Method, device, computer equipment and storage medium for tracking fallen objects

Abstract

The present application relates to a method, device, computer equipment and storage medium for tracking a falling object. The method comprises: obtaining a set of multiple captured images, identifying a falling object based on the set of multiple captured images, obtaining a set of captured images including images of the falling object, obtaining an image acquisition device identifier corresponding to the set of captured images including images of the falling object based on the set of captured images including images of the falling object, obtaining device coordinate parameters of the image acquisition device corresponding to the image acquisition device identifier based on the image acquisition device identifier, locking the position of the falling object based on the device coordinate parameters, and obtaining multiple coordinate parameters of the falling object within a preset range of the position of the falling object, determining the target falling trajectory of the falling object based on the coordinate parameters, and tracking the falling object based on the target falling trajectory. The use of this method can respond to falling objects based on the tracking results, significantly reducing the risk of being hit by falling objects.

Description

Technical Field

[0001] The present application relates to the field of construction engineering technology, and in particular to a method, device, computer equipment and storage medium for tracking fallen objects. Background Art

[0002] With the development of modern large-scale building systems, more and more high-rise buildings and large construction sites have emerged. When pedestrians are near high-rise buildings and large construction sites, there is a great risk of being hit by falling objects.

[0003] Take a construction site as an example. A construction site refers to a place where a construction project is being developed and civil engineering is being carried out. The area is often enclosed by fences, wire mesh or walls to restrict the entry and exit of personnel, materials, machinery and vehicles. On construction sites, workers are often injured by falling materials from high-rise buildings. Workers on construction sites are at great risk of being injured by falling objects. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for tracking falling objects that can accurately track falling objects and significantly reduce the risk of being hit by falling objects in order to address the above technical problems.

[0005] A method for tracking a fallen object, the method comprising:

[0006] Acquire a set of multiple captured images, identify the falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0007] According to the captured image set including the image of the falling object, an image acquisition device identification corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identification, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identification is obtained;

[0008] The position of the falling object is locked according to the coordinate parameters of the device, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters;

[0009] Track falling objects based on their target falling trajectory.

[0010] In one embodiment, acquiring a set of multiple captured images and identifying a falling object based on the set of multiple captured images comprises:

[0011] Obtaining a capture time interval corresponding to a set of multiple captured images and a frame number identifier carried by each captured image frame;

[0012] Obtaining a set of images of objects to be identified in each frame of captured images according to a preset target detection algorithm;

[0013] Determining the capture order of the captured images according to the frame number identifier carried by each frame of the captured image;

[0014] Calculating first distance information and second distance information of each to-be-identified object image in the to-be-identified object image set according to the capture order of the captured images, the first distance information and the second distance information being position distance information of each to-be-identified object image in any two frames of captured images;

[0015] The distance difference between the first distance information and the second distance information is calculated, and the falling object is identified according to the distance difference and the capture time interval.

[0016] In one embodiment, identifying the falling object according to the distance difference and the capture time interval includes:

[0017] Calculate the acceleration of each object to be identified based on the distance difference and the capture time interval;

[0018] Calculate the acceleration difference between the acceleration and the acceleration due to gravity;

[0019] When the acceleration difference is less than a preset difference threshold, the object to be identified is determined to be a falling object;

[0020] When the acceleration difference is greater than the difference threshold, the tracking number is obtained. According to the capture order of the captured images, the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time interval of the tracking number is calculated. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object.

[0021] In one embodiment, the position of the falling object is locked according to the device coordinate parameters, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters, including:

[0022] Determine a set of image acquisition devices belonging to the same group according to the image acquisition device identifier;

[0023] Obtaining device coordinate parameters of each image acquisition device in each group of image acquisition device sets;

[0024] According to the captured images and device coordinate parameters collected by each image acquisition device, the location of the falling object is locked, and multiple coordinate parameters of the falling object within a preset range of the location of the falling object are obtained;

[0025] According to the coordinate parameters, the parabola of the falling object is fitted, and according to the parabola of the falling object, the initial falling trajectory of the falling object is determined;

[0026] According to a preset acquisition interval, a set of captured images to be analyzed is continuously acquired from the image acquisition device, and a target falling trajectory of the falling object is obtained according to the set of captured images to be analyzed and the initial falling trajectory.

[0027] In one embodiment, fitting a parabola of the falling object according to the coordinate parameters, and determining an initial falling trajectory of the falling object according to the parabola of the falling object includes:

[0028] Fitting the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the position of the falling object;

[0029] Obtaining multiple falling object coordinate information according to the coordinate parameters, and obtaining a horizontal displacement distance and a vertical displacement distance according to the falling object coordinate information, wherein the horizontal displacement distance and the vertical displacement distance are the displacement difference between any two falling object coordinates in the parabola of the falling object;

[0030] Obtaining the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance;

[0031] The initial falling trajectory of the falling object is determined based on the horizontal displacement distance, vertical displacement distance and displacement time.

[0032] In one embodiment, according to a preset acquisition interval, continuously acquiring a set of captured images to be analyzed from an image acquisition device, and obtaining a target falling trajectory of the falling object according to the set of captured images to be analyzed and the initial falling trajectory includes:

[0033] Continuously acquiring a set of captured images to be analyzed from an image acquisition device according to a preset acquisition interval;

[0034] According to the captured image set to be analyzed and the device coordinate parameters of the image acquisition device, a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object are obtained;

[0035] The initial falling trajectory is corrected according to the coordinate parameters to be processed to obtain the target falling trajectory of the falling object.

[0036] In one embodiment, after tracking the falling object according to the target falling trajectory, the method further includes:

[0037] Determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object according to the falling object trajectory;

[0038] According to the horizontal coordinate information and the vertical coordinate information, the preset building coordinate system is compared to determine the target coordinate information of the falling object in the building coordinate system;

[0039] According to the target coordinate information, obtain the capture net number corresponding to the falling trajectory in the building coordinate system;

[0040] Outputting a control instruction to the capture net corresponding to the falling trajectory according to the capture net number, so that the capture net captures the falling object;

[0041] The dangerous area is determined according to the target coordinate information, and the preset environment map is updated according to the coordinate information of the determined dangerous area.

[0042] A device for tracking a falling object, the device comprising:

[0043] A first acquisition module is used to acquire a set of multiple captured images, identify the falling object according to the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0044] A second acquisition module is used to acquire, based on the captured image set including the image of the falling object, an image acquisition device identifier corresponding to the captured image set including the image of the falling object, and acquire, based on the image acquisition device identifier, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identifier;

[0045] A processing module, used to lock the position of the falling object according to the device coordinate parameters, and obtain multiple coordinate parameters of the falling object within a preset range of the falling object position, and determine the target falling trajectory of the falling object according to the coordinate parameters;

[0046] The tracking module is used to track the falling object according to the target falling trajectory.

