A scalable infrared camera monitoring system based on stereo ranging

Abstract

The present invention relates to the technical field of wildlife monitoring, and in particular to a measurable infrared camera monitoring system based on stereo ranging. In the present invention, a target is identified by an infrared monitoring device. When the target is identified as entering a monitorable area, a binocular ranging device is used to respectively obtain images of the target, a radar ranging device is used to determine the distance between the camera and the target, and feature points of the two target images are respectively obtained. The corresponding feature points are marked as feature point pairs, and depth information of the target is determined based on the relationship between each feature point pair. The depth information reflects the distance between each point on the target and the ranging device. Considering features such as the continuity and smoothness of contour lines can help optimize the acquisition of depth information. Therefore, the monitored target is further analyzed based on the image information and the contour lines, thereby improving the analysis accuracy of the monitored target information and improving the analysis efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of wild animal monitoring, and in particular to a measurable infrared camera monitoring system based on stereo ranging. Background Art

[0002] Wild animals are an important part of the ecosystem. By monitoring the number, distribution, and behavior of wild animals, we can gain a deeper understanding of the structure and function of the ecosystem. Existing technologies use real-time transmission of thermal imaging signals from wild animals and real-time tracking and shooting signals with infrared cameras, and provide airbags to seal the monitoring module to prevent damage to the system itself due to complex outdoor weather. However, there is a lack of monitoring technology for the size of animals, and the size of the monitored animals is mostly determined manually, resulting in low analysis efficiency and insufficient accuracy.

[0003] Chinese patent application number: CN202310188708.3 discloses a wildlife dynamic monitoring and feedback system based on an infrared camera, including: a monitoring module, a power module, a solar power generation module, and a communication module. The monitoring module is used for real-time monitoring of wildlife, and includes a box body, an infrared camera and a thermal imaging camera arranged in parallel on the front end face of the box body, and the infrared camera includes a camera holder and an infrared camera; the power module is used to drive the infrared camera to extend and retract relative to the front end face of the box body, and the power module includes an air pump, a transmission component connected to the air pump, and a pressure relief valve provided on the connecting pipeline between the air pump and the transmission component; the monitoring feedback system provided by the present invention can transmit the thermal imaging signal of wild animals and the real-time tracking and shooting signal of the infrared camera in real time, and the arrangement of the first airbag and the second airbag can achieve sealing of the monitoring module in various working states of the infrared camera, thereby preventing damage to the system body under complex outdoor weather conditions.

[0004] However, the prior art still has the following problems:

[0005] There is a lack of monitoring technology for the size of animals, and the size of the monitored animals is mostly determined manually, resulting in low analysis efficiency and insufficient analysis accuracy. Summary of the Invention

[0006] To this end, the present invention provides a measurable infrared camera monitoring system based on stereo ranging to overcome the problems in the prior art of animal size monitoring technology being relatively scarce, relying mostly on manual determination of the size of the monitored animals, resulting in low analysis efficiency and insufficient analysis accuracy.

[0007] To achieve the above objectives, the present invention provides a scalable infrared camera monitoring system based on stereo ranging. It includes:

[0008] An infrared monitoring module, which is used to send a monitoring signal when a target to be monitored is identified;

[0009] A radar ranging module, connected to the infrared monitoring module, for detecting the detection distance between the target to be monitored and the camera;

[0010] A depth image acquisition module, comprising a first acquisition device for acquiring a first image and a second acquisition device for acquiring a second image, for acquiring an image of a target to be monitored;

[0011] a data processing module connected to the depth image acquisition module, configured to extract feature points based on the image acquired by the depth image acquisition module, and determine the depth information of the target to be monitored based on the extracted feature points;

[0012] an analysis module, connected to the infrared monitoring module, the radar ranging module, the depth image acquisition module, and the data processing module, respectively, for analyzing whether the acquired image is a target to be calculated based on the depth information of the target to be monitored and the length of the contour line in the image of the target to be monitored, and performing a secondary determination on whether the acquired image is a target to be calculated based on historical image information when the acquired image is initially determined to be not a target to be calculated, or analyzing the reason why the acquired image is not a target to be calculated based on the distance between each pair of feature points;

[0013] A storage module is connected to the analysis module and is used to store image information.

