Road disaster detection method, electronic device and storage device
Through the correction of illumination subcomponents and reflective subcomponents and infrared image fusion of the road disaster detection system, the problems of low efficiency and poor accuracy of traditional detection methods are solved, and more efficient and accurate road disaster detection is achieved.
Patent Information
- Application Number
- CN202411249617.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-06
AI Technical Summary
Traditional road disaster detection methods are inefficient and are greatly affected by environmental and bright factors, resulting in low detection accuracy.
The road disaster detection system is adopted, combined with visible light and infrared image acquisition components, and corrected by obtaining the illumination subcomponents and reflective subcomponents of the initial image to generate a target visible light image with uniform brightness and fusing it with the infrared image to improve the accuracy of the detection results.
The impact of environmental factors on the detection results is reduced, the accuracy and efficiency of road disaster detection is improved, and the generated target detection images contain rich image information, enhancing the clarity of the detection results.
Smart Images

Figure CN118762153B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to a road disaster detection method, electronic equipment and storage device. Background Art
[0002] In the field of road disaster detection, traditional manual inspection methods are inefficient and greatly restricted by environmental conditions. In order to improve detection efficiency and save labor costs, image recognition is usually performed on the corresponding road sections to timely discover potential disaster hazards. However, since visible light images are easily affected by environmental and light factors, the detection accuracy is low in some scenarios.
[0003] In view of this, how to propose a road disaster detection method with high efficiency and accuracy has become an urgent problem to be solved. Summary of the invention
[0004] The main technical problem solved by the present application is to provide a road disaster detection method, electronic equipment and storage device, which can improve the accuracy of road disaster detection.
[0005] In order to solve the above technical problems, a technical solution adopted by the present application is: to provide a road disaster detection method, the road disaster detection method is implemented by using a road disaster detection system, the road disaster detection system includes a visible light acquisition component and an infrared image acquisition component, the road disaster detection method includes: obtaining an initial visible light image collected by the visible light acquisition component and an initial infrared image collected by the infrared image acquisition component; obtaining an illumination sub-component and a reflection sub-component corresponding to the initial visible light image, and correcting the illumination sub-component and the reflection sub-component based on the brightness mean of the illumination sub-component; wherein the illumination sub-component and the reflection sub-component are obtained based on the initial brightness component corresponding to the visible light image; obtaining a corrected target visible light image based on the corrected illumination sub-component and the corrected reflection sub-component; and obtaining a target detection result based on the target visible light image and the initial infrared image.
[0006] To solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, comprising a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the road disaster detection method mentioned in the above technical solution.
[0007] In order to solve the above technical problems, another technical solution adopted by the present application is: providing a storage device storing program instructions that can be executed by a processor, wherein the program instructions are used to implement the road disaster detection method mentioned in the above technical solution.
[0008] The beneficial effects of the present application are as follows: Different from the prior art, the road disaster detection method proposed in the present application collects the initial visible light image through the visible light collection component, and obtains the corresponding illumination sub-component and reflection sub-component according to the initial brightness component corresponding to the initial visible light image. The illumination sub-component and the reflection sub-component are corrected respectively using the brightness mean corresponding to the illumination sub-component, so as to obtain a target visible light image with uniform brightness. In addition, the initial infrared image collected by the infrared collection component is combined with the target visible light image to obtain a target detection image containing rich image information, and the target detection result is obtained according to the target detection image, thereby reducing the influence of environmental factors on the target detection result and improving the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0010] Figure 1 It is a flow chart of an implementation method of a road disaster detection method of the present application;
[0011] Figure 2 yes Figure 1 Step S102 corresponds to a flow chart of another implementation method;
[0012] Figure 3 yes Figure 1 A flowchart corresponding to an implementation method after step S101;
[0013] Figure 4 yes Figure 1 Step S104 corresponds to a flow chart of another implementation method;
[0014] Figure 5 yes Figure 1 A flow chart of an implementation method corresponding to step S104;
[0015] Figure 6 It is a structural schematic diagram of an implementation method of a road disaster detection system of the present application;
[0016] Figure 7 It is a structural schematic diagram of an embodiment of the electronic device of the present application;
[0017] Figure 8 It is a structural diagram of an implementation method of a storage device of the present application. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments, and different embodiments can be adaptively combined. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0019] See also Figure 1 , Figure 1 1 is a flow chart of an embodiment of a road disaster detection method of the present application. The road disaster detection method is implemented by a road disaster detection system. The road disaster detection system includes a visible light acquisition component and an infrared image acquisition component. The road disaster detection method specifically includes:
[0020] S101: Acquire an initial visible light image acquired by a visible light acquisition component and an initial infrared image acquired by an infrared image acquisition component.
