Traffic load prediction method based on image enhancement and related device

Abstract

The embodiment of the invention relates to the field of image processing, and provides a traffic load prediction method based on image enhancement and a related device, and the method comprises the steps: obtaining a traffic image of a to-be-detected road region in a traffic load information collection duration, and obtaining a first traffic image set; performing defogging enhancement processing on first traffic images in the first traffic image set to obtain a second traffic image set; performing target extraction on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected; and determining the traffic load information of the to-be-detected road area according to the vehicle information and the traffic load information acquisition duration, so that defogging enhancement processing can be performed on the traffic image, and traffic load prediction can be performed by using the enhanced traffic image, thereby improving the accuracy of traffic load prediction.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a traffic load prediction method based on image enhancement and a related device. Background Art

[0002] Images taken in foggy weather will have reduced contrast and image quality due to the absorption and scattering of light, and the features of objects will become blurred, making it impossible to obtain more image details, resulting in reduced accuracy when using images for traffic load prediction. Summary of the invention

[0003] The embodiment of the present application provides a traffic load prediction method based on image enhancement and a related device, which can perform defogging and enhancement processing on traffic images, and use the enhanced traffic images to predict traffic load, thereby improving the accuracy of traffic load prediction.

[0004] A first aspect of an embodiment of the present application provides a traffic load prediction method based on image enhancement, the method comprising: Acquire traffic images of the road area to be detected within the traffic load information collection time to obtain a first traffic image set; performing defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; Performing target extraction on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected; The traffic load information of the road area to be detected is determined according to the vehicle information and the traffic load information collection time.

[0005] In this example, a first traffic image set is obtained by acquiring traffic images of the road area to be detected within the traffic load information collection time, dehazing and enhancing the first traffic image in the first traffic image set is performed to obtain a second traffic image set, and target extraction is performed on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected, and the traffic load information of the road area to be detected is determined based on the vehicle information and the traffic load information collection time. Therefore, the traffic image can be dehazing and enhanced, and the traffic load prediction can be performed using the enhanced traffic image, thereby improving the accuracy of traffic load prediction.

[0006] In a possible implementation, performing defogging and enhancement processing on the first traffic image in the first traffic image set to obtain the second traffic image set includes: Determining a first transmittance correction value according to environmental information of the road area to be detected; Acquire a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; Calculate the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; Defogging the target traffic image using the target transmittance to obtain a second traffic image; Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, and performing defogging on the target traffic image using the target transmittance to obtain the second traffic image, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

[0007] In a possible implementation, determining the first transmittance correction value according to the environmental information of the road area to be detected includes: Extracting wind speed information, solid particle information and humidity information from the environmental information; Acquire the combined influence degree between the humidity information and the solid particulate matter information; Determine a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; Determining haze dispersion trend information according to the wind speed information; determining a second reference transmittance correction value according to the haze dispersion trend information; The first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value.

[0008] In a possible implementation, the acquiring the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value includes: Acquire an associated image of the target traffic image to obtain an associated image set, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image; Acquire background light intensity values ​​of associated images in the associated image set to obtain a reference background light intensity value set; Determining a background light intensity correction value according to reference background light intensity values ​​and corresponding variances in a reference background light intensity value set; Acquire a first background light intensity value of a target traffic image; The first background light intensity value is corrected using the background light intensity correction value to obtain the target background light intensity value.

[0009] In a possible implementation, determining the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection duration includes: Extracting sub-vehicle information of each lane in the road area to be detected from the vehicle information to obtain a sub-vehicle information set; The traffic load information of the road area to be detected is determined according to the sub-vehicle information set and the traffic load information collection time.

[0010] A second aspect of an embodiment of the present application provides a traffic load prediction device based on image enhancement, the device comprising: An acquisition unit, used to acquire traffic images of the road area to be detected within a traffic load information collection period to obtain a first traffic image set; an enhancement unit, configured to perform defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; an extraction unit, configured to extract objects from the second traffic images in the second traffic image set to obtain vehicle information of the road area to be detected; The determination unit is used to determine the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection time.

[0011] In a possible implementation, the enhancement unit is specifically configured to: Determining a first transmittance correction value according to environmental information of the road area to be detected; Acquire a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; Calculate the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; Defogging the target traffic image using the target transmittance to obtain a second traffic image; Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, and performing defogging on the target traffic image using the target transmittance to obtain the second traffic image, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

[0012] In a possible implementation manner, in determining the first transmittance correction value according to the environmental information of the road area to be detected, the enhancing unit is specifically configured to: Extracting wind speed information, solid particle information and humidity information from the environmental information; Acquire the combined influence degree between the humidity information and the solid particulate matter information; Determine a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; Determining haze dispersion trend information according to the wind speed information; determining a second reference transmittance correction value according to the haze dispersion trend information; The first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value.

