Target object heat map determination method and apparatus, electronic device, and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for determining a target object heatmap. The method includes: identifying target objects in at least two statistical regions; determining target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical regions; adjusting the size and / or frequency of the statistical regions based on the target object parameters of each statistical region; and determining the target object heatmap based on the number of target objects in each adjusted statistical region. This invention enables dynamic adjustment of the statistical regions and frequencies, optimizing the performance and accuracy of the target object heatmap.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a heat map of a target object. Background Technology

[0002] Heatmap systems typically divide an entire area or into multiple statistical regions, and count target objects in each region at a fixed statistical frequency to generate a heatmap of the target objects, which is used to show the distribution and density of the target objects.

[0003] However, existing methods for determining heatmaps also have some significant drawbacks: First, there is a trade-off between spatial resolution and accuracy in target object heatmaps. More detailed statistical region division improves accuracy, but drastically increases computational load, leading to reduced system efficiency; conversely, larger statistical regions reduce computational burden but decrease accuracy. Second, dynamic target response is insufficient; heatmaps often lag behind real-time dynamic changes in target objects, failing to effectively reflect their movement. Third, excessively high target object density can cause cumulative count saturation, making it impossible to reflect higher target object densities through heatmaps. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining a heat map of a target object, thereby enabling dynamic adjustment of statistical regions and statistical frequencies and optimizing the performance and accuracy of the heat map of the target object.

[0005] In a first aspect, embodiments of the present invention provide a method for determining a heat map of a target object, the method comprising:

[0006] Target object identification is performed on at least two statistical regions to determine target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical regions;

[0007] Based on the target object parameters of each statistical region, adjust the size of the statistical region and / or the statistical frequency of the target statistical region;

[0008] Based on the adjusted number of target objects in each statistical region, a heatmap of the target objects is determined.

[0009] Secondly, embodiments of the present invention also provide a device for determining a heat map of a target object, the device comprising:

[0010] The data determination module is used to identify target objects in at least two statistical regions, including target object parameters.

[0011] The target statistical region adjustment module is used to adjust the size and / or frequency of the target statistical region based on the target object parameters of each statistical region.

[0012] The target object heatmap determination module is used to determine the target object heatmap based on the number of target objects in each statistical region after adjustment.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for determining a heat map of a target object as described in any of the embodiments of the present invention.

[0014] Fourthly, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform a method for determining a heat map of a target object as described in any of the embodiments of the present invention.

[0015] The technical solution of this invention identifies target objects in each statistical region, obtaining at least one target object parameter for each region: target object size, target object movement speed, and target object density. Based on these parameters, the size and / or frequency of the statistical regions are adjusted. Finally, a target object heatmap is determined based on the adjusted number of target objects in each statistical region. This solves the problems of spatial resolution versus accuracy, insufficient dynamic target response, and target object density accumulation saturation in existing heatmap determination methods. It achieves dynamic adjustment of the statistical region and frequency, optimizing the performance and accuracy of the target object heatmap.

[0016] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a method for determining a heat map of a target object according to Embodiment 1 of the present invention;

[0019] Figure 2This is a flowchart of a method for determining a heat map of a target object according to Embodiment 2 of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of a device for determining the heat map of a target object according to Embodiment 3 of the present invention;

[0021] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0024] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0025] Example 1

[0026] Figure 1 The flowchart of a method for determining a heat map of a target object is provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of determining a heat map of a target object. The method can be executed by a device for determining a heat map of a target object. The device for determining a heat map of a target object can be implemented in hardware and / or software and can be configured in an electronic device or a server.

[0027] like Figure 1 As shown, the method includes:

[0028] S110. Target object identification is performed on at least two statistical regions to determine target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical region.

[0029] In this context, a statistical region refers to the smallest statistical unit used for counting target objects when generating a heatmap. In existing technologies, when generating a target object heatmap, the entire area corresponding to the heatmap is divided into several statistical regions on an average basis, and target objects are identified and counted in each statistical region. The size of the statistical region and the statistical frequency of counting target objects in each statistical region directly affect the accuracy of the target object heatmap.

[0030] This embodiment does not restrict the area or specific division method of the statistical region before adjusting parameters such as the size and frequency of the statistical region. In one optional embodiment, the standard size of the statistical region can be predetermined. After determining all regions corresponding to the heatmap, the entire region is divided into several statistical regions according to the standard size. In another optional embodiment, the statistical regions can also be divided according to the historical target object density of all regions corresponding to the heatmap. Specifically, the higher the historical target object density, the smaller the statistical region.

[0031] The target object can be a person, vehicle, moving object, etc. This embodiment does not limit the type of target object. Target object recognition algorithms or pre-trained target object recognition models can be used to identify target objects in each statistical region. This embodiment does not limit this either. Furthermore, target object recognition can be performed based on images captured by a camera, radar images collected by a radar sensor, infrared images collected by an infrared sensor, etc. This embodiment does not limit this either.