[0021] In one embodiment, in order to accurately detect road condition information, a road disaster detection system is provided on the target unit, and the system includes a visible light acquisition component and an infrared image acquisition component. An initial visible light image acquired by the visible light acquisition component is acquired, and the initial visible light image is an image in RGB format. Furthermore, the infrared image acquisition component acquires infrared data of a preset wavelength in real time to obtain an initial infrared image.
[0022] In one implementation scenario, the target unit is a vehicle, and the road hazard detection system is installed on the target unit to detect the road condition of the target unit when it travels to the corresponding road section. Alternatively, the target unit is fixedly installed on one or both sides of the road, and the road hazard detection system on the target unit is used to detect the road condition in the corresponding road section.
[0023] In one implementation scenario, the infrared image acquisition component collects long-wave infrared to obtain an initial infrared image with a wider collection range, and the wavelength range of the long-wave infrared is generally 8 to 14 microns; or, the infrared image acquisition component collects medium-wave infrared to obtain an initial infrared image with a higher resolution, and the wavelength range of the medium-wave infrared is generally 3 to 5 microns.
[0024] In another embodiment, the visible light acquisition component performs preprocessing after acquiring the image to obtain an initial visible light image, and the infrared image acquisition component performs preprocessing after acquiring the image to obtain an initial infrared image, wherein the preprocessing method includes removing noise and the like.
[0025] S102: Obtain an illumination sub-component and a reflection sub-component corresponding to the initial visible light image, and correct the illumination sub-component and the reflection sub-component based on the brightness mean of the illumination sub-component; wherein the illumination sub-component and the reflection sub-component are obtained based on the initial brightness component corresponding to the visible light image.
[0026] In one embodiment, in response to the acquired initial visible light image being in RGB format, the initial visible light image is converted into HSV space to obtain an initial brightness component (i.e., Value), an initial hue component (i.e., Hue), and an initial saturation component (i.e., Saturation) corresponding to the initial visible light image. The brightness component is filtered to extract the corresponding illumination sub-component and reflection sub-component.
[0027] Furthermore, the average value of the brightness values corresponding to all pixels in the illumination sub-component is taken as the brightness mean, and the brightness mean is used to correct the illumination sub-component and the reflection sub-component respectively, so as to obtain a corrected illumination sub-component and a corrected reflection sub-component.
[0028] S103: Acquire a corrected target visible light image based on the corrected illumination sub-component and the corrected reflection sub-component.
[0029] In one embodiment, the corrected illumination sub-component and the corrected reflection sub-component are recombined to obtain a corrected target brightness component.
[0030] Furthermore, in response to the initial visible light image also corresponding to an initial hue component and an initial saturation component, a target visible light image is obtained based on the target brightness component, the initial hue component and the initial saturation component obtained above.
[0031] Specifically, the target brightness component and the initial hue component and the initial saturation component corresponding to the initial visible light image are converted into an image in RGB format to obtain a corrected target visible light image.
[0032] S104: Obtaining a target detection result based on the target visible light image and the initial infrared image.
[0033] In one implementation, the target visible light image and the initial infrared image are fused to obtain a target detection image.
[0034] Furthermore, the target detection image is identified and analyzed to obtain a corresponding target detection result, wherein the target detection result is used to characterize whether a road disaster occurs.
