Method and device for preventing birds from impacting glass curtain wall and electronic equipment

Abstract

The invention provides a method and device for preventing birds from impacting a glass curtain wall and electronic equipment, and relates to the technical field of bird anti-collision, and the method comprises the following steps: obtaining at least one impact flight path of the glass curtain wall, at least one impact risk area and visual misjudgment factors of each impact risk area; acquiring a monitoring image of a bird activity area corresponding to the target collision risk area acquired by image acquisition equipment and a visual factor of any target collision risk area in the at least one collision risk area; calculating the flight path of the target bird in the monitoring image; according to the flight path, the at least one impact flight path, the visual factor and a visual misjudgment factor of the target impact risk area, analyzing whether the target bird will impact the target impact risk area; under the condition that it is determined that the target bird will collide with the target collision risk area, a warning signal is sent out; the warning signal is used for warning the target bird to change the current flight path. According to the invention, bird strike events can be prevented.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of bird collision prevention technology, and in particular to a method and device for preventing birds from colliding with glass curtain walls and an electronic device. BACKGROUND

[0002] With the increasing use of glass curtain walls in urban buildings, bird collisions are becoming increasingly common.

[0003] Bird collisions refer to the phenomenon in which birds, unable to recognize the existence of glass curtain walls due to their transparent and reflective properties, collide with buildings, especially glass windows, and are injured or killed. Bird collisions are one of the main threats faced by birds in cities. In the United States, it is estimated that there are over 100 million birds killed each year due to collisions with glass windows. In Canada, it is estimated that there are over 10 million birds killed each year due to collisions with building glass. Although there is no precise global data, based on the data from the United States and Canada, it is estimated that there are tens of billions of birds killed each year due to collisions with glass worldwide. Bird collisions not only pose a threat to bird life, but also increase the risk of accidents and safety hazards in cities.

[0004] Therefore, it is a pressing problem to effectively prevent bird collisions. SUMMARY

[0005] The present application provides a method and device for preventing birds from colliding with glass curtain walls, which effectively prevents bird collisions and reduces the threat to bird life caused by glass curtain walls and effectively prevents accidents caused by glass damage and falling due to bird collisions.

[0006] The present application provides a method for preventing birds from colliding with glass curtain walls, comprising: obtaining at least one collision flight trajectory of a glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area; acquiring monitoring images of a target collision risk area corresponding to a bird activity area collected by an image acquisition device, and visual factors of the target collision risk area; the target collision risk area is any one of the at least one collision risk area; calculating the flight trajectory of a target bird in the monitoring images; analyzing whether the target bird will collide with the target collision risk area based on the flight trajectory, at least one collision flight trajectory, visual factors, and visual misjudgment factors of the target collision risk area; issuing a warning signal if it is determined that the target bird will collide with the target collision risk area; the warning signal is used to alert the target bird to change the current flight trajectory.

[0007] The method for preventing birds from colliding with a glass curtain wall according to the present application further comprises the following steps before obtaining the monitoring image of the bird activity area corresponding to the target collision risk area and the visual factor of the target collision risk area: obtaining the building measurement data of the glass curtain wall, the collision measurement data of the birds colliding with the glass curtain wall in history, and the historical collision scene; wherein the collision measurement data comprises the collision time, the historical collision flight trajectory spatial position at the collision time, and the historical collision position of the historical flight trajectory flying to the glass curtain wall based on the historical collision flight trajectory spatial position; establishing a three-dimensional model of the glass curtain wall according to the building measurement data of the glass curtain wall; obtaining the collision flight trajectory of the birds reaching the three-dimensional model of the glass curtain wall according to the historical collision flight trajectory spatial position, the collision time, and the historical collision position, and obtaining at least one collision flight trajectory; determining at least one collision gathering area on the three-dimensional model of the glass curtain wall according to the historical collision position, and taking each collision gathering area in the at least one collision gathering area as a collision risk area; and obtaining the visual misjudgment factor of the collision risk area according to the historical collision scene corresponding to the collision risk area.

[0008] The method for preventing birds from colliding with a glass curtain wall according to the present application further comprises the following steps after determining at least one collision gathering area on the three-dimensional model of the glass curtain wall according to the historical collision position: analyzing whether there is a similar risk area in other areas of the glass curtain wall except the at least one collision gathering area according to the curtain wall picture scene of the at least one collision gathering area; wherein the scene similarity of the curtain wall picture scene of the similar risk area and the curtain wall picture scene of the collision gathering area is greater than a set scene similarity; and determining the similar risk area as a collision risk area in the case that it is determined that there is a similar risk area on the glass curtain wall.

[0009] The method for preventing birds from colliding with a glass curtain wall according to the present application further comprises the following steps of analyzing whether the target bird will collide with the target collision risk area according to the flight trajectory, the at least one collision flight trajectory, the visual factor, and the visual misjudgment factor of the target collision risk area: calculating the trajectory similarity of the flight trajectory and the target collision flight trajectory; wherein the target collision flight trajectory is any one of the at least one collision flight trajectory; judging whether there is a visual misjudgment factor in the visual factor of the target collision risk area in the case that the trajectory similarity is greater than a set trajectory similarity; and determining that the target bird will collide with the target collision risk area in the case that there is a visual misjudgment factor in the visual factor of the target collision risk area.

[0010] The method for preventing birds from colliding with a glass curtain wall provided by the application comprises the following steps: obtaining at least one bird collision flight track, at least one bird collision risk area, and visual misjudgment factors of each bird collision risk area; obtaining a monitoring image of a bird activity area corresponding to a target bird collision risk area and visual factors of the target bird collision risk area; calculating a flight speed of the target bird and a predicted flight track of the target bird according to the monitoring image; calculating flash control information according to the flight speed and the predicted flight track; and controlling the flash to irradiate the bird activity area according to the flash control information.

