Image transmission recorder data processing method and system

Abstract

The invention discloses a data processing method and system for an image transmission recorder, and relates to the technical field of data analysis, and the method comprises the steps: collecting an image data stream through the image transmission recorder, setting a sampling time window T for the image data stream, and obtaining N frames of images in the sampling time window T; calculating a pixel change value between adjacent frames of the N frames of images, and generating a differential data sequence; based on the differential data sequence, a threshold value R is set for data screening, and differential data larger than the threshold value R are marked as abnormal frames; encoding and packaging the abnormal frames according to a time sequence to generate an abnormal event data packet; and performing timestamp association on the abnormal event data packet and an original image data stream to form an associated data record. In the processing process, the pixel change of the adjacent frames is calculated through differential operation, the abnormal frames are screened through the self-adaptive threshold value, and it is ensured that the abnormal events are sensitively recognized in the variable monitoring environment.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a data processing method and system for an image transmission recorder. Background Art

[0002] With the development of video surveillance technology, image transmission and recording systems have been widely used in various industries, especially in security monitoring, traffic management, industrial production and other fields. Traditional image transmission recorders are usually used to capture and record image data streams in real time and transmit them to storage media or cloud servers. However, with the dramatic increase in the amount of image data, how to efficiently process these large amounts of image data has become an urgent problem to be solved. In order to improve data processing efficiency, the technology of image transmission recorders has been continuously developed, adding functions such as compression coding, image differential analysis, and event-driven data capture. These technologies can effectively reduce data storage requirements, optimize the use of network bandwidth, and improve the real-time performance of data processing.

[0003] Although the existing technology has made many progresses in image data processing, there are still some shortcomings. For example, the existing system can only rely on simple frame-to-frame differences to screen data, and fails to make full use of pixel change information to conduct in-depth analysis of image content. This method may generate a large amount of irrelevant data or mislabeling, resulting in an increased burden on storage and transmission. In event-driven data capture, traditional technologies mostly rely on fixed time intervals or simple trigger mechanisms, which can easily miss some important abnormal events and cannot accurately locate and mark the time of occurrence of abnormal events. In addition, the existing image data stream processing system also lacks efficient solutions for the encoding and association of abnormal events, which makes subsequent data retrieval and analysis difficult. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention proposes a data processing method and system for an image transmission recorder.

[0005] Therefore, the present invention provides a data processing method for an image transmission recorder, which can solve the problems mentioned in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for processing data of an image transmission recorder, which comprises:

[0008] Collecting an image data stream through an image transmission recorder, setting a sampling time window T for the image data stream, and acquiring N frames of images within the sampling time window T;

[0009] Calculating pixel change values ​​between adjacent frames of the N frames of image to generate a differential data sequence;

[0010] Based on the differential data sequence, a threshold R is set to perform data screening, and differential data greater than the threshold R is marked as an abnormal frame;

[0011] Encode and package the abnormal frames in chronological order to generate abnormal event data packets;

[0012] The abnormal event data packet is associated with the original image data stream by time stamp to form an associated data record.

[0013] As a preferred solution of the data processing method of the image transmission recorder of the present invention, the generation of the differential data sequence includes:

[0014] The N frames of images are read in time series order, and pixel-level difference calculation is performed between every two consecutive frames;

[0015] Based on the difference value of each pixel, construct the difference matrix D;

[0016] The elements in the difference matrix D are normalized, and the normalized difference matrix D is arranged in chronological order to form a difference data sequence containing N-1 matrices.

[0017] As a preferred solution of the data processing method of the image transmission recorder of the present invention, the differential operation is as follows:

[0018] D(x,y,i)=|P(x,y,i+1)-P(x,y,i)|×w(x,y)

[0019] Where D(x,y,i) represents the difference between the i-th frame and the i+1-th frame at the coordinate (x,y), P(x,y,i) represents the pixel value of the i-th frame image at the coordinate (x,y), and w(x,y) is the spatial weight coefficient;

[0020] The spatial weight coefficient is calculated by the following formula:

[0021]

[0022] Among them, σ is the Gaussian kernel parameter, which is used to adjust the spatial sensitivity, and α(i) is the time attenuation factor;

[0023] The time decay factor is calculated by the following formula:

[0024] α(i)=λ (N-i) ×(1+β×V(i))

[0025] Among them, λ is the attenuation base, V(i) is the local variance, β is the variance adjustment coefficient, and N is the total number of frames in the input image sequence.