[0032] The target object parameters can be one or more of the following: target object size, target object movement speed, and target object density in the statistical area. This embodiment does not impose any restrictions on these parameters.

[0033] Taking the identification of target objects based on images captured by a camera as an example, the field of view of the camera needs to cover the corresponding statistical area. The size of the target object can refer to the pixel area of ​​the target object in the image captured by the camera at the current moment, or it can refer to the actual area of ​​the target object obtained by converting the pixel area and pixel ratio.

[0034] Let's continue with the example of target object recognition based on images captured by a camera. The target object's motion speed refers to its speed within the image captured by the camera at the current moment. Specifically, target object recognition can be performed on consecutive video frames, and then target tracking algorithms such as Kalman filtering, particle filtering, or optical flow can be used to track the target object's motion within those frames. The displacement of the target object is calculated based on its trajectory in adjacent video frames, and the motion speed is then calculated based on this displacement and the time interval between adjacent video frames.

[0035] The target object density of a statistical region can be calculated based on the number of target objects within the region at the current moment and the area of ​​the statistical region. Furthermore, if a target object spans multiple statistical regions, it is returned to the statistical region where it first appeared and counted, until the target object completely leaves that region. If a target object, upon completely leaving a statistical region, crosses multiple other statistical regions, it is returned to the statistical region with the largest area proportion within each of the other statistical regions and counted accordingly.

[0036] In this embodiment, factors affecting the size and frequency of the statistical region, such as the size of the target object, the speed of the target object's movement, and the density of the target object in the statistical region, are continuously monitored to facilitate subsequent dynamic adjustment of the size and frequency of the statistical region.

[0037] S120. Adjust the size and / or frequency of the statistical area of ​​the target statistical area according to the target object parameters of each statistical area.

[0038] The target statistical region refers to the statistical region within each statistical region that requires adjustment of its size and / or frequency. This can be one or several statistical regions, or it can refer to the entire statistical region. The size of the statistical region refers to its area, and the statistical frequency refers to the frequency at which the statistical quantity of target objects within the statistical region is updated.

[0039] Furthermore, in an optional embodiment, all statistical regions can be directly used as target statistical regions. For each statistical region, the influence of target object size, target object movement speed, and target object density is considered simultaneously, and the size and / or statistical frequency of the statistical region are readjusted. The advantage of this setting is that it enables real-time dynamic updates of each statistical region, thereby improving the accuracy of the target object heatmap.

[0040] In another optional embodiment, the target object size, target object movement speed, and target object density of each statistical region can be continuously monitored at different times. If at least one parameter of a statistical region at the current time is found to have changed by a factor greater than or equal to a preset change threshold compared to the previous time, then that statistical region is designated as the target statistical region. Here, the parameters refer to the target object size, target object movement speed, and target object density. This setup improves the stability of the target object heatmap and reduces computational load.

[0041] It should be noted that in this embodiment, when there are at least two target objects within the statistical region, the size of the target objects within the statistical region can refer to either the average size of all target objects or the maximum size of all target objects. Similarly, the movement speed of the target objects can refer to either the average speed of all target objects or the maximum speed of all target objects. This embodiment does not impose any restrictions on this.

[0042] Specifically, if the size of the target object in the target statistical region meets the statistical region adjustment conditions, the size of the statistical region in the target statistical region is adjusted according to the size of the target object in each statistical region; wherein, the size of the target object is directly proportional to the size of the statistical region, the larger the size of the target object, the larger the size of the statistical region in which the target object is located.

[0043] In an optional embodiment, the target object size meets the statistical region adjustment conditions. This can be achieved by pre-setting a fluctuation range for the target object size. Within this range, no adjustment to the statistical region size is necessary to save computational resources. If the target object size exceeds this fluctuation range, the statistical region size is adjusted accordingly.

[0044] In another optional embodiment, the target object size satisfies the statistical region adjustment condition. Alternatively, the target object size can be determined to have an increasing / decreasing trend based on the current target object size at the current moment and the historical target object size at least one historical moment prior to the current moment. For example, this can be determined by judging whether the difference between the current target object size and the historical target object size is greater than or equal to a preset threshold, or by judging whether the curvature of the target object size-time curve at the current moment is greater than a preset curvature threshold. This embodiment does not impose any limitations on this.

[0045] Understandably, when the target object is large, it may span two or more statistical regions, leading to inaccurate counting in each region. Furthermore, if the target object occupies a large portion of a statistical region, using the existing region for counting will increase computational load and consume more resources. Therefore, the size of the target object is a significant factor influencing the size of the statistical region. Moreover, larger target objects require larger statistical regions, and smaller target objects require smaller statistical regions to improve the accuracy of target object counting within the region and reduce computational load.

[0046] For example, in the field of traffic safety, taking the creation of vehicle heatmaps as an example, the statistical area is set according to the standard size of 20m*20m. If a towing truck is detected, its length itself reaches more than ten meters, which can easily lead to the aforementioned problem of inaccurate counting caused by spanning multiple statistical areas, as well as the problem of increased calculation workload due to occupying most of the statistical area. In this case, the statistical area can be expanded to 50m*50m.

