visually seen on the display control terminal, stable, accurate and real-time positioning and tracking can be achieved along with movement of the infrared device or the highest temperature point, and the premise is provided for correctly and effectively achieving airport bird repelling work.

Description

Technical Field

[0001] The present invention relates to the technical field of infrared image processing, and is applicable to bird-repelling at airports. Specifically, the present invention relates to a method, system and device for infrared image processing and hotspot tracking for bird-repelling at airports. Background Art

[0002] With the rapid development of the economy and society and the continuous improvement of the ecological environment, the number of airports and various aircraft has increased, and the number of birds has also continued to increase. There has been a fierce competition for space between aircraft and birds, and bird strikes have continued to rise. In the face of the severe bird strike risk prevention situation, in addition to the corresponding bird strike prevention measures designed into the aircraft structure, relevant bird repellent equipment has also been added around the airport.

[0003] In the existing technology, airports can reduce the probability of bird strikes to a certain extent by using a variety of bird-repelling methods to drive away birds. The main technical means at present is to set up fixed and mobile sentries at the airport and patrol with human eyes or telescopes. In most cases, monitors cannot timely and effectively detect dangerous bird flocks. In addition, this work is labor-intensive, with a small observation range and is greatly affected by factors such as weather and light. Bird-repelling work is relatively passive and cannot achieve timely detection, especially at night, which poses a serious threat to flight safety. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and device for infrared image processing and hotspot tracking for airport bird repellent. Infrared image data is acquired through a non-cooled infrared detector, the pixel coordinate position of the highest temperature point in the infrared image is obtained by analysis, and a visual box is superimposed in the infrared image to track the position of the highest temperature point in real time, so that airport monitoring personnel can intuitively see the position of birds in the image, thereby carrying out bird repellent work through bird repellent equipment more quickly, more effectively and more accurately.

[0005] According to a first aspect of the present invention, a method for infrared image processing and hotspot tracking for bird repelling at an airport is provided, comprising the following steps:

[0006] Step 1, obtaining infrared image data collected by an uncooled infrared detector;

[0007] Step 2: performing image processing operations on the collected infrared image data, including non-uniform correction, image noise reduction, and image enhancement;

[0008] Step 3: Based on the infrared image data after image noise reduction in the image processing operation, hot spot detection is performed to analyze all pixel points in the infrared image, and the highest temperature point of the infrared image is determined to determine its coordinates;

[0009] Step 4: Based on the infrared image data after image enhancement in the image processing operation and in combination with the result after hotspot detection, the position of the highest temperature point is marked in real time on the image through a visual display box, and the position of the box is changed in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation;

[0010] Step 5: Perform time sequence control on the infrared image after the infrared image processing and hot spot tracking operations, and output an infrared image with the position of the highest temperature point marked.

[0011] According to a second aspect of the present invention, a device for infrared image processing and hotspot tracking for bird repelling at an airport is provided, comprising:

[0012] An image acquisition module for acquiring infrared image data collected by an uncooled infrared detector;

[0013] An image processing module for performing image processing operations on the collected infrared image data, wherein the image processing operations include non-uniformity correction, image noise reduction, and image enhancement;

[0014] A hot spot detection module for performing hot spot detection based on infrared image data after image noise reduction in an image processing operation, configured to determine the highest temperature point in the infrared image by analyzing all pixels in the infrared image and determine its coordinates;

[0015] A hotspot tracking module for marking the position of the highest temperature point in real time on the image through a visual display box based on the infrared image data after image enhancement in the image processing operation and the result after hotspot detection, and changing the position of the box in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation;

[0016] An infrared image output module is used to perform timing control on infrared images after infrared image processing and hot spot tracking operations, and output infrared images marked with the position of the highest temperature point.

[0017] According to a third aspect of the present invention, a computer system is provided, comprising:

[0018] one or more processors;

[0019] A memory stores operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors perform operations, wherein the operations include the process of the aforementioned infrared image processing and hotspot tracking method for bird repelling at airports.

