Automated formation group guidance method based on scene perception

Abstract

The embodiments of the present disclosure disclose an automated formation group guidance method based on scene perception. A specific implementation of the method includes: in response to receiving jump position information, determining whether the jump position corresponding to the jump position information is within any exhibit area; in response to determining that the jump position is within any exhibit area, determining the initial visit position queue corresponding to the target exhibit based on the social distance threshold and the number of people in the queue; optimizing the position of each initial visit position to obtain an optimized visit position queue; based on a preset matching strategy, matching the optimized visit position queue and the current visitor position information queue to obtain a target visitor position information queue, so as to guide each visitor to perform position jump and browse the target exhibit. This implementation can simplify the guide's operations when planning navigation routes and user viewing positions, improve the efficiency of group navigation, and improve the viewing experience of visitors.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the fields of computer graphics and virtual reality, and particularly to an automated formation group guidance method based on scene perception. Background Art

[0002] In the field of virtual reality (VR), more and more virtual reality navigation technologies allow users to freely and quickly browse the content of virtual spaces. However, in many scenarios, there is a lack of guidance technology for groups, such as in museums and cultural tourism scenarios. Therefore, group guidance technology has emerged. Group guidance technology aims to overcome the limitations of personal navigation. In a group guidance system, navigation instructions are the responsibility of one member, and other members move according to the navigation instructions. This method improves navigation efficiency and reduces the repetition of navigation instructions, helps VR users interact and explore the virtual world more effectively, and reduces various problems related to personal navigation.

[0003] However, existing group guidance technologies require a guide to select appropriate positions for each team member. On the one hand, the guide needs to select appropriate positions to ensure that there are no collisions between different members and between members and scene objects; on the other hand, the guide needs to select a better position for each member to ensure a good browsing experience. Since the above group guidance process requires the guide to first observe and then manually select positions, the operations of the guide in planning navigation routes and user viewing positions are too cumbersome, thus resulting in a reduction in group navigation efficiency.

[0004] The above information disclosed in this background art section is only used to enhance the understanding of the background of the concept of the present disclosure, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art in this country. Summary of the Invention

[0005] This summary of the present disclosure is used to introduce concepts in a concise form, and these concepts will be described in detail in the following detailed implementation section. This summary of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to be used to limit the scope of the claimed technical solution.

[0006] To solve the technical problems mentioned in the above background art section, some embodiments of the present disclosure propose an automated formation group guidance method based on scene perception. The method includes: in response to receiving jump position information for a browsing area, determining whether the jump position corresponding to the jump position information is within any exhibit area, where the browsing area includes a non-exhibit area and at least one exhibit area, and each exhibit area in the at least one exhibit area corresponds to an exhibit; in response to determining that the jump position is within any of the exhibit areas, determining an initial visit position queue corresponding to the target exhibit based on a preset social distance threshold and the number of people in the queue, where the target exhibit is the exhibit displayed in the target exhibit area, the target exhibit area is the exhibit area including the jump position, and the number of people in the queue is the number of each visitor in the visitor group; optimizing the positions of each initial visit position in the initial visit position queue to obtain an optimized visit position queue, where each optimized visit position in the optimized visit position queue is a viewpoint position with higher view quality, and the view is the image when viewing the exhibit through a virtual reality device; performing a matching process on the optimized visit position queue and the current visitor position information queue based on a preset matching strategy to obtain a target visitor position information queue for guiding each visitor in the visitor group to perform position jumps and view the target exhibit, where the matching strategy is to minimize the sum of the position deflection angles of each visitor, and the position deflection angle is the angle less than a preset degree between the orientation before the visitor jumps and the orientation after the visitor jumps.

