A high-altitude projectile detection method and device, electronic equipment and medium

Abstract

This application discloses a method, apparatus, electronic device, and medium for detecting objects thrown from heights. The method includes: if a target lens detects a projectile in either a short-focal-length lens or a long-focal-length lens, then, based on a target image captured by the target lens, determining first motion information of the projectile within the target lens's field of view; based on the first motion information of the projectile within the target field of view and another field of view of the other lens, determining second motion information of the projectile within another field of view; and verifying the projectile detection result of the target lens based on the detection result of an object satisfying the second motion information in another captured image of the other lens. This solution can improve the accuracy of projectile detection by using the predicted second motion information of the projectile in another field of view and verification in another captured image when one lens detects a projectile, through the synergistic effect of the two lenses.

Description

Technical Field

[0001] This application relates to the field of high-altitude object throwing detection technology, and in particular to a high-altitude object throwing detection method, device, electronic equipment and medium. Background Technology

[0002] Throwing objects from heights refers to the act of throwing objects from buildings or other high-altitude structures. This is an uncivilized behavior that causes significant social harm. Currently, technological means can be used to detect and identify such acts, enabling timely warnings and interventions. This technology primarily relies on video surveillance and artificial intelligence, which can automatically identify, track, and record the process of objects being thrown from heights, providing timely warnings and tracing the responsible party in the event of such incidents.

[0003] Currently, the application of image acquisition devices to monitor or trace the behavior of objects thrown from high-rise buildings is becoming increasingly widespread. However, the accuracy of high-rise object detection using image acquisition devices has not improved significantly. It is easily affected by weather, lights, birds, floating objects, etc., resulting in false detections and missed detections. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and medium for detecting objects thrown from heights, which improves detection accuracy through the coordinated detection of telephoto and short-focus lenses.

[0005] According to one aspect of this application, a method for detecting objects thrown from heights is provided, the method comprising:

[0006] If a target lens detects a parabola in either the short-focus lens or the long-focus lens, then based on the target image captured by the target lens of the parabola, the first motion information of the parabola within the target field of view of the target lens is determined; wherein the field of view of the long-focus lens and the field of view of the short-focus lens cover the target floor and are arranged in a vertical direction.

[0007] Based on the first motion information of the parabola within the target field of view and the other field of view of another lens, the second motion information of the parabola within the other field of view is determined; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the long focal length lens;

[0008] The parabolic detection result of the target lens is verified based on the detection result of an object satisfying the second motion information in another acquired image of the other lens.

[0009] According to one aspect of this application, a high-altitude object throwing detection device is provided, the device comprising:

[0010] The first motion information determination module is used to determine the first motion information of the parabola within the target field of view of the target lens if a target lens detects a parabola in either the short-focal-length lens or the long-focal-length lens; wherein the field of view of the long-focal-length lens and the field of view of the short-focal-length lens cover the target floor and are arranged in a vertical direction.

[0011] The second motion information determination module is used to determine the second motion information of the parabola within the other field of view based on the first motion information of the parabola within the target field of view and the other field of view of the other lens; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the telephoto lens;

[0012] The verification module is used to verify the parabolic detection result of the target lens based on the detection result of an object that satisfies the second motion information in another acquired image of the other lens.

[0013] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the high-altitude object throwing detection method of any embodiment of the present application.

[0017] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the high-altitude object detection method of any embodiment of this application.

[0018] In the technical solution of this application embodiment, if a target lens detects a parabola in either the short-focal-length lens or the telephoto lens, then based on the target image captured by the target lens of the parabola, first motion information of the parabola within the target field of view of the target lens is determined; wherein, the field of view of the telephoto lens and the field of view of the short-focal-length lens cover the target floor and are arranged vertically; based on the first motion information of the parabola within the target field of view and another field of view of the other lens, second motion information of the parabola within the other field of view is determined; wherein, the other lens is a lens of another type besides the target lens among the short-focal-length lens and the telephoto lens; based on the detection result of an object satisfying the second motion information in another captured image of the other lens, the parabola detection result of the target lens is verified. The above scheme can determine the first motion information of the parabola by using the target image captured by the target lens when one of the telephoto and short-focal-length lenses detects the parabola. Based on this, it can predict the second motion information of the parabola in another field of view of the other lens. The result of the parabola detection by the target lens is verified by combining the second motion information with another image captured by the other lens, thereby improving the accuracy of parabola detection.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a method for detecting objects thrown from heights, as provided in this application embodiment;

[0022] Figure 2 A schematic diagram showing the field of view and the corresponding target building in the embodiments of this application;

[0023] Figure 3 A flowchart of a method for detecting objects thrown from heights is provided in another embodiment of this application;

[0024] Figure 4 Another embodiment of this application provides a schematic diagram of the horizontal coordinates of a parabola;

[0025] Figure 5 A schematic diagram of the vertical coordinates of a parabola is provided in another embodiment of this application;

[0026] Figure 6 A flowchart of a method for detecting objects thrown from heights, provided in another embodiment of this application;