[0014] Furthermore, the data processing module is used to perform pairing processing on corresponding feature points in the first feature point group and the second feature point group to obtain a plurality of feature point pairs, and to determine the depth information of the target to be monitored based on the distance between each feature point pair.

[0015] The first feature point group is determined based on the first image, and the second feature point group is determined based on the second image.

[0016] Furthermore, the analysis module is used to calculate the depth mean corresponding to each pair of feature points of the target to be monitored, and calculate the ratio of the depth mean to the length of the contour line of the target to be monitored in the image, so as to analyze whether the acquired image is the target to be calculated based on the ratio, including:

[0017] When determining that the acquired image is the target to be calculated, recording the image information into the storage module;

[0018] When the image is initially determined to be a non-target to be calculated, a secondary determination is made based on historical image information to determine whether the image is a target to be calculated.

[0019] Alternatively, it is determined that the acquired image is not the target to be calculated, and the reason why the acquired image is not the target to be calculated is analyzed based on the distance between each pair of feature points.

[0020] Furthermore, the analysis module is further configured to determine the depth mean calculated at each time node in the historical image information, and the length of the contour line of the target to be monitored in the corresponding image, and calculate the ratio of each depth mean to the contour line length, and calculate the variance of each ratio to perform a secondary determination on whether the acquired image is the target to be calculated based on the variance, including:

[0021] When determining that the acquired image is not the target to be calculated, analyzing the reason why the acquired image is not the target to be calculated based on the distance between each pair of feature points;

[0022] When it is determined that the target to be monitored is in a moving state, the contour features of the target to be monitored in the image are obtained, and the direction of the target to be monitored is determined based on the contour features.

[0023] Furthermore, the analysis module is further configured to adjust a preset standard interval based on the determined angle between the orientation of the target to be monitored and the direction facing the camera, wherein the expansion amount of the preset standard interval is negatively correlated with the angle.

[0024] Furthermore, the analysis module is further configured to calculate an average value of the distances between each pair of feature points to obtain a distance mean, and analyze the reasons why the acquired image is not the target to be calculated based on the distance mean, including:

[0025] The reason for determining that the acquired image is not the target to be calculated is the environmental influence;

[0026] The analysis module determines the reason why the acquired image is not the target to be calculated based on the mean value of each distance in the historical data.

[0027] Alternatively, the reason for determining that the acquired image is not the target to be calculated is that the acquisition is unqualified.

[0028] Furthermore, the analysis module is further configured to correct the noise reduction ratio based on the ambient brightness under the condition of environmental influence, wherein the increase in the noise reduction ratio is positively correlated with the ambient brightness.

[0029] Furthermore, the analysis module is further configured to calculate the distance variance of each distance mean in the historical data, and based on the distance variance, to secondary determine the reason why the acquired image is not the target to be calculated, including:

[0030] The reason why the acquired image is determined to be a non-target to be calculated is due to environmental influence.

[0031] Alternatively, the reason for determining that the acquired image is not the target to be calculated is that the detection distance does not match the camera position.

[0032] Furthermore, the analysis module is further configured to adjust the distance between the first acquisition device and the second acquisition device based on the detection distance, wherein an increase in the distance is positively correlated with the detection distance.

[0033] Furthermore, the analysis module is further configured to adjust the detection sensitivity based on the ambient temperature when the acquisition is determined to be unqualified, wherein the reduction in the detection sensitivity is negatively correlated with the ambient temperature.