[0020] The infrared image processing and hotspot tracking method for bird repelling at airports according to the above embodiment of the present invention provides imaging support for airport bird repelling equipment to detect bird flocks in time, deal with them in time and reduce the probability of bird strikes on aircraft, and is a key imaging device for airport bird repelling equipment. The infrared image processing and hotspot tracking method for bird repelling at airports according to the present invention has the characteristics of convenient use and excellent imaging performance, and can be used in military and civil airports, substations and other bird-prone areas, and fully automatic unattended bird pest control. It can also be extended to security monitoring, criminal investigation, outdoor sports, hunting and other related fields, and has broad application prospects.

[0021] It should be understood that all combinations of the aforementioned concepts and the additional concepts described in more detail below can be considered as part of the inventive subject matter of the present disclosure as long as such concepts are not mutually inconsistent. In addition, all combinations of the claimed subject matter are considered as part of the inventive subject matter of the present disclosure.

[0022] The foregoing and other aspects, embodiments and features of the present invention can be more fully understood from the following description in conjunction with the accompanying drawings. Other additional aspects of the present invention, such as the features and / or beneficial effects of the exemplary embodiments, will be apparent from the following description or learned from the practice of the specific embodiments according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are not intended to be drawn to scale. In the accompanying drawings, each identical or nearly identical component shown in each figure may be represented by the same reference numeral. For clarity, not every component is labeled in each figure. Embodiments of various aspects of the present invention will now be described by way of example and with reference to the accompanying drawings.

[0024] Figure 1 The figure is a flow chart of an infrared image processing and hotspot tracking method for bird repelling at an airport according to an embodiment of the present invention.

[0025] Figure 2 It is a schematic diagram of an uncooled infrared hotspot tracking image output according to an embodiment of the present invention.

[0026] Figure 3 It is a schematic diagram of online displaying of an uncooled infrared hot spot tracking image and its pseudo-color image on a display and control terminal according to an embodiment of the present invention.

[0027] Figure 4 Schematic diagram of an infrared image processing and hotspot tracking device for bird repelling at an airport according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to better understand the technical content of the present invention, specific embodiments are given and described as follows in conjunction with the accompanying drawings.

[0029] Various aspects of the present invention are described in this disclosure with reference to the accompanying drawings, in which many illustrative embodiments are shown. The embodiments of the present disclosure are not necessarily intended to include all aspects of the present invention. It should be understood that the various concepts and embodiments introduced above, as well as those described in more detail below, can be implemented in any of many ways, because the concepts and embodiments disclosed by the present invention are not limited to any implementation. In addition, some aspects disclosed by the present invention can be used alone or in any appropriate combination with other aspects disclosed by the present invention.

[0030] {Example 1}

[0031] Combination Figure 1 As shown, the method for infrared image processing and hotspot tracking for bird repelling at an airport according to an embodiment of the present invention comprises the following steps:

[0032] Step 1, obtaining infrared image data collected by an uncooled infrared detector;

[0033] Step 2: performing image processing operations on the collected infrared image data, including non-uniform correction, image noise reduction, and image enhancement;

[0034] Step 3: Based on the infrared image data after image noise reduction in the image processing operation, hot spot detection is performed to analyze all pixel points in the infrared image, and the highest temperature point of the infrared image is determined to determine its coordinates;

[0035] Step 4: Based on the infrared image data after image enhancement in the image processing operation and in combination with the result after hotspot detection, the position of the highest temperature point is marked in real time on the image through a visual display box, and the position of the box is changed in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation;

[0036] Step 5: Perform time sequence control on the infrared image after the infrared image processing and hot spot tracking operations, and output an infrared image with the position of the highest temperature point marked.

[0037] As an optional embodiment, in step 2, the non-uniform correction of the collected infrared image data is performed using a two-point correction method, including the following steps:

[0038] Using a black body as a uniform radiation source, the focal plane of the uncooled infrared detector is illuminated at different temperatures of radiance, and high-temperature and low-temperature images are collected to obtain the output value V at high-temperature and low-temperature radiances. i,j (T h ) and V i,j (T l ), and store;

[0039] The average value of the pixel under high temperature and low temperature radiance and as the expected response value;

[0040] Based on the output value V at high and low temperature radiance i,j (T h ) and V i,j (T l ), and the pixel averages at high and low temperature radiances and Calculate the gain correction parameter and the offset correction parameter;

[0041] The collected infrared image data is subjected to non-uniform correction based on the gain correction parameter and the offset correction parameter to obtain infrared image data after two-point correction.