[0013] In a possible implementation, in acquiring the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, the enhancement unit is specifically configured to: Acquire an associated image of the target traffic image to obtain an associated image set, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image; Acquire background light intensity values ​​of associated images in the associated image set to obtain a reference background light intensity value set; Determining a background light intensity correction value according to reference background light intensity values ​​and corresponding variances in a reference background light intensity value set; Acquire a first background light intensity value of a target traffic image; The first background light intensity value is corrected using the background light intensity correction value to obtain the target background light intensity value.

[0014] In a possible implementation, the determining unit is specifically configured to: Extracting sub-vehicle information of each lane in the road area to be detected from the vehicle information to obtain a sub-vehicle information set; The traffic load information of the road area to be detected is determined according to the sub-vehicle information set and the traffic load information collection time.

[0015] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0016] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0017] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0019] Figure 1 A flow chart of a traffic load prediction method based on image enhancement is provided for an embodiment of the present application; Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application; Figure 3 A structural schematic diagram of a traffic load prediction device based on image enhancement is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0020] 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. 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.

[0021] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0022] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0023] In order to better understand the traffic load prediction method based on image enhancement provided by the embodiment of the present application, the following first briefly introduces the scenario of applying the traffic load prediction method based on image enhancement. When predicting the traffic load of a road, it is usually for the purpose of analyzing the traffic in order to carry out better urban road planning, traffic diversion, etc. At this time, it is necessary to analyze the real-time traffic conditions of the road and the historical traffic conditions. When performing real-time traffic load analysis, due to the influence of factors such as weather and environment, there will be some inaccurate analysis through image analysis. For example, when there is foggy weather or haze weather, due to the influence of haze, the accuracy of directly extracting vehicle information from the image will be sharply reduced. Even in the case of very low visibility in haze, if the vehicle is directly identified, it will lead to recognition errors, or the vehicle cannot be correctly identified, thereby affecting the prediction of road load. In the existing scheme, when performing vehicle recognition on traffic images, background light extraction is usually performed on the collected images. After the background light intensity value is extracted, the transmittance is directly calculated without analyzing the severity of haze, etc., resulting in poor effect of the image after image enhancement processing, and then the accuracy of vehicle information extraction using the enhanced image is reduced, which ultimately leads to a reduction in the accuracy of traffic load acquisition, thereby affecting the accuracy of subsequent road traffic diversion.

[0024] In order to solve the above-mentioned problems, an embodiment of the present application provides a traffic load prediction method based on image enhancement, which can determine a more accurate transmittance in combination with the environmental information of the road to be detected, and then use the transmittance to enhance the traffic image, thereby improving the image quality of the enhanced traffic image, and then improving the accuracy of subsequent traffic load acquisition, etc.

[0025] See also Figure 1 , Figure 1 A flow chart of a traffic load prediction method based on image enhancement is provided for an embodiment of the present application. Figure 1 As shown, the method includes: 101. Obtain traffic images of a road area to be detected within a traffic load information collection period to obtain a first traffic image set.

[0026] The road area to be detected may be a road area with traffic congestion, for example, a road area with traffic congestion during rush hour, a crossroad, a bridge intersection, etc. The traffic load information acquisition duration can be understood as the duration of image sampling of the road to be detected, for example, it may be a duration during traffic congestion, for example, 10 minutes, 15 minutes, etc. During the acquisition duration, image acquisition is performed according to a certain acquisition cycle, for example, an acquisition cycle of 0.5s, 1s, etc., and multiple images are acquired in each acquisition cycle, thereby obtaining a first traffic image set. The first traffic image includes the road area to be detected, and vehicles in the road area to be detected, etc.

[0027] 102. Perform defogging and enhancement processing on a first traffic image in the first traffic image set to obtain a second traffic image set.