[0047] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0048] Acquire a set of multiple captured images, identify the falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0049] According to the captured image set including the image of the falling object, an image acquisition device identification corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identification, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identification is obtained;

[0050] The position of the falling object is locked according to the coordinate parameters of the device, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters;

[0051] Track falling objects based on their target falling trajectory.

[0052] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0053] Acquire a set of multiple captured images, identify the falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0054] According to the captured image set including the image of the falling object, an image acquisition device identification corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identification, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identification is obtained;

[0055] The position of the falling object is locked according to the coordinate parameters of the device, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters;

[0056] Track falling objects based on their target falling trajectory.

[0057] The above-mentioned method, device, computer equipment and storage medium for tracking fallen objects identify fallen objects by acquiring and comparing a plurality of captured image sets, obtaining a captured image set including images of fallen objects, acquiring an image acquisition device identifier corresponding to the captured image set including images of fallen objects based on the captured image set including images of fallen objects, acquiring corresponding device coordinate parameters based on the image acquisition device identifier, locking the location of the fallen object based on the device coordinate parameters, and obtaining a plurality of coordinate parameters of the fallen object within a preset range of the location of the fallen object, determining the target falling trajectory of the fallen object based on the coordinate parameters, and tracking the fallen object based on the target falling trajectory. In the whole process, the fallen object is accurately identified and tracked based on the target falling trajectory, so that the fallen object can be dealt with based on the tracking results, significantly reducing the risk of being hit by the falling object. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of a flow chart of a method for tracking a fallen object in one embodiment;

[0059] Figure 2 In one embodiment Figure 1 Schematic diagram of the sub-process of step S102;

[0060] Figure 3 In one embodiment Figure 2 Schematic diagram of the sub-process of step S210;

[0061] Figure 4 In one embodiment Figure 1 Schematic diagram of the sub-process of step S106;

[0062] Figure 5 In one embodiment Figure 4 Schematic diagram of the sub-process of step S408;

[0063] Figure 6 In one embodiment Figure 4 Schematic diagram of the sub-process of step S410;

[0064] Figure 7 A schematic flow chart of a method for tracking a fallen object in another embodiment;

[0065] Figure 8 is a structural block diagram of a device for tracking a fallen object in one embodiment;

[0066] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] In one embodiment, Figure 1 As shown, a method for tracking a falling object is provided, the method comprising the following steps:

[0069] S102: Acquire a set of multiple captured images, identify a falling object based on the set of multiple captured images, and obtain a set of captured images including images of the falling object.

[0070] A frame refers to a single image that is the smallest unit in an image animation. A frame is a still picture, and continuous frames form an animation. A multi-frame captured image set is obtained from an image acquisition device. An image acquisition device refers to a device that is set within a preset range to capture images of objects. A multi-frame captured image set includes at least three frames of captured images captured by the same image acquisition device. After obtaining the multi-frame captured image set, the server will identify the falling object based on the multi-frame captured image set to obtain a captured image set that includes the image of the falling object. Specifically, the server communicates with the image acquisition device, and the server can obtain data such as captured images from the image acquisition device through 5G technology.

[0071] Identifying a falling object based on a set of multiple captured images includes obtaining an image of an object to be identified from the multiple captured images, and determining whether the object to be identified is a falling object based on the position of the image of the object to be identified in each captured image frame and the capture time interval. Because the object to be identified is only affected by gravity and resistance in the vertical direction, it is possible to determine whether the object to be identified is a falling object by calculating the acceleration of the object to be identified in the vertical direction.

[0072] S104: Based on the captured image set including the image of the falling object, obtain the image acquisition device identification corresponding to the captured image set including the image of the falling object, and based on the image acquisition device identification, obtain the device coordinate parameters of the image acquisition device corresponding to the image acquisition device identification.

[0073] The captured image carries an image acquisition device identifier, which is used to determine the image acquisition device corresponding to the captured image. After obtaining a captured image set including images of falling objects, the server will obtain the image acquisition device identifier corresponding to the captured image set including images of falling objects based on the captured image set including images of falling objects. The image acquisition device that captured the falling object can be determined based on the image acquisition device identifier, and then the device coordinate parameters of the image acquisition device can be obtained. The device coordinate parameters of the image acquisition device refer to the coordinate parameters of the image acquisition device in a preset coordinate system within a preset range. Among them, the preset coordinate system can be set as needed, usually a spatial rectangular coordinate system. For example, if the preset environment refers to a construction site, then the device coordinate parameters of the image acquisition device refer to the position parameters of the image acquisition device on the construction site.

[0074] S106: Lock the position of the falling object according to the device coordinate parameters, obtain multiple coordinate parameters of the falling object within a preset range of the position of the falling object, and determine the target falling trajectory of the falling object according to the coordinate parameters.

[0075] The image acquisition devices are grouped as units. The server first determines the position information of the falling object in the captured image corresponding to the image acquisition device, and then locks the position of the falling object according to the device coordinate parameters of a group of image acquisition devices and the position information of the falling object in the captured image captured by the group of image acquisition devices, and obtains multiple coordinate parameters of the falling object within the preset range of the falling object's position. Specifically, a frame of captured image set of each group of image acquisition devices can determine a coordinate parameter of the falling object, and the coordinate parameter refers to a set of coordinate values ​​of the falling object within the preset range. The number of groups of image acquisition devices can be determined according to the size of the preset range and the line of sight of the image acquisition device. If the preset range of the image acquisition device can cover the entire preset range, then only one group of image acquisition devices is needed here. If it cannot be covered, multiple groups of image acquisition devices are required.

[0076] Because the falling object falls from a high altitude, there will be a corresponding relationship between the parabola where the falling object is located and the preset coordinate system within the preset range. Specifically, the corresponding relationship can be that the falling surface where the falling object is located will be perpendicular to the horizontal coordinate plane within the preset range. After obtaining multiple coordinate parameters, the server can fit the parabola of the falling object according to these multiple coordinate parameters and the corresponding relationship between the falling object and the preset coordinate system within the preset range, and then according to the positional relationship between the parabola and the preset coordinate system, convert the multiple coordinate parameters into multiple falling object coordinate information with the parabola as the reference coordinate system, and determine the initial falling trajectory of the falling object based on the falling object coordinate information.