[0042] As an optional embodiment, in step 2, after the collected infrared image data is subjected to non-uniform correction, a joint filtering and noise reduction in the spatial domain and the temporal domain using a median filter and a bilateral filter algorithm is performed, including the following steps:

[0043] (1) Select the first filter to perform sliding median filtering on the infrared image data after non-uniform correction, sort the grayscale values ​​of all pixels in the sliding area, and find the middle value x mid , and replace the original grayscale value of the central pixel with the intermediate value;

[0044] (2) A bilateral filtering algorithm is used to estimate the grayscale value of the current pixel using the pixel grayscale values ​​of consecutive historical frames, thereby achieving a smooth transition of the grayscale values ​​of the same pixel between consecutive frames.

[0045] As an optional implementation manner, in step 2, after performing image denoising on the collected infrared image data, a detail enhancement method of weighted fusion of high- and low-frequency information is adopted based on image layering to obtain infrared image data with enhanced details.

[0046] As an optional embodiment, the method of detail enhancement based on image layering and weighted fusion of high-frequency and low-frequency information to obtain infrared image data after detail enhancement includes the following steps:

[0047] Using a second filter to separate high-frequency detail information and low-frequency background information from the infrared image data after image noise reduction;

[0048] For low-frequency background information, the histogram equalization algorithm is used to enhance the contrast and highlight the outline of the target; for high-frequency detail information, the original image is obtained by subtracting the low-frequency background information, and the adaptive gain control algorithm is used to improve the detail information;

[0049] The weighted fusion method is adopted to fuse the low-frequency information with the high-frequency information based on the fusion coefficient, and the enhanced infrared image data is output.

[0050] As an optional implementation mode, in step 3, the infrared image data after image noise reduction in the image processing operation is used to perform hot spot detection, analyze all pixels in the infrared image, and determine the highest temperature point of the infrared image and determine its coordinates, including:

[0051] Using the third filter to traverse each pixel in the infrared image data output after image noise reduction, calculate the average value of the pixel points in each filter window;

[0052] Based on the comparison of the average values ​​output from each window, the maximum value point and its coordinate value are determined and stored.

[0053] As an optional implementation manner, in step 4, the size and border thickness of the visual display frame are adjustable and are set by a host computer.

[0054] As an optional implementation mode, in step 5, the infrared image marked with the position of the highest temperature point is output as a digital video to a display control terminal via CameraLink for real-time display, and the digital video includes the position information of the highest temperature point;

[0055] The display and control terminal converts the infrared image into a pseudo-color image sequence by pseudo-color coding for visual representation.

[0056] Therefore, in combination with the infrared image processing and hotspot tracking method for airport bird repelling of the above embodiment, after the infrared image is detected and obtained, the infrared image preprocessing operation is first performed, including non-uniformity correction, image noise reduction, and image enhancement processing. After that, the hotspot detection operation is performed on the image after image noise reduction to determine the highest temperature point in the image, and the position of the highest temperature point is displayed in real time on the 8-bit image after image enhancement by a visualization box to implement the hotspot tracking operation, thereby realizing the real-time display and online monitoring functions of infrared image processing and hotspot tracking.

[0057] The infrared image processing and hotspot tracking method for airport bird repellent of the present invention can clearly and intuitively see the position of the highest temperature point in the infrared image on the display without affecting the image display and storage, and can stably, accurately and real-time locate and track as the infrared device or the highest temperature point moves, providing a prerequisite for correctly and effectively realizing the work of airport bird repellent.

[0058] In particular, the infrared image data processed by the method of the present invention outputs digital video to the display and control terminal through CameraLink for real-time display, and the digital video includes the location information of the highest temperature point. The display and control terminal can be a PC, a mobile phone, a tablet device, etc. The user can realize real-time online observation of the infrared image at the terminal, and the display frame in the picture can intuitively display the location of the highest temperature point. Furthermore, the display and control terminal can also convert the collected infrared image data sequence into a pseudo-color image sequence in real time through a pseudo-color coding method, thereby improving the resolution of the infrared image and facilitating visualization of the human visual system.

