Energy use efficiency evaluation method in ibms based on image recognition

Abstract

The present application relates to the field of image processing, and it relates to an energy use efficiency evaluation method in IBMS based on image recognition, which solves the problem that the traditional static energy efficiency evaluation is disconnected with the actual dynamic human consumption. The method comprises the following steps: synchronously collecting floor energy consumption power and image data; calculating camera area stability weight (first weight) based on image change pixel fluctuation; extracting personnel distribution through frame difference and connected domain clustering, and generating density weight (second weight) according to the reciprocal of the average distance between geometric centers of classes; verifying and excluding noise by using the continuity of the positions of classes in front and back frames, and determining the flow weight (third weight) by the effective personnel pixel ratio; fusing the three weights and calculating dynamic energy consumption parameters in real time by using real-time energy consumption; and judging the energy efficiency rationality by the variance fluctuation of the parameters. The present application realizes the accurate evaluation of the dynamic correlation between human and energy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, and in particular to an IBMS energy use efficiency evaluation method based on image recognition. BACKGROUND

[0002] With the rapid development of smart cities and green buildings, intelligent building management systems (IBMS) have become the core platform for modern building energy management. By integrating key energy-consuming systems such as HVAC, lighting, and elevators, IBMS realizes real-time data collection and intelligent control of multi-source data, and is widely used in high-energy-consuming buildings such as commercial complexes and hospitals. Intelligent management not only optimizes equipment operation efficiency, but also significantly reduces energy waste through data-driven decision support systems, providing important technical support for implementing the "double carbon" goal.

[0003] However, traditional energy management methods have obvious limitations. Although IBMS can accurately monitor the energy consumption data of individual devices, the evaluation system based on static energy efficiency indicators (such as EUI) cannot fully reflect the overall building energy use efficiency (EUE). Relying solely on historical data or fixed benchmark values for evaluation often leads to significant deviations between energy efficiency analysis results and actual conditions, making it difficult to provide accurate guidance for energy-saving optimization.

[0004] To address this key issue, the present method collects real-time energy use parameters through IBMS, including the operating status and energy consumption data of each subsystem, and calculates the current actual energy consumption. At the same time, image processing is performed on the images obtained by the camera to obtain people flow data, establishing a relationship between the crowd situation and the corresponding power at the moment, and realizing real-time quantitative evaluation of building energy efficiency. SUMMARY

[0005] The present application provides an IBMS energy use efficiency evaluation method based on image recognition to address the existing problem that existing IBMS relies on historical data or fixed benchmarks for evaluation, resulting in significant deviations between analysis results and actual conditions.

[0006] The IBMS energy use efficiency evaluation method based on image recognition of the present application adopts the following technical solutions:

[0007] In the first aspect of the present application, an IBMS energy use efficiency evaluation method based on image recognition is provided, which includes the following steps:

[0008] Real-time collection of energy use power data at different times on different floors through the IBMS system, while the camera system collects images of the corresponding floors at the same time, and then performs time alignment traversal processing on the synchronously collected power data and image data;

[0009] According to the fluctuation size of the number of pixel points of the image collected by different cameras on different floors, the first weight of all images collected by each camera is calculated;

[0010] According to the change position of the pixel points in the previous frame of each image collected by different cameras on different floors, all suspected personnel pixel point clusters are obtained, the suspected personnel density parameters of each image are obtained according to the distance distribution of the suspected personnel pixel point clusters in each image, and the suspected personnel density parameters of each image are recorded as the second weight of each image;

[0011] According to the position change of the suspected personnel pixel point clusters of each image and its previous and subsequent frame images collected by different cameras on different floors, the suspected noise pixel point clusters are excluded, the personnel pixel point clusters of each image are obtained, and the third weight of each image is obtained according to the proportion of the number of pixel points in the suspected personnel pixel point clusters in each image to the total number of image pixel points;

[0012] The energy consumption parameters of each floor at each time are obtained by combining the first weight, the second weight and the third weight of all images of each floor at each time with the energy consumption power of each floor at each time;

[0013] According to the fluctuation degree of the energy consumption parameters of each floor at each time, whether the energy use efficiency of each floor is reasonable is judged.

[0014] Further, the energy use power data of different floors at different times is collected in real time through the IBMS system, at the same time, the camera system collects the images of the corresponding floor at the same time, and then the synchronous collected power data and image data are subjected to time alignment traversal processing, and the specific method includes:

[0015] For F floors, all cameras of each floor, every U seconds, simultaneously take one image, each camera takes T images and is grayed, at the same time of taking, the energy consumption output power of each floor is collected, the unit is kW / h, the collected images are triple-iterated according to the floor and the camera sequence distributed on each floor and the image collection sequence, and the collected energy consumption output power is double-iterated according to the corresponding floor and the collection time sequence.