[0026] As a preferred solution of the data processing method of the image transmission recorder of the present invention, the normalization processing is shown as follows:

[0027]

[0028] Where K(i) is the adaptive correction factor;

[0029] The adaptive correction factor is calculated by the following formula:

[0030] K(i)=1+γ×log(1+mean(D(i)))

[0031] Among them, γ is an adjustable parameter, mean(D(i)) is the mean of the difference matrix of the i-th frame, max(D) is the maximum difference value in the i-th difference matrix D, and min(D) is the minimum difference value in the i-th difference matrix D.

[0032] As a preferred solution of the data processing method of the image transmission recorder of the present invention, wherein: the threshold R is dynamically set, comprising the following steps:

[0033] Calculate the mean and standard deviation for each difference matrix;

[0034] Using environmental factors to modify the threshold;

[0035] Calculate the quality assessment factor based on the local variance to obtain the threshold R;

[0036] The environmental factor is determined by the image entropy value and motion complexity, wherein the image entropy value represents the richness of image information, and the motion complexity index reflects the intensity of scene motion;

[0037] The quality assessment factor is used to measure the impact of image quality on the threshold.

[0038] As a preferred solution of the data processing method of the image transmission recorder of the present invention, the calculation of the threshold R is shown in the following formula:

[0039] R(i)=μ(i)+k×σ(i)×F(i)

[0040] Among them, μ(i) is the mean of the i-th difference matrix, σ(i) is the standard deviation, k is the adjustment coefficient, and F(i) is the environmental factor;

[0041] The calculation of the environmental factor is shown in the following formula:

[0042] F(i)=[1+η×H(i)]×S(i)

[0043] Among them, η is the weight coefficient, S(i) is the signal-to-noise ratio evaluation value, and H(i) is the image entropy function;

[0044] The image entropy function is shown in the following formula:

[0045] H(i)=-∑[p(j)×log(p(j))]×M(i)

[0046] Among them, p(j) is the normalized probability distribution of the gray value of the difference matrix, and M(i) is the motion complexity index;

[0047] The calculation of the motion complexity index is shown in the following formula:

[0048]

[0049] Among them, A is the normalization coefficient, Q(i) is the quality assessment factor;

[0050] The quality assessment factor is calculated as follows:

[0051] Q(i)=1-exp(-θ×V local (i))

[0052] Among them, θ is an adjustable parameter, V local (i) is the local variance.

[0053] As a preferred solution of the data processing method of the image transmission recorder of the present invention, after determining the threshold R, the differential data sequence is screened, that is, each differential matrix D in the differential data sequence is norm (x, y, i), calculate its statistical eigenvalue E(i);

[0054] The calculation of the statistical characteristic value E(i) is shown in the following formula:

[0055]

[0056] When the condition E(i)>R(i) is met, the corresponding i-th frame is marked as an abnormal frame, and the abnormality coefficient C(i) is recorded:

[0057] C(i)=[E(i)-R(i)]×B(i)

[0058] Where B(i) is the reliability evaluation coefficient:

[0059] B(i)=tanh(ρ×S(i))×(1-exp(-E(i)))

[0060] Among them, ρ is an adjustable parameter and S(i) is the signal-to-noise ratio evaluation value.

[0061] As a preferred solution of the data processing method of the image transmission recorder of the present invention, the triggering of the dynamic adjustment of the threshold R includes:

[0062] When the ambient light changes significantly, the statistical characteristics of the difference matrix will fluctuate, which will trigger the adjustment of the threshold R.