[0034] Compared with the prior art, the beneficial effect of the present invention lies in that, in the present invention, a target is identified by an infrared monitoring device. When the target is identified as entering a monitorable area, a binocular ranging device is used to respectively obtain images of the target, a radar ranging device is used to determine the distance between the camera and the target, and feature points of the two target images are respectively obtained. The corresponding feature points are marked as feature point pairs, and the depth information of the target is determined according to the relationship between each feature point pair. The depth information reflects the distance between each point on the target and the ranging device. Considering the continuity and smoothness of the contour line and other features, it can help optimize the acquisition of depth information. Therefore, the monitoring target is further analyzed according to the image information and the contour line, thereby improving the analysis accuracy of the monitoring target information, and the volume information of the target is further determined according to the acquired depth information of the target, avoiding artificial determination of the target volume and avoiding errors caused by artificial determination of the volume information, thereby unifying the analysis process parameters and improving the analysis efficiency.

[0035] Furthermore, the present invention takes into account that the clarity of the target contour line in the acquired target image has a great influence on the depth information of the determined target. For example, the tail of an animal is blocked by the body or the legs block each other. This occlusion will cause some depth information and contour information to be missing, affecting the accurate estimation of the volume. Therefore, the accuracy of the determined depth information is further analyzed based on the degree of fluctuation of the depth information calculated at each feature point, thereby improving the accuracy of the analysis of the target information.

[0036] Furthermore, the present invention takes into account that during the image acquisition process, the ambient brightness will have a great impact on the image information. If there is an exposure phenomenon, the contour line of the identified target will be inaccurate, affecting the analysis accuracy. Therefore, the noise reduction ratio is adjusted according to the ambient brightness, thereby improving the control accuracy of the image acquisition process and further improving the analysis accuracy of the target depth information.

[0037] Furthermore, the present invention takes into account that the greater the distance between feature points, the higher the accuracy of the depth information, because a larger distance between feature points can provide more obvious parallax changes, thereby more accurately calculating the depth. Therefore, the depth information of the target is analyzed according to the fluctuation of the distance values ​​between each feature point, thereby improving the accuracy of the analysis of the depth information of the target. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematic diagram of the structure of the scalable infrared camera monitoring system based on stereo ranging of the present invention;

[0039] Figure 2 A flow chart for determining whether the image obtained by analysis is the target to be calculated;

[0040] Figure 3 A flow chart for determining whether the acquired image is the target to be calculated for the second time;

[0041] Figure 4 A flowchart for determining why the image obtained for analysis is not the target to be calculated;

[0042] In the figure: 1-infrared monitoring camera; 2-first acquisition device; 3-second acquisition device; 4-radar ranging module; 5-infrared monitoring module; 6-wireless transmission device; 7-GNSS positioning device. DETAILED DESCRIPTION

[0043] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0044] It should be noted that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical data of the six months before the current determination and the corresponding historical determination results by the system of the present invention. It can be understood by those skilled in the art that the system of the present invention can determine the above parameters for each of the above parameters by selecting the value with the highest proportion as the preset standard parameter based on the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter, or other selection methods, as long as the system of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0045] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0046] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0047] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0048] See also Figure 1 As shown, it is a structural diagram of the measurable infrared camera monitoring system based on stereo ranging of the present invention.

[0049] This embodiment provides a scalable infrared camera monitoring system based on stereo ranging, including:

[0050] An infrared monitoring module, which is used to send a monitoring signal when a target to be monitored is identified;

[0051] A radar ranging module, connected to the infrared monitoring module, for detecting the detection distance between the target to be monitored and the camera;

[0052] A depth image acquisition module, comprising a first acquisition device for acquiring a first image and a second acquisition device for acquiring a second image, for acquiring an image of a target to be monitored;

[0053] a data processing module connected to the depth image acquisition module, configured to extract feature points based on the image acquired by the depth image acquisition module, and determine the depth information of the target to be monitored based on the extracted feature points;

[0054] an analysis module, connected to the infrared monitoring module, the radar ranging module, the depth image acquisition module, and the data processing module, respectively, for analyzing whether the acquired image is a target to be calculated based on the depth information of the target to be monitored and the length of the contour line in the image of the target to be monitored, and performing a secondary determination on whether the acquired image is a target to be calculated based on historical image information when the acquired image is initially determined to be not a target to be calculated, or analyzing the reason why the acquired image is not a target to be calculated based on the distance between each pair of feature points;

[0055] A storage module is connected to the analysis module and is used to store image information.