[0011] The method for preventing birds from colliding with a glass curtain wall provided by the application comprises the following steps: obtaining at least one bird collision flight track, at least one bird collision risk area, and visual misjudgment factors of each bird collision risk area; obtaining a monitoring image of a bird activity area corresponding to a target bird collision risk area and visual factors of the target bird collision risk area; calculating a flight speed of the target bird and a predicted flight track of the target bird according to the monitoring image; calculating flash control information according to the flight speed and the predicted flight track; and controlling the flash to irradiate the bird activity area according to the flash control information.

[0012] The application further provides a device for preventing birds from colliding with a glass curtain wall, which comprises an acquisition module, a calculation module, an analysis module and a warning module.

[0013] The acquisition module is used for obtaining a monitoring image of a bird activity area corresponding to a target bird collision risk area and visual factors of the target bird collision risk area when at least one bird collision flight track, at least one bird collision risk area and visual misjudgment factors of each bird collision risk area are obtained.

[0014] The calculation module is used for calculating a flight track of a target bird in the monitoring image.

[0015] The analysis module is used for analyzing whether the target bird will collide with the target bird collision risk area according to the flight track, the at least one bird collision flight track, the visual factors and the visual misjudgment factors of the target bird collision risk area.

[0016] The warning module is used for issuing a warning signal when it is determined that the target bird will collide with the target bird collision risk area; and the warning signal is used for warning the target bird to change the current flight track.

[0017] The application further provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor; and the processor implements the method for preventing birds from colliding with a glass curtain wall according to any one of the above methods when executing the program.

[0018] The application further provides a computer readable storage medium, which stores a computer program; and the computer program is executed by a processor to implement the method for preventing birds from colliding with a glass curtain wall according to any one of the above methods.

[0019] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements any of the above methods for preventing birds from colliding with a glass curtain wall.

[0020] The application provides a method and device for preventing birds from colliding with a glass curtain wall and an electronic device. In the method, at least one collision flight trajectory of the glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area are obtained, a monitoring image of a bird activity area corresponding to a target collision risk area is acquired by an image acquisition device, and visual factors of the target collision risk area are acquired. The target collision risk area is any one of the at least one collision risk area. A flight trajectory of a target bird in the monitoring image is calculated. Whether the target bird will collide with the target collision risk area is analyzed according to the flight trajectory, the at least one collision flight trajectory, the visual factors, and the visual misjudgment factors of the target collision risk area. A warning signal is sent out when it is determined that the target bird will collide with the target collision risk area. The warning signal is used to alert the target bird to change the current flight trajectory. Therefore, the application can determine whether the target bird will collide with the target collision risk area by analyzing the visual misjudgment factors of the collision risk area of the glass curtain wall and the flight trajectory of the target bird, and send a warning signal to the target bird when it is determined that the target bird will collide with the target collision risk area, so as to alert the target bird to change the current flight path, thereby avoiding bird collision. The application solves the problem that the prior art cannot effectively prevent bird collision, and effectively prevents bird collision, reduces the threat of the glass curtain wall to birds, and effectively prevents the glass on the building from being damaged and falling due to bird collision, thereby preventing safety accidents. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0022] Figure 1 is one of the flowcharts of the method for preventing birds from colliding with a glass curtain wall provided by the embodiments of the application.

[0023] Figure 2 is another flowchart of the method for preventing birds from colliding with a glass curtain wall provided by the embodiments of the application.

[0024] Figure 3 is an example of a collision flight trajectory fitted according to the spatial positions of a plurality of historical collision flight trajectories in the method for preventing birds from colliding with a glass curtain wall provided by the embodiments of the application.

[0025] Figure 4 is an example of multiple impact flight trajectories obtained in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0026] Figure 5 is an example of multiple impact positions obtained on a three-dimensional model of a glass curtain wall in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0027] Figure 6 is an example of multiple impact aggregation areas obtained on a three-dimensional model of a glass curtain wall in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0028] Figure 7 is a third flowchart of the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0029] Figure 8 is an example of a predicted flight trajectory of a target bird in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0030] Figure 9 is an example of an impact position in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0031] Figure 10 is an example of a sound signal interfering with a flight trajectory of a target bird in the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0032] Figure 11 is a structural schematic diagram of the device for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application.

[0033] Figure 12 is a structural schematic diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, but not all embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0035] The method for preventing birds from impacting a glass curtain wall of the present application will be described below. Figures 1-10

[0036] Figure 1 is a first flowchart of the method for preventing birds from impacting a glass curtain wall provided by an embodiment of the present application. As shown in the figure, the method comprises the following steps. Figure 1 ​As shown, the method for preventing birds from colliding with the glass curtain wall according to the embodiments of the present application comprises S110-S140.

[0037] It should be noted that before performing S110-S140, first, at least one collision flight trajectory of the glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area are obtained.

[0038] The collision flight trajectory is the flight trajectory of the bird before colliding with the glass curtain wall, the collision risk area is the area where the bird frequently collides with the glass curtain wall, and the visual misjudgment factor is the visual factor on the glass curtain wall that causes the bird to visually misjudge.

[0039] There are many reasons for birds to collide with the glass curtain wall, one of which is misidentification of the glass curtain wall. For example, when the weather is fine, the glass curtain wall reflects the sky, making the bird think that the position of the glass curtain wall is the sky and thus colliding with the glass curtain wall; for another example, green plants are placed behind the glass curtain wall, making the bird misjudge that the position of the glass curtain wall is the green plants and thus colliding with the glass curtain wall. The sky reflected on the glass curtain wall mentioned above, and the landscape such as green plants behind the glass curtain wall transmitted by the glass curtain wall, which are visual factors that cause the bird to visually misjudge the existence of the glass curtain wall, can all be used as visual misjudgment factors.