[0016] Further, the first weight of all images collected by each camera is calculated according to the fluctuation size of the number of pixel points of the image collected by different cameras on different floors, and the specific method includes:

[0017] When there is no one in the coverage area of each camera in the floor, each camera collects one image, and the image collected by each camera is recorded as the reference image of each camera. The number of pixel points with a changed gray value exceeding v in each image is recorded by comparing each image with the reference image of the corresponding camera. The variance of the number of pixel points with a changed gray value exceeding v in all images captured by each camera is calculated. The first weight of all images captured by each camera in each floor is calculated according to the variance corresponding to each camera in each floor. The specific formula is as follows:

[0018]

[0019] In the formula, indicates the first weight of all images captured by the cth camera in the fth floor, indicates the number of cameras in the fth floor, indicates the variance of the number of pixel points with a changed gray value exceeding v in each image captured by the cth camera in the fth floor, indicates the variance of the number of pixel points with a changed gray value exceeding v in each image captured by the jth camera in the fth floor.

[0020] Further, the suspected personnel pixel point clusters are obtained according to the changed positions of pixel points in the previous frame of each image collected by different cameras in different floors. The suspected personnel density parameter of each image is obtained according to the distance distribution of the suspected personnel pixel point clusters in each image, and the suspected personnel density parameter of each image is recorded as the second weight of each image. The specific method includes:

[0021] For the T frames of images of the cth camera in the fth floor traversed in time sequence, each frame is differentiated with the previous frame to detect the pixel points with a changed gray value and mark them as unallocated, except for the first frame. Starting from the top left corner of the image, raster scanning is performed. When an unallocated changed pixel point is encountered: take this point as the seed point of the current class and mark it as allocated. Check the 8-neighborhood of the point. For each unallocated changed pixel point in the 8-neighborhood, recursively repeat the above process by taking it as a new seed point. When there is no unallocated changed point in the 8-neighborhood of a point, backtracking is ended. At this time, all marked pixel points constitute a connected changed region, which is recorded as a class of pixel points. Continue to scan the image and repeat the process for the remaining unallocated changed points until all pixel points are scanned. The distribution position and number of pixel points of the class in the second frame of image are assigned to the first frame of image.

[0022] After all the labels in the image are completed, the geometric center of each class is calculated, and then the Euclidean distance from the geometric center of each class to the geometric center of all other classes in the image is calculated, and the arithmetic mean of these distances is calculated to obtain the average distance of the class, and the arithmetic mean of the average distances of all classes is calculated to obtain the average distance per person of the image, and the density of each image is obtained as the second weight of each image according to the average distance per person of each image, and the specific method is as follows:

[0023]

[0024] In the formula, is the second weight of the tth image of the fth floor and the cth camera, is the average distance per person of the tth image of the fth floor and the cth camera.

[0025] Further, the position change of the suspected personnel pixel point cluster of each image collected by different floors and different cameras and the previous and subsequent frame images is used to exclude suspected noise pixel point clusters, obtain the personnel pixel point cluster of each image, and obtain the third weight of each image according to the proportion of the number of pixel points in the suspected personnel pixel point cluster of each image to the total number of pixel points in the image, and the specific method is as follows:

[0026] For the tth image collected by the cth camera of the fth floor, the time position is verified: only when the pixel space range of the class contains the geometric center of at least one class in the adjacent effective frame, the class is retained in the final result, and the specific rule is: if t is the first frame, at least one class geometric center in the next frame is required; if t is the last frame, at least one class geometric center in the previous frame is required; if t is the middle frame, at least one class geometric center in the previous frame and the next frame is required, finally, only the classes that pass the above verification are retained in the tth frame image, and the classes that do not meet the conditions are removed, and each image is processed according to the above rule, and the third weight of each image is obtained according to the ratio of the number of pixel points in the retained class to the total number of pixel points in each image, and the specific method is as follows:

[0027]

[0028] The third weight of the tth image of the cth camera of the fth floor is represented, and Count() represents the number of pixel points, The i th class in the tth image of the cth camera of the fth floor is represented, The number of classes in the tth image of the cth camera of the fth floor is represented, The tth image of the cth camera of the fth floor is represented.

[0029] Further, the first weight, the second weight and the third weight of all images of each floor at each time are combined with the energy consumption power of each floor at each time to obtain the energy consumption parameter of each floor at each time, and the specific method comprises:

[0030]

[0031] In the formula, The energy consumption parameter of the fth floor at the tth time is represented, The number of cameras of the fth floor is represented, The first weight of all images shot by the cth camera of the fth floor is represented, The second weight of the tth image of the cth camera of the fth floor is represented, The third weight of the tth image shot by the cth camera of the fth floor is represented, The energy consumption power of the fth floor at the tth time is represented.

[0032] Further, the energy consumption parameter of each floor at each time is used to determine whether the energy use efficiency of each floor is reasonable, and the specific method comprises:

[0033] The variance of the energy consumption parameter of the fth floor at all times is calculated as an evaluation basis for the energy use efficiency, and a threshold value K is set according to historical statistical data analysis, when the variance of the energy consumption parameter of the fth floor is greater than the threshold value K, it is considered that the energy use condition is unreasonable, and when the variance of the energy consumption parameter of the fth floor is less than or equal to the threshold value K, it is considered that the energy use condition is reasonable.