[0063] When the motion pattern of the target in the monitoring scene changes, adjust the threshold R;

[0064] When there is a problem with the image acquisition quality, adjust the threshold R accordingly;

[0065] When the background structure of the monitoring scene changes, the threshold R is adjusted;

[0066] When multiple moving targets interfere with each other in the scene, threshold adjustment is performed.

[0067] In a second aspect, an embodiment of the present invention provides a data processing system for an image transmission recorder, comprising:

[0068] A data acquisition module, used to acquire an image data stream through an image transmission recorder, set a sampling time window T for the image data stream, and acquire N frames of images within the sampling time window T;

[0069] A data sequence generation module, used for calculating pixel change values ​​between adjacent frames of the N frames of image, and generating a differential data sequence;

[0070] A threshold adjustment module, used for setting a threshold R for data screening based on the differential data sequence;

[0071] An abnormality judgment module, used for marking the differential data greater than the threshold R as an abnormal frame, encoding and packaging the abnormal frame in chronological order, and generating an abnormal event data packet;

[0072] The recording module is used to associate the abnormal event data packet with the original image data stream by time stamp to form an associated data record.

[0073] The beneficial effect of the present invention is that the detection accuracy and reliability of image changes are improved by introducing spatial weights, time attenuation and local variance adjustment. During the processing, the pixel changes of adjacent frames are calculated by differential operations, and the abnormal frames are screened using adaptive thresholds to ensure sensitive identification of abnormal events in a changeable monitoring environment. At the same time, the abnormal frames are effectively encoded and compressed, and timestamps are associated with the original image data stream to ensure the efficiency and integrity of data storage and transmission. This method is suitable for target monitoring in dynamic environments, and can be adaptively adjusted in different scenarios, improving the intelligence and response speed of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0075] Figure 1 The present invention is a flow chart of a method for processing data of an image transmission recorder. DETAILED DESCRIPTION

[0076] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0077] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0078] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0079] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0080] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0081] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0082] Example 1

[0083] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for processing data of a video transmission recorder, comprising:

[0084] S1: collecting an image data stream through an image transmission recorder, setting a sampling time window T for the image data stream, and acquiring N frames of images within the sampling time window T;

[0085] When collecting image data streams through an image transmission recorder, the image acquisition unit in the image transmission recorder receives image signals, performs image digital conversion on the image signals at a fixed frame rate, and forms a continuous image data stream. For the image data stream, a sampling time window T is set according to actual monitoring requirements, and the length of the sampling time window T is configured through user interface parameters; within the sampling time window T, N frames of images are continuously collected from the image data stream at a preset sampling frequency of 25 frames / second, wherein the number N of N frames of images is equal to the product of the sampling time window T and the sampling frequency; the N frames of images are stored in the cache unit of the image transmission recorder in a time series manner, and each frame of the image carries corresponding time information;

[0086] S2: performing inter-frame difference operation on the N frames of images, calculating pixel change values ​​between adjacent frames, and generating a difference data sequence;

[0087] The N frames of images are read in time series order, and pixel-level difference operation is performed between every two consecutive frames. The difference operation includes: subtracting the grayscale value of the corresponding pixel points of the i-th frame image from the i+1-th frame image. The grayscale value adopts 8-bit data depth and has a value range of 0-255. The difference calculation formula is:

[0088] D(x,y,i)=|P(x,y,i+1)-P(x,y,i)|×w(x,y)

[0089] Where D(x,y,i) represents the difference between the i-th frame and the i+1-th frame at the coordinate (x,y), P(x,y,i) represents the pixel value of the i-th frame image at the coordinate (x,y), and w(x,y) is the spatial weight coefficient, which is calculated by the following formula:

[0090]

[0091] Among them, σ is the Gaussian kernel parameter, which is used to adjust the spatial sensitivity, and α(i) is the time attenuation factor, which is calculated as follows:

[0092] α(i)=λ (N-i) ×(1+β×V(i))

[0093] Among them, λ is the attenuation base (0<λ<1), V(i) is the local variance, and β is the variance adjustment coefficient.