[0040] Before performing S110, refer to Figure 2 As shown, S210-S250 are performed to obtain at least one collision flight trajectory of the glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area.

[0041] S210: Obtain building measurement data of the glass curtain wall, collision measurement data of birds colliding with the glass curtain wall in history, and historical collision scenes; wherein the collision measurement data comprises: collision time, historical collision flight trajectory spatial position at the collision time, and historical collision position obtained by flying the historical flight trajectory based on the historical collision flight trajectory spatial position to collide with the glass curtain wall.

[0042] The building measurement data can include data such as the size and floor position of the glass curtain wall.

[0043] The building measurement data can be obtained from the architectural drawings of the glass curtain wall. For example, the architectural drawings of the glass curtain wall record data such as the size and floor position of the glass curtain wall, and these data are obtained as building measurement data.

[0044] The building measurement data can also be obtained by measuring the size, floor position, etc. of the glass curtain wall on site.

[0045] In practice, data related to the size and floor location of the glass curtain wall can be obtained first from the architectural drawings of the glass curtain wall. If the data is missing, the missing data can be obtained through on-site measurement.

[0046] Historical impact location refers to the location where birds struck the glass curtain wall during historical bird strikes.

[0047] The spatial location of the historical impact flight trajectory at the time of impact refers to the spatial location of the bird in flight at the time of impact, prior to the bird strike in history.

[0048] When acquiring the spatial location of historical impact flight trajectories, a high-definition camera can be set up to capture the spatial location of the bird in flight at the time of impact before the bird strike. Similarly, when acquiring historical impact locations, a high-definition camera can be set up to capture the impact location of the bird on the glass curtain wall at the time of the bird strike. In some embodiments, the actual impact measurement data can be found in Table 1 below.

[0049] Table 1 Event number Date Time Floor Weather condition Flight trajectory Impact point 001 2023-05-02 10:20:15 8 Sunny A4, B4, C4 X1, Y1 002 2023-05-03 15:45:30 9 Cloudy to sunny A2, B2, C2 X2, Y2 003 2023-05-04 7:50:00 9 Rainy A3, B3, C3 X3, Y3

[0050] The events recorded in Table 1 are all bird strikes against the glass curtain wall.

[0051] The dates and times in Table 1 refer to the aforementioned impact times.

[0052] The impact event with event number 001 in Table 1 occurred on May 2, 2023. Figure 3 The incident occurred on May 2, 2023, at 10:20:15. Figure 3 (10:20:15). In practice, the more precise the recorded time of occurrence, the more accurate the calculation of the historical impact's spatial flight position. Therefore, the occurrence time can be accurate to the second, thus enabling precise capture of the bird's historical impact spatial flight position.

[0053] The spatial location of historical impact trajectories can be represented using three-dimensional coordinates in three-dimensional space. For example... Figure 3 The historical impact trajectory of the impact event with event number 001 at 10:20:15 on May 2, 2023 is represented by three-dimensional coordinates (a4, b4, c4) in three-dimensional space.

[0054] like Figure 3 As shown, historical impact locations can be represented by planar coordinates on the glass curtain wall. For example, the impact point (i.e., the historical impact location) in impact event number 001 is represented by planar coordinates (x1, y1).

[0055] It should be noted that after the impact time of the impact is obtained (for example, the impact time of event 001 in Table 1 is 10:20:15), based on the impact time, a plurality of time points within a set time range (set by a person skilled in the art according to actual conditions) before the impact time is obtained, and the three-dimensional coordinates of the bird in the three-dimensional space when the bird impacts at each time point in the plurality of time points, so as to infer the impact flight trajectory of the bird.

[0056] For example Figure 3 The three-dimensional coordinates of the bird in the three-dimensional space when the bird impacts at the impact event are (a4, b4, c4), the three-dimensional coordinates (a1, b1, c1) corresponding to time point 1, the three-dimensional coordinates (a2, b2, c2) corresponding to time point 2, and the three-dimensional coordinates (a3, b3, c3) corresponding to time point 3 within a set time range before the impact event are obtained, and the three-dimensional coordinates (a4, b4, c4) at the impact event are combined to infer the impact flight trajectory of the bird.

[0057] The historical impact scene factors may include, for example, weather conditions, impact intensity, glass curtain wall transparency, glass curtain wall reflectivity, floor, and other factors related to the impact scene.

[0058] The impact intensity can be obtained by setting a vibration sensor on the glass curtain wall and converting the sensor data output by the vibration sensor.

[0059] As shown in Table 1, the floor is the floor where the impact point is located. The weather condition is the weather when the bird impact occurs, such as sunny, rainy, cloudy and sunny, etc.

[0060] The weather condition will affect the bird's recognition of the glass curtain wall, so it is necessary to record the weather condition when the bird impact occurs.

[0061] S220: According to the building measurement data of the glass curtain wall, a three-dimensional model of the glass curtain wall is established.

[0062] According to the building measurement data of the glass curtain wall obtained in the previous step, a three-dimensional model corresponding to the glass curtain wall is established, which is the three-dimensional model of the glass curtain wall.

[0063] S230: According to the historical impact flight trajectory spatial position, the impact time, and the historical impact position, the impact flight trajectory of the bird reaching the glass curtain wall three-dimensional model is obtained, and at least one impact flight trajectory is obtained.

[0064] Specifically, according to the historical impact flight trajectory spatial position, the impact time, and the glass curtain wall three-dimensional model, the impact flight trajectory of the bird reaching the glass curtain wall three-dimensional model is reconstructed.