[0027] Figure 7 This is a schematic diagram of a parabolic trajectory provided in yet another embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of a high-altitude object throwing detection device provided in an embodiment of this application;

[0029] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Figure 1 This is a flowchart illustrating a method for detecting objects thrown from heights, provided in an embodiment of this application. This embodiment is applicable to situations requiring the detection of objects thrown from heights. The method can be executed by a high-altitude object-throwing detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. For example... Figure 1 As shown, the method includes:

[0033] S110. If a target lens detects a parabola in either the short-focus lens or the long-focus lens, then based on the target image captured by the target lens of the parabola, the first motion information of the parabola within the target field of view of the target lens is determined; wherein the field of view of the long-focus lens and the field of view of the short-focus lens cover the target floor and are arranged in a vertical direction.

[0034] In this context, "short focal length lens" and "telephoto lens" are conventional lens names in the field of image acquisition. In the application scenario of this application embodiment, the focal length of the short focal length lens can be 4mm-6mm, and the focal length of the telephoto lens can be 8mm-12mm. Generally, short focal length lenses are used to shoot closer scenes, and telephoto lenses are used to shoot farther scenes. In this application embodiment, at least one short focal length lens and at least one telephoto lens can be used to acquire images of the target floor. If both the short focal length lens and the telephoto lens are set at a low position, both the telephoto lens and the short focal length lens will look upwards to acquire images of the target floor. The short focal length lens mainly acquires images of the target floor on lower floors, and the telephoto lens mainly acquires images of the target floor on higher floors. If the short focal length lens and the telephoto lens are set at a high position, such as at the same height as the roof, the short focal length lens can be used to acquire images of the target floor on higher floors, and the telephoto lens can be used to acquire images of the target floor on lower floors. The field of view of the short-focal-length lens and the telephoto lens both cover the target floor surface to be detected. The fields of view are arranged vertically and may or may not overlap. The target lens is either the short-focal-length lens or the telephoto lens that detected the parabola. The other lens is a different type of lens than the target lens. If the target lens is a short-focal-length lens, the other lens is a telephoto lens; if the target lens is a telephoto lens, the other lens is a short-focal-length lens. The target floor surface is generally the side of the building.

[0035] For example, if a target lens detects a parabola in both a short-focal-length lens and a long-focal-length lens, the first motion information of the parabola within the target lens's field of view can be determined based on the target image captured by the target lens. The first motion information can include the parabola's velocity, descent height, and motion time. The target image used to determine the first motion information of the parabola within the target field of view can be at least two frames to determine the parabola's motion.

[0036] Specifically, when setting up short-focal-length and telephoto lenses, the correspondence between the lens's field of view and the actual area of ​​the target floor can be predetermined, thereby determining the correspondence between the pixel range of the acquired image and the actual area of ​​the target floor. Floor information, such as floor height and building spacing, can be pre-calibrated. Based on the installation positions and field of view information of the telephoto and short-focal-length lenses, the range of the target floor corresponding to the telephoto lens and the range of the target floor corresponding to the short-focal-length lens are determined. For example, ... Figure 2 As shown, assuming both the short-focus lens and the telephoto lens are set up at a low angle to capture images of the target building, then... Figure 2 The target floors from the 6th to the 10th floor are within the field of view of a telephoto lens, while the target floors from the 1st to the 5th floor are within the field of view of a short-focus lens.

[0037] Determining the first motion information of the parabola within the target's field of view can help determine the actual motion information of the parabola relative to the target floor. This means converting the motion information of the parabola in the pixel coordinates of the target image into actual motion information relative to the target floor, such as the actual height and speed.

[0038] S120. Based on the first motion information of the parabola within the target field of view and the other field of view of the other lens, determine the second motion information of the parabola within the other field of view; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the long focal length lens.

[0039] For example, the second motion information of the parabola within another field of view is the motion information assuming the parabola passes through the other field of view. The other field of view can be its position relative to the target floor, such as information corresponding to the height range of the target floor. The second motion information of the parabola within the other field of view can be determined based on the first motion information of the parabola within the target field of view and the different heights within the other field of view.

[0040] Specifically, based on the principle of parabolic fall and the first motion information of the parabola, the horizontal position of the parabola at different heights within another field of view can be calculated. Information such as the velocity at different heights can also be calculated to obtain the second motion information of the parabola within the other field of view. The first and second motion information reflect the trajectory of the parabola, thereby determining its position when it appears in the target image and another acquired image.

[0041] S130. Verify the parabolic detection result of the target lens based on the detection result of the object satisfying the second motion information in another acquired image of the other lens.

[0042] For example, another image captured by another lens can be acquired. This other image also needs to have been captured within the time period during which the predicted parabola appears in another field of view. The other image is then inspected to determine if there are any detection results for objects that satisfy the second motion information, thereby verifying the parabola detection results of the target lens.