[0034] In the second aspect of the present application, an energy use efficiency evaluation system based on image recognition in an IBMS is provided, which comprises a data acquisition module, a first weight calculation module, a second weight calculation module, a third weight calculation module, an energy consumption parameter calculation module and an energy consumption judgment module, wherein:

[0035] The data acquisition module is used to acquire the energy use power data of different floors at different times in real time through the IBMS system, at the same time, the camera system acquires the images of the corresponding floors at the same time, and then the synchronous acquired power data and image data are subjected to time alignment traversal processing;

[0036] The first weight calculation module is used to calculate the first weight of all images collected by each camera according to the fluctuation size of the number of pixel points of the images collected by different floors and different cameras;

[0037] A second weight calculation module is configured to obtain all suspected personnel pixel clusters according to the changed positions of the pixel points in the previous frame of each image collected by different cameras on different floors, obtain a suspected personnel density parameter of each image according to the distance distribution of the suspected personnel pixel clusters in each image, and record the suspected personnel density parameter of each image as a second weight of each image.

[0038] A third weight calculation module is configured to exclude suspected noise pixel clusters according to the position changes of the suspected personnel pixel clusters in each image and the previous and subsequent frame images of the image collected by different cameras on different floors, obtain personnel pixel clusters of each image, and obtain a third weight of each image according to the proportion of the number of pixel points in the suspected personnel pixel clusters in each image in the total number of pixel points in the image.

[0039] An energy consumption parameter calculation module is configured to obtain an energy consumption parameter of each floor at each time according to the first weight, the second weight and the third weight of all images of each floor at each time and the energy consumption power of each floor at each time.

[0040] An energy consumption judgment module is configured to judge whether the energy use efficiency of each floor is reasonable according to the fluctuation degree of the energy consumption parameter of each floor at each time.

[0041] In a third aspect of the present application, a computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above-mentioned energy use efficiency evaluation method in an IBMS based on image recognition.

[0042] In a fourth aspect of the present application, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned energy use efficiency evaluation method in an IBMS based on image recognition when executing the computer program.

[0043] The technical scheme of the present application has the following beneficial effects:

[0044] The accurate space-time alignment of images and energy consumption data is realized through triple iteration, the time sequence deviation in collection is eliminated, and the reliability of human-energy dynamic correlation analysis is ensured.

[0045] The weight is assigned based on the reciprocal of the variance of the changed pixels, the evaluation contribution of the stable area of personnel activity is strengthened, the influence of sudden interference is weakened, and the robustness of regional energy consumption evaluation is improved.

[0046] The spatial distribution density is quantified by using connected domain clustering and inter-class geometric distance, the distribution blind area of traditional total quantity statistics is solved, and the differential needs of the aggregation effect on energy consumption are accurately reflected.

[0047] Through cross-frame class geometric center continuity verification, transient noise such as flying insects, light and shadow shaking is effectively filtered out, and physical authenticity of the personnel scale parameter (the third weight) is ensured.

[0048] The dynamic energy consumption parameter is constructed by fusing the triple weights, space density, personnel scale and regional stability are uniformly modeled, and precise quantification of the energy consumption intensity of unit people flow is realized. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0050] Figure 1 A step flow chart of an energy use efficiency evaluation method in an IBMS based on image recognition according to the present application;

[0051] Figure 2 A structural block diagram of an energy use efficiency evaluation system in an IBMS based on image recognition according to the present application. DETAILED DESCRIPTION

[0052] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following describes the specific implementation, structure, features and effects of the energy use efficiency evaluation method in an IBMS based on image recognition according to the present application in detail in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0054] The specific scheme of the energy use efficiency evaluation method in an IBMS based on image recognition provided by the present application is specifically described below in combination with the drawings.

[0055] Please refer to Figure 1 which shows the first object of the present application, a step flow chart of an energy use efficiency evaluation method in an IBMS based on image recognition, which comprises the following steps:

[0056] Step S001: Collect the energy use power data of different floors at different times through the IBMS system in real time, and at the same time, the camera system collects the images of the corresponding floors at the same time. Then, the power data and image data collected synchronously are processed by time alignment traversal.

[0057] To solve the core problem that the static indicators in traditional IBMS energy evaluation are inconsistent with the actual dynamic human consumption (such as the inability to capture the energy consumption changes caused by instantaneous flow fluctuations), this method uses hardware-level space-time alignment collection: at the same time when the IBMS records the power consumption of the floor, all cameras on the floor are triggered to take images synchronously. This ensures that the energy consumption data is strictly bound to the spatial flow of people, laying a space-time consistent data foundation for subsequent construction of a "person-energy" dynamic mapping model (including image change analysis, weight calculation, and energy consumption parameter generation), thereby overcoming historical benchmarking bias and achieving real-time and accurate energy efficiency evaluation.

[0058] Specifically, the energy use power data of different floors at different times is collected through the IBMS system in real time, and at the same time, the camera system collects the images of the corresponding floors at the same time. Then, the power data and image data collected synchronously are processed by time alignment traversal, the specific method is as follows:

[0059] For F floors, all cameras on each floor, every U seconds take a picture, each camera takes T pictures and is grayed, at the same time of shooting, collect the energy consumption output power of each floor, unit: kW / h, collect the images according to the floor and the sequence of cameras distributed on each floor and the image collection order, and the collected energy consumption output power is also double-iterated according to the corresponding floor and collection time sequence.