[0047] The process of adjusting the size of the statistical region based on the size of the target object in each statistical region will be explained in a unified manner later.

[0048] Specifically, if the movement speed of the target object in the target statistical region meets the statistical region adjustment conditions, the size and / or frequency of the statistical region of the target statistical region are adjusted according to the movement speed of the target object in each statistical region; wherein, the movement speed of the target object is inversely proportional to the size of the statistical region, the greater the movement speed of the target object, the smaller the size of the statistical region in which the target object is located; the movement speed of the target object is directly proportional to the statistical frequency, the greater the movement speed of the target object, the greater the statistical frequency of the statistical region in which the target object is located.

[0049] The target object's motion speed within the target statistical region meets the statistical region adjustment conditions. This can mean that the target object's motion speed is greater than or equal to a preset motion speed threshold. Alternatively, it can be determined that the target object's motion speed shows a relatively rapid trend based on the current motion speed of the target object at the current moment and the historical motion speed of the target object at least one historical moment prior to the current moment. The motion speed trend can be determined by calculating acceleration based on the current and historical motion speeds of the target object and judging whether the acceleration is greater than a preset acceleration threshold; alternatively, it can be determined by whether the curvature of the target object's motion speed-time curve at the current moment is greater than a preset curvature threshold. This embodiment does not impose any restrictions on this method.

[0050] Understandably, when the target object moves at a high speed, if the statistical region is also large, the dynamic changes of the target object within the statistical region, as reflected in the target object count and heatmap, will not be adequately represented. Conversely, when the target object moves at a low speed or remains stationary, setting a small statistical region will result in a large number of statistical regions, increasing the computational load and consuming computational resources. Therefore, the target object's movement speed is a significant factor influencing the size of the statistical region. Furthermore, the higher the target object's movement speed, the smaller the statistical region needs to be, and the lower the target object's movement speed, the larger the statistical region needs to be, in order to promptly address the target object's dynamic changes and effectively reflect its movement.

[0051] Meanwhile, when the target object moves at a high speed, a low statistical frequency in the statistical region will prevent timely capture of the target object's movement. Conversely, when the target object moves at a low speed or remains stationary, a high statistical frequency in the statistical region increases the computational burden and wastes computational resources. Therefore, the target object's movement speed is a significant factor influencing the statistical frequency. Furthermore, the higher the target object's movement speed, the higher the statistical frequency needs to be set, and the lower the target object's movement speed, the lower the statistical frequency needs to be set, in order to capture the target object's movement in a timely manner, improve response efficiency, and save computational resources.

[0052] Similarly, the process of adjusting the size of the statistical area of ​​the target statistical area according to the movement speed of the target object in each statistical area will be explained in a unified manner later.

[0053] Specifically, if the target object density of the target statistical region meets the statistical region adjustment conditions, the size of the statistical region of the target statistical region is adjusted according to the target object density of each statistical region; wherein, when the target object density is greater than or equal to a preset density threshold, the target object density is inversely proportional to the size of the statistical region, the larger the target object density, the smaller the size of the statistical region corresponding to the target object density.

[0054] The target object density of the target statistical region meets the statistical region adjustment conditions, which can mean that the target object density of the target statistical region is greater than or equal to the density threshold.

[0055] Understandably, when displaying a heatmap, the target object density of each statistical region is converted into color, and there is a mapping relationship between target object density and color. If the target object density is too high, there will be insufficient colors to correspond to it, causing cumulative count saturation, making the final target object heatmap unable to effectively reflect the distribution of the target object quantity. Furthermore, since the target object density is calculated based on the number of target objects and the size of the statistical region, the target object density is a significant factor affecting the size of the statistical region. Moreover, since there is no cumulative count saturation problem when the target object density is below a density threshold, this embodiment, when the target object density is greater than or equal to the density threshold, influences the size of the statistical region; the higher the target object density, the smaller the statistical region size, to avoid cumulative count saturation and ensure that the target object heatmap effectively reflects the distribution of the target object quantity.

[0056] For example, if the mapping relationship between target object density and color is pre-set as follows: target object density of 0 corresponds to blue; target object density of 1-5 corresponds to a color between blue and red, closer to blue; target object density of 6-10 corresponds to a color exactly between blue and red; target object density of 11-15 corresponds to a color between blue and red, closer to red; and target object density of 16 and above corresponds to red. According to this mapping rule, when the target object density is greater than or equal to 16, regardless of how much the target object density increases, it will only be displayed as red. This would prevent the target object heatmap from intuitively reflecting higher target object densities. Therefore, the size of the statistical region can be reduced to decrease the target object density in each statistical region and avoid saturation.

[0057] In an optional embodiment, when adjusting the size and / or frequency of the statistical region of the target statistical region, the adjusted size and / or frequency can be determined directly based on the target object size, target object movement speed, and target object density within the target statistical region. Specifically, mathematical formulas can be used to define the relationship between the target object size, target object movement speed, and target object density and the statistical region size, and also to define the relationship between the target object movement speed and the statistical frequency.