[0028] When performing image acquisition, the environmental monitoring sensor can simultaneously acquire environmental information of the road area to be detected, and the environmental information includes wind speed information, solid particle information, and air humidity information. After acquiring the environmental information, the environmental information is used to determine the transmittance correction value, and the background light intensity corresponding to the first traffic image is extracted. The transmittance correction value and the background light intensity are used to calculate the transmittance to obtain the transmittance of the first traffic image, and finally the transmittance is used to perform defogging on the first traffic image to obtain the second traffic image. When the transmittance is used to perform defogging on the first traffic image, a general defogging method can be used to perform defogging to obtain the second traffic image.

[0029] 103. Perform target extraction on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected.

[0030] A general target extraction method may be used to extract targets from the second traffic image to obtain vehicle information of the road area to be detected. For example, a general target extraction network may be used for extraction, or a general target extraction algorithm may be used for extraction, which is only an example.

[0031] 104. Determine the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection time.

[0032] Among them, the sub-vehicle information of each lane in the road area to be detected can be extracted from the vehicle information, and the traffic load information can be determined according to the sub-vehicle information and the traffic load information collection time. The traffic load information can reflect the average vehicle flow of the road area to be detected during the detection time.

[0033] In this example, a first traffic image set is obtained by acquiring traffic images of the road area to be detected within the traffic load information collection time, dehazing and enhancing the first traffic image in the first traffic image set is performed to obtain a second traffic image set, and target extraction is performed on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected, and the traffic load information of the road area to be detected is determined based on the vehicle information and the traffic load information collection time. Therefore, the traffic image can be dehazing and enhanced, and the traffic load prediction can be performed using the enhanced traffic image, thereby improving the accuracy of traffic load prediction.

[0034] In a possible implementation, a method for performing defogging and enhancement processing on a first traffic image in the first traffic image set to obtain a second traffic image set includes: A1. Determine a first transmittance correction value according to the environmental information of the road area to be detected; A2. Obtaining a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; A3, calculating the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; A4, performing defogging processing on the target traffic image using the target transmittance to obtain a second traffic image; A5. Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, until the step of performing defogging on the target traffic image using the target transmittance to obtain the second traffic image is obtained, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

[0035] Among them, wind speed information, solid particle information, humidity information, etc. can be extracted from the environmental information. Then, the first reference transmittance correction value is determined using the humidity information and solid particle information, and the second reference transmittance correction value is determined using the wind speed information. Finally, the first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value. Therefore, the first transmittance correction value can be determined by combining the wind speed information, solid particle information, humidity information, etc. in the environmental information, thereby improving the accuracy of obtaining the first transmittance correction value.

[0036] When obtaining the target background light intensity value of the target traffic image, a general background light intensity value obtaining method may be used to obtain the target background light intensity value. For example, the target background light intensity value may be obtained by calculating the Euclidean distance between pixels.

[0037] Of course, it is also possible to extract an associated image of the target traffic image, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image, for example, an image captured k moments before and k moments after the target traffic image. The reference background light intensity value of each associated image in the associated image set and the variance of the corresponding background light intensity value are calculated respectively, and finally the variance and the reference background light intensity value are used to determine the correction value of the first background light intensity value corresponding to the target image and perform correction processing to obtain the target background light intensity value.

[0038] The transmittance can be calculated according to the target background light intensity value and the first transmittance correction value using the method shown in the following formula to obtain the target transmittance, specifically: , in, is the target transmittance, is the first transmittance correction value, is the pixel value of the first sub-image block in the image block group, A is the target background light intensity value, c is the three color channels, is the minimum filter window, is the pixel point within the filter window, To perform the minimum operation, It is the value of the target background light intensity in three color channels.

[0039] The target traffic image may be defogged using a general defogging method and target transmittance to obtain a second traffic image. In this example, a first transmittance correction value is determined in combination with environmental information, and a target transmittance is calculated using the first transmittance correction value and a target background light intensity value of a target traffic image. Finally, the target transmittance is used to perform dehazing processing on the target traffic image, thereby improving the image quality of the obtained second traffic image.

[0040] In a possible implementation, a method for determining a first transmittance correction value according to environmental information of the road area to be detected includes: B1. extracting wind speed information, solid particle information and humidity information from the environmental information; B2. Obtaining the joint influence between the humidity information and the solid particulate matter information; B3, determining a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; B4. Determine haze dispersion trend information according to the wind speed information; B5. determining a second reference transmittance correction value according to the haze dispersion trend information; B6. Fusing the first reference transmittance correction value and the second reference transmittance correction value to obtain the first transmittance correction value.