[0094] Preferably, the differential calculation method mentioned in this embodiment introduces spatial weights so that different image areas show different response sensitivities in the differential calculation, which can more accurately reflect the movement or changes of each area. In particular, the Gaussian kernel function is used to adjust the weight of the spatial distribution so that the central area or a specific area of ​​interest obtains a higher differential calculation weight, which effectively improves the detection accuracy of key areas. Secondly, considering the continuity and complexity of image information in dynamic scenes, this embodiment adds time attenuation and local variance adjustment. The time attenuation factor gradually reduces the impact on historical frames in an exponentially decreasing manner, so that the differential calculation pays more attention to the change characteristics of the current frame and the adjacent frames. At the same time, the local variance adjustment dynamically adjusts the weight according to the local complexity of the image, so that changes can be captured more sensitively in rapidly changing areas, while unnecessary fluctuations are reduced in stable areas.

[0095] Furthermore, based on the difference value of each pixel, a difference matrix D is constructed, and the dimension of the difference matrix D is the same as the resolution of the original image. The elements in the difference matrix D are normalized to map the difference value to the range of 0-1. The normalization process adopts an improved maximum and minimum value normalization method:

[0096]

[0097] Where K(i) is the adaptive correction factor:

[0098] K(i)=1+γ×log(1+mean(D(i)))

[0099] Among them, γ is an adjustable parameter, mean(D(i)) is the mean of the difference matrix of the i-th frame, max(D) is the maximum difference value in the i-th difference matrix D, and min(D) is the minimum difference value in the i-th difference matrix D.

[0100] The normalized difference matrix D is arranged in chronological order to form a difference data sequence containing N-1 matrices; each difference matrix in the difference data sequence is accompanied by corresponding time tag information for subsequent data tracing; in the difference operation process, parallel computing is used to improve the operation efficiency, and the image data is processed in blocks and then the results are merged.

[0101] S3: Based on the differential data sequence, a threshold R is set to perform data screening, and differential data greater than the threshold R is marked as an abnormal frame;

[0102] Specifically, for each differential matrix in the differential data sequence, image feature parameters of the local area are extracted, including the regional grayscale mean, edge density value and texture complexity value.

[0103] A weight coefficient is set for the image feature parameter, and a scene feature index is obtained by weighted combination. The scene feature index is multiplied by a reference threshold to obtain an adaptive threshold R for the current scene, which is expressed by the following formula:

[0104] R(i)=μ(i)+k×σ(i)×F(i)

[0105] Among them, μ(i) is the mean of the i-th difference matrix, σ(i) is the standard deviation, k is the adjustment coefficient, and F(i) is the environmental factor. The calculation formula is:

[0106] F(i)=[1+η×H(i)]×S(i)

[0107] Among them, η is the weight coefficient, S(i) is the signal-to-noise ratio evaluation value, and H(i) is the image entropy function:

[0108] H(i)=-∑[p(j)×log(p(j))]×M(i)

[0109] Among them, p(j) is the normalized probability distribution of the gray value of the difference matrix, and M(i) is the motion complexity index:

[0110]

[0111] Among them, A is the normalization coefficient and Q(i) is the quality assessment factor:

[0112] Q(i)=1-exp(-θ×V local (i))

[0113] Among them, θ is an adjustable parameter, V local (i) is the local variance;

[0114] After determining the threshold R, the differential data sequence is screened, that is, each differential matrix D in the differential data sequence is norm (x,y,i), calculate its statistical eigenvalue E(i):

[0115]

[0116] When the condition E(i)>R(i) is met, the corresponding i-th frame is marked as an abnormal frame, and the abnormality coefficient C(i) is recorded:

[0117] C(i)=[E(i)-R(i)]×B(i)

[0118] Where B(i) is the reliability evaluation coefficient:

[0119] B(i)=tanh(ρ×S(i))×(1-exp(-E(i)))

[0120] Among them, ρ is an adjustable parameter and S(i) is the signal-to-noise ratio evaluation value.

[0121] The abnormal frame and its corresponding abnormality degree coefficient C(i) are stored in an abnormal frame buffer queue, and the abnormal frame buffer queue adopts a ring buffer structure and has an automatic overflow processing mechanism.