[0065] For example, as Figure 3As shown, according to the historical impact flight trajectory spatial position, bird A has a bird strike, the spatial position of bird A at time 1 corresponds to three-dimensional coordinates (a1, b1, c1), the spatial position of bird A at time 2 after time 1 corresponds to three-dimensional coordinates (a2, b2, c2), the spatial position of bird A at time 3 after time 2 corresponds to three-dimensional coordinates (a3, b3, c3), and the spatial position of bird A at time 4 after time 3 corresponds to three-dimensional coordinates (a4, b4, c4), and bird A strikes the three-dimensional glass curtain wall (100) at time 4. Figure 3 As shown, according to the historical impact flight trajectory spatial position, bird A has a bird strike, the spatial position of bird A at time 1 corresponds to three-dimensional coordinates (a1, b1, c1), the spatial position of bird A at time 2 after time 1 corresponds to three-dimensional coordinates (a2, b2, c2), the spatial position of bird A at time 3 after time 2 corresponds to three-dimensional coordinates (a3, b3, c3), and the spatial position of bird A at time 4 after time 3 corresponds to three-dimensional coordinates (a4, b4, c4), and bird A strikes the three-dimensional glass curtain wall (100) at time 4. Figure 3 As shown, according to the historical impact flight trajectory spatial position, bird A has a bird strike, the spatial position of bird A at time 1 corresponds to three-dimensional coordinates (a1, b1, c1), the spatial position of bird A at time 2 after time 1 corresponds to three-dimensional coordinates (a2, b2, c2), the spatial position of bird A at time 3 after time 2 corresponds to three-dimensional coordinates (a3, b3, c3), and the spatial position of bird A at time 4 after time 3 corresponds to three-dimensional coordinates (a4, b4, c4), and bird A strikes the three-dimensional glass curtain wall (100) at time 4. Figure 3 As shown, according to the historical impact flight trajectory spatial position, bird A has a bird strike, the spatial position of bird A at time 1 corresponds to three-dimensional coordinates (a1, b1, c1), the spatial position of bird A at time 2 after time 1 corresponds to three-dimensional coordinates (a2, b2, c2), the spatial position of bird A at time 3 after time 2 corresponds to three-dimensional coordinates (a3, b3, c3), and the spatial position of bird A at time 4 after time 3 corresponds to three-dimensional coordinates (a4, b4, c4), and bird A strikes the three-dimensional glass curtain wall (100) at time 4.

[0066] Through the above process of reconstructing the impact flight trajectory, at least one impact flight trajectory can be obtained.

[0067] In a specific implementation, according to all impact times in all impact measured data obtained and historical impact flight trajectory spatial positions at each impact time, the corresponding impact flight trajectory can be reconstructed, and multiple impact flight trajectories (multiple colored lines circled by the dashed line in FIG. 10) can be obtained as shown in FIG. 10. Figure 4 Figure 4

[0068] It should be noted that the above is only described for one glass curtain wall three-dimensional model and at least one impact flight trajectory corresponding thereto.

[0069] In actual situations, the number of glass curtain wall three-dimensional models is multiple, and each glass curtain wall three-dimensional model has at least one impact flight trajectory corresponding thereto. In the multiple glass curtain wall three-dimensional models, at least one impact flight trajectory of a bird reaching each glass curtain wall three-dimensional model is obtained.

[0070] S240: According to the historical impact position, at least one impact aggregation area is determined on the glass curtain wall three-dimensional model, and each impact aggregation area in the at least one impact aggregation area is taken as an impact risk area.

[0071] The impact measured data of the historical impact position is converted into a three-dimensional coordinate system in which the glass curtain wall three-dimensional model is located, and multiple impact positions (i.e., positions at which birds strike the glass curtain wall) can be obtained on the glass curtain wall three-dimensional model.

[0072] As shown in FIG. 5, the glass curtain wall three-dimensional model 500 has multiple position points (red part in FIG. 5), and the multiple position points one-to-one correspond to the multiple impact positions. Figure 5 Figure 5

[0073] ​​​​The distribution of multiple points on the 3D model of the glass curtain wall is analyzed, and the areas where the distribution of points is relatively concentrated are identified as impact accumulation areas, thus obtaining at least one impact accumulation area.

[0074] The method for obtaining areas with relatively concentrated location point distribution can be set by those skilled in the art according to the actual situation, and the embodiments of the present invention do not limit this.

[0075] For example, such as Figure 6 As shown, by analyzing the distribution of multiple points on the 3D model of the glass curtain wall, three impact clusters with relatively concentrated impact points were identified. Figure 6 The areas circled in red in the middle are respectively Figure 6 The first region is F1, the second region is F2, and the third region is F3.

[0076] Because birds frequently strike glass curtain walls in areas prone to collisions, these areas are considered high-risk zones for bird strikes and are thus designated as impact risk zones.

[0077] In some embodiments, based on the curtain wall scene in at least one impact cluster area, it is analyzed whether there are similar risk areas in other areas of the glass curtain wall besides the at least one impact cluster area; wherein, the scene similarity between the curtain wall scene in the similar risk area and the curtain wall scene in the impact cluster area is greater than a set scene similarity.

[0078] The scene displayed on the curtain wall can include, for example, the background image seen through the glass curtain wall, the intensity of the light illuminating the glass curtain wall, and the visible viewing distance of the glass curtain wall.

[0079] The method for calculating scene similarity and the setting of scene similarity values ​​shall be determined by those skilled in the art based on the actual situation.

[0080] If similar risk areas are identified on the glass curtain wall, these similar risk areas will be designated as impact risk areas.

[0081] For example Figure 6 Three impact clusters were obtained: the first region F1, the second region F2, and the third region F3. The curtain wall scene of the first region F1 is K1, the curtain wall scene of the second region F2 is K2, and the curtain wall scene of the third region F3 is K3.