[0060] It should be noted that in this embodiment, the number of floors F = 18, the image shooting interval U = 1 second, and each camera takes T = 28800 images. The present application does not limit the number of floors F, the image shooting interval U, and the number of images taken by each camera. The number of floors, the image shooting interval, and the number of images taken by each camera in other embodiments are determined according to the implementation.

[0061] Step S002: According to the fluctuation size of the number of changed pixel points in the images collected by different floors and different cameras, calculate the first weight of all images collected by each camera.

[0062] It should be noted that in step S001, a series of region images arranged in time sequence and the corresponding power at the time are obtained. Next, in order to facilitate the evaluation of energy use, a function of crowd change (based on crowd density and flow) and instantaneous power is constructed to evaluate energy use.

[0063] Further need to be explained is that, since the fluctuation range of the human flow is negatively correlated with the reliability of the energy evaluation: the greater the variance, the more unstable the personnel activities in the region (such as sudden gathering / dispersion), and the correlation between the pixel changes and the energy consumption caused thereby is difficult to accurately quantify, resulting in a decrease in the applicability of the evaluation. In order to preferentially use reliable region data with stable personnel flow, the operation assigns weights through variance reciprocal normalization, so that low-fluctuation regions (such as regular activities in office areas) obtain higher weights, while high-fluctuation regions (such as temporary activity areas) automatically attenuate the weights, ensuring that the energy consumption evaluation relies on strong predictability of the baseline scene.

[0064] Specifically, according to the fluctuation size of the number of pixel points that change in the images collected by different cameras on different floors, the first weight of all images collected by each camera is calculated, and the specific method is as follows:

[0065] When there is no one in the coverage area of each camera on the floor, each camera collects one image, and the image collected by each camera is recorded as the baseline image of each camera. By comparing each image with the baseline image of the corresponding camera, the number of pixel points with a changed gray value and a changed gray value exceeding v in each image is recorded, the variance of the number of pixel points with a changed gray value exceeding v in all images taken by each camera is calculated, and the first weight of all images taken by each camera on each floor is calculated according to the variance corresponding to each camera on each floor. The specific formula is as follows:

[0066]

[0067] In the formula, Wf,c represents the first weight of all images taken by the cth camera on the fth floor, Nf represents the number of cameras on the fth floor, σf,c represents the variance of the number of pixel points with a changed gray value exceeding v in each image taken by the cth camera on the fth floor, σf,j represents the variance of the number of pixel points with a changed gray value exceeding v in each image taken by the jth camera on the fth floor.

[0068] It should be noted that the greater the variance, the greater the fluctuation range of the human flow, indicating that the environmental change in the region is more significant, and the applicability of the energy use evaluation is lower. Therefore, the reliability of the evaluation result decreases, and a lower weight should be given in comprehensive consideration, and vice versa, is calculated according to According to the change position of the pixel points in the previous frame of each image collected by different cameras on different floors, all suspected personnel pixel point clusters are obtained, and according to the distance distribution of the suspected personnel pixel point clusters in each image, a suspected personnel density parameter of each image is obtained, and the suspected personnel density parameter of each image is recorded as a second weight of each image.

[0069] Step S003: According to the change position of the pixel points in the previous frame of each image collected by different cameras on different floors, all suspected personnel pixel point clusters are obtained, and according to the distance distribution of the suspected personnel pixel point clusters in each image, a suspected personnel density parameter of each image is obtained, and the suspected personnel density parameter of each image is recorded as a second weight of each image.

[0070] It should be noted that the traditional image analysis method only relies on the total amount of changed pixels to evaluate the crowd density, and ignores the key influence of personnel spatial distribution form on energy consumption. Since the influence of dense distribution (such as conference scene) and scattered distribution (such as corridor walking) on regional heat load / lighting demand is significantly different, the inter-class geometric distance is introduced as the core index of distribution density in the operation: by calculating the average Euclidean distance (distance per person) of the geometric centers of all connected regions in the image, the smaller the value, the higher the degree of spatial aggregation of personnel in the region, and the more concentrated the energy consumption demand per unit area. Therefore, the spatial density weight is quantified in an inverse relationship, so that high aggregation areas have stronger representation.

[0071] It should be further noted that by quantifying the crowd distribution density in the space, a more accurate energy consumption evaluation method can be established. The higher the density of the region, the higher the energy required per unit area, and its theoretical allocation weight should be increased by the same proportion; otherwise, low-density areas need to compress redundant quotas. Based on this, the crowd density of each floor is calculated in this step.