[0059] {Example 2}

[0060] In this embodiment, we combine Figures 2 to 4 As shown, the method of the aforementioned embodiment is further elaborated and illustrated.

[0061] The infrared image processing and hotspot tracking method for airport bird repellent in this example aims to realize infrared image data processing and hotspot detection and tracking of input infrared images, and provide imaging support for airport bird repellent equipment. The specific implementation process and steps are as follows:

[0062] First, the infrared image data is collected using an uncooled infrared detector;

[0063] Then, a non-uniformity correction algorithm is used to process the collected infrared image data, and the input infrared image is subjected to non-uniform correction based on a gain coefficient and a bias coefficient;

[0064] Then, for the infrared image data after non-uniform correction, the median filter and bilateral filter algorithms are used to realize the joint filtering and denoising in the spatial domain and the temporal domain. The median filter is used to eliminate the salt and pepper noise of the image, and the bilateral filter solves the problems of tailing and blurring caused by moving targets in the image, ultimately ensuring the detailed information in the image while reducing the noise.

[0065] After image denoising, high-frequency detail information and low-frequency background information are dynamically compressed based on image layering, and then weighted fusion of the image is performed to enhance the image details, compressing the infrared image from 14 bits to 8 bits to maximize the image contrast and detail information.

[0066] For the infrared image output after the above image denoising, a filter of a certain size is used to determine the highest temperature point in the image and its coordinate value, and store them;

[0067] Finally, the coordinate value of the highest temperature point is displayed in real time on the infrared image data after image enhancement through a visualization display frame, and the size and border thickness of the visualization display frame can be set through the host computer.

[0068] The final output infrared image contains the location indication of the highest temperature point, and the visual display frame can change in real time as the location of the highest temperature point changes.

[0069] As an example, an uncooled infrared detector and a customized lens are used to collect infrared image data and output digital signals using an imaging circuit, with an image resolution of 640×512.

[0070] In the above method, the gain correction parameter and the offset correction parameter are determined according to the two-point correction algorithm, and then the corrected infrared image data is obtained. The steps are as follows:

[0071] Step 201: At high temperature radiance T h =50℃ and low temperature radiation T l = 0℃, respectively illuminate the focal plane of the detector, collect high temperature and low temperature images and store them, and obtain the output value V at high temperature and low temperature radiance i,j (T h ) and V i,j (T l );

[0072] Step 202: Average the pixel values ​​under high temperature and low temperature radiances and As the expected response value, it is defined as:

[0073]

[0074] Among them, M represents the number of rows of a frame image, and N represents the number of columns of a frame image;

[0075] Step 203: Calculate the gain correction parameter a and the offset correction parameter b, which are defined as:

[0076]

[0077] Step 204: Correct the infrared image data based on the gain correction parameter and the offset correction parameter to obtain a two-point corrected image. The response output value of the (i, j)th pixel is:

[0078] V i,j ′=a×V i,j +b.

[0079] As an optional embodiment, in actual use, the bias correction parameters may drift with the increase of the working temperature of the uncooled detector. The baffle correction may also be performed at fixed time intervals to update the bias correction parameters in real time.

[0080] Therefore, in view of the non-uniformity problem of the response of the uncooled detector to the external radiation, the non-uniformity correction method of the above two-point correction is used to solve the problems of increased image noise and blurred image caused by the non-uniformity.

[0081] After the non-uniform correction operation, the median filter and bilateral filter algorithms are used to implement joint filtering and denoising in the spatial and temporal domains for the spatial and temporal noise in the infrared image, so as to protect the edge of the target, reduce image noise, and solve the problems of tailing and blurring caused by moving targets in the image.

[0082] On the one hand, by selecting a filter window of a certain size, median filtering is performed on the image data after non-uniform correction, and the grayscale values ​​of all pixels in the sliding area of ​​the filter are sorted to find the middle value x mid , and use x mid Replace the original gray value of the center pixel;

[0083] On the other hand, a bilateral filtering algorithm is used to estimate the grayscale value of the current pixel using the pixel grayscale values ​​of consecutive historical frames, so as to achieve a smooth transition of the grayscale values ​​of the same pixel between consecutive frames and solve the problems of tailing and blurring caused by moving targets.