[0007] The above embodiments of the present disclosure have the following beneficial effects: Through the method for automatically forming a formation group guidance based on scene perception in some embodiments of the present disclosure, the efficiency of group navigation can be improved. Specifically, to solve the technical problem of "reduced group navigation efficiency" mentioned in the background art section, in the method for automatically forming a formation group guidance based on scene perception in some embodiments of the present disclosure, after the guide determines the next target exhibit to be viewed, first, an initial visit position queue is generated for the group of visitors according to the jump position corresponding to the target exhibit selected by the guide. Then, the positions in the initial visit position queue are optimized to obtain an optimized visit position queue. Thus, various viewpoint positions with relatively high view quality when viewing the exhibit can be obtained for subsequent assignment to each visitor. Finally, based on a preset matching strategy, the optimized visit position queue and the current visitor position information queue are matched to obtain a target visitor position information queue for guiding each visitor in the group of visitors to perform position jumps and view the target exhibit. Among them, the above matching strategy is to minimize the sum of the position deflection angles of all visitors before and after the jump. Thus, each visitor can match and jump to an optimized visit position with relatively high view quality to observe the target exhibit better. Therefore, in the method for automatically forming a formation group guidance based on scene perception in some embodiments of the present disclosure, by automatically generating various jump positions with better viewing effects for the group of visitors after the guide selects the jump position, the operations of the guide in planning the navigation route and the viewing positions of users can be simplified, the operation burden and fatigue level of the guide can be reduced, and the efficiency of group navigation can be improved. Also, because the view quality corresponding to each optimized visit position is relatively high, the viewing experience of visitors when viewing the exhibit can be improved. In addition, by adopting the strategy of minimizing the sum of the position deflection angles of all visitors before and after the jump to match an optimized visit position for each visitor, the probability of visitors experiencing 3D (Three-dimensional) dizziness due to excessive position deflection angles before and after the jump can be significantly reduced, thereby further improving the viewing experience of visitors. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0009] Figure 1 is a flowchart of some embodiments of the method for automatically forming a formation group guidance based on scene perception according to the present disclosure;

[0010] Figure 2It is a schematic diagram of a scenario for generating an optimized visit location queue in a circular exhibit area according to the scenario-aware automated formation group guidance method of the present disclosure;

[0011] Figure 3 It is a schematic diagram of a scenario for generating an optimized visit location queue in an arc-shaped exhibit area according to the scenario-aware automated formation group guidance method of the present disclosure;

[0012] Figure 4 It is a schematic diagram of a scenario for respective viewpoint scores corresponding to the optimized visit location queue according to the scenario-aware automated formation group guidance method of the present disclosure;

[0013] Figure 5 It is a comparison schematic diagram before and after position jump according to the scenario-aware automated formation group guidance method of the present disclosure. Detailed implementation manners

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0015] In addition, it should be noted that for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0016] It should be noted that concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly stated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the drawings and in combination with the embodiments.

[0020] Figure 1Flow 100 of some embodiments of a scenario-aware automated formation group guidance method according to the present disclosure is shown. The scenario-aware automated formation group guidance method includes the following steps:

[0021] Step 101, in response to receiving jump position information for a browsing area, determine whether the jump position corresponding to the jump position information is within any exhibit area.

[0022] In some embodiments, the execution subject (such as a computing device) of the scenario-aware automated formation group guidance method can, in response to receiving jump position information for a browsing area, determine whether the jump position corresponding to the jump position information is within any exhibit area. Among them, the above-mentioned browsing area may include a non-exhibit area and at least one exhibit area. The above-mentioned non-exhibit area may be a pre-set transition area for jumping between various exhibit areas. The exhibit area may be an area where exhibits for visitors to view are displayed. Each exhibit area in the above-mentioned at least one exhibit area may correspond to an exhibit one by one. The above-mentioned jump position information may be information on the jump position selected by the guide through the VR handle. The above-mentioned guide may be a person responsible for guiding a group of visitors to view various exhibits in the browsing area. For example, the above-mentioned guide may be a tour guide or a museum docent. The above-mentioned group of visitors may be a group composed of individual visitors. The above-mentioned jump position information may be information on the coordinates of the jump position in the virtual reality scene. The above-mentioned jump position may be the landing position of the next jump selected by the guide in the virtual reality scene. The jump position corresponding to the jump position information can be matched with the browsing area map built into the VR device through map matching technology in the virtual reality scene to determine whether the above-mentioned jump position is within any exhibit area included in the above-mentioned browsing area. Among them, the above-mentioned browsing area map may be a VR map for showing the position division of the non-exhibit area and each exhibit area in the browsing area.