[0072] Specifically, according to the change position of the pixel points in the previous frame of each image collected by different cameras on different floors, all suspected personnel pixel point clusters are obtained, and according to the distance distribution of the suspected personnel pixel point clusters in each image, a suspected personnel density parameter of each image is obtained, and the suspected personnel density parameter of each image is recorded as a second weight of each image, and the specific method is as follows:

[0073] For the T frame images of the fth floor and the cth camera in chronological order, each frame is different from the previous frame, the pixel points with gray value changes are detected and marked as unassigned, except for the first frame; starting from the top left corner of the image, raster scanning is performed, and when an unassigned changing pixel point is encountered: this point is taken as the seed point of the current category and marked as assigned; the 8-neighborhood of the point is checked, and for each unassigned changing pixel point in the 8-neighborhood, the above process is repeated recursively by taking it as a new seed point, and when there is no unassigned changing point in the 8-neighborhood of a point, the backtracking ends, at this time all the marked pixel points constitute a connected changing region, which is recorded as a class of pixel points, the image is continuously scanned, and the above process is repeated for the remaining unassigned changing points until all the pixel points are scanned, and the class of pixel points of the second frame image is assigned to the first frame image;

[0074] After all the labels in the image are completed, the geometric center of each class is calculated, then each class is traversed, the Euclidean distance from its geometric center to the geometric centers of all other classes in the image is calculated, and the arithmetic mean of these distances is calculated to obtain the average distance of the class, and the average distance of all classes is calculated again to obtain the average distance per person of the image, and the density of each image is obtained according to the average distance per person of each image as the second weight of each image, and the specific method is as follows:

[0075]

[0076] In the formula, is the second weight of the tth image of the fth floor and the cth camera, is the average distance per person of the tth image of the fth floor and the cth camera.

[0077] It should be noted that the indoor crowd density changes with the average distance per person in a linearly related form, and the density increases when the average distance per person decreases.

[0078] Step S004: According to the position change of the suspected personnel pixel point cluster of each image collected by different floors and different cameras and the front and rear frame images, the suspected noise pixel point cluster is excluded, the personnel pixel point cluster of each image is obtained, and the third weight of each image is obtained according to the proportion of the number of pixel points in the suspected personnel pixel point cluster of each image to the total number of pixel points of the image.

[0079] It should be noted that in the previous step, the crowd density of each image (second weight) has been calculated, in order to more reasonably calculate the crowd change, the crowd flow of each image is calculated in this step, which can more reasonably calculate the energy consumption demand.

[0080] Further need to be explained is that in a dynamic scene, pixel changes caused by transient interference (such as light flickering, flying insects passing by) will form false "classes", mixed with real person moving classes, resulting in distortion of the density parameter (the second weight). To eliminate such noise, the present operation utilizes the spatiotemporal continuity characteristic of real person moving: the position change of a real target between adjacent frames has continuity (trajectory smoothness), and the geometric center thereof will not mutate within a short time interval. Therefore, by verifying whether the pixel region of the current frame class contains the geometric center of the adjacent frame class, isolated noise classes can be filtered out, and the third weight (crowd flow situation) is ensured to be calculated only on the basis of persistent person activity.

[0081] Specifically, according to the position change of the suspected person pixel point cluster of each image collected by different floors and different cameras and the previous and subsequent frame images, the suspected noise pixel point cluster is excluded, the person pixel point cluster of each image is obtained, and the third weight of each image is obtained according to the proportion of the number of pixel points in the suspected person pixel point cluster of each image to the total number of pixel points of the image, including the specific method:

[0082] For the tth image collected by the cth camera on the fth floor, the time position is verified: only when the pixel space range of the class contains the geometric center of at least one class in the adjacent effective frame, the class is retained in the final result, and the specific rule is: if t is the first frame, it needs to contain the geometric center of at least one class in the next frame; if t is the last frame, it needs to contain the geometric center of at least one class in the previous frame; if t is an intermediate frame, it must contain the geometric center of at least one class in the previous frame and the next frame, finally, only the classes that pass the above verification are retained in the tth frame image, and the classes that do not meet the conditions will be removed, according to the rule, each image is processed, and the third weight of each image is obtained according to the ratio of the number of pixel points in the retained classes of each image to the number of all pixel points of each image, and the specific method is as follows:

[0083]

[0084] In the formula, W3(f,c,t) represents the third weight of the tth image of the cth camera on the fth floor, Count() represents the number of extracted pixel points, represents the i th class in the t th image of the c th camera on the f th floor, represents the number of classes of the tth image of the cth camera on the fth floor, represents the tth image of the cth camera on the fth floor.

[0085] It should be noted that the flow degree of the image at the time point can be quantified by calculating the proportion of pixels changed between adjacent frames in the total pixels. The flow degree index, as a key parameter representing the intensity of crowd dynamic activity, will be included in the subsequent energy consumption evaluation model.

[0086] Step S005: Obtain the energy consumption parameter of each floor at each time point by combining the first weight, the second weight and the third weight of all images of each floor at each time point with the energy consumption power of each floor at each time point.

[0087] It should be noted that the traditional energy consumption evaluation does not decouple the differential effects of personnel spatial distribution form, regional stability and absolute scale on energy consumption, resulting in distortion of key signals; this operation solves this defect by cooperating with the three weights: the spatial density weight captures the aggregation effect, the personnel scale enhancement quantifies the absolute personnel base, and the regional reliability weight suppresses high fluctuation noise; after the three are coupled in multiplication, the normalized parameter is generated by dividing the real-time power to realize the precise modeling of "unit flow momentum energy consumption intensity".