[0084] In the above method, the median filter in image denoising uses a 3×3 filter window to slide the infrared image, sorts the grayscale values ​​of all pixels in the sliding area, and finds the middle value x mid , and replace the original grayscale value of the center pixel with the intermediate value.

[0085] As an optional approach, the size of the median filter window can be tried starting from a small size and gradually increasing the window size until the desired effect is achieved.

[0086] The bilateral filtering algorithm in image denoising introduces the influence of the grayscale values ​​of the pixel neighborhood, so that when estimating the grayscale value of the current pixel, the spatial proximity and pixel value similarity of the image are combined. The processing result of each pixel is expressed as the weighted mean of the pixels in its adjacent area.

[0087] The definition of bilateral filtering is:

[0088]

[0089] in, is the gray value of the filtered image at the pixel point (x, y), g(i, j) is the gray value of the original image at the pixel point (x, y), Z is the weight normalization coefficient of the filter, S xy is the filtering window, w S is the spatial filter function, w ris the grayscale filtering function, and Gaussian function is generally used as these two functions, σ S and σ r is the standard deviation.

[0090] Among them, the filtering weight of bilateral filtering is given by w S and w r Multiplying together gives:

[0091]

[0092] After that, the grayscale values ​​of pixels in consecutive frames are introduced to correct the filter weights to solve the problems of tailing and blurring caused by moving targets in the image. Therefore, for each pixel, the corrected filter estimate can be defined as:

[0093]

[0094] Where N is the total number of image frames currently acquired, K is the number of filtered frames, t is the time represented by discrete frame numbers, and W P is the normalization coefficient of the modified filter weight.

[0095] After the image denoising algorithm, the infrared image is enhanced by the image enhancement method to improve the image contrast and maximize the retention of image details. Specifically, based on image stratification, dynamic compression processing is performed on high-frequency detail information and low-frequency background information respectively, and then weighted fusion of the image is performed.

[0096] As an optional embodiment, the image layering operation selects to use a bilateral filtering algorithm to perform image layering processing to obtain low-frequency background information and high-frequency detail information of the image.

[0097] For low-frequency background information, the pixel grayscale value changes slightly and smoothly. The platform histogram equalization technology is used to compress the high-order signal to the low-order signal through mapping, disperse the grayscale with a higher probability in the image histogram to more grayscales, merge or compress the grayscale with a lower probability, change the distribution range of all grayscale values ​​in the original image, indirectly change the grayscale value probability function, evenly enlarge the display range of the image, make the histogram distribution of the image more even, and finally improve the contrast of the infrared image and enhance the contrast between the target and the background.

[0098] The plateau histogram of infrared images is defined as follows:

[0099]

[0100] Where i represents the image pixel value, T represents the platform threshold, and F T (i) represents the platform histogram of the infrared image, and F(i) is the statistical histogram of the image.

[0101] Accumulate the platform histogram to get S T (i)

[0102]

[0103] The result of the point with pixel value i after platform histogram processing is D T (i)

[0104]

[0105] For high-frequency detail information, the more visible the noise is in the smooth area of ​​the infrared image, the less visible the noise is in the abrupt area of ​​the infrared image. Therefore, the adaptive gain control technology is used to perform noise reduction on the detail layer image in different regions, and the noise reduction coefficient of each region is adaptively adjusted to preserve and enhance the original detail information, while suppressing more random noise.

[0106] As an example, the adaptive denoising function is expressed as:

[0107] K(x,y)=K min +[1-f(x,y)]×(K max -K min );

[0108]

[0109] Where M(x, y) is the noise template function, which is related to the local variance of the image; f(x, y) represents the relationship between the noise visibility and the noise template function; K min is the low gain value of the image, K max High gain value for the image.

[0110] When a pixel point f(x,y) in the image → 0, the noise reduction coefficient value of the point is large, otherwise, the noise reduction coefficient value is small. In order to retain more detailed information in the image, K min and K max Usually a smaller integer is used.