[0043] For example, assuming the target lens is a telephoto lens capturing images of higher floors, and another lens is a short-focus lens capturing images of lower floors, if the telephoto lens detects a parabola, it predicts the time it will take for the parabola to fall into the other field of view of the short-focus lens, acquires another image captured at that time, and checks whether an object satisfying the second motion information exists based on that image. If it exists, it indicates that the telephoto lens's detection of the parabola is correct and reliable; if it does not exist, it can be further reported to staff for analysis of the target image captured by the telephoto lens. If the short-focus lens detects a parabola, it traces back to the second motion information of the parabola appearing in the other field of view of the telephoto lens, acquires another image captured during the predicted time of the parabola's appearance in that field of view, and checks whether an object satisfying the second motion information exists based on that image. If it exists, it indicates that the short-focus lens's detection of the parabola is correct and reliable. Additionally, this approach can reduce the false negative rate of parabola detection. If, according to the above scheme, a parabola is also detected in the short-focus lens, but the telephoto lens does not report a detection, it indicates that the telephoto lens missed a detection, and the detection results of the telephoto lens are supplemented.

[0044] If a projectile is detected in the target lens but not in the other lens, or if no object satisfying the second motion information is found in another captured image from the other lens, the sensitivity for detecting the projectile in the other captured image can be adaptively adjusted. Supplementary detection can then be performed on the other captured image. If a projectile is detected after the sensitivity adjustment, an alarm is triggered to prevent missed detections. The strategy for adjusting sensitivity here is generally to increase the sensitivity to improve the probability of detecting a projectile. If the target lens is above the target's field of view, and the other lens is below, the detection sensitivity can be increased to perform real-time detection on the other captured image when the target lens detects a projectile but the other lens does not. If the target lens is below the target's field of view, and the other lens is above, the sensitivity for detecting a projectile in the other lens's historical captured images can be increased to perform supplementary detection on those images when the target lens detects a projectile but the other lens does not.

[0045] In the technical solution of this application embodiment, if a target lens detects a parabola in either the short-focal-length lens or the telephoto lens, then based on the target image captured by the target lens of the parabola, first motion information of the parabola within the target field of view of the target lens is determined; wherein, the field of view of the telephoto lens and the field of view of the short-focal-length lens cover the target floor and are arranged vertically; based on the first motion information of the parabola within the target field of view and another field of view of the other lens, second motion information of the parabola within the other field of view is determined; wherein, the other lens is a lens of another type besides the target lens among the short-focal-length lens and the telephoto lens; based on the detection result of an object satisfying the second motion information in another captured image of the other lens, the parabola detection result of the target lens is verified. The above scheme can determine the first motion information of the parabola by using the target image captured by the target lens when one of the telephoto and short-focal-length lenses detects the parabola. Based on this, it can predict the second motion information of the parabola in another field of view of the other lens. The result of the parabola detection by the target lens is verified by combining the second motion information with another image captured by the other lens, thereby improving the accuracy of parabola detection.

[0046] Figure 3 This is a flowchart of a method for detecting objects thrown from heights, provided as another embodiment of this application. This embodiment is an optimization based on the above embodiment; solutions not described in detail in this embodiment are found in the above embodiment. Figure 3 As shown, the method in this embodiment of the application specifically includes the following steps:

[0047] S210. If a target lens detects a parabola in either the short-focus lens or the long-focus lens, then based on the target image captured by the target lens when the parabola appears at the target position in the target lens, determine the velocity and actual height of the parabola at the target position.

[0048] The target position can also reflect the actual position of the parabola relative to the target floor. A target image captured by the target lens when the parabola appears at the target position can be obtained. Based on this image, the velocity and actual height of the parabola at the target position can be determined. The velocity of the parabola at the target position can be determined based on its position and time difference within a very short period. The actual height can be determined based on the pixel position of the parabola in the target image and the correspondence between the target's field of view and the actual position of the target floor.

[0049] In this embodiment of the application, determining the velocity and actual height of the parabola at the target position based on the target image captured by the target lens when the parabola appears at the target position in the target lens includes:

[0050] Acquire the first target image and the second target image captured by the target lens within a preset time period;

[0051] Based on the pixel positions of the parabola in the first target acquisition image and the pixel positions of the parabola in the second target acquisition image, the first actual position and the second actual position of the parabola relative to the target floor are determined;

[0052] Based on the first actual position and the second actual position, as well as the image acquisition time difference between the first target acquisition image and the second target acquisition image, the velocity of the parabola when it appears at the target position is determined;

[0053] The actual height at which the parabola appears at the target position is determined based on the first actual height of the first actual position and the second actual height of the second actual position.