[0088] Specifically, the energy consumption parameter of each floor at each time point is obtained by combining the first weight, the second weight and the third weight of all images of each floor at each time point with the energy consumption power of each floor at each time point, and the specific method includes:

[0089]

[0090] In the formula, represents the energy consumption parameter of the fth floor at the tth time point, represents the number of cameras of the fth floor, represents the first weight of all images taken by the cth camera of the fth floor, is the second weight of the tth image of the cth camera of the fth floor, represents the third weight of the tth image taken by the cth camera of the fth floor, represents the energy consumption power of the fth floor at the tth time point.

[0091] It should be noted that because is very small, in order to avoid over-influencing the energy consumption parameter, 1 is added to when multiplying to avoid the value of being too small to have too much influence on the energy consumption parameter.

[0092] Step S006: Determine whether the energy use efficiency of each floor is reasonable according to the fluctuation degree of the energy consumption parameter of each floor at each time point.

[0093] It's important to note that traditional energy efficiency assessments rely on static thresholds (e.g., fixed energy consumption caps) and fail to distinguish reasonable fluctuations (e.g., cyclical changes in foot traffic) from abnormal, uncontrolled fluctuations (e.g., energy efficiency degradation caused by equipment failure). This approach is based on the principle of dynamic stability of energy consumption parameters: when a building is operating healthily, energy consumption per unit of foot traffic should be stable (i.e., the variance of energy consumption parameters is small), while abnormalities manifest as wild fluctuations in parameters (e.g., high energy consumption when no one is in the building due to air conditioning failure). Therefore, by calculating the time-series variance of energy consumption parameters and comparing it with K, we transform this volatility into a quantifiable criterion for energy efficiency rationality.

[0094] Specifically, the energy efficiency of each floor is judged to be reasonable based on the fluctuation degree of the energy consumption parameters of each floor at each moment. The specific methods include:

[0095] The variance of the energy consumption parameters of the f-th floor at all times is calculated as the basis for evaluating energy utilization efficiency. The threshold K is set based on historical statistical data analysis. When the variance of the energy consumption parameters of the f-th floor is greater than the threshold K, the energy utilization is considered unreasonable. When the variance of the energy consumption parameters of the f-th floor is less than or equal to the threshold K, the energy utilization is considered reasonable.

[0096] It should be noted that the energy consumption changes in IBMS should be consistent with the changes in the population. The population situation at each moment can be compared with the current power to obtain a series of values. The smaller and more stable the change in this value is, the more reasonable the energy use is. Due to the differences in building areas and population densities, this embodiment only selects the value of the threshold K based on the historical fluctuations of the energy consumption parameter. In this embodiment, The present invention does not specifically limit the value of the threshold K. In other embodiments, the value of the threshold K depends on the specific implementation situation.

[0097] See also Figure 2 , which shows the second object of the present invention, a structural block diagram of an energy efficiency evaluation system in IBMS based on image recognition, the system includes the following modules:

[0098] The data acquisition module is used to collect energy usage power data of different floors at different times in real time through the IBMS system. At the same time, the camera system collects images of the corresponding floors at the same time. These synchronously collected power data and image data are then time-aligned and processed;

[0099] A first weight calculation module is used to calculate a first weight of all images collected by each camera according to the fluctuation of the number of pixels that change in the images collected by different cameras on different floors;

[0100] The second weight calculation module is configured to obtain all suspected personnel pixel clusters according to the change positions of the pixel points in the previous frame of each image collected by different cameras on different floors, obtain a suspected personnel density parameter of each image according to the distance distribution of the suspected personnel pixel clusters in each image, and record the suspected personnel density parameter of each image as a second weight of each image.

[0101] The third weight calculation module is configured to exclude suspected noise pixel clusters according to the position changes of the suspected personnel pixel clusters in each image and the previous and subsequent frame images of the image collected by different cameras on different floors, obtain personnel pixel clusters of each image, and obtain a third weight of each image according to the proportion of the number of pixel points in the suspected personnel pixel clusters in each image in the total number of pixel points in the image.

[0102] The energy consumption parameter calculation module is configured to obtain an energy consumption parameter of each floor at each moment by combining the first weight, the second weight and the third weight of all images of each floor at each moment and the energy consumption power of each floor at each moment.

[0103] The energy consumption judgment module is configured to judge whether the energy use efficiency of each floor is reasonable according to the fluctuation degree of the energy consumption parameter of each floor at each moment.

[0104] A third object of the embodiments of the present application is to provide a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned energy use efficiency evaluation method in an IBMS based on image recognition when executing the computer program.

[0105] A fourth object of the embodiments of the present application is to provide a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the above-mentioned energy use efficiency evaluation method in an IBMS based on image recognition when executed by a processor.

[0106] The present application has the following beneficial effects:

[0107] The accurate space-time alignment of images and energy consumption data is realized through triple iteration, the time sequence deviation in collection is eliminated, and the reliability of human-energy dynamic correlation analysis is ensured.