[0077] After obtaining the initial falling trajectory, due to the influence of wind resistance and error, it is necessary to correct the initial falling trajectory in real time to obtain the target falling trajectory. The specific method can be that while the falling object continues to fall, the server continuously obtains the set of captured images to be analyzed from the image acquisition device according to the preset acquisition interval, and obtains multiple coordinate parameters to be processed within the preset range of the falling object's position by analyzing the set of captured images to be analyzed and the device coordinate parameters of the image acquisition device, thereby continuously fitting the parabola of the falling object according to the coordinate parameters to be processed, reducing the error between the fitted parabola and the actual parabola, and finally determining the target falling trajectory of the falling object according to the fitted parabola and the multiple coordinate parameters to be processed, reducing the error, and realizing accurate calculation of the target falling trajectory. Among them, the preset acquisition interval can be set as needed.

[0078] S108: Tracking the falling object according to the target falling trajectory.

[0079] The falling trajectory refers to the falling path of the falling object. After obtaining the falling trajectory of the falling object, the falling object can be tracked according to the falling trajectory, and the area where the falling object may pass within the preset range can be predicted, and then a warning can be issued for the area to reduce the risk of being hit by the falling object. Furthermore, if a falling object capture net is installed in the area, the capture net can also be triggered to capture the falling object.

[0080] The above-mentioned method of tracking a fallen object identifies a fallen object by acquiring and comparing a set of captured images of multiple frames, obtaining a set of captured images including the image of the fallen object, acquiring an image acquisition device identifier corresponding to the set of captured images including the image of the fallen object based on the set of captured images including the image of the fallen object, acquiring corresponding device coordinate parameters based on the image acquisition device identifier, locking the location of the fallen object based on the device coordinate parameters, and obtaining multiple coordinate parameters of the fallen object within a preset range of the location of the fallen object, determining the falling trajectory of the fallen object based on the coordinate parameters, and tracking the fallen object based on the target falling trajectory. In the whole process, the fallen object is accurately identified and tracked according to the target falling trajectory, so that the fallen object can be dealt with according to the tracking results, significantly reducing the risk of being hit by the falling object.

[0081] In one embodiment, if Figure 2 As shown, S102 includes:

[0082] S202: Acquire a capture time interval corresponding to a set of multiple captured image frames and a frame number identifier carried by each captured image frame;

[0083] S204: Obtaining a set of images of objects to be identified in each frame of captured image according to a preset target detection algorithm;

[0084] S206: determining a capture order of the captured images according to the frame number identifier carried by each captured image frame;

[0085] S208: Calculating first distance information and second distance information of each to-be-identified object image in the to-be-identified object image set according to the capture order of the captured images, the first distance information and the second distance information being position distance information of each to-be-identified object image in any two frames of captured images;

[0086] S210: Calculate the distance difference between the first distance information and the second distance information, and identify the falling object according to the distance difference and the capture time interval.

[0087] The capture time interval refers to the time interval for the image acquisition device to capture images, and the frame number identifier refers to the sequence identifier carried by each frame of the captured image, which is used to determine the capture order of the captured images. The server will obtain a set of images of objects to be identified in each frame of the captured image according to the preset target detection algorithm. The images of objects to be identified refer to abnormal objects that appear in the captured image. The abnormal objects are identified by the target detection algorithm. Specifically, when training the target detection algorithm, common high-altitude falling objects can be used as sample sets for training. The target detection algorithm here can be a common target detection algorithm based on deep learning, including R-CNN (Region-CNN), YOLO (You Only Look Once) and SSD (Single Shot MultiBox Detector).

[0088] After obtaining the set of images of objects to be identified, the server will determine the capture order of the captured images according to the frame number identifier carried by each frame of the captured image, and then calculate the first distance information and the second distance information of each image of the object to be identified in the set of images of objects to be identified according to the capture order of the captured images, wherein the first distance information and the second distance information are the position distance information of each image of the object to be identified in any two frames of captured images, and specifically, the position distance information here refers to the distance information of the object to be identified in the vertical direction in any two frames of captured images. The first distance information and the second distance information can be obtained by comparing the positions of each image of the object to be identified in each frame of captured images. Specifically, the distance difference can refer to the pixel distance between the positions of each image of the object to be identified in each frame of captured images. After obtaining the distance difference, the server will further identify the falling object based on the distance difference and the capture time interval.

[0089] In one embodiment, if Figure 3 As shown, S210 includes:

[0090] S302: Calculating the acceleration of each object to be identified according to the distance difference and the capture time interval;

[0091] S304: Calculate the acceleration difference between the acceleration and the gravity acceleration;

[0092] S306: When the acceleration difference is less than a preset difference threshold, determining that the object to be identified is a falling object;

[0093] S308: When the acceleration difference is greater than the difference threshold, obtain the number of tracking times, and calculate the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time interval of the tracking number according to the capture order of the captured images. When the acceleration difference within any capture time interval is less than the difference threshold, determine that the object to be identified is a falling object.

[0094] Because the first distance information and the second distance information refer to the position distance information of each object image to be identified in any two frames of captured images, it is necessary to convert the distance difference to obtain the corresponding distance value of the distance difference in the preset coordinate system when identifying falling objects. Specifically, the scaling relationship between the unit distance in the preset coordinate system and the unit pixel distance in the captured image can be determined by pre-calibration, and then the distance difference is converted according to the scaling relationship to obtain the corresponding distance value in the preset coordinate system. Then, the acceleration of each object to be identified is calculated according to the distance value and the capture time interval. Furthermore, when the acquisition screen of the captured image contains a scaffolding background, the scaffolding background can also be used to form a natural screen size grid, and the scaling relationship between the pixel distance and the scaffolding grid spacing can be pre-calibrated to obtain the corresponding distance value of the distance difference in the preset coordinate system.

[0095] Because the object to be identified is only affected by gravity and resistance after falling, and the time interval between each two frames of image capture is very short, it can be considered that the object to be identified moves at a uniform speed in the horizontal direction, and then in the vertical direction, it can be calculated according to the common displacement formula s=0.5*a*t 2 , calculate the acceleration of the object to be identified. For example, the calculation process can be: first distance information s1 = 0.5*a*t1 2 , the second distance information s2 = 0.5*a*t2 2 , because t2-t1 can be obtained according to the capture order and capture time interval of the captured images, the acceleration of the object to be identified can be obtained by calculating s2-s1. After obtaining the acceleration of the object to be identified, the object to be identified can be identified by calculating the acceleration difference between the acceleration and the gravity acceleration. Specifically, when the acceleration difference is less than the preset difference threshold, the object to be identified is determined to be a falling object. When the acceleration difference is greater than the difference threshold, the server needs to continue to track the object to be identified to eliminate calculation errors and accidental errors. The specific tracking method can be: obtain the number of tracking times, and calculate the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time interval according to the capture order of the captured images. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object. The difference threshold here can be determined according to the resistance encountered by the falling object. The resistance of falling objects mainly refers to air resistance, which is proportional to the square of the falling speed of the object to be identified, and is also related to the air friction coefficient and the shape of the object to be identified. In addition, it is also affected by wind speed and wind direction. Among them, information such as wind speed and wind direction can be obtained from the data released by the local meteorological department.