[0111] Finally, the low-frequency information and the high-frequency information are weightedly fused by selecting appropriate fusion coefficients to obtain a new image.

[0112] The fusion coefficient, as the size of the image fusion ratio, controls the degree of detail in the final image. The larger the value, the more obvious the image detail enhancement, the clearer the image will be, but it is prone to over-sharpening. The smaller the value, the weaker the image detail enhancement, the image is too smooth, and the image will be more blurred.

[0113] In the embodiment of the present invention, the proportion α of the high-frequency detail information is selected to be 0.5-0.8, and the fusion effect is better.

[0114] f o (x,y)=α·f′ h (x,y)+(1-α)·f l '(x,y)

[0115] Furthermore, the purpose of hot spot detection is to determine the highest temperature point and its coordinate value in the infrared image output after image noise reduction. As an example, the steps for determining the highest temperature point in the image through hot spot detection are as follows:

[0116] Select a filter window of a predetermined size, taking 3×3 as an example;

[0117] Use a 3×3 filter to traverse each pixel in the infrared image data output after the image denoising operation, and calculate the average value of the pixels in each filter window

[0118] Compare the average values ​​of each filter window output and determine the maximum value point x max and its corresponding coordinate values ​​(x, y), and store the maximum value point x max As the highest temperature point in the image.

[0119] As an optional example, the operator manually sets the initial size and border thickness of the visualization display frame through the host computer so that it can cover the highest temperature point and its target object obtained by the hotspot detection algorithm as much as possible, and the center of the display frame is the coordinate value of the highest temperature point. The final output infrared image contains the position indication of the highest temperature point, and the visualization display frame can change in real time as the position of the highest temperature point changes.

[0120] For example, the shape of the display frame can be a square, a rectangle, etc. In this example, a square is used as an example, the size covers 32 pixels, and the thickness can be 5 pixels. The configuration process of the display frame can be realized by inputting settings or selecting from the host computer, which is quick to operate and can be completed when the target object is in motion.

[0121] When the highest temperature point (i.e., the target object) continues to move within the display screen range of the display control terminal, the visual display frame can move synchronously. As an optional method, when the highest temperature point moves to the edge of the screen, by comparing the coordinate value of the highest temperature point with the distance from the edge of the image, the coordinate values ​​of the four vertices of the display frame are determined so that they meet the screen resolution range of the display control terminal and do not overflow, so as to achieve the shape change of the display frame.

[0122] As an optional method, while the hotspot tracking algorithm continues to lock on to the target, a more sophisticated display frame of any size and thickness that fits the target can be manually selected by the host computer according to actual needs, so that the final output infrared image contains an indication of the position of the highest temperature point, and the visual display frame can change in real time as the position of the highest temperature point changes.

[0123] Combination Figure 2 It can be seen from the uncooled infrared hot spot tracking image shown that by using the method of the present invention, the infrared image data imaging effect is good, the position of the highest temperature point in the image can be located in real time, and the visualization box can change shape as the temperature point position changes, and adapt to the image display area.

[0124] Furthermore, the infrared image data processed by the method of the present invention can be output as digital video to a display and control terminal via CameraLink for real-time display; the digital video includes the location information of the highest temperature point, and the display and control terminal can be a PC, a mobile phone, a tablet device, etc.

[0125] like Figure 3 As shown, the user can observe the infrared image in real time online on the display and control terminal, and the display frame in the screen can intuitively display the position of the highest temperature point. As a preferred embodiment, the collected real-time infrared image data sequence can also be converted into a pseudo-color image sequence through a pseudo-color coding method, thereby improving the infrared image resolution and facilitating visualization of the human visual system.