[0122] It should be noted that the specific scenarios that trigger the change of threshold calculation include:

[0123] When the ambient illumination changes significantly, the statistical characteristics of the difference matrix will fluctuate, which will trigger the adjustment of the threshold R: first, the degree of illumination change is detected by the change of the image entropy value H(i). When the entropy value change of adjacent time windows exceeds the preset threshold, the environmental factor F(i) is adjusted accordingly; second, based on the local variance V local The statistical results of (i) are used to update the quality assessment factor Q(i) to compensate for the impact of illumination changes. Finally, the baseline value of the threshold R is adjusted through the calculation results of the motion complexity index M(i), so that the system has a stronger adaptability to illumination changes.

[0124] It should be noted that the definition of significant changes in ambient illumination includes calculating the overall brightness mean μ(i) of the image, defining it as significant when the brightness mean change rate Δμ / μ of adjacent frames exceeds ±20%, statistically analyzing the grayscale histogram distribution of the image, and determining it as significant when the histogram peak position offset exceeds 25% of the total grayscale range, and calculating the brightness variance ratio σ between frames. 2 (i) / σ 2 (i-1), when the ratio exceeds the interval [0.5, 2.0], it is considered a significant change; analyze the brightness gradient of the local area, and when the proportion of pixels with a gradient change rate exceeding ±30% exceeds 40% of the image area, it is considered significant.

[0125] When the motion pattern of the target in the monitoring scene changes, the threshold R needs to be adjusted in time: First, based on the difference matrix D norm The statistical characteristics of (x, y, i) are used to calculate the motion complexity index M(i). When the motion complexity exceeds the preset range, the threshold adjustment is triggered. Second, the stability of the current motion characteristics is evaluated by calculating the reliability evaluation coefficient B(i). Third, according to the changing trend of the signal-to-noise ratio evaluation value S(i), the environmental factor F(i) is dynamically adjusted so that the threshold R can adapt to the new motion pattern.

[0126] When there is a problem with the image acquisition quality, the system needs to adjust the threshold R accordingly: first, the image quality status is monitored in real time through the quality assessment factor Q(i). When the quality index is lower than the safety threshold, the compensation mechanism is triggered; second, based on the local variance V local (i) is analyzed and the reliability evaluation coefficient B(i) is adjusted; finally, the threshold R is corrected through dynamic calculation of the environmental factor F(i) to reduce the risk of misjudgment caused by quality anomalies.

[0127] When the background structure of the monitored scene changes, the threshold R is triggered to update: first, the degree of change of the background complexity is detected through the image entropy function H(i); second, the impact range of the background change is analyzed based on the statistical eigenvalue E(i) of the difference matrix; third, the environmental factor F(i) and the motion complexity index M(i) are adjusted so that the threshold R can adapt to the new background environment.

[0128] When multiple moving targets interfere with each other in the scene, the threshold is adjusted: first, the comprehensive characteristics of the multi-target motion are evaluated by the motion complexity index M(i); second, based on the local variance V local (i) Analyze the mutual influence between targets; finally, by calculating the reliability evaluation coefficient B(i) and the environmental factor F(i), optimize the value of the threshold R and improve the system's adaptability to multi-target scenarios.

[0129] S4: Encode and package the abnormal frames in chronological order to generate an abnormal event data packet;

[0130] First, extract the timestamp information of each abnormal frame, including year, month, day, hour, minute, second and millisecond to ensure the integrity of time accuracy. Then, read the abnormal degree coefficient and quantize it, converting it into an integer value in the range of 0-255 for unified processing. Then, construct a descriptor for each abnormal frame, including basic information such as frame type identification, resolution information, color space parameters, etc., to fully describe the characteristics of the frame. Next, calculate the characteristic hash value of the abnormal frame to verify the integrity of the data.

[0131] On this basis, the time interval between adjacent abnormal frames is calculated through the timestamp information. When the interval is less than the preset threshold, these frames are classified into the same event cluster. At the same time, the original image data is compressed and encoded, and an adaptive compression ratio is used. The compression parameters are dynamically adjusted according to the abnormal degree coefficient to optimize data storage. Next, the abnormal frame descriptor is structured and encoded in a compact binary format to improve data transmission efficiency. After that, the temporal feature vector is encoded to ensure that the time information is accurately preserved.