[0023] As an example, if the next exhibit to be visited is far from the current exhibit, then during the process of jumping from the area where the current exhibit is located to the area where the next exhibit is located, it is necessary to jump to the non-exhibit area for intermediate transition. If the next exhibit to be visited is close to the current exhibit, then it is possible to directly jump from the area where the current exhibit is located to the area where the next exhibit is located.

[0024] Optionally, each visitor in the above-mentioned group of visitors meets a preset set of visitor position conditions. The above-mentioned preset set of visitor position conditions may be a pre-set set of conditions for restricting the position and orientation of the visitors. The above-mentioned preset set of visitor position conditions may include:

[0025] Condition 1: In response to determining that the above-mentioned jump position is within any of the above-mentioned exhibit areas, each visitor in the above-mentioned visitor group faces the centroid of the above-mentioned target exhibit. Among them, the above-mentioned target exhibit may be an exhibit displayed in the target exhibit area. The above-mentioned target exhibit area may be an exhibit area including the above-mentioned jump position.

[0026] Condition 2: The straight-line distance between any two visitors in the above-mentioned visitor group is not less than the social distance threshold. Among them, the above-mentioned social distance threshold may be the lower limit value of the straight-line distance between any two visitors.

[0027] Condition 3: Each visitor in the above-mentioned visitor group does not collide with an obstacle. Among them, the obstacle may be an object that affects the movement of visitors in the virtual reality scene. For example, the above-mentioned obstacle may be, but is not limited to, one of the following: an obstacle exhibit, a pillar, a wall. The above-mentioned obstacle exhibit may be another exhibit relative to the target exhibit.

[0028] Step 102, in response to determining that the jump position is within any exhibit area, based on a preset social distance threshold and the number of people in the queue, determine the initial visit position queue corresponding to the target exhibit.

[0029] In some embodiments, the above-mentioned execution entity may, in response to determining that the above-mentioned jump position is within any of the above-mentioned exhibit areas, through various means, based on a preset social distance threshold and the number of people in the queue, determine the initial visit position queue corresponding to the target exhibit. Among them, the above-mentioned number of people in the queue may be the number of each visitor in the visitor group. The above-mentioned initial visit position queue may be composed of each initial visit position that meets the social distance condition and the non-collision condition. The initial visit position in the above-mentioned initial visit position queue may be a position for visitors to observe the exhibit. The above-mentioned social distance condition may be that the straight-line distance between any two initial visit positions is not less than the above-mentioned social distance threshold. The above-mentioned non-collision condition may be that there is no obstacle at each initial visit position.

[0030] In some alternative implementation manners of some embodiments, the above-mentioned execution entity may determine the initial visit position queue corresponding to the target exhibit through the following steps based on a preset social distance threshold and the number of people in the queue:

[0031] First step, determine whether the shape of the above-mentioned target exhibit area is circular or arc-shaped. First, according to a preset spatial overlap checking method, determine whether there are walls within a preset distance range around the target exhibit. Among them, the above-mentioned spatial overlap checking method can be a method for detecting overlaps between various items in space. The above-mentioned preset distance range can be a circular area centered on the target exhibit with a preset distance as the radius. Then, in response to determining that there are no walls within the preset distance range around the target exhibit, determine the shape of the above-mentioned target exhibit area as circular. Finally, in response to determining that there are walls within the preset distance range around the target exhibit, determine the shape of the above-mentioned target exhibit area as arc-shaped.

[0032] As an example, the above-mentioned spatial overlap checking method can be a geometric shape checking method.

[0033] Second step, in response to determining that the shape of the above-mentioned target exhibit area is circular, based on a set social distance threshold and the number of people in the queue, determine the radius of the circular area. Among them, the above-mentioned radius of the circular area can be the radius of the circle corresponding to the target exhibit area. The radius of the circular area can be generated by the following formula:

[0034] r1 = d / 2sin(π / n).

[0035] Among them, r1 represents the radius of the circular area. d represents the social distance threshold. n represents the number of visiting positions corresponding to the number of people in the queue. sin(·) represents the sine function.