[0054] The preset time can be an extremely short period, such as the image acquisition time between two adjacent frames, to more accurately determine the instantaneous velocity of the parabola. Specifically, for two target acquisition images containing the parabola within a very short time frame, the pixel positions of the parabola in the first acquisition image and the second acquisition image can be determined respectively, thereby determining the first and second actual positions of the parabola relative to the target floor, and thus determining the displacement of the parabola within the preset time. Based on the image acquisition time difference between the first and second target acquisition images, the time corresponding to the parabola falling to the aforementioned displacement can be determined. Based on the displacement and time, the velocity of the parabola when it appears at the target position can be determined. Specifically, the first actual height of the parabola at the first actual position and the second actual height of the parabola at the second actual position can be determined based on the floor calibration information. Since the velocity of the parabola is the average velocity calculated from the first to the second actual position, the average of the first and second actual heights can be used as the actual height of the parabola when it appears at the target position. Determining the velocity and actual height of the parabola facilitates subsequent reconstruction of the parabola's trajectory and determination of the second motion information of the parabola within another field of view.

[0055] Specifically, assuming the telephoto lens detects a parabola, the position of the parabola in the target image is as follows: Figure 4 As shown, in pn, p represents the p-th floor of the target floor, and n represents the n-th unit from the left, which corresponds to... Figure 2 Each floor unit in the image. The parabola is located within the floor unit corresponding to pn in the target image, and m is the position of the parabola, which can be determined by the pixel distance a from m to the left edge of pn. nAnd the horizontal pixel distance 'a' of pn determines the specific position of the parabola relative to the target floor. Assuming the coordinates of the left edge of the target floor are 0, and the length of a floor unit in the horizontal direction is 1, then the specific position of m in the horizontal direction relative to the target floor is n-1+a. n / a. Assume the pixel distance from the left edge of the parabola to pn in the first target image is a1, and the acquisition time is t1; the pixel distance from the left edge of pn to pn in the second target image is a2, and the acquisition time is t2; then the horizontal velocity is... The same applies in the vertical direction, such as... Figure 5 As shown, the pixel distance from the bottom edge of the parabola m is b. p Let b be the pixel distance from the top edge to the bottom edge of cell pn. Assume the coordinate of the bottom edge of the target floor is 0, and the length of a floor cell in the vertical direction is 1. The specific position of m in the vertical direction relative to the target floor is p-1+b. p / b. Assuming the distance between the parabola and the upper edge of pn in the first target image is b1, and the acquisition time is t1, and the distance between the parabola and the upper edge of pn in the second target image is b2, and the acquisition time is t2, then the vertical velocity... The height of m, H = d*(p-1+b) p / b), where d is the floor height. The height of the parabola can be represented by the average height of the parabola in the first target acquisition image and the second target acquisition image, i.e.

[0056] S220. Based on the speed, the actual height, and the gravitational acceleration, the trajectory of the parabola is reconstructed within the other field of view to obtain the second motion information of the parabola within the other field of view.

[0057] In addition, H can also be represented using the principle of parabolic motion, that is... Solving the two equations simultaneously, we can obtain T, which is the time it takes for the parabola to fall from point m to the ground. The horizontal displacement of the parabola is S = V0 * T.

[0058] Based on this, by substituting any height *h* within another field of view into the above formula, we can calculate the horizontal position and velocity of the parabola when it falls to that height, thus obtaining the second motion information of the parabola within the other field of view. For example, calculating the horizontal displacement of the parabola at a height of 3 floors determines its horizontal position, and calculating the horizontal displacement at a height of 2 floors determines its horizontal position. In other words, we can obtain the coordinates of multiple parabolas, and connecting them gives the trajectory of the parabola.

[0059] Similarly, if a short focal length lens detects a parabola, the final velocity of the parabola falling into the target's field of view within the short focal length lens's image is calculated from the target image captured by the short focal length lens. This allows us to deduce the initial velocity and position of the parabola when it appears in the other field of view of the telephoto lens.

[0060] S230. Verify the parabolic detection result of the target lens based on the detection result of the object satisfying the second motion information in another acquired image of the other lens.

[0061] According to the scheme in the above embodiments, the second motion information of the parabola within another field of view has been calculated. This information can be used to detect another captured image from another lens to determine whether an object satisfying the second motion information exists. For example, the trajectory point of the parabola when it appears within the other field of view can be determined based on the second motion information. It can then be detected whether an object exists at the corresponding trajectory point in the other captured image. If an object exists, it is confirmed that the parabola does exist, and the detection result of the target lens is accurate.

[0062] In this embodiment of the application, if the target field of view is located above the other field of view, the parabolic detection result of the target lens is verified based on the detection result of an object satisfying the second motion information in another acquired image of the other lens, including:

[0063] Based on the second motion information of the parabola within the other field of view, predict the region image in which the parabola appears in the other acquired image;

[0064] Real-time region metering and / or region enhancement are performed on the region image to detect whether there is a detection result for an object in the region image that satisfies the second motion information.