[0058] In another optional embodiment, when adjusting the size and / or frequency of the statistical region of the target statistical region, the influence of the target object size, the target object movement speed, and the target object density on the size of the statistical region can be considered separately before comprehensive consideration. Additionally, the influence of the target object movement speed on the statistical frequency can be considered.

[0059] In one example, the statistical region sizes corresponding to different target object size ranges, different target object movement speed ranges, and different target object density ranges can be pre-defined. The size of the first statistical region corresponding to the target object size range, the size of the second statistical region corresponding to the target object movement speed range, and the size of the third statistical region corresponding to the target object density range when the target object density is greater than or equal to a density threshold (the third statistical region size can be the standard statistical region size when the target object density is less than the density threshold) are determined. Weights are pre-defined for the three parameters: target object size, target object movement speed, and target object density. The first, second, and third statistical region sizes are then weighted and summed to obtain the final statistical region size. The size of the statistical region corresponding to different target object movement speed ranges is pre-defined, and the size of the statistical region corresponding to the target object movement speed range is determined.

[0060] In another example, we can also pre-set the statistical region size change corresponding to different target object size change intervals, the statistical region size change corresponding to different target object movement speed change intervals, and the statistical region size change corresponding to different target object density change intervals when the target object density is greater than or equal to a density threshold. The subsequent processing is similar to the example above, and will not be repeated here. After obtaining the final statistical region size change, the statistical region size change is added to the current statistical region size to obtain the adjusted statistical region size.

[0061] The change can refer to either the change in the parameter at the current moment compared to the parameter at the previous moment (which could be the acquisition time of the previous frame or a moment determined according to a pre-set adjustment frequency), or the change in the parameter at the current moment compared to the average parameter value of all statistical regions at the current moment. It should be noted that the change can be positive or negative; correspondingly, the change range can include both positive and negative ranges, and the change in the size of the corresponding statistical region can also be positive or negative.

[0062] The statistical frequency change corresponding to different ranges of target object speed change is preset. The target object speed change at the current moment is determined. The statistical frequency change corresponding to the range in which the target object is located is added to the statistical frequency at the current moment to obtain the adjusted statistical frequency.

[0063] In another example, mathematical formulas can be used to define the relationship between the target object size and the statistical region size, the relationship between the target object's movement speed and the statistical region size, and the relationship between the target object's density and the statistical region size when the target object's density is greater than or equal to a density threshold. Based on the target object size, target object movement speed, and target object density within the target statistical region, the corresponding first, second, and third statistical region sizes are obtained, respectively. These are then weighted and summed using the same method to obtain the final statistical region size. Alternatively, mathematical formulas can be used to define the relationship between the change in target object size and the change in statistical region size, the relationship between the change in target object movement speed and the change in statistical region size, and the relationship between the change in target object density and the change in statistical region size when the target object's density is greater than or equal to a density threshold. The final change in statistical region size is obtained using the same method and then added to the current statistical region size.

[0064] It should be noted that this embodiment allows setting a range for the size of the statistical region and the statistical frequency. Taking the size of the statistical region as an example, if the adjusted size of the statistical region is greater than the maximum value of the range, then the maximum value of the range will be used as the adjusted size of the statistical region; or, if the adjusted size of the statistical region is less than the minimum value of the range, then the minimum value of the range will be used as the adjusted size of the statistical region.

[0065] In this embodiment, by dynamically adjusting the size of the statistical region and / or the statistical frequency based on the target object size, target object movement speed, and target object density, the target object heat map can be drawn more effectively and quickly, improving the performance and accuracy of the target object heat map.

[0066] S130. Based on the number of target objects in each statistical area after adjustment, determine the target object heat map.

[0067] In this embodiment, after adjusting the size and frequency of the statistical region, the current statistical period is determined based on the statistical frequency, and the number of target objects within the adjusted statistical region during the current statistical period is counted. Then, a heatmap of the target objects is drawn based on the mapping rules between the number or density of target objects and their colors.

[0068] Furthermore, when the target statistical region is a subset of the total statistical region, the adjusted sizes of each statistical region may differ. In this case, a heatmap of the target object can be drawn based on the mapping rules between the target object's density and color to ensure the accuracy of the heatmap.

[0069] For example, a heat map of the target object can be drawn using a heat map drawing tool, such as drawing software or data visualization tools. This embodiment does not limit the specific drawing process of the target object heat map.

[0070] The technical solution of this invention identifies target objects in each statistical region, obtaining the target object size, target object movement speed, and target object density in each region. Based on this data, the size and / or frequency of the statistical regions are adjusted. Finally, a target object heatmap is determined based on the adjusted number of target objects in each statistical region. This solves the problems of spatial resolution versus accuracy, insufficient dynamic target response, and target object density accumulation saturation in existing heatmap determination methods. It achieves dynamic adjustment of statistical regions and frequencies, optimizing the performance and accuracy of the target object heatmap.