[0082] The glass curtain wall, except for at least one impact accumulation area, can be divided into multiple sub-regions. The similarity between the curtain wall scene in each sub-region and the scene of K1 (or K2 or K3) can be calculated. If the scene similarity is greater than the set scene similarity, the sub-region with the scene similarity greater than the set scene similarity is regarded as a similar risk area.

[0083] The curtain wall picture scene of the similar risk area is similar to the curtain wall picture scene of the impact gathering area, and has a possibility of causing bird impact, so the similar risk area is also taken as an impact risk area.

[0084] The risk degree of the similar risk area is less than that of the impact gathering area, and when the risk level is set, the risk level of the impact gathering area can be set as S1, and the risk level of the similar risk area can be set as S2, S2 < S1.

[0085] For the impact gathering area and the similar risk area obtained above, when setting up a camera for collecting monitoring images of the bird activity area corresponding to each area, for the impact gathering area, i.e. the area with a risk level of S1, a first number of cameras can be installed for intensive monitoring and protection. For the similar risk area, i.e. the area with a risk level of S2, a second number of cameras can be installed for monitoring and tracking. The first number is greater than the second number, and the first number is greater than or equal to 2.

[0086] In some embodiments, the frequency of bird impact events at different times can also be counted and analyzed according to the impact measured data. The impact time period with the highest frequency of bird activity and the high-risk impact time period (e.g. the period with a high probability of causing bird death) are identified. The main factors affecting the bird impact risk are determined using multivariate statistical analysis methods (such as Principal Components Analysis (PCA) or logistic regression model). A risk prediction model is generated for predicting the impact risk under different conditions in the future, so that corresponding anti-impact measures can be taken in the case of high impact risk.

[0087] S250: Obtain visual misjudgment factors of the impact risk area according to the historical impact scene corresponding to the impact risk area.

[0088] According to the weather conditions, impact intensity, glass curtain wall transparency, glass curtain wall reflectivity, floor and other information in the historical impact scene when the bird impact occurs, the visual picture of the bird is analyzed to obtain the visual misjudgment factors of the impact risk area in the historical impact scene that cause visual misjudgment to the bird.

[0089] The visual misjudgment factors are, for example, natural landscape images reflected on the glass curtain wall, and for example, indoor landscape transmitted that causes the bird to be unable to identify the glass curtain wall. The visual misjudgment factors can have various forms according to the actual situation.

[0090] Through S210-S250, at least one impact flight trajectory of the glass curtain wall, at least one impact risk area, and visual misjudgment factors of each impact risk area are obtained. Next, S110-S140 is executed.

[0091] S110: Obtain a monitoring image of a bird activity area corresponding to a target impact risk area collected by an image collection device, and a visual factor of the target impact risk area, in a case where at least one impact flight trajectory of the glass curtain wall, at least one impact risk area, and visual misjudgment factors of each impact risk area are obtained. The target impact risk area is any one of the at least one impact risk area.

[0092] The image collection device is, for example, a smart camera, a camera, or the like installed for the impact risk area.

[0093] In a case where the impact risk area includes an impact gathering area and a risk similar area, the number of cameras arranged for the impact gathering area is a first number, and the number of cameras arranged for the risk similar area is a second number.

[0094] In a case where the target impact risk area is an impact gathering area, a monitoring image of a bird activity area corresponding to the impact gathering area collected by a first number of image collection devices arranged for the impact gathering area is obtained, and a first number of monitoring images corresponding one-to-one to the first number of cameras can be obtained.

[0095] In a case where the target impact risk area is a similar risk area, a monitoring image of a bird activity area corresponding to the similar risk area collected by a second number of image collection devices arranged for the similar risk area is obtained, and a second number of monitoring images corresponding one-to-one to the second number of cameras can be obtained.

[0096] The visual factor of the target impact risk area can include an image element of a visual picture of the target impact risk area, such as a blue sky reflected on the target impact risk area, green plants, or an internal landscape of a building transmitted by the target impact risk area, such as green plants inside the building, a mural hung inside the building, and the like.

[0097] S120: Calculate a flight trajectory of the target bird in the monitoring image.

[0098] The monitoring image is subjected to image processing, the target bird in the monitoring image is identified, and the flight trajectory of the target bird is extracted from the monitoring image according to the identification result. For example, the flight trajectory of the bird can be fitted according to the positions of the bird in the monitoring image at different times.

[0099] S130: Analyze whether the target bird will impact the target impact risk area according to the flight trajectory, at least one impact flight trajectory, the visual factor, and the visual misjudgment factor.

[0100] In some embodiments, the trajectory similarity of the flight trajectory and a target impact flight trajectory can be calculated first; wherein the target impact flight trajectory is any one of the at least one impact flight trajectory.

[0101] The way of calculating the trajectory similarity and the size of the trajectory similarity can be set by those skilled in the art according to actual conditions.

[0102] For example, the flight trajectory of the target bird is matched with any of the at least one impact flight trajectory obtained above, and the trajectory similarity is calculated by selecting the third number (for example, 3) of position points in the flight trajectory of the target bird and the matched impact flight trajectory. If the trajectory similarity is greater than the set similarity, it indicates that the flight trajectory of the target bird highly coincides with any of the impact flight trajectories, and the target bird is likely to impact the target impact risk area. It is further determined whether there is a visual misjudgment factor in the visual factor of the target impact risk area. For example, the visual factor of the target impact risk area includes a reflected blue sky, and the visual misjudgment factor also includes a reflected blue sky. It is determined that there is a visual misjudgment factor in the visual factor of the target impact risk area, and in this case, it is determined that the target bird will impact the target impact risk area.