[0065] For example, if a target lens in the upper field of view detects a parabola, another lens in the lower field of view may not yet have triggered a detection alarm. To improve the positive detection rate of the other lens, the region in the other acquired image where the parabola might appear can be predicted based on the pre-predicted second motion information of the parabola within the other field of view. This means predicting which area in the other acquired image the parabola might appear in. Real-time region metering and / or region enhancement can be performed on the region image to reduce the impact of environmental factors such as lighting and sunlight on parabola detection, thus improving the accuracy of region image detection. This increases the probability that the other lens will detect the parabola if it actually exists within the other field of view. If an object satisfying the second motion information is detected during region image detection, it indicates that a parabola has been detected and can be reported, improving the positive detection rate of the other lens. If the other lens still does not detect the parabola, its sensitivity can be adaptively increased to improve its detection accuracy.

[0066] This application provides a method for detecting objects thrown from high altitudes. Based on the target image captured by the target lens when the object appears at a target position in the target lens, the velocity and actual height of the object at the target position are determined. Based on the velocity, the actual height, and gravitational acceleration, the trajectory of the object is reconstructed within another field of view to obtain second motion information of the object within that other field of view. This method can accurately deduce the second motion information of the object appearing in another field of view based on the information captured by the target lens. Therefore, based on the second motion information and the other captured image, object detection is performed to verify the detection results of the target lens and supplement any missed detections by the other lens.

[0067] Figure 6 This is a flowchart of a method for detecting objects thrown from heights, provided as another embodiment of this application. This embodiment is an optimization based on the above embodiments; solutions not described in detail in this embodiment are found in the above embodiments. Figure 6 As shown, the method in this embodiment of the application specifically includes the following steps:

[0068] S310. If a target lens detects a parabola in either the short-focus lens or the long-focus lens, then based on the target image captured by the target lens of the parabola, the first motion information of the parabola within the target field of view of the target lens is determined; wherein the field of view of the long-focus lens and the field of view of the short-focus lens cover the target floor and are arranged in a vertical direction.

[0069] S320. Based on the first motion information of the parabola within the target field of view and the other field of view of the other lens, determine the second motion information of the parabola within the other field of view; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the long focal length lens.

[0070] S330. Predict the second parabolic size of the parabolic object in the other acquired image based on the first parabolic size in which the parabolic object appears in the target acquired image.

[0071] For example, the pixel range occupied by the parabola can be determined within the target image. Based on the image acquisition parameters of the target lens, such as focal length and field of view, the relationship between the target image and the actual field of view can be determined, thereby determining the actual size of the parabola. Based on the actual size and the relationship between another acquired image and the actual field of view, the size of a second parabola appearing in the other acquired image can be determined.

[0072] In this embodiment of the application, predicting the second parabolic size of the parabolic object appearing in the other acquired image based on the first parabolic size of the parabolic object appearing in the target acquired image includes:

[0073] The actual size of the parabola is determined based on the focal length of the target lens, the actual distance between the target lens and the parabola, the first height of the parabola within the target field of view, and the first size of the parabola.

[0074] The second parabolic size of the parabolic object appearing in the other acquired image is determined based on the focal length of the other lens, the predicted distance between the other lens and the parabolic object, the second height of the parabolic object within the other field of view, and the actual size of the parabolic object.

[0075] For example, assuming the focal length of the target lens is f1, the actual distance between the target lens and the parabola is approximately equal to the distance D between the target lens and the target building surface, which is known during pre-installation. The first height H1 of the parabola within the target's field of view, and the first parabola size, can be the pixel range of the parabola in the target's captured image, for example, the pixel range r1 it occupies. Then, according to the formula... Determine the actual size r0 of the parabola.

[0076] The focal length of the other lens is f2, and the actual distance between the other lens and the parabola is approximately equal to the distance D between the other lens and the target building. The second height H2 of the parabola within the other field of view can be determined using the following formula. Determine the second parabolic size r2 within another acquired image. m2 can be the range of pixels occupied by the parabolic object within the other acquired image. If we assume the parabolic object is circular in the target acquired image, it will also be circular in the other acquired image, i.e., a circle occupying the range of r2 pixels. The advantage of the above scheme is that it can accurately predict the size of the parabolic object when it appears in another field of view of another lens. Therefore, when performing detection based on the second motion information and the other acquired image, the detection is performed by combining the size of the parabolic object within the other field of view of the other lens. In other words, it detects whether an object that satisfies the second parabolic size and the second motion information appears in the other acquired image, thereby improving the accuracy of detection.

[0077] In this embodiment of the application, the process of determining the other acquired image includes:

[0078] Predict the target time period during which the parabola will appear within the other field of view based on the second motion information;

[0079] The image captured by the other lens during the target time period is used as the other captured image.

[0080] For example, when acquiring another image for verification, there are certain requirements regarding the acquisition time of that image. The target time period for the parabola to appear within another field of view can be predicted based on the second motion information. Specifically, the upper and lower limits of the other field of view can be substituted into the formula in the above scheme to calculate the target time period for the parabola to appear within that field of view. An image acquired by another lens within the target time period is then used as the other acquired image. Detection within this other acquired image within the target time period maximizes the probability of detecting the parabola.

[0081] S340. Based on the second parabolic size and the second motion information, predict the predicted presentation result of the parabolic object in the other acquired image.