[0035] In another embodiment, the target detection result obtained may also be the road condition information of the corresponding road section, such as at least one of traffic flow information, traffic accident information, and road congestion information.
[0036] The road disaster detection method proposed in the present application collects an initial visible light image through a visible light acquisition component, and obtains the corresponding illumination sub-component and reflection sub-component according to the initial brightness component corresponding to the initial visible light image. The illumination sub-component and the reflection sub-component are corrected respectively using the brightness mean corresponding to the illumination sub-component, thereby obtaining a target visible light image with uniform brightness. In addition, the initial infrared image collected by the infrared acquisition component is combined with the target visible light image to obtain a target detection image containing rich image information, and the target detection result is obtained according to the target detection image, thereby reducing the influence of environmental factors on the target detection result and improving the accuracy of detection.
[0037] See also Figure 2 , Figure 2 yes Figure 1 Step S102 in the figure corresponds to a flow chart of another embodiment. Specifically, the process of correcting the illumination sub-component and the reflection sub-component in step S102 includes:
[0038] S201: Obtain the brightness mean corresponding to the illumination sub-component.
[0039] In one embodiment, first brightness values corresponding to all pixels in the illumination sub-component are obtained, and an average value of all first brightness values corresponding to the illumination sub-component is calculated to obtain a brightness mean value.
[0040] In another embodiment, in response to the initial visible light being collected at the current moment, in order to avoid the accidental collection, the brightness average is obtained by combining multiple historical visible light images collected by the visible light collection component, wherein the collection time of the historical visible light images is before the collection time of the initial visible light image.
[0041] Specifically, the historical brightness mean of the historical illumination sub-component corresponding to each historical visible light image is obtained, and the current brightness mean of the current illumination sub-component corresponding to the initial visible light image is obtained, and the average of all historical brightness means and the current brightness mean is taken as the brightness mean. The number of historical visible light images used can be set according to actual conditions.
[0042] S202: Obtain an illumination correction coefficient based on the brightness mean, and use the illumination correction coefficient to correct the illumination sub-component.
[0043] In one embodiment, according to the brightness mean value obtained in step S201, a reference difference between the first brightness value corresponding to each pixel point in the illumination sub-component and the brightness mean value is obtained. Based on the reference difference value and the brightness mean value, an illumination correction coefficient corresponding to each pixel point in the illumination sub-component is obtained. The specific calculation formula of the illumination correction coefficient is as follows:
[0044]
[0045] in, represents the illumination correction factor, Indicates the first brightness value of the pixel, Indicates the mean brightness corresponding to the illumination sub-component.
[0046] Furthermore, the brightness value of each pixel in the illumination sub-component is corrected using the illumination correction coefficient.
[0047] Specifically, the illumination correction coefficient is used as an index of the brightness value of the pixel point of the illumination sub-component to calculate the corrected second brightness value. In addition, in response to completing the correction of the brightness value of each pixel point in the illumination sub-component, the corrected illumination sub-component is obtained. By correcting the illumination sub-component using the calculated illumination correction coefficient, the brightness distribution in the illumination sub-component is made more uniform.
[0048] The specific correction formula is as follows:
[0049]
[0050] in, Indicates the corrected second brightness value.
[0051] S203: Obtain a reflection correction coefficient based on the brightness mean, and use the reflection correction coefficient to correct the reflection sub-component.
[0052] In one implementation, a preset parameter is obtained, and a reflection correction coefficient is obtained based on the preset parameter and the brightness mean.
[0053] Specifically, the preset parameter is multiplied by the brightness mean corresponding to the illumination sub-component to obtain the reflection correction coefficient. The preset parameter may be estimated by relevant technical personnel, or may be obtained by reverse deduction after multiple experiments.
[0054] Furthermore, a filtered image and a residual image corresponding to the reflection sub-component are obtained, and the residual image is adaptively adjusted using the reflection correction coefficient to obtain a corrected residual image.