[0132] Subsequently, a packet header is generated, which contains basic information such as version number, packet length, and checksum. The abnormal frame data is organized by event cluster to ensure that each event cluster is arranged in chronological order. At the same time, a packet index table is established to record the starting position and length information of each event cluster for quick access. Finally, integrity check information and end mark are added to the end of the packet to ensure the integrity of data transmission.

[0133] S5: Associating the abnormal event data packet with the original image data stream by time stamp to form an associated data record.

[0134] Furthermore, this embodiment also provides a data processing system for an image transmission recorder, comprising:

[0135] A data acquisition module, used to acquire an image data stream through an image transmission recorder, set a sampling time window T for the image data stream, and acquire N frames of images within the sampling time window T;

[0136] A data sequence generation module, used for calculating pixel change values ​​between adjacent frames of the N frames of image, and generating a differential data sequence;

[0137] A threshold adjustment module, used for setting a threshold R for data screening based on the differential data sequence;

[0138] An abnormality judgment module, used for marking the differential data greater than the threshold R as an abnormal frame, encoding and packaging the abnormal frame in chronological order, and generating an abnormal event data packet;

[0139] The recording module is used to associate the abnormal event data packet with the original image data stream by time stamp to form an associated data record.

[0140] This embodiment also provides a computer device, which is suitable for the case of the image transmission recorder data processing method, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the image transmission recorder data processing method proposed in the above embodiment.

[0141] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0142] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for processing data of an image transmission recorder proposed in the above embodiment is implemented.

[0143] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0144] Example 2

[0145] This is the second embodiment of the present invention. This embodiment provides a data processing method for an image transmission recorder. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0146] This experiment was implemented and verified in the security monitoring system of a large commercial complex. The experimental environment includes a main hall of a shopping mall with a construction area of ​​about 12,000 square meters, with 16 high-definition network cameras, including 8 fixed cameras and 8 dome cameras. The camera uses a 2-megapixel CMOS sensor, outputs a video stream with a resolution of 1920×1080, and the frame rate is set to 25fps. The image transmission recorder uses an industrial computer with an Intel i7-11700 processor and 32GB memory, equipped with an NVIDIARTX 3060 graphics card for parallel computing acceleration.

[0147] The experiment was conducted in four time periods: daytime, nighttime, peak traffic flow, and low traffic flow. The test duration for each period was 4 hours. The sampling time window T was set to 2 seconds, that is, 50 frames of images were acquired in each sampling window. For the parameters in the differential calculation, the Gaussian kernel parameter σ was set to 1.5, the time attenuation base λ was taken as 0.95, and the variance adjustment coefficient α was set to 0.8. In the adaptive threshold calculation, the adjustment coefficient β was set to 0.6, the weight coefficient w was taken as [0.4, 0.3, 0.3], and the adjustable parameter γ was set to 0.75.

[0148] During the experiment, the system performance was tested according to the characteristics of different scenarios: (1) Normal crowd flow scenario: simulate the movement of people in a daily shopping environment; (2) Sudden gathering scenario: simulate the gathering of people during shopping mall promotions; (3) Light change scenario: simulate the change of natural light and the switching of lighting systems; (4) Multi-target interference scenario: simulate the cross-interference of multiple fast-moving targets. During the operation of the system, all raw data streams are recorded through a high-performance solid-state hard drive, and the detected abnormal events are stored separately for subsequent analysis and comparison. The specific experimental data are shown in Table 1 below:

[0149] Table 1 Experimental data table

[0150]

[0151]

[0152] Through the analysis of experimental data, the present invention shows significant advantages in multiple key performance indicators. First, in the normal flow of people scenario, the system shows the best overall performance, with a frame processing time of only 12.5ms and a detection accuracy of 94.8%, while maintaining a low false alarm rate (3.2%) and false alarm rate (2.0%). This is due to the improved differential algorithm and adaptive threshold mechanism adopted by the present invention, which effectively balances the detection sensitivity and system stability.