[0108] The weight is allocated based on the reciprocal of the variance of the changed pixels, the evaluation contribution of the stable area of personnel activity is strengthened, the influence of sudden interference is weakened, and the robustness of regional energy consumption evaluation is improved.

[0109] The spatial distribution density is quantified by using connected domain clustering and inter-class geometric distance, the distribution blind area of traditional total quantity statistics is solved, and the differential needs of the aggregation effect on energy consumption are accurately reflected.

[0110] Through cross-frame class geometric center continuity verification, transient noise such as flying insects, light and shadow tremor is effectively filtered out, and physical authenticity of the personnel scale parameter (the third weight) is ensured.

[0111] The dynamic energy consumption parameter is constructed by fusing the triple weight, space density, personnel scale and regional stability are uniformly modeled, and precise quantification of the unit people flow momentum energy consumption intensity is realized.

[0112] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0113] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the flow Figure 1 The function specified in one or more flows and / or blocks. Figure 1 The means for performing the function specified in one or more flows and / or blocks.

[0114] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flow Figure 1 The function specified in one or more flows and / or blocks. Figure 1 The means for performing the function specified in one or more flows and / or blocks.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the flow Figure 1 The function specified in one or more flows and / or blocks. Figure 1 The means for performing the function specified in one or more flows and / or blocks.

[0116] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for evaluating energy efficiency in IBMS based on image recognition, characterized in that: The method comprises the following steps: The IBMS system collects energy usage power data on different floors at different times in real time. Simultaneously, the camera system captures images of the corresponding floors at exactly the same time. These synchronously collected power data and image data are then time-aligned and processed. Calculate the first weight of all images collected by each camera based on the fluctuation in the number of pixels that change in the images collected by different cameras on different floors; Based on the change position of the pixel points in the previous frame of each image captured by different cameras on different floors, all suspected person pixel point clusters are obtained. Based on the distance distribution of the suspected person pixel point clusters in each image, the suspected person density parameter of each image is obtained, and the suspected person density parameter of each image is recorded as the second weight of each image; Based on the position changes of the suspected person pixel clusters in each image captured by different cameras on different floors and the images before and after it, the suspected noise pixel clusters are excluded to obtain the person pixel clusters of each image. The third weight of each image is obtained based on the number of pixels in the suspected person pixel cluster and the ratio of the total number of pixels in the image. Combining the first weight, the second weight, and the third weight of all images on each floor at each moment with the energy consumption power of each floor at each moment, to obtain the energy consumption parameter of each floor at each moment; Whether the energy utilization efficiency of each floor is reasonable is judged based on the fluctuation degree of the energy consumption parameters of each floor at each moment.

2. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The IBMS system collects energy usage power data of different floors at different times in real time. At the same time, the camera system collects images of the corresponding floors at exactly the same time. The synchronously collected power data and image data are then time-aligned and processed. The specific method includes: For F floors, all cameras on each floor simultaneously capture an image every U seconds. Each camera captures T images and converts them to grayscale. At the same time, the energy output power of each floor is collected in kW / h. The collected images are traversed three times according to the floor, the camera sequence distributed on each floor, and the image collection order. The collected energy output power is also traversed twice according to the corresponding floor and collection time sequence.

3. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The specific method of calculating the first weight of all images collected by each camera according to the fluctuation of the number of pixels changed in the images collected by different cameras on different floors is as follows: When there is no one in the area covered by each camera on a floor, each camera captures an image. The image captured by each camera is recorded as the baseline image of each camera. Each image is compared with the baseline image of its corresponding camera. The number of pixels in each image whose grayscale value changes and the grayscale value change exceeds v is recorded. The variance of the number of pixels in all images captured by each camera whose grayscale value changes by more than v is calculated. The first weight of all images captured by each camera on each floor is calculated based on the variance corresponding to each camera on each floor. The specific formula is as follows: Where, represents the first weight of all images taken by the c-th camera on the f-th floor, represents the number of cameras on the f-th floor, represents the variance of the number of pixels whose grayscale value changes by more than v in each image taken by the c-th camera on the f-th floor, It represents the variance of the number of pixels whose grayscale value changes by more than v in each image taken by the j-th camera on the f-th floor.

4. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The method of obtaining the clustering of all suspected person pixel points based on the changed positions of the pixel points in the previous frame of each image captured by different cameras on different floors, obtaining the suspected person density parameter of each image based on the distance distribution of the suspected person pixel point clusters in each image, and recording the suspected person density parameter of each image as the second weight of each image includes the following specific methods: For the T-frame images traversed by the c-th camera in the f-th layer in time sequence, each frame is differentiated from the previous frame, and the pixels with changed grayscale values ​​are detected and marked as unassigned, except for the first frame; raster scanning starts from the upper left corner of the image. When an unassigned changed pixel is encountered: this point is used as the seed point of the current category and marked as assigned; the 8-neighborhood of the point is checked, and for each unassigned changed pixel in it, the above process is recursively repeated as a new seed point. When there is no unassigned changed point in the 8-neighborhood of a certain point, the backtracking ends. At this time, all the marked pixels constitute a connected change area, which is recorded as a class of pixels. The image is scanned continuously, and this process is repeated for the remaining unassigned changed points until all pixels are scanned. The pixel distribution position and number of the class of the second frame image are assigned to the first frame image; After completing all the markings in the image, calculate the geometric center of each class. Then, traverse each class and calculate the Euclidean distance from its geometric center to the geometric centers of all other classes in the image. Then calculate the arithmetic mean of these distances to get the average distance of the class. The arithmetic mean of the average distance of all classes is calculated again to get the average distance per person of the image. According to the average distance per person of each image, the density of each image is obtained as the second weight of each image. The specific method is as follows: Where, is the second weight of the t-th image of the c-th camera in the f-th layer, is the average distance per person in the t-th image of the c-th camera in the f-th layer.

5. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The method of obtaining the person pixel clusters of each image captured by different cameras on different floors and the previous and next frames based on the position changes of the suspected person pixel clusters and the suspected noise pixel clusters is eliminated, and the third weight of each image is obtained based on the number of pixels in the suspected person pixel clusters of each image and the ratio of the total number of pixels in the image. The specific method includes: For the t-th image captured by the c-th camera on the f-th floor, verification is performed based on its time position: only when the pixel space range of the class contains the geometric center of at least one class in the adjacent valid frame, the class is retained in the final result. The specific rule is: if t is the first frame, it must contain the geometric center of at least one class in the next frame; if t is the last frame, it must contain the geometric center of at least one class in the previous frame; if t is the middle frame, it must contain the geometric center of at least one class in both the previous frame and the next frame. Finally, only the classes that pass the above verification are retained in the t-th frame image, and the classes that do not meet the conditions will be removed. Each image is processed according to this rule, and the third weight of each image is obtained according to the ratio of the number of pixels in the retained class to the total number of pixels in each image. The specific method is as follows: Where, represents the third weight of the t-th image taken by the c-th camera on the f-th floor, Count() represents the number of extracted pixels, represents the i-th class in the t-th image taken by the c-th camera on the f-th floor, represents the number of classes of the t-th image taken by the c-th camera on the f-th floor, represents the tth image taken by the cth camera on the fth floor.

6. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The specific method of combining the first weight, the second weight, and the third weight of all images on each floor at each moment with the energy consumption power of each floor at each moment to obtain the energy consumption parameter of each floor at each moment includes: Where, represents the energy consumption parameter of the f-th floor at the t-th moment, represents the number of cameras on the f-th floor, represents the first weight of all images taken by the c-th camera on the f-th floor, is the second weight of the t-th image of the c-th camera in the f-th layer, represents the third weight of the t-th image taken by the c-th camera on the f-th floor, Represents the energy consumption of the f-th floor at the t-th moment.

7. The method for evaluating energy efficiency in IBMS based on image recognition according to claim 1, characterized in that: The specific method for judging whether the energy efficiency of each floor is reasonable based on the fluctuation degree of the energy consumption parameters of each floor at each moment is as follows: The variance of the energy consumption parameters of the f-th floor at all times is calculated as the basis for evaluating energy utilization efficiency. The threshold K is set based on historical statistical data analysis. When the variance of the energy consumption parameters of the f-th floor is greater than the threshold K, the energy utilization is considered unreasonable. When the variance of the energy consumption parameters of the f-th floor is less than or equal to the threshold K, the energy utilization is considered reasonable.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating energy efficiency in IBMS based on image recognition as claimed in any one of claims 1 to 7 are implemented.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for evaluating energy utilization efficiency in IBMS based on image recognition as described in any one of claims 1 to 7 are implemented.

10. An energy efficiency evaluation system in IBMS based on image recognition, characterized in that: The system includes the following modules: The data acquisition module is used to collect energy usage power data of different floors at different times in real time through the IBMS system. At the same time, the camera system collects images of the corresponding floors at the same time. These synchronously collected power data and image data are then time-aligned and processed; A first weight calculation module is used to calculate a first weight of all images collected by each camera according to the fluctuation of the number of pixels that change in the images collected by different cameras on different floors; A second weight calculation module is used to obtain the clustering of all suspected person pixels based on the changed positions of the pixels in the previous frame of each image captured by different cameras on different floors, and obtain the suspected person density parameter of each image based on the distance distribution of the suspected person pixel clusters in each image, and record the suspected person density parameter of each image as the second weight of each image; A third weight calculation module is used to obtain the person pixel clusters for each image based on the position changes of the suspected person pixel clusters in each image captured by different cameras on different floors and the images before and after it, excluding the suspected noise pixel clusters, and obtain the third weight of each image based on the ratio of the number of pixels in the suspected person pixel clusters to the total number of pixels in the image; An energy consumption parameter calculation module, configured to combine the first weight, the second weight, and the third weight of all images on each floor at each moment with the energy consumption power of each floor at each moment to obtain the energy consumption parameter of each floor at each moment; The energy consumption judgment module is used to judge whether the energy utilization efficiency of each floor is reasonable based on the fluctuation degree of the energy consumption parameters of each floor at each moment.

Images