[0055] Specifically, the reflection sub-component is filtered by guided filtering technology, and a filtered image and a residual image corresponding to the reflection sub-component are obtained. The residual image is multiplied by the reflection correction coefficient to remove noise interference in the residual image, and a corrected residual image is obtained.
[0056] Furthermore, based on the filtered image and the corrected residual image, a corrected reflection sub-component is obtained.
[0057] Specifically, the filtered image and the corrected residual image are fused to obtain the corrected reflection sub-component. The specific calculation formula is as follows:
[0058]
[0059] in, represents the corrected reflection subcomponent, represents the filtered image, represents the reflection correction coefficient, represents the residual image before correction.
[0060] It should be noted that after obtaining the brightness mean corresponding to the illumination sub-component, the illumination sub-component and the reflection sub-component may be corrected in another order. For example, the illumination sub-component and the reflection sub-component may be corrected at the same time, that is, the above steps S202 and S203 are performed at the same time; or, the reflection sub-component may be corrected first, and then the illumination sub-component may be corrected, that is, step S203 is performed first and then step S202 is performed.
[0061] See also Figure 3 , Figure 3 yes Figure 1 The process flow diagram after step S101 in one embodiment corresponds to the process flow diagram of an embodiment. Specifically, after acquiring the initial infrared image, the process further includes:
[0062] S301: Based on the initial grayscale values corresponding to the pixels in the initial infrared image, a minimum grayscale value and a maximum grayscale value corresponding to the initial infrared image are obtained.
[0063] In one embodiment, in response to each pixel in the initial infrared image matching a corresponding initial grayscale value, the minimum initial grayscale value corresponding to the initial infrared image is used as the minimum grayscale value, and the maximum initial grayscale value corresponding to the initial infrared image is used as the maximum grayscale value.
[0064] In another embodiment, all initial grayscale values corresponding to the initial infrared image are sorted in ascending order to obtain a grayscale value sequence. The first initial grayscale value corresponding to the grayscale value sequence is used as the minimum grayscale value, and the last initial grayscale value corresponding to the grayscale value sequence is used as the maximum grayscale value.
[0065] S302: Correcting the initial infrared image using the minimum grayscale value and the maximum grayscale value to obtain a target infrared image.
[0066] In one embodiment, a reference grayscale difference between the maximum grayscale value and the minimum grayscale value is obtained, and a target grayscale difference between the initial grayscale value and the minimum grayscale value of each pixel in the initial infrared image is obtained.
[0067] Furthermore, based on the ratio between the target grayscale difference and the reference grayscale difference, an infrared image of the target is obtained.
[0068] Specifically, the image pixel depth corresponding to the initial infrared image is obtained, and the initial grayscale value of each pixel in the initial infrared image is corrected according to the image pixel depth and the ratio between the target grayscale difference and the reference grayscale difference to obtain a corrected target grayscale value. In response to completing the correction of each pixel in the initial infrared image, a target infrared image is obtained. The specific calculation formula for correcting each pixel in the initial infrared image is as follows:
[0069]
[0070] in, represents the target grayscale value after correction, represents the image pixel depth of the original infrared image, represents the initial gray value, represents the minimum gray value corresponding to the initial infrared image, Indicates the maximum gray value corresponding to the initial infrared image.
[0071] The above scheme, by obtaining the target infrared image, enhances the expression of image information in the initial infrared image, thereby helping to make the final target detection image contain richer image information and helping to improve the accuracy of obtaining the target detection result.
[0072] In another embodiment, the infrared image acquisition component in the road disaster detection system includes a long-wave infrared collector and a medium-wave infrared collector. Figure 1 The process of acquiring the initial infrared image in step S101 includes: simultaneously acquiring the initial long-wave infrared image acquired by the long-wave infrared image collector and the initial medium-wave infrared image acquired by the medium-wave infrared image collector.
[0073] Specifically, the long-wave infrared image collector collects infrared waves within the corresponding wavelength range to obtain an initial long-wave infrared image that is less affected by the environment; at the same time, the medium-wave infrared image collector collects infrared waves within the corresponding wavelength range to obtain an initial medium-wave infrared image with higher resolution.