[0103] In the case that there is a visual misjudgment factor in the visual factor of the target impact risk area, it is determined that the target bird will impact the target impact risk area.

[0104] In some embodiments, the bird will impact the target impact risk area based on the at least one impact flight trajectory. Based on this, the function relationship between the flight trajectory and the impact point can be obtained (for example, a corresponding function relationship model is obtained by using a machine learning algorithm) according to the at least one impact flight trajectory and the target impact risk area. Then, the position of the glass curtain wall reached by the bird if the bird continues to fly according to the flight trajectory is calculated as a pre-judgment impact point according to the flight trajectory and the function relationship. It is then determined whether the pre-judgment impact point is located in the target impact risk area. If the determination result is that the pre-judgment impact point is located in the target impact risk area, it indicates that the target bird is likely to impact the target impact risk area. It is further determined whether there is a visual misjudgment factor in the visual factor of the target impact risk area. For example, the visual factor of the target impact risk area includes a reflected blue sky, and the visual misjudgment factor also includes a reflected blue sky. It is determined that there is a visual misjudgment factor in the visual factor of the target impact risk area, and in this case, it is determined that the target bird will impact the target impact risk area. If the determination result is that the pre-judgment impact point is not located in the target impact risk area, it is determined that the target bird will not impact the target impact risk area, and it is no longer determined whether there is a visual misjudgment factor in the visual factor of the target impact risk area.

[0105] S140: In the case that it is determined that the target bird will impact the target impact risk area, a warning signal is sent out. The warning signal is used to warn the target bird to change the current flight trajectory.

[0106] In some embodiments, the warning signal comprises a flash light signal. As Figure 7 S140 can comprise S710-S730 as shown in the following: S710: in the case that the target bird is determined to hit the impact risk area, calculate the flight speed of the target bird and the predicted flight trajectory of the target bird according to the monitoring image.

[0107] According to the flight trajectory of the target bird, the predicted flight trajectory of the target bird is calculated, and the impact position of the target bird in the target impact risk area can be inferred according to the predicted flight trajectory.

[0108] For example, as Figure 8 shown in the following, the camera Figure 8 monitors the position of the bird activity area, and when the target bird flies to position D, it can be determined that the target bird will hit the impact risk area through S130, at this time, the predicted flight trajectory of the target bird flying from position D to the green square in the three-dimensional glass curtain wall Figure 8 (as shown by the yellow dashed line in Figure 9 ) can be calculated, and the predicted impact position of the target bird hitting the glass curtain wall (corresponding to the impact point in Figure 8 ) can be calculated.

[0109] S720: according to the flight speed and the predicted flight trajectory, calculate the flash light control information.

[0110] The flash light control information can include: flash light starting time, flash light frequency, flash light irradiation angle, and flash light intensity, etc.

[0111] According to the predicted flight trajectory, the predicted impact position of the target bird hitting the glass curtain wall can be obtained, and thus the remaining flight distance of the target bird before hitting the glass curtain wall can be obtained.

[0112] The ratio of the remaining flight distance and the flight speed is obtained, and the remaining flight time of the target bird before hitting the glass curtain wall is obtained, and the flash light starting time, the flash light frequency, the flash light intensity, etc. are calculated according to the remaining flight time.

[0113] According to the predicted flight trajectory, the flash light irradiation angle is calculated, so that the flash light warning signal emitted by the flash light at the flash light irradiation angle can effectively cover the flight path of the bird.

[0114] In some embodiments, the target bird in the monitoring image can also be identified to obtain the type of the target bird (such as large bird, medium bird or small bird); then according to the type of the target bird, the visual characteristics of the target bird are obtained; and the flash light intensity of the flash light is adjusted according to the visual characteristics of the target bird, so as to reduce the disturbance to the bird.

[0115] In some embodiments, the flash intensity of the flash can be adjusted according to the flight speed of the target bird to provide an appropriate warning to the target bird. For example, if the target bird is flying faster than a set speed threshold (set by those skilled in the art based on actual conditions), the flash intensity can be increased accordingly; conversely, if the target bird is flying slower than the speed threshold, the flash intensity can be decreased accordingly.

[0116] S730: Controls the flash to illuminate the area where birds are active, based on the flash control information.

[0117] The gimbal is rotated based on the flash's illumination angle to adjust the flash's angle. When the flash start time is reached, the flash is controlled to flash at a set frequency, with the flash intensity set in the flash control information. By illuminating the bird's activity area with the flash, target birds are alerted to change their current flight path, thus preventing bird strikes.

[0118] For example, such as Figure 9 As shown, after obtaining the predicted flight trajectory, the target bird's position on the three-dimensional glass curtain wall is calculated based on the predicted flight trajectory. Figure 9 The predicted impact location (corresponding to the green box in the image) is shown. Figure 9 (The location of the impact point), then rotate the gimbal so that the flash warning signal emitted by the flash can reach the impact point and be refracted to cover the bird's visual range. Then start flashing the flash 3 times. The purpose is to change the bird's current flight trajectory by flashing the area that the bird misjudges (impact risk area). As shown in the figure below, the blue line is the light reflection path after the flash.

[0119] In some embodiments, the warning signal further includes an audible warning signal. The audible warning signal assists the visual warning signal in causing birds to change their current flight path. It is used when, after the flashlight control information illuminates the bird's activity area, and the bird fails to change its current flight path despite the flashlight warning signal, the remaining time for the target bird to reach the glass curtain wall is calculated based on the monitoring image. If the remaining time is less than a set time, an audible warning signal is issued.

[0120] The remaining time can be set by those skilled in the art according to the actual situation, for example, 3 seconds. The audible warning signal can be a high-frequency sound signal or a high-decibel sound signal. The audible warning signal only needs to be able to effectively attract the birds' attention. The audible warning signal should not be harsh to prevent harm to the birds.