[0096] In one embodiment, if Figure 4 As shown, S106 includes:

[0097] S402: Determine a set of image acquisition devices belonging to the same group according to the image acquisition device identifier;

[0098] S404: Obtaining device coordinate parameters of each image acquisition device in each group of image acquisition device sets;

[0099] S406: According to the captured images and device coordinate parameters collected by each image acquisition device, the location of the falling object is locked, and a plurality of coordinate parameters of the falling object within a preset range of the location of the falling object are obtained;

[0100] S408: fitting a parabola of the falling object according to the coordinate parameters, and determining an initial falling trajectory of the falling object according to the parabola of the falling object;

[0101] S410: According to a preset acquisition interval, continuously acquire a set of captured images to be analyzed from an image acquisition device, and obtain a target falling trajectory of the falling object according to the set of captured images to be analyzed and the initial falling trajectory.

[0102] The server can determine the image acquisition device set belonging to the same group according to the image acquisition device identifier. Specifically, the image acquisition device set of the same group may include two or three image acquisition devices for all-round acquisition of images within a preset range. The server will obtain the device coordinate parameters of each image acquisition device in each group of image acquisition device sets, and the device coordinate parameters include the viewing angle parameter information and position parameter information of the image acquisition device. The server can determine the position information of the falling object in the captured image according to the captured images collected by each image acquisition device, and then according to the viewing angle parameter information and the position parameter information, the position information of the falling object in the captured image can be converted into the coordinate parameters within the preset range of the position of the falling object. Among them, the position information refers to a set of coordinate values ​​of the falling object in the captured image, including horizontal position information and vertical coordinate information, and the coordinate parameters refer to a set of coordinate values ​​of the falling object within the preset range. Converting the position information into coordinate parameters means expressing the coordinate parameters with the position information. For example, in a group of image acquisition devices including a first image acquisition device and a second image acquisition device, the position information of the falling object acquired by the first image acquisition device is (x3, y3), and the position parameter information of the device corresponding to the first image acquisition identifier is (x1, y1, z1), the viewing angle parameter information is (θ1), and the direction is (α1, β1, γ1), the coordinate parameters of the falling object in the XZ plane within the preset range can be obtained as follows:

[0103] p1(x,z)=f(x1,y1,z1)(θ1)(α1,β1,γ1)(x3,y3)

[0104] When the position information of the falling object collected by the second image acquisition device is (x4, y4), and the second image acquisition identifier corresponds to the position parameter information (x2, y2, z2), the viewing angle parameter information (θ2), and the direction (α2, β2, γ2) of the device, the coordinate parameters of the falling object in the YZ plane within the preset range can be obtained as follows:

[0105] p1(y,z)=f(x2,y2,z2)(θ2)(α2,β2,γ2)(x4,y4)

[0106] Because p1(x2, z2) and p1(y2, z2) contain the same coordinate information z2, the coordinate parameters of the falling object can be obtained as p1(x2, y2, z2) based on p1(x2, z2) and p1(y2, z2).

[0107] Because the falling object falls from a high altitude, there will be a corresponding relationship between the parabola where the falling object is located and the preset coordinate system within the preset range. Specifically, the corresponding relationship can be that the falling surface where the falling object is located will be perpendicular to the horizontal coordinate plane within the preset range. After obtaining multiple coordinate parameters, the server can fit the parabola of the falling object according to these multiple coordinate parameters and the corresponding relationship between the falling object and the preset coordinate system within the preset range, and then according to the positional relationship between the parabola and the preset coordinate system, convert the multiple coordinate parameters into multiple falling object coordinate information with the parabola as the reference coordinate system, and determine the initial falling trajectory of the falling object based on the falling object coordinate information.

[0108] After obtaining the initial falling trajectory, due to the influence of wind resistance and error, it is necessary to correct the initial falling trajectory in real time to obtain the target falling trajectory. The specific method can be that while the falling object continues to fall, the server continuously obtains the set of captured images to be analyzed from the image acquisition device according to the preset acquisition interval, and obtains multiple coordinate parameters to be processed within the preset range of the falling object's position by analyzing the set of captured images to be analyzed and the device coordinate parameters of the image acquisition device, thereby continuously fitting the parabola of the falling object according to the coordinate parameters to be processed, reducing the error between the fitted parabola and the actual parabola, and finally determining the target falling trajectory of the falling object according to the fitted parabola and the multiple coordinate parameters to be processed, reducing the error, and realizing accurate calculation of the target falling trajectory. Among them, the preset acquisition interval can be set as needed.

[0109] In one embodiment, if Figure 5 As shown, S408 includes:

[0110] S502: fitting the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the position of the falling object;

[0111] S504: obtaining a plurality of falling object coordinate information according to the coordinate parameters, and obtaining a horizontal displacement distance and a vertical displacement distance according to the falling object coordinate information, wherein the horizontal displacement distance and the vertical displacement distance are displacement differences between any two falling object coordinates in the parabola of the falling object;

[0112] S506: Obtaining displacement time corresponding to the horizontal displacement distance and the vertical displacement distance;

[0113] S508: Determine the initial falling trajectory of the falling object according to the horizontal displacement distance, the vertical displacement distance and the displacement time.

[0114] Because the falling object falls from a high altitude, there will be a corresponding relationship between the parabola where the falling object is located and the preset coordinate system within the preset range. Specifically, the corresponding relationship can be that the falling surface where the falling object is located is perpendicular to the horizontal coordinate plane within the preset range. After obtaining multiple coordinate parameters, the server can fit the parabola of the falling object based on these multiple coordinate parameters and the corresponding relationship between the falling object and the preset coordinate system within the preset range. For example, because there is a corresponding relationship between the parabola where the falling object is located and the preset coordinate system within the preset range, the linear equation corresponding to the parabola where the falling object is located can be calculated through multiple coordinate parameters, and then the angle between the parabola where the falling object is located and a coordinate plane of the preset coordinate system can be calculated through multiple coordinate parameters, and finally the corresponding parabola can be determined through the linear equation and the angle.