[0041] Among them, the joint influence degree between humidity information and solid particle information can understand the degree of influence of solid particles on vision in air with different air humidity. Solid particle information can include solid particle concentration information, solid particle type information, etc. Different types of particles have different degrees of influence on vision at different concentrations and air humidity. For example, if the particles are dust, the higher the concentration and the higher the air humidity, the greater the viscosity between the dust, and thus the greater the adverse effect on vision, and it is also easy to block vehicles, etc., so that the transmittance is lower. When the particles are other types, for example, ‌ash‌: particles produced during the combustion process, such as silicate particles produced when coal and wood are burned; ‌fog‌: small droplets or ice crystals generated by condensation of water vapor; haze‌: particles formed by dust or salt particles suspended in the atmosphere, making the atmosphere turbid and light blue or slightly yellow, etc., it has its corresponding influence information on transmittance. Therefore, the joint influence degree, humidity information and solid particle information can be combined for quantitative analysis to determine the first reference transmittance correction value.

[0042] Determining the haze dispersion trend information according to the wind speed information can be understood as the existence of wind will accelerate the dispersion speed of haze when it is dispersed, so the corresponding dispersion acceleration information can be determined according to the wind speed information (including wind force and wind direction). The greater the wind speed, the greater the dispersion acceleration, and the smaller the wind speed, the smaller the dispersion acceleration. At the same time, due to the existence of wind, the haze will have a certain tendency when it is dispersed. The dispersion trend is usually related to the wind direction. The haze dispersion trend information can be determined according to the wind speed information through a general aerodynamic analysis method. Since the haze is dispersed gradually, the transmittance will change gradually due to the occurrence of dispersion, so the second reference transmittance correction value can be determined according to the dispersion trend information. The greater the dispersion force in the dispersion trend information, the greater the possibility that the haze is blown away, and the transmittance will therefore show a faster increase, and vice versa. Therefore, the second reference transmittance correction value can be determined according to the correlation between the dispersion force and the transmittance.

[0043] The weights of the first reference transmittance correction value and the second reference transmittance correction value can be obtained respectively, and weight calculation is performed according to the corresponding weights to perform fusion processing to obtain the first transmittance correction value.

[0044] In this example, the first transmittance correction value is determined by the humidity information in the environmental information, the solid particle information and the wind speed, so that the first transmittance correction value can be determined in combination with the trend of environmental changes, thereby improving the accuracy of determining the first transmittance correction value.

[0045] In a possible implementation, a method for obtaining a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value includes: C1. Acquire an associated image of a target traffic image to obtain an associated image set, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image; C2. Obtaining background light intensity values ​​of associated images in the associated image set to obtain a reference background light intensity value set; C3. determining a background light intensity correction value according to the reference background light intensity values ​​and corresponding variances in the reference background light intensity value set; C4, obtaining a first background light intensity value of the target traffic image; C5. Use the background light intensity correction value to correct the first background light intensity value to obtain the target background light intensity value.

[0046] The associated image may be the first traffic image captured within a preset time interval with the target traffic image, for example, images captured at the first k capturing moments and images captured at the last k capturing moments of the target traffic image, where k may be 5, 10, etc. A general background light intensity value acquisition method may be used to acquire the reference background light intensity value corresponding to the associated image and the first background light intensity value of the target traffic image.

[0047] According to the reference background light intensity values ​​and the corresponding variances in the reference background light intensity value set, the method for determining the background light intensity correction value can be: calculating the mean of the reference background light intensity values, and normalizing the variance to obtain a normalized value, which is between 0 and 1. The background light intensity correction value is determined by using the mean and normalized value of the reference background light intensity values. Specifically, it can be: the ratio of the sum of the mean and normalized values ​​of the reference background light intensity values ​​to the mean of the reference background light intensity values ​​is determined as the background light intensity correction value. When calculating, it is necessary to assign a value to the normalized value, which can be specifically understood as, if the normalized value is less than the threshold, it is negative, and if it is greater than the threshold, it is positive. Since the larger the normalized value, the greater the degree of discreteness, it can be indicated that the change in the atmospheric light intensity value may be large.

[0048] Specifically, since the variance can characterize the change relationship between the reference background light intensity values ​​in the reference background light intensity value set, and since the shooting interval is very small, the value of the variance will be small, or even close to 0. Since the value of the variance is small, the mean and variance can be combined to perform corresponding correction processing to amplify the fluctuation and feedback it to correct the first background light intensity value, thereby improving the accuracy of the target background light intensity value obtained. The product of the background light intensity correction value and the first background light intensity value can be determined as the target background light intensity value.