[0153] In the system stress test scenario (burst aggregation scenario), although the processing time increased to 15.8ms, the detection accuracy was still maintained at an acceptable level of 92.3%. This proves that the parallel computing architecture proposed in the present invention has good load balancing capabilities and can maintain stable performance even under high load conditions. In particular, in terms of memory usage, even in the most complex multi-target interference scenario, the peak is only 945MB, thanks to the innovative ring buffer structure and efficient memory management mechanism.

[0154] The test results of the scene with changing lighting are particularly noteworthy. Traditional algorithms often have a large number of false alarms when the lighting changes dramatically. However, by introducing adaptive environmental factors and quality assessment mechanisms, the present invention controls the false alarm rate in the scene with changing lighting to 3.4%, which is significantly better than the industry's general level of 5-8%. This verifies the outstanding advantages of the present invention in environmental adaptability.

[0155] The test data of the multi-target interference scenario shows that although this is the most challenging application scenario, the system still maintains a detection accuracy of 89.7%, and the increase in response delay is also controlled within an acceptable range (25.4ms). This proves that the multi-target processing strategy and motion complexity evaluation mechanism proposed in the present invention can effectively handle target detection tasks in complex scenarios.

[0156] In various scenario tests, the CPU usage rate was controlled within a relatively ideal range (45.2%-63.8%), which shows that the system has good computing resource utilization efficiency. Especially in the composite scenario test, despite the superposition effect of multiple interference factors, the system still maintained a detection accuracy of 90.8%, which fully demonstrated the robustness and practical value of the present invention. In summary, the experimental data fully verified the comprehensive advantages of the present invention in terms of accuracy, real-time performance, stability, etc., and provided reliable technical support for practical applications.

[0157] A special illumination mutation experiment was designed to verify the environmental adaptability of the system by controlling the illumination system to produce different degrees of illumination changes. In the multi-target scene test, multiple testers were arranged to move crosswise along the preset path to verify the system's ability to handle complex motion patterns. At the same time, a professional-level video quality analyzer was introduced to monitor image quality parameters in real time to ensure the reliability of the test data.

[0158] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A data processing method for an image transmission recorder, characterized in that: include: Collecting an image data stream through an image transmission recorder, setting a sampling time window T for the image data stream, and acquiring N frames of images within the sampling time window T; Calculating pixel change values ​​between adjacent frames of the N frames of image to generate a differential data sequence; Based on the differential data sequence, a threshold R is set to perform data screening, and differential data greater than the threshold R is marked as an abnormal frame; Encode and package the abnormal frames in chronological order to generate abnormal event data packets; The abnormal event data packet is associated with the original image data stream by time stamp to form an associated data record.

2. The image transmission recorder data processing method according to claim 1, characterized in that: The generation of the differential data sequence includes: The N frames of images are read in time series order, and pixel-level difference calculation is performed between every two consecutive frames; Based on the difference value of each pixel, construct the difference matrix D; The elements in the difference matrix D are normalized, and the normalized difference matrix D is arranged in chronological order to form a difference data sequence containing N-1 matrices.

3. The image transmission recorder data processing method according to claim 2, characterized in that: The difference operation is shown as follows: D(x,y,i)=|P(x,y,i+1)-P(x,y,i)|×w(x,y) Where D(x,y,i) represents the difference between the i-th frame and the i+1-th frame at the coordinate (x,y), P(x,y,i) represents the pixel value of the i-th frame image at the coordinate (x,y), and w(x,y) is the spatial weight coefficient; The spatial weight coefficient is calculated by the following formula: Among them, σ is the Gaussian kernel parameter, which is used to adjust the spatial sensitivity, and α(i) is the time attenuation factor; The time decay factor is calculated by the following formula: α(i)=λ (N-i) ×(1+β×V(i)) Among them, λ is the attenuation base, V(i) is the local variance, β is the variance adjustment coefficient, and N is the total number of frames in the input image sequence.