[0115] After obtaining the parabola, the server will first convert multiple coordinate parameters into multiple falling object coordinate information with the parabola as the reference coordinate system based on the positional relationship between the parabola and the preset coordinate system, specifically the angle between the parabola and a coordinate plane of the preset coordinate system, and obtain the horizontal displacement distance and vertical displacement distance of the falling object according to the falling object coordinate information. The horizontal displacement distance and the vertical displacement distance are the displacement difference between any two falling object coordinates in the parabola of the falling object. Then the server will obtain the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance, where the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance is the same. Finally, the server will determine the initial falling trajectory of the falling object based on the horizontal displacement distance, the vertical displacement distance and the displacement time. Specifically, the server will first calculate the initial velocity v1 of the falling object in the horizontal direction based on the horizontal displacement distance and the displacement time, and calculate the initial velocity v2 of the falling object in the vertical direction based on the vertical displacement distance and the displacement time, so as to obtain the falling object curve according to v1 and v2.

[0116] For example, the calculation method can be: first, the server obtains two points (m1, n1) and (m2, n2) in the parabola, as well as the displacement time t between the two points. Because in the extremely short time t, wind resistance is ignored, the horizontal direction can be approximately regarded as a falling object doing uniform linear motion, then m2-m1=v1*t, v1 is the horizontal initial velocity. In the vertical direction, n2-n1=v2*t+0.5*a*t 2 , ignoring wind resistance, a can be approximated as gravity acceleration in the vertical direction, then v2 can be calculated, and the expression for the coordinates of any falling object on the falling object curve is (v1*t, v2*t+0.5*a*t 2 ).

[0117] In one embodiment, if Figure 6 As shown, S410 includes:

[0118] S602: Continuously acquiring a set of captured images to be analyzed from an image acquisition device according to a preset acquisition interval;

[0119] S604: obtaining a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object according to the captured image set to be analyzed and the device coordinate parameters of the image acquisition device;

[0120] S606: Correct the initial falling trajectory according to the coordinate parameters to be processed to obtain the target falling trajectory of the falling object.

[0121] After obtaining the initial falling trajectory, due to the influence of wind resistance and error, it is necessary to correct the initial falling trajectory in real time to obtain the target falling trajectory. The specific method can be that while the falling object continues to fall, the server continuously obtains the set of captured images to be analyzed from the image acquisition device according to the preset acquisition interval, and obtains multiple coordinate parameters to be processed within the preset range of the falling object's position by analyzing the set of captured images to be analyzed and the device coordinate parameters of the image acquisition device, thereby continuously fitting the parabola of the falling object according to the coordinate parameters to be processed, reducing the error between the fitted parabola and the actual parabola, and finally determining the target falling trajectory of the falling object according to the fitted parabola and the multiple coordinate parameters to be processed, reducing the error, and realizing accurate calculation of the target falling trajectory. Among them, the preset acquisition interval can be set as needed.

[0122] In one embodiment, if Figure 7 As shown, after S108, it also includes:

[0123] S702: Determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object according to the falling object trajectory;

[0124] S704: comparing the preset building coordinate system according to the horizontal coordinate information and the vertical coordinate information to determine the target coordinate information of the falling object in the building coordinate system;

[0125] S706: According to the target coordinate information, obtain the capture net number corresponding to the falling trajectory in the building coordinate system;

[0126] S708: Outputting a control instruction to the capture net corresponding to the falling trajectory according to the capture net number, so that the capture net captures the falling object;

[0127] S710: Determine a dangerous area according to the target coordinate information, and update a preset environment map according to the coordinate information of the determined dangerous area.

[0128] The server can determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object based on the falling trajectory, and then compare the preset building coordinate system based on the horizontal coordinate information and the vertical coordinate information to determine the target coordinate information of the falling object in the building coordinate system. Specifically, the building coordinate system corresponds to the preset coordinate system, and the correspondence between the parabola and the preset coordinate system can be used to determine the correspondence between the parabola and the building coordinate system. After determining the target coordinate information of the falling object in the building coordinate system, the server will calculate the parabola curve of the falling object in the building coordinate system based on the target coordinate information, extend the parabola curve, obtain the intersection of the parabola curve and the preset capture net plane, and determine the capture net number corresponding to the falling trajectory based on the intersection.

[0129] Specifically, the capture net is set on a plane at a preset height from the ground on the construction site, and the preset height can be set as needed. Because the length and width of the capture net are known, the capture range of each capture net can be delineated within the capture net plane. According to the intersection of the parabola and the capture net plane, it can be predicted which capture net the falling object will fall into, and the corresponding capture net can be determined. Then, the capture net number corresponding to the falling trajectory is obtained, and the control instruction is output to the capture net corresponding to the falling trajectory according to the capture net number. The capture net captures the falling object, thereby reducing the risk of being hit by the falling object. Specifically, the server communicates with the corresponding capture net, and the server outputs the control instruction to the capture net corresponding to the falling trajectory, which can be achieved through 5G technology.

[0130] After determining the target coordinate information of the falling object in the building coordinate system, the server will calculate the parabolic curve of the falling object in the building coordinate system based on the target coordinate information, extend the parabolic curve to obtain the intersection of the parabolic curve and the ground, and predict the possible falling point of the falling object based on the intersection of the parabolic curve and the ground. According to the possible falling point, the dangerous area is delineated, and the preset environmental map is updated according to the coordinate information of the determined dangerous area.

[0131] It should be understood that although Figure 1-7 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-7 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0132] In one embodiment, Figure 8 As shown, a falling object tracking device is provided, including: a first acquisition module 802, a second acquisition module 804, a processing module 806 and a tracking module 808, wherein:

[0133] A first acquisition module 802 is used to acquire a set of multiple captured images, identify a falling object according to the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0134] The second acquisition module 804 is used to acquire, based on the captured image set including the image of the falling object, an image acquisition device identifier corresponding to the captured image set including the image of the falling object, and acquire, based on the image acquisition device identifier, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identifier;

[0135] The processing module 806 is used to lock the position of the falling object according to the device coordinate parameters, obtain multiple coordinate parameters of the falling object within a preset range of the falling object position, and determine the target falling trajectory of the falling object according to the coordinate parameters;

[0136] The tracking module 808 is used to track the falling object according to the target falling trajectory.

[0137] The above-mentioned device for tracking a fallen object identifies a fallen object by acquiring and comparing a set of captured images of multiple frames, obtaining a set of captured images including the image of the fallen object, acquiring an image acquisition device identifier corresponding to the set of captured images including the image of the fallen object based on the set of captured images including the image of the fallen object, acquiring corresponding device coordinate parameters based on the image acquisition device identifier, locking the location of the fallen object based on the device coordinate parameters, and obtaining multiple coordinate parameters of the fallen object within a preset range of the location of the fallen object, determining the target falling trajectory of the fallen object based on the coordinate parameters, and tracking the fallen object based on the target falling trajectory. In the whole process, the fallen object is accurately identified and tracked based on the target falling trajectory, so that the fallen object can be dealt with based on the tracking results, significantly reducing the risk of being hit by the falling object.