[0056] Specifically, in this embodiment, the specific structures of the infrared monitoring module and the radar ranging module are not limited. The infrared monitoring module can adopt an infrared sensor or an infrared detector, and the radar ranging module can adopt a pulse radar ranging device or a continuous wave radar ranging device. These belong to the existing technology and will not be repeated here.

[0057] Specifically, in this embodiment, the specific structure of the depth image acquisition module is not limited, and it only needs to be able to realize the corresponding function. A binocular vision camera can be used, which belongs to the existing technology and will not be repeated here.

[0058] Specifically, in this embodiment, the specific structures of the analysis module and the storage module are not limited, and they can be composed of logic components, and the logic components include a field programmable processor, a computer, and a microprocessor in the computer.

[0059] In the present invention, an infrared monitoring device is used to identify a target. When the target is identified as entering a monitorable area, a binocular ranging device is used to respectively obtain images of the target, a radar ranging device is used to determine the distance between a camera and the target, and feature points of the two target images are respectively obtained. The corresponding feature points are marked as feature point pairs, and the depth information of the target is determined according to the relationship between each feature point pair. The depth information reflects the distance between each point on the target and the ranging device. Considering features such as the continuity and smoothness of the contour line can help optimize the acquisition of depth information, the monitored target is further analyzed based on the image information and the contour line, thereby improving the analysis accuracy of the monitored target information, and further determining the volume information of the target based on the obtained depth information of the target, avoiding artificial determination of the target volume and errors caused by artificial determination of the volume information, thereby unifying the analysis process parameters and improving the analysis efficiency.

[0060] Specifically, the data processing module is used to perform pairing processing on the corresponding feature points in the first feature point group and the second feature point group to obtain a plurality of feature point pairs, and to determine the depth information of the target to be monitored based on the distance between each feature point pair.

[0061] The first feature point group is determined based on the first image, and the second feature point group is determined based on the second image.

[0062] Specifically, in this embodiment, determining the depth information of the target to be monitored based on feature point pairs belongs to the existing technology. For example, the extracted feature points can be matched, the parallax can be calculated, and the depth information of the target to be monitored can be calculated based on the triangulation principle, which will not be repeated here.

[0063] See also Figure 2 As shown in FIG, it is a flow chart for determining whether the acquired image is the target to be calculated.

[0064] Specifically, the analysis module is used to calculate the depth mean corresponding to each pair of feature points of the target to be monitored, and calculate the ratio of the depth mean to the length of the contour line of the target to be monitored in the image, so as to analyze whether the acquired image is the target to be calculated based on the ratio, including:

[0065] If the ratio is within a first preset standard interval, the analysis module determines that the acquired image is a target to be calculated, and records the image information into the storage module;

[0066] If the ratio is within a second preset standard interval, the analysis module preliminarily determines that the acquired image is not a target to be calculated, and performs a secondary determination on whether the acquired image is a target to be calculated based on historical image information;

[0067] If the ratio is within a third preset standard range, the analysis module determines that the acquired image is a non-target to be calculated, and analyzes the reason why the acquired image is a non-target to be calculated based on the distance between each pair of feature points.

[0068] Specifically, in this embodiment, the first preset standard interval is obtained in advance, and the body shape information data of the target of the same type as the current monitored target is obtained, images of each target at each angle are obtained, feature points are determined and the depth of each feature point is obtained respectively, the depth mean of each feature point is calculated, the ratio of the depth mean to the length of the contour line in the corresponding image is calculated, and the single-angle body shape ratio is obtained. The average value of the single-angle body shape ratios of the images of a single target at each angle is calculated to obtain the body shape ratio of a single target, the body shape ratios of several targets of the same type are calculated, the number of each body shape ratio is counted, and the body shape ratio with the largest number is recorded as the body shape ratio standard. The first preset standard interval is [0.9×body shape ratio standard, 1.2×body shape ratio standard], the second preset standard interval is [0.85×body shape ratio standard, 0.9×body shape ratio standard) or (1.2×body shape ratio standard, 1.3×body shape ratio standard], and the third preset standard interval is a range that is neither the first preset standard interval nor the second preset standard interval.