[0071] Example 2

[0072] Figure 2 This is a flowchart of a method for determining a heat map of a target object according to Embodiment 2 of the present invention. Based on the above embodiments, the present invention further specifies the process of determining the size and frequency of the statistical region of the target statistical region, and adds a pre-adjustment process for the statistical region following the target statistical region in the direction of the target object's movement.

[0073] like Figure 2 As shown, the method includes:

[0074] S210. Target object identification is performed on at least two statistical regions to obtain the target object size, target object movement speed and target object density in each statistical region.

[0075] The process of determining the size, speed, and density of the target object has been described in the above embodiments and will not be repeated here.

[0076] S220. Determine the size of the statistical region of the target statistical region based on the mean and standard deviation of at least one target object parameter.

[0077] The above embodiments have described the adjustment methods for the size of the statistical region and / or the statistical frequency of the target statistical region. Based on the above embodiments, this embodiment provides a method for limiting the relationship between the size of the target object, the movement speed of the target object, and the density of the target object and the size of the statistical region based on mathematical formulas, and a method for limiting the relationship between the size of the target object, the movement speed of the target object, and the statistical frequency based on mathematical formulas.

[0078] The ratio of standard deviation to mean is called the coefficient of variation, which measures the relative dispersion of data. In this embodiment, the coefficient of variation of the target object parameter can be used to measure the dispersion of the target object parameter, thereby determining the degree of adjustment for the size of the statistical region. Understandably, taking the target object size as an example, if the coefficient of variation is large for the entire statistical region as a whole, it indicates that the target object sizes differ significantly across statistical regions, requiring a larger adjustment to the size of the statistical region.

[0079] In an optional embodiment, the size of the target statistical region is determined based on the mean and standard deviation of at least one target object parameter. This can be achieved by dividing the target object parameter of the target statistical region by the mean of the target object parameter of each statistical region, multiplying the resulting value by the coefficient of variation calculated based on the ratio of the standard deviation to the mean, and then multiplying by the standard statistical region size to obtain the adjusted statistical region size of the target statistical region.

[0080] In another optional embodiment, if the mean and standard deviation of a target object parameter are used to determine the size of the target statistical region, taking the target object parameter as the target object size as an example, it can be expressed by the following formula: Where R(t) represents the adjusted statistical region size, k is the scaling factor, A(t) represents the target object size at time t, x represents the weighting factor for the target object size, and δ A μ represents the standard deviation of the target object size for each target object. A This represents the average size of all target objects. The calculation formula is similar when the target object parameter is the target object's movement speed or target object density, and will not be repeated in this embodiment.

[0081] If we use the mean and standard deviation of two target object parameters to determine the size of the target statistical region, taking the target object size and target object movement speed as an example, it can be expressed by the following formula: Where v(t) represents the velocity of the target object at time t, y represents the weighting coefficient of the target object's velocity, and δ V μ represents the standard deviation of the velocity of each target object. V This represents the average speed of the target objects. The formula for determining the size of the statistical region of the target statistical area using any two target object parameters is similar to the formula described above, and will not be repeated in this embodiment.

[0082] Furthermore, S220 may include: determining the size of the statistical region of the target statistical region using the following formula:

[0083]

[0084] Where R(t) represents the adjusted statistical region size, k is the scaling factor, A(t) represents the target object size at time t, v(t) represents the target object velocity at time t, and μ p P represents the average density of target objects in each statistical region. max δ represents the maximum target object density in each statistical region, x represents the weighting coefficient for target object size, and δ represents the maximum target object density in each statistical region. A μ represents the standard deviation of the target object size for each target object. A δ represents the average size of each target object, y represents the weighting coefficient of the target object's motion speed, and δ represents the average size of each target object. V μ represents the standard deviation of the velocity of each target object. V δ represents the average velocity of each target object, z represents the weighting coefficient of the target object density, and δ represents the average velocity of each target object. p This represents the standard deviation of the target object density in each statistical region.

[0085] Understandably, according to the above formula, the size of the target object is directly proportional to the size of the statistical area, while the target object's movement speed is inversely proportional to the size of the statistical area. For target object density, the ratio of the average to the maximum value can be used to measure how close the overall target object density of the entire area corresponding to the heatmap is to the maximum value. The larger the ratio, the closer the average value is to the maximum value, and the more concentrated the target object density is within a higher numerical range in each statistical area. The smaller the value, the smaller the statistical area.

[0086] At the same time, the ratio of standard deviation to mean can be called the coefficient of variation, which is used to measure the degree of fluctuation of the density of target objects in each statistical region relative to the mean. The higher the coefficient of variation, the worse the data stability or consistency. The higher the value, the greater the difference in the size of the target objects within the target statistical region. The larger the value, the larger the statistical area. The higher the value, the greater the difference in the movement speed of the target object within the target statistical area. The smaller the value, the smaller the statistical area. The higher the value, the greater the difference between the target object density in the target statistical region and the average target object density. The smaller the value, the smaller the statistical area.