[0082] For example, based on the second parabolic size and the second motion information, the predicted rendering result of the parabola appearing in another acquired image can be predicted. That is, it can be predicted that an object with the second parabolic size will appear in the other acquired image, moving according to the second motion information, and appearing at the position reflected by the second motion information. For example, such as... Figure 7 As shown, assuming that the position of the parabola appearing in another field of view of the short focal length lens is m1-m5 based on the second motion information, it can be predicted that an object of the second parabola size will appear at the position m1-m5 in another acquired image.

[0083] S350. Detect whether the predicted rendering result of the object appears in the other acquired image, and verify the parabolic detection result of the target lens based on the detection result of the predicted rendering result of the object.

[0084] For example, another acquired image is tested to see if the predicted object will appear. For instance, does an object of the second parabolic size appear at positions m1-m5 in the other acquired image? If so, it indicates that the target lens's detection result is accurate. If the other lens does not trigger a parabolic detection alarm, it indicates that the other lens missed detection.

[0085] In this embodiment of the application, the parabolic detection result of the target lens is verified based on the detection result of the predicted rendering result of the object, including:

[0086] If the predicted rendering result of the object appears in the other acquired image, then the parabolic detection result of the target lens is determined to be correct;

[0087] Otherwise, based on the predicted rendering result, the region image in which the parabola appears in the other acquired image is predicted. After performing regional metering and / or regional enhancement on the region image, the predicted rendering result of the object is detected again in the region image.

[0088] For example, if the predicted object appears in another acquired image, the parabolic detection result of the target lens is determined to be correct. If the predicted object does not appear in the other acquired image, the region in the other acquired image where the parabola will appear can be predicted based on the predicted object. Region metering and / or region enhancement processing is then performed on the region image to reduce the impact of environmental factors such as lighting and sunlight on parabolic detection. After performing region metering and / or region enhancement processing on the region image, the predicted object appears again in the region image to resolve the issue of missing parabolas due to image brightness problems.

[0089] As a non-limiting implementation, the method also includes:

[0090] Determine the parabolic trajectory based on the first motion information and the second motion information;

[0091] Based on the parabolic trajectory, determine the actual initial height when the parabolic velocity is zero;

[0092] Based on the actual initial height relative to the target floor, the position of the thrower of the projectile on the target floor is locked.

[0093] For example, the trajectory of the projectile can be derived based on the first and second motion information, as described in the embodiments above. The actual initial height at which the projectile's velocity is zero can be determined based on its trajectory, thus determining where the projectile originated. Based on the position of the actual initial height relative to the target floor, the position of the projectile thrower on the target floor can be located. For example, as... Figure 7 As shown, by tracing the trajectory of the parabola, it can be determined that the position where the parabola's velocity is zero is located in unit 9-3, thus identifying the person who launched the parabola as being in unit 9-3. This method can accurately pinpoint the starting position of the parabola, thereby pinpointing the location of the person who launched it.

[0094] As a non-limiting implementation, after determining the actual initial height when the parabolic velocity is zero, the method further includes:

[0095] If the actual initial height exceeds the field of view of the short focal length lens and the upper limit of the field of view of the telephoto lens, then the frequency of the parabola being thrown and the actual size of the parabola are statistically analyzed.

[0096] If the throwing frequency reaches a preset frequency and the actual size of the projectile meets the preset object size, then the short focal length lens and the long focal length lens are notified to stop detecting projectiles that meet the trajectory and actual size.

[0097] For example, after determining the actual initial height when the projectile velocity is zero, further detection can be performed based on this actual initial height. If the actual initial height exceeds the upper limit of the field of view of the short-focus and long-focus lenses, that is, exceeds the upper limit of the target floor, it indicates that the projectile may not be an object thrown from the target floor. The throwing frequency and actual size of the projectile can then be statistically analyzed. If the throwing frequency reaches a preset frequency, such as a high frequency, and the actual size of the projectile meets a preset object size, such as the size of rain or snow, it indicates that the current projectile is rain or snow. In this case, the short-focus and long-focus lenses are notified to stop detecting projectiles that meet the above conditions, reducing the detection sensitivity for this type of projectile and thus saving unnecessary resource consumption.

[0098] Figure 8 This is a schematic diagram of a high-altitude object throwing detection device provided in an embodiment of this application. This device can execute the high-altitude object throwing detection method provided in any embodiment of this application, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 8 As shown, the device includes:

[0099] The first motion information determination module 410 is used to determine the first motion information of the parabola within the target field of view of the target lens based on the target image captured by the target lens of the parabola if a target lens detects a parabola in either the short focal length lens or the long focal length lens; wherein the field of view of the long focal length lens and the field of view of the short focal length lens cover the target floor and are arranged in a vertical direction.

[0100] The second motion information determination module 420 is used to determine the second motion information of the parabola in the other field of view based on the first motion information of the parabola in the target field of view and the other field of view of the other lens; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the long focal length lens.