[0069] See also Figure 3 As shown in FIG, it is a flow chart for determining whether the acquired image is the target to be calculated for the second time.

[0070] Specifically, the analysis module is further used to determine the depth mean calculated at each time node in the historical image information, and the length of the contour line of the target to be monitored in the corresponding image, and calculate the ratio of each depth mean to the length of the contour line, and calculate the variance of each ratio to perform a secondary determination on whether the acquired image is the target to be calculated based on the variance, including:

[0071] If the variance is less than or equal to a preset variance standard threshold, the analysis module determines that the acquired image is a non-target to be calculated, and analyzes the reason why the acquired image is a non-target to be calculated based on the distance between each pair of feature points;

[0072] If the variance is greater than the preset variance standard threshold, the analysis module determines that the target to be monitored is in a moving state, obtains contour features of the target to be monitored in the image, and determines the direction of the target to be monitored based on the contour features.

[0073] Specifically, in this embodiment, the preset variance standard threshold is obtained by pre-measurement, determining the single-angle body size ratio of a single target of the same type as the current monitored target, calculating the variance of the single-angle body size ratio of each angle image, and calculating the mean variance of the single-angle body size ratios of several targets of the same type to obtain the preset variance standard threshold.

[0074] The present invention takes into account that the clarity of the target contour line in the acquired target image has a great influence on the determined depth information of the target. For example, the tail of an animal is blocked by the body or the legs block each other. This occlusion will cause some depth information and contour information to be missing, affecting the accurate estimation of the volume. Therefore, the accuracy of the determined depth information is further analyzed based on the degree of fluctuation of the depth information calculated at each feature point, thereby improving the accuracy of the analysis of the target information.

[0075] Specifically, the analysis module is further configured to adjust the preset standard interval based on the determined angle between the orientation of the target to be monitored and the direction facing the camera, wherein the expansion amount of the preset standard interval is negatively correlated with the angle.

[0076] In this embodiment, optionally,

[0077] Compare the angle with the first preset angle standard threshold and the second preset angle standard threshold,

[0078] If the angle is less than or equal to the first preset angle standard threshold, the first preset standard interval range is expanded by the first interval range, and the expanded range is expanded to the left and right ends of the first preset standard interval range by 0.04×body size standard units respectively;

[0079] If the angle is greater than the first preset angle standard threshold and less than or equal to the second preset angle standard threshold, the first preset standard interval is expanded by a second interval, and the expanded range is expanded to the left and right ends of the first preset standard interval by 0.03×body size standard units respectively;

[0080] If the angle is greater than the second preset angle standard threshold, the first preset standard interval is expanded to a third interval, and the expanded range is 0.02×body size ratio units to the left and right ends of the first preset standard interval respectively;

[0081] Among them, the second preset standard interval range is reduced by the corresponding number unit.

[0082] Specifically, in this embodiment, when the preset standard interval is adjusted, the acquired image is re-analyzed based on the ratio of the depth mean to the length of the contour line of the target to be monitored in the image to determine whether it is the target to be calculated, including:

[0083] If the ratio is within the adjusted first preset standard range, determining that the acquired image is a target to be calculated, and recording the image information into the storage module;

[0084] If the ratio is outside the adjusted first preset standard range, the acquired image is determined to be a non-target to be calculated, and the reason why the acquired image is a non-target to be calculated is analyzed based on the distance between each pair of feature points.

[0085] See also Figure 4 As shown, it is a flow chart for determining why the image obtained by analysis is not the target to be calculated.