[0036] Third step, based on the above-mentioned radius of the circular area and the above-mentioned number of people in the queue, determine the initial visiting position queue corresponding to the above-mentioned target exhibit. Among them, the initial visiting positions in the initial visiting position queue can be generated by the following formula:

[0037] P[i] = e.p + r1·(cos(2π×i / n), sin(2π×i / n)).

[0038] Among them, P represents the initial visiting position queue. i represents the serial number of the initial visiting position in the initial visiting position queue. P[i] represents the i-th initial visiting position in the initial visiting position queue. e represents the target exhibit. p represents the position point. e·p represents the position of the exhibit. cos(·) represents the cosine function.

[0039] Fourth step, for each initial visiting position in the above-mentioned initial visiting position queue, in response to determining that there is an obstacle at the above-mentioned initial visiting position, iteratively update the above-mentioned initial visiting position through the following formula to obtain the initial visiting position that meets the above-mentioned condition three:

[0040]

[0041] Among them, δ represents the change in the distance by which the initial visiting position moves towards the target exhibit during each iterative update. Δ represents the cumulative distance by which the initial visiting position moves towards the target exhibit after each iterative update.

[0042] Optionally, the above-mentioned execution entity may also perform the following steps:

[0043] In the first step, in response to determining that the shape of the above-mentioned target exhibit area is arc-shaped, based on the above-mentioned social distance threshold and the number of people in the queue, determine the radius of the arc area. Among them, the radius of the arc area may be the radius of the arc corresponding to the target exhibit area. The radius of the arc area can be generated by the following formula:

[0044]

[0045] Among them, r2 represents the radius of the arc area. represents the angle. In the target exhibit area, represents the obtuse or right angle formed by the wall on one side of the target exhibit and the plane where the centroid of the target exhibit is located. represents the acute angle formed by the wall on the other side of the target exhibit and the plane where the centroid of the target exhibit is located. represents the included angle between the two walls of the target exhibit, and is also the central angle of the arc corresponding to the above-mentioned target exhibit area.

[0046] In the second step, based on the above-mentioned radius of the arc area and the number of people in the queue, determine the initial visiting position queue corresponding to the above-mentioned target exhibit. Among them, the initial visiting position in the initial visiting position queue is generated by the following formula:

[0047]

[0048] In the third step, for each initial visiting position in the above-mentioned initial visiting position queue, in response to determining that there is an obstacle at the above-mentioned initial visiting position, iteratively update the above-mentioned initial visiting position through the following formula to obtain an initial visiting position that meets the above-mentioned condition three:

[0049]

[0050] Step 103, perform position optimization on each initial visiting position in the initial visiting position queue to obtain an optimized visiting position queue.

[0051] In some embodiments, the above-mentioned execution entity can optimize the positions of each initial visit position in the above-mentioned initial visit position queue in various ways to obtain an optimized visit position queue. Each optimized visit position in the above-mentioned optimized visit position queue can be a viewpoint position with relatively high view quality. The above-mentioned view can be an image when a visitor views an exhibit through a virtual reality device. The viewpoint position can be the position where a visitor is located when viewing an exhibit in a virtual scene. The viewpoint position is also associated with orientation information. The orientation information can be information about the orientation of a visitor when viewing an exhibit in a virtual scene.

[0052] In some alternative implementation manners of some embodiments, the above-mentioned execution entity can perform the following steps for each initial visit position in the above-mentioned initial visit position queue to generate an optimized visit position in the optimized visit position queue:

[0053] Take the above-mentioned initial visit position as the position to be optimized, and based on the position to be optimized, perform the following optimized visit position generation steps:

[0054] First step, determine a candidate transfer position group corresponding to the position to be optimized. Among them, the candidate transfer positions in the above-mentioned candidate transfer position group can be position points that the position to be optimized can transfer to. The above-mentioned position to be optimized can be used as the center, and a preset number of position points are evenly selected within a preset limited distance around the position to be optimized, and each position point is determined as a candidate transfer position to obtain a candidate transfer position group. Among them, the above-mentioned preset limited distance can be half of the above-mentioned social distance threshold. For example, when the social distance threshold is 0.6 meters, the above-mentioned preset distance can be 0.3 meters. The above-mentioned preset number can be the number of position points set in advance.