[0087] The technical solution of this embodiment can comprehensively control the size of the statistical region by combining three parameters: the size of the target object, the speed of the target object's movement, and the density of the target object.

[0088] Similarly, in this embodiment, a range of values ​​can be set for the size of the statistical region. If the calculated size of the statistical region is greater than the maximum value of the range, the maximum value of the range will be used as the adjusted size of the statistical region; or, if the calculated size of the statistical region is less than the minimum value of the range, the minimum value of the range will be used as the adjusted size of the statistical region.

[0089] S230. Determine the statistical frequency of the target statistical region based on the size of the target object and / or the speed of the target object's movement within the target statistical region.

[0090] In this embodiment, the statistical frequency of the target statistical region is adjusted based on at least one of the target object size and the target object movement speed.

[0091] In an optional embodiment, taking the adjustment of the statistical frequency of the target statistical region based on the target object size as an example, the ratio of the target object size of the target statistical region to the average target object size of each statistical region can be multiplied by a preset statistical frequency to obtain the adjusted statistical frequency of the target statistical region. The adjustment of the statistical frequency of the target statistical region based on the target object's movement speed is similar. Taking the adjustment of the statistical frequency of the target statistical region based on both target object size and target object movement speed as an example, the ratio of the target object size of the target statistical region to the average target object size of each statistical region is multiplied by a target object size weight, and the ratio of the target object movement speed of the target statistical region to the average target object movement speed of each statistical region is multiplied by a target object movement speed weight. The sum of these two products is multiplied by a preset statistical frequency, and the resulting value is used as the adjusted statistical frequency of the target statistical region.

[0092] In another optional embodiment, taking the adjustment of the statistical frequency of the target statistical region based on the size of the target object as an example, the statistical frequency of the target statistical region can be determined by the following formula: T(t)=m×(μ V +ΔV(t)), where T(t) represents the adjusted statistical frequency, m represents the influence coefficient of the target object's movement speed on the statistical frequency, and ΔV(t) represents the change in the target object's movement speed. The adjustment of the statistical frequency of the target statistical region based on the target object's movement speed is similar.

[0093] Taking the adjustment of the statistical frequency of the target statistical region based on the size and speed of the target object as an example, the statistical frequency of the target statistical region can be determined using the following formula: Where T(t) represents the adjusted statistical frequency, m represents the influence coefficient of the target object's movement speed on the statistical frequency, ΔV(t) represents the change in the target object's movement speed, and n represents the influence coefficient of the target object's size on the statistical frequency.

[0094] In this embodiment, when adjusting the statistical frequency, a target object size parameter was added. It is understandable that if the target object size varies greatly within the target statistical area, high-frequency statistics are required to capture changes in the target object in a timely manner.

[0095] According to the above formula, when the target object changes from stationary or with a small speed to a large speed, ΔV(t) is larger, resulting in a larger statistical frequency. However, when the target object maintains rapid movement, the frequency is higher through μ. V +ΔV(t) can keep the statistical frequency high while maintaining relative stability. The higher the value, the greater the difference in the size of the target objects within the target statistical region. The larger the value, the greater the statistical frequency.

[0096] The technical solution of this embodiment can achieve dynamic control of statistical frequency by combining the size of the target object and the speed of the target object's movement.

[0097] S240. Based on the target object parameters of the target statistical region, adjust the size and / or frequency of the statistical region of at least one statistical region following the target statistical region along the movement direction of the target object.

[0098] When the target statistical region is a statistical region in which the change of at least one parameter in each statistical region is greater than or equal to the change threshold, this embodiment also provides a method for pre-adjusting the statistical region after the target statistical region in the direction of movement of the target object.

[0099] Specifically, the statistical region is determined after the target object's direction of movement. If there are multiple target objects within the statistical region, the statistical region can be determined either based on the direction of movement of the target object with the fastest movement speed, or based on the direction of movement of the target object with a speed greater than or equal to a preset speed threshold. This embodiment does not impose any restrictions on this.

[0100] After determining the statistical region following the direction of movement of the target object, the size and frequency of the statistical region are pre-adjusted. Specifically, the same method described above, such as the mathematical formula mentioned, can be used to calculate the size and frequency of the statistical region. Based on the calculated size and frequency of the statistical region, as well as its current size and frequency, a smoothing process is performed to obtain the final size and frequency of the statistical region.

[0101] In this embodiment, by pre-adjusting the statistical region following the target statistical region in the direction of the target object's movement, timely and rapid response to dynamic target objects can be achieved, improving the stability and timeliness of the target object's heat map.

[0102] S250. Based on the adjusted number of target objects in each statistical region, determine the target object heat map.

[0103] The specific method for determining the heat map has been described in the above embodiments, and will not be repeated here.