[0086] Specifically, the analysis module is further configured to calculate the average value of the distances between each pair of feature points to obtain a distance mean, and analyze the reasons why the acquired image is not the target to be calculated based on the distance mean, including:

[0087] If the distance mean is less than or equal to a first preset distance mean standard threshold, the analysis module determines that the reason why the acquired image is not the target to be calculated is environmental influence;

[0088] If the distance mean is greater than the first preset distance mean standard threshold and less than or equal to the second preset distance mean standard threshold, the analysis module determines based on the distance mean values ​​in the historical data that the acquired image is not the target to be calculated and performs a secondary determination on the reason;

[0089] If the distance mean is greater than the second preset distance mean standard threshold, the reason why the analysis module determines that the acquired image is not the target to be calculated is that the acquisition is unqualified.

[0090] Specifically, in this embodiment, the first preset distance mean standard threshold and the second preset distance mean standard threshold are obtained in advance, and several target images that meet the target depth prediction requirements are obtained, the distance between each feature point is calculated, and the distance mean is solved. The first preset distance mean standard threshold is 0.85 to 1.05 times the distance mean, and the second preset distance mean standard threshold is 1.1 to 1.2 times the distance mean.

[0091] Specifically, the analysis module is further configured to modify the noise reduction ratio based on the ambient brightness under the condition of environmental influence, wherein the increase in the noise reduction ratio is positively correlated with the ambient brightness.

[0092] In this embodiment, optionally,

[0093] Compare the ambient brightness with the first preset ambient brightness standard threshold and the second preset ambient brightness standard threshold,

[0094] If the ambient brightness is less than or equal to the first preset ambient brightness standard threshold, increase the first noise reduction magnification, which is 0.1 times the initial noise reduction magnification;

[0095] If the ambient brightness is greater than the first preset ambient brightness standard threshold and less than or equal to the second preset ambient brightness standard threshold, then increase the second noise reduction magnification, which is 0.2 times the initial noise reduction magnification;

[0096] If the ambient brightness is greater than the second preset ambient brightness standard threshold, the third noise reduction magnification is increased, and the third noise reduction magnification is 0.25 times the initial noise reduction magnification;

[0097] Among them, the first preset ambient brightness standard threshold and the second preset ambient brightness standard threshold are obtained in advance, and the optimal ambient brightness for capturing the target image is determined based on big data. The first preset ambient brightness standard threshold is 0.9 times the optimal ambient brightness, and the second preset ambient brightness standard threshold is 1.2 times the optimal ambient brightness.

[0098] The present invention takes into account that during the image acquisition process, the ambient brightness will have a great impact on the image information. If there is an exposure phenomenon, the contour line of the identified target will be inaccurate, affecting the analysis accuracy. Therefore, the noise reduction ratio is adjusted according to the ambient brightness, thereby improving the control accuracy of the image acquisition process and further improving the analysis accuracy of the target depth information.

[0099] Specifically, the analysis module is further configured to calculate the distance variance of each distance mean in the historical data, and based on the distance variance, to secondary determine the reason why the acquired image is not the target to be calculated, including:

[0100] If the distance variance is less than or equal to a preset distance variance standard threshold, the analysis module determines that the reason why the acquired image is not the target to be calculated is environmental influence;

[0101] If the distance variance is greater than the preset distance variance standard threshold, the reason why the analysis module determines that the acquired image is not the target to be calculated is that the detection distance does not match the camera position.

[0102] Specifically, in this embodiment, the preset distance variance standard threshold is obtained by pre-measurement, obtaining several images that meet the depth prediction requirements for the target image, determining the distance between each feature point, and solving the variance of each distance to obtain the preset distance variance standard threshold.

[0103] The present invention takes into account that the greater the distance between feature points, the higher the accuracy of the depth information, because a larger distance between feature points can provide more obvious parallax changes, thereby more accurately calculating the depth. Therefore, the depth information of the target is analyzed according to the fluctuation of the distance values ​​between each feature point, thereby improving the accuracy of the analysis of the depth information of the target.

[0104] Specifically, the analysis module is further configured to adjust the distance between the first acquisition device and the second acquisition device based on the detection distance, wherein an increase in the distance is positively correlated with the detection distance.