[0121] For example, see Figure 10As shown, in the case that the target bird does not change the current flight trajectory under the flash warning, the gimbal control system adjusts the orientation of the sound device, so that the sound device emits a sound warning signal, directly transmits the sound warning signal to the target bird, and warns the bird to change the current flight trajectory in the form of a sound warning.

[0122] The method for preventing bird collision with glass curtain wall provided by the application comprises the following steps: obtaining at least one collision flight trajectory of a glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area; acquiring monitoring images of a bird activity area corresponding to a target collision risk area collected by an image acquisition device and visual factors of the target collision risk area; the target collision risk area is any one of the at least one collision risk area; calculating a flight trajectory of a target bird in the monitoring images; analyzing whether the target bird will collide with the target collision risk area according to the flight trajectory, the at least one collision flight trajectory, the visual factors, and the visual misjudgment factors of the target collision risk area; and issuing a warning signal in the case that it is determined that the target bird will collide with the target collision risk area; the warning signal is used to warn the target bird to change the current flight trajectory. Therefore, the application can analyze the visual misjudgment factors of the collision risk area flying towards the glass curtain wall and the flight trajectory of the target bird to determine whether the target bird will collide with the target collision risk area, and issue a warning signal to the target bird in the case that it is determined that the target bird will collide with the target collision risk area, so as to warn the target bird to change the current flight path, thereby avoiding bird collision. The application solves the defect that the prior art cannot effectively prevent bird collision, realizes effective prevention of bird collision, reduces the threat to the lives of birds caused by glass curtain walls, and effectively prevents the glass on the building from being damaged and falling due to bird collision, thereby preventing safety accidents.

[0123] The device for preventing bird collision with glass curtain wall provided by the application will be described below, and the device for preventing bird collision with glass curtain wall described below can be correspondingly referred to the method for preventing bird collision with glass curtain wall described above.

[0124] Figure 11 FIG. 1 is a structural schematic diagram of the device for preventing bird collision with glass curtain wall provided by the embodiments of the application. As shown in FIG. 1, Figure 11 The device 1100 for preventing bird collision with glass curtain wall comprises: The acquisition module 1101 is configured to acquire monitoring images of a bird activity area corresponding to a target collision risk area collected by an image acquisition device and visual factors of the target collision risk area in the case that at least one collision flight trajectory of a glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area are obtained; the target collision risk area is any one of the at least one collision risk area.

[0125] The computing module 1102 is configured to calculate a flight trajectory of the target bird in the monitoring image.

[0126] The analyzing module 1103 is configured to analyze whether the target bird will collide with the target collision risk area according to the flight trajectory, the at least one collision flight trajectory, the visual factor and the visual misjudgment factor of the target collision risk area.

[0127] The warning module 1104 is configured to issue a warning signal in the case that the target bird will collide with the target collision risk area; the warning signal is used to warn the target bird to change the current flight trajectory.

[0128] The device for preventing bird collision with glass curtain wall provided by the application can analyze the visual misjudgment factor of the collision risk area that the target bird flies to and the flight trajectory of the target bird, determine whether the target bird will collide with the target collision risk area, and issue a warning signal to the target bird to change the current flight path in the case that the target bird will collide with the target collision risk area, so as to avoid bird collision and solve the problem that the prior art cannot effectively prevent bird collision.

[0129] Figure 12 An example of a schematic diagram of the physical structure of an electronic device is shown in FIG. 1. Figure 12As shown, the electronic device can include a processor 1210, a communications interface 1220, a memory 1230, and a communications bus 1240, wherein the processor 1210, the communications interface 1220, and the memory 1230 complete mutual communication through the communications bus 1240. The processor 1210 can invoke a logic instruction in the memory 1230 to execute the method for preventing bird impact on the glass curtain wall, the method comprising: obtaining at least one impact flight trajectory of the glass curtain wall, at least one impact risk area, and visual misjudgment factors of each impact risk area, acquiring a monitoring image of a bird activity area corresponding to a target impact risk area collected by an image acquisition device, and a visual factor of the target impact risk area; the target impact risk area is any one of the at least one impact risk area; calculating a flight trajectory of a target bird in the monitoring image; analyzing whether the target bird will impact the target impact risk area according to the flight trajectory, the at least one impact flight trajectory, the visual factor, and the visual misjudgment factor of the target impact risk area; issuing a warning signal in a case where it is determined that the target bird will impact the target impact risk area; the warning signal is used to alert the target bird to change the current flight trajectory.

[0130] In addition, the logic instruction in the memory 1230 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0131] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a computer readable storage medium, and the computer program can be executed by a processor to enable the computer to perform the method for preventing birds from colliding with a glass curtain wall, comprising: obtaining at least one collision flight track of the glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area, acquiring monitoring images of a bird activity area corresponding to a target collision risk area collected by an image collection device and visual factors of the target collision risk area, the target collision risk area being any one of the at least one collision risk area, calculating a flight track of a target bird in the monitoring images, analyzing whether the target bird will collide with the target collision risk area according to the flight track, the at least one collision flight track, the visual factors, and the visual misjudgment factors of the target collision risk area, and issuing a warning signal when it is determined that the target bird will collide with the target collision risk area, the warning signal being used to alert the target bird to change the current flight track.