4. The image transmission recorder data processing method according to claim 3, characterized in that: The normalization process is shown in the following formula: Where K(i) is the adaptive correction factor; The adaptive correction factor is calculated by the following formula: K(i)=1+γ×log(1+mean(D(i))) Among them, γ is an adjustable parameter, mean(D(i)) is the mean of the difference matrix of the i-th frame, max(D) is the maximum difference value in the i-th difference matrix D, and min(D) is the minimum difference value in the i-th difference matrix D.

5. The image transmission recorder data processing method according to claim 4, characterized in that: The threshold R is set dynamically, including the following steps: Calculate the mean and standard deviation for each difference matrix; Using environmental factors to modify the threshold; Calculate the quality assessment factor based on the local variance to obtain the threshold R; The environmental factor is determined by the image entropy value and motion complexity, wherein the image entropy value represents the richness of image information, and the motion complexity index reflects the intensity of scene motion; The quality assessment factor is used to measure the impact of image quality on the threshold.

6. The image transmission recorder data processing method according to claim 5, characterized in that: The calculation of the threshold R is shown in the following formula: R(i)=μ(i)+k×σ(i)×F(i) Among them, μ(i) is the mean of the i-th difference matrix, σ(i) is the standard deviation, k is the adjustment coefficient, and F(i) is the environmental factor; The calculation of the environmental factor is shown in the following formula: F(i)=[1+η×H(i)]×S(i) Among them, η is the weight coefficient, S(i) is the signal-to-noise ratio evaluation value, and H(i) is the image entropy function; The image entropy function is shown in the following formula: H(i)=-∑[p(j)×log(p(j))]×M(i) Among them, p(j) is the normalized probability distribution of the gray value of the difference matrix, and M(i) is the motion complexity index; The calculation of the motion complexity index is shown in the following formula: Among them, A is the normalization coefficient, Q(i) is the quality assessment factor; The quality assessment factor is calculated as follows: Q(i)=1-exp(-θ×V local (i)) Among them, θ is an adjustable parameter, V local (i) is the local variance.

7. The data processing method of the image transmission recorder according to claim 6, characterized in that: After determining the threshold R, the differential data sequence is screened, that is, each differential matrix D in the differential data sequence is norm (x, y, i), calculate its statistical eigenvalue E(i); The calculation of the statistical characteristic value E(i) is shown in the following formula: When the condition E(i)>R(i) is met, the corresponding i-th frame is marked as an abnormal frame, and the abnormality coefficient C(i) is recorded: C(i)=[E(i)-R(i)]×B(i) Where B(i) is the reliability evaluation coefficient: B(i)=tanh(ρ×S(i))×(1-exp(-E(i))) Among them, ρ is an adjustable parameter and S(i) is the signal-to-noise ratio evaluation value.

8. The image transmission recorder data processing method according to claim 7, characterized in that: The triggering of the dynamic adjustment of the threshold R includes: When the ambient light changes significantly, the statistical characteristics of the difference matrix will fluctuate, which will trigger the adjustment of the threshold R. When the motion pattern of the target in the monitoring scene changes, adjust the threshold R; When there is a problem with the image acquisition quality, adjust the threshold R accordingly; When the background structure of the monitoring scene changes, the threshold R is adjusted; When multiple moving targets interfere with each other in the scene, threshold adjustment is performed.

9. A data processing system for an image transmission recorder, based on the data processing method for an image transmission recorder according to any one of claims 1 to 8, characterized in that: include: A data acquisition module, used to acquire an image data stream through an image transmission recorder, set a sampling time window T for the image data stream, and acquire N frames of images within the sampling time window T; A data sequence generation module, used for calculating pixel change values ​​between adjacent frames of the N frames of image, and generating a differential data sequence; A threshold adjustment module, used for setting a threshold R for data screening based on the differential data sequence; An abnormality judgment module, used for marking the differential data greater than the threshold R as an abnormal frame, encoding and packaging the abnormal frame in chronological order, and generating an abnormal event data packet; The recording module is used to associate the abnormal event data packet with the original image data stream by time stamp to form an associated data record.

Images