[0105] In this embodiment, optionally,

[0106] Compare the detection distance with the first preset detection distance standard threshold and the second preset detection distance standard threshold,

[0107] If the detection distance is less than or equal to the first preset detection distance standard threshold, the first spacing is increased, and the first spacing is 0.1 times the initial spacing;

[0108] If the detection distance is greater than the first preset detection distance standard threshold and less than or equal to the second preset detection distance standard threshold, increase the second spacing to 0.2 times the initial spacing;

[0109] If the detection distance is greater than the second preset detection distance standard threshold, increasing the third distance to 0.3 times the initial distance;

[0110] Among them, the first preset detection distance standard threshold and the second preset detection distance standard threshold are obtained in advance, and the optimal detection distance for obtaining the monitoring target is determined based on big data. The first preset detection distance standard threshold is 1.15 times the optimal detection distance, and the second preset detection distance standard threshold is 1.25 times the optimal detection distance.

[0111] Specifically, the analysis module is further configured to adjust the detection sensitivity based on the ambient temperature when the acquisition is determined to be unqualified, wherein the reduction in the detection sensitivity is negatively correlated with the ambient temperature.

[0112] In this embodiment, optionally,

[0113] Compare the ambient temperature with the first preset ambient temperature and the second preset ambient temperature,

[0114] If the ambient temperature is less than or equal to the first preset ambient temperature standard threshold, the first detection sensitivity is reduced to 0.2 times the initial detection sensitivity;

[0115] If the ambient temperature is greater than the first preset ambient temperature standard threshold and less than or equal to the second preset ambient temperature standard threshold, the second detection sensitivity is reduced to 0.15 times the initial sensitivity;

[0116] If the ambient temperature is greater than the second preset ambient temperature standard threshold, reducing the third detection sensitivity to 0.1 times the initial sensitivity;

[0117] Among them, the first preset ambient temperature standard threshold and the second preset ambient temperature standard threshold are obtained in advance, and the optimal ambient temperature during the use of the infrared monitoring device is determined based on big data. The first preset ambient temperature standard threshold is 1.2 times the optimal ambient temperature, and the second preset ambient temperature standard threshold is 1.3 times the optimal ambient temperature.

[0118] Specifically, in this embodiment, an adjustment knob is usually set on the device or there are adjustable resistors and other components in the internal circuit. For example, by rotating a potentiometer to change the resistance value in the circuit, the gain of the signal amplification circuit is changed, thereby changing the detection sensitivity of the infrared monitoring device. This belongs to the existing technology and will not be repeated here.

[0119] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0120] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A scalable infrared camera monitoring system based on stereo ranging, characterized in that: include: An infrared monitoring module, which is used to send a monitoring signal when a target to be monitored is identified; A radar ranging module, connected to the infrared monitoring module, for detecting the detection distance between the target to be monitored and the camera; A depth image acquisition module, comprising a first acquisition device for acquiring a first image and a second acquisition device for acquiring a second image, for acquiring an image of a target to be monitored; a data processing module connected to the depth image acquisition module, configured to extract feature points based on the image acquired by the depth image acquisition module, and determine the depth information of the target to be monitored based on the extracted feature points; an analysis module, which is respectively connected to the infrared monitoring module, the radar ranging module, the depth image acquisition module and the data processing module, and is used to analyze whether the acquired image is the target to be calculated based on the depth information of the target to be monitored and the length of the contour line in the image of the target to be monitored, and if the ratio is within a second preset standard interval, the acquired image is preliminarily determined to be not the target to be calculated, and a secondary determination is made on whether the acquired image is the target to be calculated based on historical image information, and if the ratio is within a third preset standard interval, the acquired image is determined to be not the target to be calculated, and the reason why the acquired image is not the target to be calculated is analyzed based on the distance between each pair of feature points, wherein the ratio is the ratio of the depth mean to the length of the contour line of the target to be monitored; A storage module is connected to the analysis module and is used to store image information.

2. The scalable infrared camera monitoring system based on stereo ranging according to claim 1, characterized in that: The data processing module is used to perform pairing processing on corresponding feature points in the acquired first feature point group and the second feature point group to obtain a plurality of feature point pairs, and to determine the depth information of the target to be monitored based on the distance between each feature point pair. The first feature point group is determined based on the first image, and the second feature point group is determined based on the second image.