[0101] The verification module 430 is used to verify the parabolic detection result of the target lens based on the detection result of an object that satisfies the second motion information in another acquired image of the other lens.

[0102] In this embodiment of the application, the first motion information determination module 410 determines the first motion information of the parabola within the target field of view of the target lens based on the target image captured by the target lens, including:

[0103] Based on the target image captured by the target lens when the parabola appears at the target position in the target lens, the velocity and actual height of the parabola at the target position are determined;

[0104] Accordingly, based on the first motion information of the parabola within the target field of view and the other field of view of the other lens, the second motion information of the parabola within the other field of view is determined, including:

[0105] Based on the speed, the actual height, and the gravitational acceleration, the trajectory of the parabola is reconstructed within the other field of view to obtain the second motion information of the parabola within the other field of view.

[0106] In this embodiment of the application, the first motion information determination module 410 determines the velocity and actual height of the parabola at the target position based on the target image captured by the target lens when the parabola appears at the target position in the target lens, including:

[0107] Acquire the first target image and the second target image captured by the target lens within a preset time period;

[0108] Based on the pixel positions of the parabola in the first target acquisition image and the pixel positions of the parabola in the second target acquisition image, the first actual position and the second actual position of the parabola relative to the target floor are determined;

[0109] Based on the first actual position and the second actual position, as well as the image acquisition time difference between the first target acquisition image and the second target acquisition image, the velocity of the parabola when it appears at the target position is determined;

[0110] The actual height at which the parabola appears at the target position is determined based on the first actual height of the first actual position and the second actual height of the second actual position.

[0111] In this embodiment of the application, the verification module 430 verifies the parabolic detection result of the target lens based on the detection result of an object satisfying the second motion information in the image acquired by the other lens, including:

[0112] Predict the second parabolic size in the other acquired image based on the first parabolic size in which the parabolic object appears within the target acquired image;

[0113] Based on the second parabolic size and the second motion information, predict the predicted rendering result of the parabolic object in the other acquired image;

[0114] The predicted rendering result of the object appears in the other acquired image. Based on the detection result of the predicted rendering result of the object, the parabolic detection result of the target lens is verified.

[0115] In this embodiment of the application, the verification module 430 predicts the second parabolic size of the parabolic object appearing in the other acquired image based on the first parabolic size of the parabolic object appearing in the target acquired image, including:

[0116] The actual size of the parabola is determined based on the focal length of the target lens, the actual distance between the target lens and the parabola, the first height of the parabola within the target field of view, and the first size of the parabola.

[0117] The second parabolic size of the parabolic object appearing in the other acquired image is determined based on the focal length of the other lens, the predicted distance between the other lens and the parabolic object, the second height of the parabolic object within the other field of view, and the actual size of the parabolic object.

[0118] In this embodiment of the application, the device further includes:

[0119] The target time period determination module is used to predict the target time period in which the parabola appears within the other field of view based on the second motion information.

[0120] Another target acquisition image determination module is used to use the image acquired by the other lens during the target time period as the other acquisition image.

[0121] In this embodiment of the application, if the target field of view is located above the other field of view, the verification module 430 verifies the parabolic detection result of the target lens based on the detection result of an object satisfying the second motion information in another acquired image of the other lens, including:

[0122] Based on the second motion information of the parabola within the other field of view, predict the region image in which the parabola appears in the other acquired image;

[0123] Real-time region metering and / or region enhancement are performed on the region image to detect whether there is a detection result for an object in the region image that satisfies the second motion information.

[0124] In this embodiment of the application, the device further includes:

[0125] A parabolic trajectory determination module is used to determine the parabolic trajectory based on the first motion information and the second motion information;

[0126] The actual initial height determination module is used to determine the actual initial height when the parabolic velocity is zero, based on the parabolic trajectory.

[0127] The position determination module is used to lock the position of the thrower of the projectile on the target floor based on the position of the actual initial height relative to the target floor.

[0128] In this embodiment of the application, after determining the actual initial height when the parabolic velocity is zero, the method further includes:

[0129] If the actual initial height exceeds the field of view of the short focal length lens and the upper limit of the field of view of the telephoto lens, then the frequency of the parabola being thrown and the actual size of the parabola are statistically analyzed.

[0130] If the throwing frequency reaches a preset frequency and the actual size of the projectile meets the preset object size, then the short focal length lens and the long focal length lens are notified to stop detecting projectiles that meet the trajectory and actual size.

[0131] The high-altitude object throwing detection device provided in this application embodiment can execute a high-altitude object throwing detection method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.

[0132] Figure 9 A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0133] like Figure 9 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless high-altitude object throwing detection transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0135] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the high-altitude object detection method.

[0136] In some embodiments, the high-altitude object throwing detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the high-altitude object throwing detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the high-altitude object throwing detection method by any other suitable means (e.g., by means of firmware).

[0137] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable high-altitude object throwing detection device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0141] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0142] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0143] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.