[0104] The technical solution of this embodiment determines the target object size, target object movement speed, and target object density for each statistical region. Based on these three data points, it comprehensively determines the size of the statistical region for the target statistical region. This improves the accuracy of target object counting within the statistical region, reduces computational load, enables timely response to dynamic changes in target objects, improves response efficiency, and effectively reflects the movement of target objects. Determining the statistical frequency based on the target object size and movement speed avoids the problem of cumulative counting saturation, allowing the target object heatmap to effectively reflect the distribution of target object numbers. After adjusting the size and frequency of the statistical region for the target statistical region, pre-adjustment is performed on the statistical regions following the target statistical region along the target object's movement direction. Adjusting the size and frequency of the statistical regions enables timely and rapid response to dynamic target objects, improving the stability and timeliness of the target object heatmap. Finally, the target object heatmap is generated based on the adjusted number of target objects in each statistical region.

[0105] Example 3

[0106] Figure 3 This is a schematic diagram of a device for determining the thermal map of a target object according to Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0107] The target object parameter determination module 310 is used to identify target objects in at least two statistical regions and determine target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical region.

[0108] The target statistical region adjustment module 320 is used to adjust the size and / or frequency of the target statistical region according to the target object parameters of each statistical region.

[0109] The target object heatmap determination module 330 is used to determine the target object heatmap based on the number of target objects in each statistical region after adjustment.

[0110] The technical solution of this invention identifies target objects in each statistical region, obtaining at least one target object parameter for each region: target object size, target object movement speed, and target object density. Based on these parameters, the size and / or frequency of the statistical regions are adjusted. Finally, a target object heatmap is determined based on the adjusted number of target objects in each statistical region. This solves the problems of spatial resolution versus accuracy, insufficient dynamic target response, and target object density accumulation saturation in existing heatmap determination methods. It achieves dynamic adjustment of the statistical region and frequency, optimizing the performance and accuracy of the target object heatmap.

[0111] Based on the above embodiments, optionally, when the target object parameter is the target object size, the target statistical region adjustment module 320 includes:

[0112] The first statistical region size adjustment unit is used to adjust the size of the statistical region of the target statistical region according to the size of the target object of each statistical region if the size of the target object of the target statistical region meets the statistical region adjustment conditions.

[0113] The size of the target object is directly proportional to the size of the statistical region; the larger the target object, the larger the size of the statistical region in which the target object is located.

[0114] Based on the above embodiments, optionally, when the target object parameter is the target object's movement speed, the target statistical region adjustment module 320 includes:

[0115] The statistical region size and / or statistical frequency adjustment unit is used to adjust the statistical region size and / or statistical frequency of the target statistical region according to the target object movement speed in each statistical region if the target object movement speed in the target statistical region meets the statistical region adjustment conditions.

[0116] The target object's movement speed is inversely proportional to the size of the statistical region; the greater the target object's movement speed, the smaller the size of the statistical region where the target object is located.

[0117] The target object's movement speed is directly proportional to the statistical frequency; the greater the target object's movement speed, the greater the statistical frequency of the statistical region where the target object is located.

[0118] Based on the above embodiments, optionally, when the target object parameter is the target object density of the statistical region, the target statistical region adjustment module 320 includes:

[0119] The second statistical region size adjustment unit is used to adjust the size of the statistical region of the target statistical region according to the target object density of each statistical region if the target object density of the target statistical region meets the statistical region adjustment conditions.

[0120] Specifically, when the target object density is greater than or equal to a preset density threshold, the target object density is inversely proportional to the size of the statistical region; the greater the target object density, the smaller the size of the statistical region corresponding to the target object density.

[0121] Based on the above embodiments, optionally, the target statistical area adjustment module 320 includes:

[0122] The statistical region size determination unit is used to determine the size of the target statistical region based on the mean and standard deviation of at least one target object parameter.

[0123] The statistical frequency determination unit is used to determine the statistical frequency of the target statistical region based on the size of the target object and / or the movement speed of the target object.

[0124] Based on the above embodiments, optionally, the statistical region size determination unit is specifically used for:

[0125] The size of the target statistical region can be determined using the following formula:

[0126]

[0127] Where R(t) represents the adjusted statistical region size, k is the scaling factor, A(t) represents the target object size at time t, v(t) represents the target object velocity at time t, and μ p P represents the average density of target objects in each statistical region. max δ represents the maximum target object density in each statistical region, x represents the weighting coefficient for target object size, and δ represents the maximum target object density in each statistical region. A μ represents the standard deviation of the target object size for each target object. A δ represents the average size of each target object, y represents the weighting coefficient of the target object's motion speed, and δ represents the average size of each target object. V μ represents the standard deviation of the velocity of each target object. V δ represents the average velocity of each target object, z represents the weighting coefficient of the target object density, and δ represents the average velocity of each target object. p This represents the standard deviation of the target object density in each statistical region.

[0128] The statistical frequency determination unit is specifically used for:

[0129] The statistical frequency of the target statistical region can be determined using the following formula:

[0130]

[0131] Where T(t) represents the adjusted statistical frequency, m represents the influence coefficient of the target object's movement speed on the statistical frequency, ΔV(t) represents the change in the target object's movement speed, and n represents the influence coefficient of the target object's size on the statistical frequency.