3. The scalable infrared camera monitoring system based on stereo ranging according to claim 1, characterized in that: The analysis module is used to calculate the depth mean corresponding to each pair of feature points of the target to be monitored, and calculate the ratio of the depth mean to the length of the contour line of the target to be monitored in the image, so as to analyze whether the acquired image is the target to be calculated based on the ratio, including: If the ratio is within the first preset standard range, the image is determined to be a target to be calculated, and the image information is recorded in the storage module; If the ratio is within the second preset standard range, it is preliminarily determined that the acquired image is not a target to be calculated, and a secondary determination is made on whether the acquired image is a target to be calculated based on historical image information. Furthermore, if the ratio is within the third preset standard interval, the acquired image is determined to be a non-target to be calculated, and the reason why the acquired image is a non-target to be calculated is analyzed based on the distance between each pair of feature points.

4. The scalable infrared camera monitoring system based on stereo ranging according to claim 3 is characterized in that: The analysis module is further configured to determine the depth mean calculated at each time node in the historical image information, and the length of the contour line of the target to be monitored in the corresponding image, and calculate the ratio of each depth mean to the contour line length, and calculate the variance of each ratio to perform a secondary determination on whether the acquired image is the target to be calculated based on the variance, including: When determining that the acquired image is not the target to be calculated, analyzing the reason why the acquired image is not the target to be calculated based on the distance between each pair of feature points; When it is determined that the target to be monitored is in a moving state, the contour features of the target to be monitored in the image are obtained, and the direction of the target to be monitored is determined based on the contour features.

5. The scalable infrared camera monitoring system based on stereo ranging according to claim 4 is characterized in that: The analysis module is further configured to adjust a preset standard interval based on the determined angle between the orientation of the target to be monitored and the direction facing the camera, wherein the expansion amount of the preset standard interval is negatively correlated with the angle.

6. The scalable infrared camera monitoring system based on stereo ranging according to claim 2, characterized in that: The analysis module is further configured to calculate an average value of distances between each pair of feature points to obtain a distance mean, and analyze the reasons why the acquired image is not a target to be calculated based on the distance mean, including: If the distance mean is less than or equal to a first preset distance mean standard threshold, the analysis module determines that the reason why the acquired image is not the target to be calculated is environmental influence; Furthermore, if the distance mean is greater than the first preset distance mean standard threshold and less than or equal to the second preset distance mean standard threshold, the analysis module determines that the acquired image is not the target to be calculated based on the distance mean in the historical data. Furthermore, if the distance mean is greater than the second preset distance mean standard threshold, the reason why the analysis module determines that the acquired image is not the target to be calculated is that the acquisition is unqualified.

7. The scalable infrared camera monitoring system based on stereo ranging according to claim 6, characterized in that: The analysis module is further configured to modify the noise reduction ratio based on the ambient brightness under the condition of environmental influence, wherein the increase in the noise reduction ratio is positively correlated with the ambient brightness.

8. The scalable infrared camera monitoring system based on stereo ranging according to claim 6, characterized in that: The analysis module is further configured to calculate the distance variance of each distance mean in the historical data, and based on the distance variance, to secondary determine the reason why the acquired image is not the target to be calculated, including: The reason why the acquired image is determined to be a non-target to be calculated is due to environmental influence. Alternatively, the reason for determining that the acquired image is not the target to be calculated is that the detection distance does not match the camera position.

9. The scalable infrared camera monitoring system based on stereo ranging according to claim 8, characterized in that: The analysis module is further configured to adjust the distance between the first acquisition device and the second acquisition device based on the detection distance, wherein an increase in the distance is positively correlated with the detection distance.

10. The scalable infrared camera monitoring system based on stereo ranging according to claim 6, characterized in that: The analysis module is further configured to adjust the detection sensitivity based on the ambient temperature when the acquisition is determined to be unqualified, wherein the reduction in the detection sensitivity is negatively correlated with the ambient temperature.

Images