[0074] See also Figure 4 , Figure 4 yes Figure 1 Step S104 corresponds to a flowchart of another implementation method. In response to the infrared image acquisition component in the road disaster detection system including a long-wave infrared collector and a medium-wave infrared collector, and the initial infrared image includes an initial long-wave infrared image acquired by the long-wave infrared collector and an initial medium-wave infrared image acquired by the medium-wave infrared collector, based on this, the specific implementation process of step S104 includes:
[0075] S401: fusing a target visible light image, a target long-wave infrared image and a target medium-wave infrared image to obtain a target detection image; wherein the target long-wave infrared image is a corrected initial long-wave infrared image, and the target medium-wave infrared image is a corrected initial medium-wave infrared image.
[0076] In one embodiment, after obtaining an initial long-wave infrared image and an initial medium-wave infrared image, the initial long-wave infrared image and the initial medium-wave infrared image are corrected respectively, and the corrected initial long-wave infrared image is used as a target long-wave infrared image, and the corrected initial medium-wave infrared image is used as a target medium-wave infrared image.
[0077] Specifically, based on the first initial grayscale value corresponding to each pixel in the initial long-wave infrared image, the minimum grayscale value and the maximum grayscale value corresponding to the initial long-wave infrared image are obtained. The initial long-wave infrared image is corrected using the minimum grayscale value and the maximum grayscale value corresponding to the initial long-wave infrared image to obtain a target long-wave infrared image. And, based on the second initial grayscale value corresponding to each pixel in the initial medium-wave infrared image, the minimum grayscale value and the maximum grayscale value corresponding to the initial medium-wave infrared image are obtained. The initial medium-wave infrared image is corrected using the minimum grayscale value and the maximum grayscale value corresponding to the initial medium-wave infrared image to obtain a target medium-wave infrared image. The method for correcting the initial long-wave infrared image and the initial medium-wave infrared image can refer to the method for correcting the initial infrared image in the above-mentioned steps S301 to S302, and will not be described in detail here.
[0078] Furthermore, the target visible light image, target long-wave infrared image and target medium-wave infrared image are fused to obtain a target detection image containing both visible light image information and infrared image information. The target detection image has more uniform brightness and contains more information. Even if the acquisition scene is at night or the lighting conditions are poor, the obtained target detection image has higher clarity, which helps to improve the accuracy of subsequent target detection results.
[0079] S402: Obtaining a target detection result based on the target detection image; wherein the target detection result is used to indicate whether a road disaster occurs.
[0080] In one implementation scenario, the acquired target detection image is analyzed and detected to obtain a corresponding target detection result, wherein the target detection result includes road condition information of the corresponding road section and is used to indicate whether a road disaster occurs.
[0081] In one implementation scenario, the above target detection result is realized by a trained detection model, which analyzes the target detection image to identify whether a road disaster occurs on the corresponding road section, and when a road disaster occurs on the corresponding road section, identifies the specific disaster type, such as a car accident or road collapse, etc. Among them, the above detection model is obtained by training with multiple training samples, and the specific structure and training method of the detection model can refer to the existing neural network model structure and training method, respectively, and will not be elaborated in detail here.
[0082] See also Figure 5 , Figure 5 yes Figure 1 The process after step S104 corresponds to a flow chart of an implementation method. Specifically, the process after step S104 also includes:
[0083] S501: Generate road warning information based on the target detection result, and send the road warning information to the warning network in the road disaster detection system.
[0084] In one embodiment, in response to the target detection result being obtained based on information collected by the road disaster detection system on the current vehicle, and the target detection result indicating that a road disaster has occurred on the corresponding road section, road warning information is generated based on the detection time corresponding to the target detection result, the specific location of the corresponding road section, and the specific type of the road disaster. The road warning information is sent to a warning network in the road disaster detection system.
[0085] In one implementation scenario, the current vehicle communicates with an early warning network in a road disaster detection system via a wireless network.