[0132] Optionally, based on the above embodiments, the device may further include:

[0133] The statistical region pre-adjustment module is used to adjust the size and / or frequency of at least one statistical region following the target statistical region along the movement direction of the target object, based on the target object parameters of the target statistical region.

[0134] The target object heat map determination device provided in the embodiments of the present invention can execute the target object heat map determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0135] Example 4

[0136] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0137] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0139] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining a heatmap of a target object.

[0140] In some embodiments, the method for determining the heatmap of a target object may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the heatmap of the target object described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the heatmap of the target object by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0146] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0147] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0148] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a heat map of a target object, characterized in that, include: Target object identification is performed on at least two statistical regions to determine target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical regions; Based on the target object parameters of each statistical region, adjust the size of the statistical region and / or the statistical frequency of the target statistical region; Based on the adjusted number of target objects in each statistical region, a heatmap of the target objects is determined.

2. The method according to claim 1, characterized in that, When the target object parameter is the target object size, the size of the statistical region of the target statistical region is adjusted according to the target object parameter of each statistical region, including: If the size of the target object in the target statistical region is determined to meet the statistical region adjustment conditions, then the size of the statistical region of the target statistical region is adjusted according to the size of the target object in each statistical region. The size of the target object is directly proportional to the size of the statistical region; the larger the target object, the larger the size of the statistical region in which the target object is located.

3. The method according to claim 1, characterized in that, When the target object parameter is the target object's movement speed, the size and / or frequency of the statistical region are adjusted according to the target object parameters of each statistical region, including: If the movement speed of the target object in the target statistical region is determined to meet the statistical region adjustment conditions, then the size and / or frequency of the statistical region of the target statistical region are adjusted according to the movement speed of the target object in each statistical region. The target object's movement speed is inversely proportional to the size of the statistical region; the greater the target object's movement speed, the smaller the size of the statistical region where the target object is located. The target object's movement speed is directly proportional to the statistical frequency; the greater the target object's movement speed, the greater the statistical frequency of the statistical region where the target object is located.

4. The method according to claim 1, characterized in that, When the target object parameter is the target object density of the statistical region, the size of the statistical region is adjusted according to the target object parameters of each statistical region, including: If the target object density of the target statistical region is determined to meet the statistical region adjustment conditions, then the size of the statistical region of the target statistical region is adjusted according to the target object density of each statistical region. Specifically, when the target object density is greater than or equal to a preset density threshold, the target object density is inversely proportional to the size of the statistical region; the greater the target object density, the smaller the size of the statistical region corresponding to the target object density.

5. The method according to claim 1, characterized in that, Based on the target object parameters of each statistical region, the size and / or frequency of the statistical region are adjusted, including: Determine the size of the target statistical region based on the mean and standard deviation of at least one target object parameter; And / or, determine the statistical frequency of the target statistical region based on the size of the target object and / or the movement speed of the target object.

6. The method according to claim 5, characterized in that, Determine the size of the target statistical region based on the mean and standard deviation of at least one target parameter, including: The size of the target statistical region can be determined using the following formula: Where R(t) represents the adjusted statistical region size, k is the scaling factor, A(t) represents the target object size at time t, v(t) represents the target object velocity at time t, and μ p P represents the average density of target objects in each statistical region. max δ represents the maximum target object density in each statistical region, x represents the weighting coefficient for target object size, and δ represents the maximum target object density in each statistical region. A μ represents the standard deviation of the target object size for each target object. A δ represents the average size of each target object, y represents the weighting coefficient of the target object's motion speed, and δ represents the average size of each target object. V μ represents the standard deviation of the velocity of each target object. V δ represents the average velocity of each target object, z represents the weighting coefficient of the target object density, and δ represents the average velocity of each target object. p The standard deviation of the target object density in each statistical region; The statistical frequency of the target statistical region is determined based on the size of the target object and / or the speed of the target object's movement within the target statistical region, including: The statistical frequency of the target statistical region can be determined using the following formula: Where T(t) represents the adjusted statistical frequency, m represents the influence coefficient of the target object's movement speed on the statistical frequency, ΔV(t) represents the change in the target object's movement speed, and n represents the influence coefficient of the target object's size on the statistical frequency.

7. The method according to claim 1, characterized in that, After adjusting the size of the statistical region and / or the statistical frequency of the target statistical region, the following is also included: Based on the target object parameters of the target statistical region, the size and / or frequency of the statistical region of at least one statistical region following the target statistical region along the direction of movement of the target object are adjusted.

8. A device for determining a heat map of a target object, characterized in that, include: The target object parameter determination module is used to identify target objects in at least two statistical regions and determine target object parameters, wherein the target object parameters include at least one of the following: target object size, target object movement speed, and target object density in the statistical region; The target statistical region adjustment module is used to adjust the size and / or frequency of the target statistical region based on the target object parameters of each statistical region. The target object heatmap determination module is used to determine the target object heatmap based on the number of target objects in each statistical region after adjustment.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for determining the heat map of the target object as described in any one of claims 1-7.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the method for determining the heat map of the target object as described in any one of claims 1-7.

Images