[0144] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting objects thrown from heights, characterized in that, The method includes: If a target lens detects a parabola in either the short-focus lens or the long-focus lens, then based on the target image captured by the target lens of the parabola, the first motion information of the parabola within the target field of view of the target lens is determined; wherein the field of view of the long-focus lens and the field of view of the short-focus lens cover the target floor and are arranged in a vertical direction. Based on the first motion information of the parabola within the target field of view and the other field of view of another lens, the second motion information of the parabola within the other field of view is determined; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the long focal length lens; The parabolic detection result of the target lens is verified based on the detection result of an object satisfying the second motion information in another acquired image of the other lens.

2. The method according to claim 1, characterized in that, Based on the target image captured by the target lens of the parabola, the first motion information of the parabola within the target field of view of the target lens is determined, including: Based on the target image captured by the target lens when the parabola appears at the target position in the target lens, the velocity and actual height of the parabola at the target position are determined; Accordingly, based on the first motion information of the parabola within the target field of view and the other field of view of the other lens, the second motion information of the parabola within the other field of view is determined, including: Based on the speed, the actual height, and the gravitational acceleration, the trajectory of the parabola is reconstructed within the other field of view to obtain the second motion information of the parabola within the other field of view.

3. The method according to claim 2, characterized in that, Based on the target image captured by the target lens when the parabola appears at the target position in the target lens, the velocity and actual height of the parabola at the target position are determined, including: Acquire the first target image and the second target image captured by the target lens within a preset time period; Based on the pixel positions of the parabola in the first target acquisition image and the pixel positions of the parabola in the second target acquisition image, the first actual position and the second actual position of the parabola relative to the target floor are determined; Based on the first actual position and the second actual position, as well as the image acquisition time difference between the first target acquisition image and the second target acquisition image, the velocity of the parabola when it appears at the target position is determined; The actual height at which the parabola appears at the target position is determined based on the first actual height of the first actual position and the second actual height of the second actual position.

4. The method according to claim 1, characterized in that, Based on the detection results of objects satisfying the second motion information in the image acquired by the other lens, the parabolic detection results of the target lens are verified, including: Predict the second parabolic size in the other acquired image based on the first parabolic size in which the parabolic object appears within the target acquired image; Based on the second parabolic size and the second motion information, predict the predicted rendering result of the parabolic object in the other acquired image; The predicted rendering result of the object appears in the other acquired image. Based on the detection result of the predicted rendering result of the object, the parabolic detection result of the target lens is verified.

5. The method according to claim 4, characterized in that, Predicting the second parabolic size in the other acquired image based on the first parabolic size appearing in the target acquired image includes: The actual size of the parabola is determined based on the focal length of the target lens, the actual distance between the target lens and the parabola, the first height of the parabola within the target field of view, and the first size of the parabola. The second parabolic size of the parabolic object appearing in the other acquired image is determined based on the focal length of the other lens, the predicted distance between the other lens and the parabolic object, the second height of the parabolic object within the other field of view, and the actual size of the parabolic object.

6. The method according to claim 1, characterized in that, If the target field of view is located above the other field of view, then the parabolic detection result of the target lens is verified based on the detection result of an object satisfying the second motion information in another acquired image of the other lens, including: Based on the second motion information of the parabola within the other field of view, predict the region image in which the parabola appears in the other acquired image; Real-time region metering and / or region enhancement are performed on the region image to detect whether there is a detection result for an object in the region image that satisfies the second motion information.

7. The method according to claim 1, characterized in that, The method further includes: Determine the parabolic trajectory based on the first motion information and the second motion information; Based on the parabolic trajectory, determine the actual initial height when the parabolic velocity is zero; Based on the actual initial height relative to the target floor, the position of the thrower of the projectile on the target floor is determined. After determining the actual initial height when the parabolic velocity is zero, the method further includes: If the actual initial height exceeds the field of view of the short focal length lens and the upper limit of the field of view of the telephoto lens, then the frequency of the parabola being thrown and the actual size of the parabola are statistically analyzed. If the throwing frequency reaches a preset frequency and the actual size of the projectile meets the preset object size, then the short focal length lens and the long focal length lens are notified to stop detecting projectiles that meet the trajectory and actual size.

8. A high-altitude object throwing detection device, characterized in that, The device includes: The first motion information determination module is used to determine the first motion information of the parabola within the target field of view of the target lens if a target lens detects a parabola in either the short-focal-length lens or the long-focal-length lens; wherein the field of view of the long-focal-length lens and the field of view of the short-focal-length lens cover the target floor and are arranged in a vertical direction. The second motion information determination module is used to determine the second motion information of the parabola within the other field of view based on the first motion information of the parabola within the target field of view and the other field of view of the other lens; wherein, the other lens is a lens of another type other than the target lens among the short focal length lens and the telephoto lens; The verification module is used to verify the parabolic detection result of the target lens based on the detection result of an object satisfying the second motion information in another acquired image of the other lens.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the high-altitude object throwing detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the high-altitude object throwing detection method according to any one of claims 1-7.

Images