[0138] In one of the embodiments, the first acquisition module is also used to obtain the capture time interval corresponding to the set of multiple frames of captured images and the frame number identifier carried by each frame of captured images, obtain the set of object images to be identified in each frame of captured images according to a preset target detection algorithm, determine the capture order of the captured images according to the frame number identifier carried by each frame of captured images, calculate the first distance information and the second distance information of each object image to be identified in the set of object images according to the capture order of the captured images, the first distance information and the second distance information are the position distance information of each object image to be identified in any two frames of captured images, calculate the distance difference between the first distance information and the second distance information, and identify the falling object according to the distance difference and the capture time interval.

[0139] In one of the embodiments, the first acquisition module is also used to calculate the acceleration of each object to be identified based on the distance difference and the capture time interval, and calculate the acceleration difference between the acceleration and the acceleration of gravity. When the acceleration difference is less than a preset difference threshold, the object to be identified is determined to be a falling object. When the acceleration difference is greater than the difference threshold, the tracking number is obtained, and the acceleration difference between the acceleration of the object to be identified and the acceleration of gravity within the capture time interval of the tracking number is calculated according to the capture order of the captured images. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object.

[0140] In one of the embodiments, the processing module is also used to determine a set of image acquisition devices belonging to the same group based on the image acquisition device identifier, obtain the device coordinate parameters of each image acquisition device in each group of image acquisition device sets, lock the position of the falling object based on the captured images and device coordinate parameters captured by each image acquisition device, and obtain multiple coordinate parameters of the falling object within a preset range of the position of the falling object, fit the parabola of the falling object based on the coordinate parameters, determine the initial falling trajectory of the falling object based on the parabola of the falling object, continuously obtain the set of captured images to be analyzed from the image acquisition device according to the preset acquisition interval, and obtain the target falling trajectory of the falling object based on the set of captured images to be analyzed and the initial falling trajectory.

[0141] In one of the embodiments, the processing module is also used to fit the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the falling object's position, obtain multiple falling object coordinate information according to the coordinate parameters, obtain the horizontal displacement distance and the vertical displacement distance according to the falling object coordinate information, the horizontal displacement distance and the vertical displacement distance are the displacement differences between any two falling object coordinates in the parabola of the falling object, obtain the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance, and determine the initial falling trajectory of the falling object according to the horizontal displacement distance, the vertical displacement distance and the displacement time.

[0142] In one of the embodiments, the processing module is also used to continuously acquire a set of captured images to be analyzed from the image acquisition device according to a preset acquisition interval, obtain a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object based on the set of captured images to be analyzed and the device coordinate parameters of the image acquisition device, correct the initial falling trajectory based on the coordinate parameters to be processed, and obtain the target falling trajectory of the falling object.

[0143] In one of the embodiments, the tracking module is also used to determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object according to the trajectory of the falling object, compare the preset building coordinate system according to the horizontal coordinate information and the vertical coordinate information, determine the target coordinate information of the falling object in the building coordinate system, obtain the capture net number corresponding to the falling trajectory on the building coordinate system according to the target coordinate information, output a control instruction to the capture net corresponding to the falling trajectory according to the capture net number, let the capture net capture the falling object, determine the dangerous area according to the target coordinate information, and update the preset environmental map according to the coordinate information of the determined dangerous area.

[0144] In one of the embodiments, the device for tracking fallen objects also includes a communication module, and the communication module is used to communicate with other devices. Specifically, the communication module can be at least one of a 3G module, a 4G module, a 5G module and a Bluetooth module.

[0145] For the specific definition of the device for tracking fallen objects, please refer to the definition of the method for tracking fallen objects above, which will not be repeated here. Each module in the above-mentioned device for tracking fallen objects can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can execute the operations corresponding to the above modules.

[0146] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for tracking a falling object is implemented.

[0147] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0149] Acquire a set of multiple captured images, identify the falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0150] According to the captured image set including the image of the falling object, an image acquisition device identification corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identification, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identification is obtained;

[0151] The position of the falling object is locked according to the coordinate parameters of the device, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters;

[0152] Track falling objects based on their target falling trajectory.

[0153] The computer device for tracking fallen objects described above identifies fallen objects by acquiring and comparing a plurality of captured image sets, obtaining a captured image set including fallen object images, acquiring an image acquisition device identifier corresponding to the captured image set including fallen object images based on the captured image set including fallen object images, acquiring corresponding device coordinate parameters based on the image acquisition device identifier, locking the location of the fallen object based on the device coordinate parameters, and obtaining a plurality of coordinate parameters of the fallen object within a preset range of the location of the fallen object, determining the target falling trajectory of the fallen object based on the coordinate parameters, and tracking the fallen object based on the target falling trajectory. In the entire process, the fallen object is accurately identified and tracked based on the target falling trajectory, so that the fallen object can be dealt with based on the tracking results, significantly reducing the risk of being hit by the falling object.

[0154] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0155] Obtaining a capture time interval corresponding to a set of multiple captured images and a frame number identifier carried by each captured image frame;

[0156] Obtaining a set of images of objects to be identified in each frame of captured images according to a preset target detection algorithm;

[0157] Determining the capture order of the captured images according to the frame number identifier carried by each frame of the captured image;

[0158] Calculating first distance information and second distance information of each to-be-identified object image in the to-be-identified object image set according to the capture order of the captured images, the first distance information and the second distance information being position distance information of each to-be-identified object image in any two frames of captured images;

[0159] The distance difference between the first distance information and the second distance information is calculated, and the falling object is identified according to the distance difference and the capture time interval.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] Calculate the acceleration of each object to be identified based on the distance difference and the capture time interval;

[0162] Calculate the acceleration difference between the acceleration and the acceleration due to gravity;

[0163] When the acceleration difference is less than a preset difference threshold, the object to be identified is determined to be a falling object;

[0164] When the acceleration difference is greater than the difference threshold, the tracking number is obtained. According to the capture order of the captured images, the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time interval of the tracking number is calculated. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object.