[0086] S502: Broadcasting road warning information using the warning network.
[0087] In one embodiment, the warning network is used to warn subsequent vehicles that are about to travel to the corresponding road section, so as to remind the subsequent vehicles that a road disaster has occurred on the corresponding road section and provide corresponding driving suggestions.
[0088] In one implementation scenario, the driving suggestion includes at least one of a recommended route and a recommended lane.
[0089] In another embodiment, to save computational cost, Figure 1 Step S102 may also be to correct any one of the illumination sub-component and the reflection sub-component based on the brightness mean of the illumination sub-component.
[0090] See also Figure 6 , Figure 61 is a schematic diagram of the structure of an embodiment of the road disaster detection system of the present application. The road disaster detection system includes a visible light acquisition component 10, an infrared image acquisition component 20 and a correction component 30 coupled to each other. The visible light acquisition component 10 is used to acquire an initial visible light image. The infrared image acquisition component 20 is used to acquire an initial infrared image. The correction component 30 is used to correct the initial visible light image to obtain a corresponding target visible light image; and the correction component 30 can also be used to correct the initial infrared image to obtain a target infrared image.
[0091] In one implementation scenario, the calibration component 30 is a digital signal processor (DSP).
[0092] In one implementation scenario, the infrared image acquisition component 20 includes a long-wave infrared collector 21 and a medium-wave infrared collector 22. The long-wave infrared collector 21 is used to acquire an initial long-wave infrared image, and the medium-wave infrared collector 22 is used to acquire an initial medium-wave infrared image.
[0093] In addition, in response to the infrared image acquisition component 20 including the long-wave infrared collector 21 and the medium-wave infrared collector 22, the correction component 30 is also used to correct the initial long-wave infrared image to obtain a target long-wave infrared image, and to correct the initial medium-wave infrared image to obtain a target medium-wave infrared image.
[0094] In a specific application scenario, the road disaster detection system further includes a fixed component, and the visible light collection component 10, the long-wave infrared collector 21, and the medium-wave infrared collector 22 are fixedly arranged on the fixed component. For example, the visible light collection component 10 is arranged in the middle of the upper part of the fixed component, the long-wave infrared collector 21 is arranged on the lower right side of the fixed component, and the medium-wave infrared collector 22 is arranged on the lower left side of the fixed component.
[0095] See also Figure 7 , Figure 7: is a structural diagram of an embodiment of an electronic device of the present application. The electronic device includes: a memory 40 and a processor 50 coupled to each other. The memory 40 stores program instructions, and the processor 50 is used to execute the program instructions to implement the road disaster detection method mentioned in any of the above embodiments. Specifically, the electronic device includes but is not limited to: a desktop computer, a laptop computer, a tablet computer, a server, etc., which are not limited here. In addition, the processor 50 can also be called a CPU (Center Processing Unit). The processor 50 may be an integrated circuit chip with signal processing capabilities. The processor 50 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 50 can be implemented by an integrated circuit chip.
[0096] See also Figure 8 , Figure 8 The storage device 60 stores program instructions 70 that can be executed by a processor, and when the program instructions 70 are executed by the processor, the road disaster detection method mentioned in any of the above embodiments is implemented.
[0097] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0099] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0100] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.