[0049] In this example, an associated image set is obtained by acquiring an associated image of a target traffic image, wherein the associated image is a first traffic image taken within a preset time interval with the target traffic image, and background light intensity values ​​of the associated images in the associated image set are acquired to obtain a reference background light intensity value set. A background light intensity correction value is determined based on the reference background light intensity values ​​in the reference background light intensity value set and the corresponding variance, and a first background light intensity value of the target traffic image is acquired. The first background light intensity value is corrected using the background light intensity correction value to obtain the target background light intensity value. Therefore, the background light intensity correction value can be determined in combination with the background light intensity values ​​of the associated image set and the related variation. Finally, the first background light intensity value is corrected to obtain the target background light intensity value, thereby improving the accuracy of the target background light intensity value.

[0050] In a possible implementation, a method for determining traffic load information of a road area to be detected based on the vehicle information and the traffic load information collection duration includes: D1. extracting sub-vehicle information of each lane in the road area to be detected from the vehicle information to obtain a sub-vehicle information set; D2. Determine the traffic load information of the road area to be detected according to the sub-vehicle information set and the traffic load information collection time.

[0051] The vehicle information includes the lane information to which the vehicle belongs, so that the sub-vehicle information of each lane can be extracted. Finally, the ratio of the sub-vehicle information to the traffic load information collection time is determined as the traffic load information to characterize the traffic flow in unit time, and the traffic load information is characterized by the traffic flow. The sub-vehicle information can include the number of vehicles, etc.

[0052] For the above embodiments, please refer to Figure 2 , Figure 2A schematic diagram of the structure of a terminal provided in an embodiment of the present application, as shown in the figure, includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps; Acquire traffic images of the road area to be detected within the traffic load information collection time to obtain a first traffic image set; performing defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; Performing target extraction on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected; The traffic load information of the road area to be detected is determined according to the vehicle information and the traffic load information collection time.

[0053] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0054] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0055] In line with the above, see Figure 3 , Figure 3 The present application provides a schematic diagram of a traffic load prediction device based on image enhancement. Figure 3 As shown, the device comprises: An acquisition unit 301 is used to acquire traffic images of a road area to be detected within a traffic load information collection period to obtain a first traffic image set; An enhancement unit 302 is configured to perform defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; An extraction unit 303, configured to extract objects from the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected; The determination unit 304 is used to determine the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection time.

[0056] In a possible implementation, the enhancement unit 302 is specifically configured to: Determining a first transmittance correction value according to environmental information of the road area to be detected; Acquire a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; Calculate the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; Defogging the target traffic image using the target transmittance to obtain a second traffic image; Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, and performing defogging on the target traffic image using the target transmittance to obtain the second traffic image, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

[0057] In a possible implementation, in determining the first transmittance correction value according to the environmental information of the road area to be detected, the enhancing unit 302 is specifically configured to: Extracting wind speed information, solid particle information and humidity information from the environmental information; Acquire the combined influence degree between the humidity information and the solid particulate matter information; Determine a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; Determining haze dispersion trend information according to the wind speed information; determining a second reference transmittance correction value according to the haze dispersion trend information; The first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value.

[0058] In a possible implementation, in acquiring the background light intensity value corresponding to the target traffic image and obtaining the target background light intensity value, the enhancing unit 302 is specifically configured to: Acquire an associated image of the target traffic image to obtain an associated image set, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image; Acquire background light intensity values ​​of associated images in the associated image set to obtain a reference background light intensity value set; Determining a background light intensity correction value according to reference background light intensity values ​​and corresponding variances in a reference background light intensity value set; Acquire a first background light intensity value of a target traffic image; The first background light intensity value is corrected using the background light intensity correction value to obtain the target background light intensity value.

[0059] In a possible implementation, the determining unit 304 is specifically configured to: Extracting sub-vehicle information of each lane in the road area to be detected from the vehicle information to obtain a sub-vehicle information set; The traffic load information of the road area to be detected is determined according to the sub-vehicle information set and the traffic load information collection time.

[0060] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the image enhancement-based traffic load prediction methods recorded in the above method embodiments.

[0061] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the image enhancement-based traffic load prediction methods recorded in the above method embodiments.

[0062] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0063] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0064] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which 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 the device or unit can be electrical or other forms.

[0065] 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 solution of this embodiment.

[0066] In addition, the functional units in the various embodiments of the 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 units may be implemented in the form of hardware or in the form of software program modules.