[0165] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0166] Determine a set of image acquisition devices belonging to the same group according to the image acquisition device identifier;

[0167] Obtaining device coordinate parameters of each image acquisition device in each group of image acquisition device sets;

[0168] According to the captured images and device coordinate parameters collected by each image acquisition device, the location of the falling object is locked, and multiple coordinate parameters of the falling object within a preset range of the location of the falling object are obtained;

[0169] According to the coordinate parameters, the parabola of the falling object is fitted, and according to the parabola of the falling object, the initial falling trajectory of the falling object is determined;

[0170] According to a preset acquisition interval, a set of captured images to be analyzed is continuously acquired from the image acquisition device, and a target falling trajectory of the falling object is obtained according to the set of captured images to be analyzed and the initial falling trajectory.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] Fitting the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the position of the falling object;

[0173] Obtaining multiple falling object coordinate information according to the coordinate parameters, and obtaining a horizontal displacement distance and a vertical displacement distance according to the falling object coordinate information, wherein the horizontal displacement distance and the vertical displacement distance are the displacement difference between any two falling object coordinates in the parabola of the falling object;

[0174] Obtaining the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance;

[0175] The initial falling trajectory of the falling object is determined based on the horizontal displacement distance, vertical displacement distance and displacement time.

[0176] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0177] Continuously acquiring a set of captured images to be analyzed from an image acquisition device according to a preset acquisition interval;

[0178] According to the captured image set to be analyzed and the device coordinate parameters of the image acquisition device, a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object are obtained;

[0179] The initial falling trajectory is corrected according to the coordinate parameters to be processed to obtain the target falling trajectory of the falling object.

[0180] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0181] Determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object according to the falling object trajectory;

[0182] According to the horizontal coordinate information and the vertical coordinate information, the preset building coordinate system is compared to determine the target coordinate information of the falling object in the building coordinate system;

[0183] According to the target coordinate information, obtain the capture net number corresponding to the falling trajectory in the building coordinate system;

[0184] Outputting a control instruction to the capture net corresponding to the falling trajectory according to the capture net number, so that the capture net captures the falling object;

[0185] The dangerous area is determined according to the target coordinate information, and the preset environment map is updated according to the coordinate information of the determined dangerous area.

[0186] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0187] Acquire a set of multiple captured images, identify the falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object;

[0188] According to the captured image set including the image of the falling object, an image acquisition device identification corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identification, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identification is obtained;

[0189] The position of the falling object is locked according to the coordinate parameters of the device, and multiple coordinate parameters of the falling object within a preset range of the position of the falling object are obtained, and the target falling trajectory of the falling object is determined according to the coordinate parameters;

[0190] Track falling objects based on their target falling trajectory.

[0191] The storage medium for tracking fallen objects described above identifies fallen objects by acquiring and comparing a plurality of captured image sets, obtaining a captured image set including images of fallen objects, acquiring an image acquisition device identifier corresponding to the captured image set including images of fallen objects based on the captured image set including images of fallen objects, acquiring corresponding device coordinate parameters based on the image acquisition device identifier, locking the location of the fallen object based on the device coordinate parameters, and obtaining a plurality of coordinate parameters of the fallen object within a preset range of the location of the fallen object, determining the target falling trajectory of the fallen object based on the coordinate parameters, and tracking the fallen object based on the target falling trajectory. In the entire process, the fallen object is accurately identified and tracked based on the target falling trajectory, so that the fallen object can be dealt with based on the tracking results, significantly reducing the risk of being hit by the falling object.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0193] Obtaining a capture time interval corresponding to a set of multiple captured images and a frame number identifier carried by each captured image frame;

[0194] Obtaining a set of images of objects to be identified in each frame of captured images according to a preset target detection algorithm;

[0195] Determining the capture order of the captured images according to the frame number identifier carried by each frame of the captured image;

[0196] Calculating first distance information and second distance information of each to-be-identified object image in the to-be-identified object image set according to the capture order of the captured images, the first distance information and the second distance information being position distance information of each to-be-identified object image in any two frames of captured images;

[0197] The distance difference between the first distance information and the second distance information is calculated, and the falling object is identified according to the distance difference and the capture time interval.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] Calculate the acceleration of each object to be identified based on the distance difference and the capture time interval;

[0200] Calculate the acceleration difference between the acceleration and the acceleration due to gravity;

[0201] When the acceleration difference is less than a preset difference threshold, the object to be identified is determined to be a falling object;

[0202] When the acceleration difference is greater than the difference threshold, the tracking number is obtained. According to the capture order of the captured images, the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time interval of the tracking number is calculated. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0204] Determine a set of image acquisition devices belonging to the same group according to the image acquisition device identifier;

[0205] Obtaining device coordinate parameters of each image acquisition device in each group of image acquisition device sets;

[0206] According to the captured images and device coordinate parameters collected by each image acquisition device, the location of the falling object is locked, and multiple coordinate parameters of the falling object within a preset range of the location of the falling object are obtained;

[0207] According to the coordinate parameters, the parabola of the falling object is fitted, and according to the parabola of the falling object, the initial falling trajectory of the falling object is determined;

[0208] According to a preset acquisition interval, a set of captured images to be analyzed is continuously acquired from the image acquisition device, and a target falling trajectory of the falling object is obtained according to the set of captured images to be analyzed and the initial falling trajectory.

[0209] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0210] Fitting the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the position of the falling object;

[0211] Obtaining multiple falling object coordinate information according to the coordinate parameters, and obtaining a horizontal displacement distance and a vertical displacement distance according to the falling object coordinate information, wherein the horizontal displacement distance and the vertical displacement distance are the displacement difference between any two falling object coordinates in the parabola of the falling object;

[0212] Obtaining the displacement time corresponding to the horizontal displacement distance and the vertical displacement distance;

[0213] The initial falling trajectory of the falling object is determined based on the horizontal displacement distance, vertical displacement distance and displacement time.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0215] Continuously acquiring a set of captured images to be analyzed from an image acquisition device according to a preset acquisition interval;

[0216] According to the captured image set to be analyzed and the device coordinate parameters of the image acquisition device, a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object are obtained;

[0217] The initial falling trajectory is corrected according to the coordinate parameters to be processed to obtain the target falling trajectory of the falling object.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] Determine the horizontal coordinate information and vertical coordinate information of the falling object on the parabola of the falling object according to the falling object trajectory;

[0220] According to the horizontal coordinate information and the vertical coordinate information, the preset building coordinate system is compared to determine the target coordinate information of the falling object in the building coordinate system;

[0221] According to the target coordinate information, obtain the capture net number corresponding to the falling trajectory in the building coordinate system;

[0222] Outputting a control instruction to the capture net corresponding to the falling trajectory according to the capture net number, so that the capture net captures the falling object;

[0223] The dangerous area is determined according to the target coordinate information, and the preset environment map is updated according to the coordinate information of the determined dangerous area.