[0101] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A road disaster detection method, It is characterized in that The road disaster detection method is implemented by using a road disaster detection system, the road disaster detection system includes a visible light acquisition component and an infrared image acquisition component, and the road disaster detection method includes: Acquire an initial visible light image acquired by the visible light acquisition component and an initial infrared image acquired by the infrared image acquisition component; Acquire an illumination sub-component and a reflection sub-component corresponding to the initial visible light image, and correct the illumination sub-component and the reflection sub-component based on the brightness mean of the illumination sub-component; wherein the illumination sub-component and the reflection sub-component are obtained based on the initial brightness component corresponding to the visible light image; Based on the corrected illumination sub-component and the corrected reflection sub-component, acquiring a corrected target visible light image; Acquire a target detection result based on the target visible light image and the initial infrared image; The correcting of the illumination sub-component and the reflection sub-component based on the brightness mean of the illumination sub-component includes: Obtaining a brightness mean value corresponding to the illumination sub-component; obtaining an illumination correction coefficient based on the brightness mean value, and correcting the illumination sub-component using the illumination correction coefficient; specifically comprising: obtaining a reference difference between a first brightness value corresponding to each pixel point in the illumination sub-component and the brightness mean value; obtaining the illumination correction coefficient corresponding to each pixel point in the illumination sub-component based on the reference difference and the brightness mean value; using the illumination correction coefficient as an index of the brightness value of the pixel point in the illumination sub-component to obtain a corrected second brightness value; and, Based on the brightness mean, a reflection correction coefficient is obtained, and the reflection sub-component is corrected using the reflection correction coefficient; specifically including: obtaining preset parameters, and obtaining the reflection correction coefficient based on the preset parameters and the brightness mean; obtaining a filtered image and a residual image corresponding to the reflection sub-component, and adjusting the residual image using the reflection correction coefficient to obtain the corrected residual image; based on the filtered image and the corrected residual image, the corrected reflection sub-component is obtained.
2. The method according to claim 1, It is characterized in that The step of acquiring a corrected target visible light image based on the corrected illumination sub-component and the corrected reflection sub-component includes: Obtaining a target brightness component based on the corrected illumination sub-component and the corrected reflection sub-component; In response to the initial visible light image also corresponding to an initial hue component and an initial saturation component, the target visible light image is obtained based on the target brightness component, the initial hue component and the initial saturation component.
3. The method according to claim 1, It is characterized in that After acquiring the initial visible light image acquired by the visible light acquisition component and the initial infrared image acquired by the infrared image acquisition component, the method further comprises: Based on the initial grayscale values corresponding to the pixels in the initial infrared image, obtaining the minimum grayscale value and the maximum grayscale value corresponding to the initial infrared image; The initial infrared image is corrected using the minimum grayscale value and the maximum grayscale value to obtain a target infrared image.
4. The method according to claim 3, It is characterized in that The method of correcting the initial infrared image by using the minimum grayscale value and the maximum grayscale value to obtain a target infrared image includes: Acquire a reference grayscale difference between the maximum grayscale value and the minimum grayscale value; and, Acquire a target grayscale difference between the initial grayscale value and the minimum grayscale value of each pixel in the initial infrared image; Based on the ratio between the target grayscale difference and the reference grayscale difference, the target infrared image is obtained.
5. The method according to claim 3, It is characterized in that The infrared image acquisition component includes a long-wave infrared collector and a medium-wave infrared collector, the initial infrared image includes an initial long-wave infrared image acquired by the long-wave infrared collector and an initial medium-wave infrared image acquired by the medium-wave infrared collector, and the target detection result is acquired based on the target visible light image and the initial infrared image, including: The target visible light image, the target long-wave infrared image and the target medium-wave infrared image are fused to obtain a target detection image; wherein the target long-wave infrared image is the corrected initial long-wave infrared image, and the target medium-wave infrared image is the corrected initial medium-wave infrared image; Based on the target detection image, the target detection result is obtained; wherein the target detection result is used to indicate whether a road disaster occurs.
6. The method according to claim 1, It is characterized in that After obtaining the target detection result based on the target visible light image and the initial infrared image, the method includes: Generate road warning information based on the target detection result, and send the road warning information to the warning network in the road disaster detection system; The road warning information is broadcasted using the warning network.
7. An electronic device, It is characterized in that It comprises a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the road disaster detection method according to any one of claims 1 to 6.
8. A storage device, It is characterized in that Program instructions that can be executed by a processor are stored, and the program instructions are used to implement the road hazard detection method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Infrared and visible light fusion visual system and method based on deep neural network
CN113947555A
Retinex variational underwater image enhancement method and device based on deep CNN denoising prior
CN117593235A