[0126] {Example 3}

[0127] Combined with the method of the above embodiment, Figure 4 As shown, according to an embodiment of the present invention, a device for infrared image processing and hotspot tracking for bird repelling at an airport is also provided, comprising:

[0128] An image acquisition module for acquiring infrared image data collected by an uncooled infrared detector;

[0129] An image processing module for performing image processing operations on the collected infrared image data, wherein the image processing operations include non-uniformity correction, image noise reduction, and image enhancement;

[0130] A hot spot detection module for performing hot spot detection based on infrared image data after image noise reduction in an image processing operation, configured to determine the highest temperature point in the infrared image by analyzing all pixels in the infrared image and determine its coordinates;

[0131] A hotspot tracking module for marking the position of the highest temperature point in real time on the image through a visual display box based on the infrared image data after image enhancement in the image processing operation and the result after hotspot detection, and changing the position of the box in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation;

[0132] An infrared image output module is used to perform timing control on infrared images after infrared image processing and hot spot tracking operations, and output infrared images marked with the position of the highest temperature point.

[0133] Among them, the aforementioned image acquisition module, image processing module, hotspot detection module, hotspot tracking module and infrared image output module are configured to be implemented in a manner corresponding to the infrared image processing and hotspot tracking method for airport bird repelling of the above-mentioned embodiment.

[0134] {Example 4}

[0135] In combination with the infrared image processing and hotspot tracking method for bird repelling at an airport in the above embodiment, a computer system is also provided according to an embodiment of the present invention, comprising:

[0136] one or more processors;

[0137] A memory stores instructions that can be operated.

[0138] When the instructions are executed by the one or more processors, the one or more processors are caused to perform operations, wherein the operations include the process of the method for infrared image processing and hotspot tracking for bird repelling at airports according to any of the above embodiments.

[0139] It should be understood that the aforementioned examples of the infrared image processing and hotspot tracking method for bird repelling at airports of the present invention can be implemented in any computer system including data storage and data processing. The computer system as an example can be at least one electronic processing system or electronic device including a processor and a memory, such as a PC, whether it is a personal PC, a commercial PC, or a PC for graphics processing, or a server-level PC. These PCs can realize wired and / or wireless data transmission, especially image data, by having a data interface and / or a network interface.

[0140] The computer system as an example generally includes at least one processor, memory and network interface connected by a system bus. The network interface is used to communicate with other devices / systems. The processor is used to provide calculation and control of the system. The memory includes a non-volatile memory and a cache. The non-volatile memory can store an operating system, a computer program and data, and these computer programs may include operable instructions, which, when executed by one or more processors, enable one or more processors to execute the process of the infrared image processing and hotspot tracking method for airport bird repelling of the aforementioned embodiment of the present invention.

[0141] Although the present invention has been disclosed as above with preferred embodiments, it is not intended to limit the present invention. A person with ordinary knowledge in the technical field to which the present invention belongs may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be determined by the definition of the claims.

Claims

1. A method for infrared image processing and hotspot tracking for bird repelling at airports, characterized in that: The following steps are involved: Step 1, obtaining infrared image data collected by an uncooled infrared detector; Step 2: performing image processing operations on the collected infrared image data, including non-uniform correction, image noise reduction, and image enhancement; Step 3: Based on the infrared image data after image noise reduction in the image processing operation, hot spot detection is performed to analyze all pixel points in the infrared image, and the highest temperature point of the infrared image is determined to determine its coordinates; Step 4: Based on the infrared image data after image enhancement in the image processing operation and in combination with the result after hotspot detection, the position of the highest temperature point is marked in real time on the image through a visual display box, and the position of the box is changed in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation; Step 5: Perform time sequence control on the infrared image after the infrared image processing and hot spot tracking operations, and output an infrared image with the position of the highest temperature point marked.

2. The method for infrared image processing and hotspot tracking for bird repelling at an airport according to claim 1, characterized in that: In step 2, the collected infrared image data is subjected to non-uniform correction using a two-point correction method, which includes the following steps: Using a black body as a uniform radiation source, the focal plane of the uncooled infrared detector is illuminated at different temperatures of radiance, and high-temperature and low-temperature images are collected to obtain the output value V at high-temperature and low-temperature radiances. i,j (T h ) and V i,j (T l ), and store; The average value of the pixel under high temperature and low temperature radiance and as the expected response value; Based on the output value V at high and low temperature radiance i,j (T h ) and V i,j (T l ), and the pixel averages at high and low temperature radiances and Calculate the gain correction parameter and the offset correction parameter; The collected infrared image data is subjected to non-uniform correction based on the gain correction parameter and the offset correction parameter to obtain infrared image data after two-point correction.