[0224] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0225] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0226] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for tracking a fallen object, the method comprising: Acquire a set of multiple captured images, identify a falling object based on the set of multiple captured images, and obtain a set of captured images including an image of the falling object; According to the captured image set including the image of the falling object, an image acquisition device identifier corresponding to the captured image set including the image of the falling object is obtained, and according to the image acquisition device identifier, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identifier is obtained; Determine a set of image acquisition devices belonging to the same group according to the image acquisition device identifier; Obtaining device coordinate parameters of each image acquisition device in each group of image acquisition device sets; According to the captured images collected by each image acquisition device and the coordinate parameters of the device, the position of the falling object is locked, and a plurality of coordinate parameters of the falling object within a preset range of the position of the falling object are obtained; Fitting a parabola of the falling object according to the coordinate parameters, and determining an initial falling trajectory of the falling object according to the parabola of the falling object; According to a preset acquisition interval, continuously acquiring a set of captured images to be analyzed from the image acquisition device, and obtaining a target falling trajectory of the falling object according to the set of captured images to be analyzed and the initial falling trajectory; The falling object is tracked according to the target falling trajectory.

2. The method according to claim 1, characterized in that The acquiring of a set of multiple captured images and identifying a falling object according to the set of multiple captured images comprises: Acquire a capture time interval corresponding to the plurality of captured image frames and a frame number identifier carried by each captured image frame; Obtaining a set of images of objects to be identified in each frame of captured images according to a preset target detection algorithm; Determining a capture order of the captured images according to frame number identifiers carried by each frame of captured images; Calculating first distance information and second distance information of each to-be-identified object image in the to-be-identified object image set according to the capturing order of the captured images, wherein the first distance information and the second distance information are position distance information of each to-be-identified object image in any two frames of captured images; The distance difference between the first distance information and the second distance information is calculated, and the falling object is identified according to the distance difference and the capture time interval.

3. The method according to claim 2, characterized in that The identifying the falling object according to the distance difference and the capture time interval comprises: Calculating the acceleration of each of the objects to be identified according to the distance difference and the capture time interval; Calculating the acceleration difference between the acceleration and the acceleration due to gravity; When the acceleration difference is less than a preset difference threshold, determining that the object to be identified is a falling object; When the acceleration difference is greater than the difference threshold, the tracking number is obtained, and the acceleration difference between the acceleration of the object to be identified and the gravity acceleration within the capture time intervals of the tracking number is calculated according to the capture order of the captured images. When the acceleration difference within any capture time interval is less than the difference threshold, the object to be identified is determined to be a falling object.

4. The method according to claim 1, characterized in that: The fitting of the parabola of the falling object according to the coordinate parameters and determining the initial falling trajectory of the falling object according to the parabola of the falling object comprises: Fitting the parabola of the falling object according to the coordinate parameters and the correspondence between the parabola of the falling object and a preset coordinate system within a preset range of the position of the falling object; Obtaining multiple falling object coordinate information according to the coordinate parameters, and obtaining a horizontal displacement distance and a vertical displacement distance according to the falling object coordinate information, wherein the horizontal displacement distance and the vertical displacement distance are displacement differences between any two falling object coordinates in the parabola of the falling object; Acquire a displacement time corresponding to the horizontal displacement distance and the vertical displacement distance; An initial falling trajectory of the falling object is determined according to the horizontal displacement distance, the vertical displacement distance and the displacement time.

5. The method according to claim 1, characterized in that The step of continuously acquiring a set of captured images to be analyzed from the image acquisition device according to a preset acquisition interval, and obtaining a target falling trajectory of the falling object according to the set of captured images to be analyzed and the initial falling trajectory comprises: According to a preset acquisition interval, continuously acquiring a set of captured images to be analyzed from the image acquisition device; According to the captured image set to be analyzed and the device coordinate parameters of the image acquisition device, a plurality of coordinate parameters to be processed of the falling object within a preset range of the position of the falling object are obtained; The initial falling trajectory is corrected according to the coordinate parameters to be processed to obtain the target falling trajectory of the falling object.

6. The method according to claim 1, characterized in that After tracking the falling object according to the target falling trajectory, the method further includes: Determine the horizontal coordinate information and the vertical coordinate information of the falling object on the parabola of the falling object according to the falling object trajectory; According to the horizontal coordinate information and the vertical coordinate information, compare with a preset building coordinate system to determine the target coordinate information of the falling object in the building coordinate system; According to the target coordinate information, obtaining a capture net number corresponding to the falling trajectory on the building coordinate system; Outputting a control instruction to a capture net corresponding to the falling trajectory according to the capture net number, so that the falling object is captured by the capture net; The dangerous area is determined according to the target coordinate information, and the preset environment map is updated according to the determined coordinate information of the dangerous area.

7. A falling object tracking device, characterized in that: The device comprises: A first acquisition module is used to acquire a set of multiple captured images, identify the falling object according to the set of multiple captured images, and obtain a set of captured images including an image of the falling object; A second acquisition module is used to acquire, based on the captured image set including the image of the falling object, an image acquisition device identifier corresponding to the captured image set including the image of the falling object, and acquire, based on the image acquisition device identifier, a device coordinate parameter of the image acquisition device corresponding to the image acquisition device identifier; a processing module, for determining a set of image acquisition devices belonging to the same group according to the image acquisition device identifier, obtaining device coordinate parameters of each image acquisition device in each set of image acquisition devices, locking a position of a falling object according to captured images acquired by each image acquisition device and the device coordinate parameters, and obtaining a plurality of coordinate parameters of the falling object within a preset range of the position of the falling object, fitting a parabola of the falling object according to the coordinate parameters, determining an initial falling trajectory of the falling object according to the parabola of the falling object, continuously obtaining a set of captured images to be analyzed from the image acquisition device according to a preset acquisition interval, and obtaining a target falling trajectory of the falling object according to the set of captured images to be analyzed and the initial falling trajectory; A tracking module is used to track the falling object according to the target falling trajectory.

8. The device according to claim 7, characterized in that The first acquisition module is also used to obtain the capture time interval corresponding to the set of multiple frames of captured images and the frame number identifier carried by each frame of captured images, obtain the set of object images to be identified in the each frame of captured images according to a preset target detection algorithm, determine the capture order of the captured images according to the frame number identifier carried by each frame of captured images, and calculate the first distance information and the second distance information of each object image to be identified in the set of object images according to the capture order of the captured images, the first distance information and the second distance information being the position distance information of each object image to be identified in any two frames of captured images, calculate the distance difference between the first distance information and the second distance information, and identify the falling object according to the distance difference and the capture time interval.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images