[0067] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, 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 memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., and other media that can store program codes.

[0068] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0069] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A traffic load prediction method based on image enhancement, characterized in that: The method comprises: Acquire traffic images of the road area to be detected within the traffic load information collection time to obtain a first traffic image set; performing defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; Performing target extraction on the second traffic image in the second traffic image set to obtain vehicle information of the road area to be detected; The traffic load information of the road area to be detected is determined according to the vehicle information and the traffic load information collection time.

2. The traffic load prediction method based on image enhancement according to claim 1 is characterized in that: The performing defogging and enhancement processing on the first traffic image in the first traffic image set to obtain the second traffic image set includes: Determining a first transmittance correction value according to environmental information of the road area to be detected; Acquire a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; Calculate the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; Defogging the target traffic image using the target transmittance to obtain a second traffic image; Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, and performing defogging on the target traffic image using the target transmittance to obtain the second traffic image, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

3. The traffic load prediction method based on image enhancement according to claim 2 is characterized in that: The determining of the first transmittance correction value according to the environmental information of the road area to be detected includes: Extracting wind speed information, solid particle information and humidity information from the environmental information; Acquire the combined influence degree between the humidity information and the solid particulate matter information; Determine a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; Determining haze dispersion trend information according to the wind speed information; determining a second reference transmittance correction value according to the haze dispersion trend information; The first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value.

4. The traffic load prediction method based on image enhancement according to claim 2 or 3, characterized in that: The step of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value includes: Acquire an associated image of the target traffic image to obtain an associated image set, wherein the associated image is a first traffic image captured within a preset time interval with the target traffic image; Acquire background light intensity values ​​of associated images in the associated image set to obtain a reference background light intensity value set; Determining a background light intensity correction value according to the reference background light intensity values ​​and corresponding variances in the reference background light intensity value set; Acquire a first background light intensity value of a target traffic image; The first background light intensity value is corrected using the background light intensity correction value to obtain the target background light intensity value.

5. The traffic load prediction method based on image enhancement according to claim 4 is characterized in that: The determining the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection time includes: Extracting sub-vehicle information of each lane in the road area to be detected from the vehicle information to obtain a sub-vehicle information set; The traffic load information of the road area to be detected is determined according to the sub-vehicle information set and the traffic load information collection time.

6. A traffic load prediction device based on image enhancement, characterized in that: The device comprises: An acquisition unit, used to acquire traffic images of the road area to be detected within a traffic load information collection period to obtain a first traffic image set; an enhancement unit, configured to perform defogging and enhancement processing on the first traffic image in the first traffic image set to obtain a second traffic image set; an extraction unit, configured to extract objects from the second traffic images in the second traffic image set to obtain vehicle information of the road area to be detected; The determination unit is used to determine the traffic load information of the road area to be detected according to the vehicle information and the traffic load information collection time.

7. The traffic load prediction device based on image enhancement according to claim 6, characterized in that: The enhancement unit is specifically used for: Determining a first transmittance correction value according to environmental information of the road area to be detected; Acquire a background light intensity value corresponding to a target traffic image to obtain a target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set; Calculate the transmittance according to the target background light intensity value and the first transmittance correction value to obtain a target transmittance; Defogging the target traffic image using the target transmittance to obtain a second traffic image; Repeat the above steps of obtaining the background light intensity value corresponding to the target traffic image to obtain the target background light intensity value, wherein the target traffic image is any first traffic image in the first traffic image set, and performing defogging on the target traffic image using the target transmittance to obtain the second traffic image, until the second traffic image corresponding to each first traffic image is obtained, and the second traffic image set is obtained according to each second traffic image.

8. The traffic load prediction device based on image enhancement according to claim 7, characterized in that: In the aspect of determining the first transmittance correction value according to the environmental information of the road area to be detected, the enhancement unit is specifically used for: Extracting wind speed information, solid particle information and humidity information from the environmental information; Acquire the combined influence degree between the humidity information and the solid particulate matter information; Determine a first reference transmittance correction value according to the combined influence degree, the humidity information and the solid particle information; Determining haze dispersion trend information according to the wind speed information; determining a second reference transmittance correction value according to the haze dispersion trend information; The first reference transmittance correction value and the second reference transmittance correction value are fused to obtain the first transmittance correction value.

9. A terminal, characterized in that: The invention comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the traffic load prediction method based on image enhancement as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the traffic load prediction method based on image enhancement according to any one of claims 1 to 5.

Images