3. The method for infrared image processing and hotspot tracking for bird repelling at airports according to claim 1, characterized in that: In step 2, after the collected infrared image data is subjected to non-uniform correction, a joint filtering and noise reduction in the spatial domain and the temporal domain using a median filter and a bilateral filter algorithm is performed, which includes the following steps: (1) Select the first filter to perform sliding median filtering on the infrared image data after non-uniform correction, sort the grayscale values ​​of all pixels in the sliding area, and find the middle value x mid , and replace the original grayscale value of the central pixel with the intermediate value; (2) A bilateral filtering algorithm is used to estimate the grayscale value of the current pixel using the pixel grayscale values ​​of consecutive historical frames, thereby achieving a smooth transition of the grayscale values ​​of the same pixel between consecutive frames.

4. The method for infrared image processing and hotspot tracking for bird repelling at an airport according to claim 1, characterized in that: In the step 2, after image denoising is performed on the collected infrared image data, a detail enhancement method of weighted fusion of high- and low-frequency information is adopted based on image layering to obtain infrared image data after detail enhancement.

5. The method for infrared image processing and hotspot tracking for bird repelling at an airport according to claim 1, characterized in that: The method of detail enhancement based on image layering and weighted fusion of high-frequency and low-frequency information to obtain infrared image data after detail enhancement includes the following steps: Using a second filter to separate high-frequency detail information and low-frequency background information from the infrared image data after image noise reduction; For low-frequency background information, the histogram equalization algorithm is used to enhance the contrast and highlight the outline of the target; for high-frequency detail information, the original image is obtained by subtracting the low-frequency background information, and the adaptive gain control algorithm is used to improve the detail information; The weighted fusion method is adopted to fuse the low-frequency information with the high-frequency information based on the fusion coefficient, and the enhanced infrared image data is output.

6. The method for infrared image processing and hotspot tracking for bird repelling at airports according to claim 1, characterized in that: In step 3, the infrared image data after image noise reduction in the image processing operation is used to perform hot spot detection, analyze all pixels in the infrared image, and determine the highest temperature point of the infrared image and determine its coordinates, including: Using the third filter to traverse each pixel in the infrared image data output after image noise reduction, calculate the average value of the pixel points in each filter window; Based on the comparison of the average values ​​output from each window, the maximum value point and its coordinate value are determined and stored.

7. The method for infrared image processing and hotspot tracking for bird repelling at an airport according to claim 1, characterized in that: In step 4, the size and border thickness of the visual display frame are adjustable and are set by the host computer.

8. The method for infrared image processing and hotspot tracking for bird repelling at airports according to claim 1, characterized in that: In step 5, the infrared image marked with the position of the highest temperature point is output as a digital video to a display and control terminal via CameraLink for real-time display, wherein the digital video includes the position information of the highest temperature point; The display and control terminal converts the infrared image into a pseudo-color image sequence by pseudo-color coding for visual representation.

9. A device for infrared image processing and hotspot tracking for bird repelling at airports, characterized in that: include: An image acquisition module for acquiring infrared image data collected by an uncooled infrared detector; An image processing module for performing image processing operations on the collected infrared image data, wherein the image processing operations include non-uniformity correction, image noise reduction, and image enhancement; A hot spot detection module for performing hot spot detection based on infrared image data after image noise reduction in an image processing operation, configured to determine the highest temperature point of the infrared image by analyzing all pixels in the infrared image and determine its coordinates; A hotspot tracking module for marking the position of the highest temperature point in real time on the image through a visual display box based on the infrared image data after image enhancement in the image processing operation and the result after hotspot detection, and changing the position of the box in real time as the highest temperature point changes, thereby realizing the hotspot tracking operation; An infrared image output module is used to perform timing control on infrared images after infrared image processing and hot spot tracking operations, and output infrared images marked with the position of the highest temperature point.

10. A computer system, characterized in that: include: one or more processors; A memory storing operable instructions, wherein when the instructions are executed by the one or more processors, the one or more processors are caused to perform operations, wherein the operations include the process of the method for infrared image processing and hotspot tracking for bird repelling at airports as described in any one of claims 1 to 8.

Images