[0132] In another aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, and the computer program can be executed by a processor to implement the method for preventing birds from colliding with a glass curtain wall, comprising: obtaining at least one collision flight track of the glass curtain wall, at least one collision risk area, and visual misjudgment factors of each collision risk area, acquiring monitoring images of a bird activity area corresponding to a target collision risk area collected by an image collection device and visual factors of the target collision risk area, the target collision risk area being any one of the at least one collision risk area, calculating a flight track of a target bird in the monitoring images, analyzing whether the target bird will collide with the target collision risk area according to the flight track, the at least one collision flight track, the visual factors, and the visual misjudgment factors of the target collision risk area, and issuing a warning signal when it is determined that the target bird will collide with the target collision risk area, the warning signal being used to alert the target bird to change the current flight track.

[0133] The device embodiments described above are merely illustrative, wherein the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0134] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0135] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of preventing bird strikes against a glass curtain wall, characterized by, The method comprises the following steps: In the case of obtaining at least one impact flight trajectory of the glass curtain wall, at least one impact risk area, and visual misjudgment factors of each impact risk area, obtaining monitoring images of a target impact risk area corresponding to a bird activity area collected by an image collection device, and visual factors of the target impact risk area; The target impact risk area is any one of the at least one impact risk area; Calculating the flight trajectory of the target bird in the monitoring image; According to the flight trajectory, the at least one impact flight trajectory, the visual factors, and the visual misjudgment factors of the target impact risk area, analyzing whether the target bird will impact the target impact risk area; In the case of determining that the target bird will impact the target impact risk area, issuing a warning signal; the warning signal is used to warn the target bird to change the current flight trajectory.

2. The method of preventing bird strikes against a glass curtain wall of claim 1, wherein, Before the step of obtaining the monitoring images of the target impact risk area corresponding to the bird activity area collected by the image collection device, and the visual factors of the target impact risk area, the method further comprises the following steps: Obtaining building measurement data of the glass curtain wall, impact measurement data of birds impacting the glass curtain wall in history, and historical impact scenes; wherein the impact measurement data comprises: impact time, historical impact flight trajectory spatial position at the impact time, and historical impact position of the glass curtain wall impacted by the historical flight trajectory obtained based on the historical impact flight trajectory spatial position; According to the building measurement data of the glass curtain wall, establishing a glass curtain wall three-dimensional model; According to the historical impact flight trajectory spatial position, the impact time, and the historical impact position, obtaining the impact flight trajectory of the bird reaching the glass curtain wall three-dimensional model, and obtaining the at least one impact flight trajectory; According to the historical impact position, determining at least one impact aggregation area on the glass curtain wall three-dimensional model, and taking each impact aggregation area in the at least one impact aggregation area as the impact risk area; According to the historical impact scene corresponding to the impact risk area, obtaining the visual misjudgment factors of the impact risk area.

3. The method of preventing bird strikes against a glass curtain wall of claim 2, wherein, After the step of determining at least one impact aggregation area on the glass curtain wall three-dimensional model according to the historical impact position, the method further comprises the following steps: According to the curtain wall picture scene in the at least one impact aggregation area, analyzing whether there is a similar risk area in other areas of the glass curtain wall except the at least one impact aggregation area; wherein the scene similarity degree of the curtain wall picture scene of the similar risk area and the curtain wall picture scene of the impact aggregation area is greater than a set scene similarity degree; in the case of determining that there is the similar risk area on the glass curtain wall, determining the similar risk area as the impact risk area.

4. The method of preventing bird strikes against a glass curtain wall according to any one of claims 1 to 3, characterized in that, The step of analyzing whether the target bird will impact the target impact risk area according to the flight trajectory, the at least one impact flight trajectory, the visual factors, and the visual misjudgment factors of the target impact risk area comprises the following steps: calculating a trajectory similarity of the flight trajectory and a target impact flight trajectory; wherein the target impact flight trajectory is any one of the at least one impact flight trajectory; in a case where the trajectory similarity is greater than a set trajectory similarity, determining whether the visual misjudgment factor exists in the visual factor of the target impact risk area; in a case where the visual misjudgment factor exists in the visual factor of the target impact risk area, determining that the target bird will impact the target impact risk area.

5. The method of preventing bird strikes against a glass curtain wall according to any one of claims 1-3, wherein, The warning signal includes a flash light warning signal. The warning signal includes a flash light warning signal. In a case where it is determined that the target bird will impact the impact risk area, calculating a flight speed of the target bird and a pre-judgment flight trajectory of the target bird according to the monitoring image; calculating flash light control information according to the flight speed and the pre-judgment flight trajectory; controlling the flash light to irradiate the bird activity area according to the flash light control information.

6. The method of preventing bird strikes against a glass curtain wall of claim 5, wherein, The warning signal also includes a sound warning signal; after the flash light is controlled to irradiate the bird activity area according to the flash light control information, the method further includes: calculating a remaining time of the target bird to the glass curtain wall according to the monitoring image; in a case where the remaining time is less than a set time, emitting the sound warning signal.

7. A device for preventing bird strikes against a glass curtain wall, characterized in that, The method includes: a obtaining module, configured to obtain a monitoring image of a target impact risk area corresponding to a bird activity area and a visual factor of the target impact risk area, which are collected by an image collection device, in a case where at least one impact flight trajectory of a glass curtain wall, at least one impact risk area, and a visual misjudgment factor of each impact risk area are obtained; the target impact risk area is any one of the at least one impact risk area; a calculating module, configured to calculate a flight trajectory of a target bird in the monitoring image; an analyzing module, configured to analyze whether the target bird will impact the target impact risk area according to the flight trajectory, the at least one impact flight trajectory, the visual factor, and the visual misjudgment factor of the target impact risk area; a warning module, configured to emit a warning signal in a case where it is determined that the target bird will impact the target impact risk area; the warning signal is used to warn the target bird to change a current flight trajectory.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the method for preventing birds from impacting a glass curtain wall according to any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method for preventing birds from impacting a glass curtain wall according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method for preventing birds from impacting a glass curtain wall according to any one of claims 1 to 6.

Images