[0055] As an example, the above-mentioned position to be optimized can be used as the center of a square, and 8 position points are evenly selected on the edge of a square with a side length of 0.2 meters, and each of the selected position points is determined as a candidate transfer position group.

[0056] Second step, determine the initial viewpoint score corresponding to the position to be optimized. Among them, the above-mentioned initial viewpoint score can represent the visual effect when a visitor observes a target exhibit at the position to be optimized through a VR device. The above-mentioned execution entity can determine the initial viewpoint score corresponding to the position to be optimized in various ways.

[0057] In some alternative implementation manners of some embodiments, the above-mentioned execution entity can determine the initial viewpoint score corresponding to the position to be optimized through the following viewpoint score generation steps:

[0058] Step 1: Determine the exhibition object observation plane corresponding to the position to be optimized. Among them, the above-mentioned exhibition object observation plane can be a plane passing through the centroid of the target exhibition object and perpendicular to the line segment of the line of sight projection. The above-mentioned line segment of the line of sight projection can be the line segment obtained by projecting the connection line between the position to be optimized and the centroid of the target exhibition object onto the horizontal plane.

[0059] Step 2: Determine the viewer device's field of view area, exhibition object projection area, and field of view occlusion area corresponding to the above-mentioned exhibition object observation plane. Among them, the above-mentioned viewer device's field of view area can be the planar area that can be seen without field of view occlusion when observing the above-mentioned exhibition object observation plane through a VR device at the above-mentioned position to be optimized. The above-mentioned exhibition object projection area can be the planar area occupied by the projection of the target exhibition object on the above-mentioned exhibition object observation plane. The above-mentioned field of view occlusion area can be the planar area corresponding to the partially occluded field of view when observing the above-mentioned exhibition object observation plane through a VR device.

[0060] Step 3: Determine the overlapping area between the above-mentioned viewer device's field of view area and the above-mentioned exhibition object projection area as the in-field exhibition object area.

[0061] Step 4: Determine the ratio between the area of the above-mentioned in-field exhibition object area and the area of the above-mentioned viewer device's field of view area as the proportion of the exhibition object's field of view area.

[0062] Step 5: Determine the ratio between the area of the above-mentioned in-field exhibition object area and the area of the above-mentioned exhibition object projection area as the proportion of the visible area of the exhibition object.

[0063] Step 6: Determine the overlapping area between the above-mentioned field of view occlusion area and the above-mentioned in-field exhibition object area as the exhibition object occlusion area.

[0064] Step 7: Determine the difference between the area of the above-mentioned in-field exhibition object area and the area of the above-mentioned exhibition object occlusion area as the unoccluded exhibition object area.

[0065] Step 8: Determine the ratio between the above-mentioned unoccluded exhibition object area and the area of the above-mentioned in-field exhibition object area as the proportion of the unoccluded exhibition object area.

[0066] Step 9: Determine the field of view color quality of the above-mentioned target exhibition object. Among them, the above-mentioned field of view color quality can be the color richness of the target exhibition object in the VR device's field of view. The above-mentioned field of view color quality can be expressed as a percentage. The field of view color quality of the above-mentioned target exhibition object can be determined by a color richness measurement method based on color space distribution.

[0067] Step ten is to determine the depth quality of the field of view of the above-mentioned target exhibit. Among them, the depth quality of the field of view can characterize whether the depth of the target exhibit in the field of view of the VR device is appropriate, neither too far nor too close. The depth quality of the field of view can be expressed as a percentage. The depth quality of the field of view of the above-mentioned target exhibit can be determined by a preset depth measurement method, which adopts the depth measurement included in the collaborative operation method based on viewpoint quality assessment. For example, the depth measurement method can be, but is not limited to, one of the following: depth measurement method based on stereo vision, depth measurement method based on depth buffer, depth measurement method based on ray casting.

[0068] Step eleven is to perform a weighted summation process on the proportion of the exhibit's field of view area, the proportion of the exhibit's visible area, the proportion of the area of the unoccluded exhibit area, the color quality of the field of view, and the depth quality of the field of view to obtain the initial viewpoint score corresponding to the position to be optimized. Among them, the weights for linear superposition can be adjusted according to the actual scenario, and there is no fixed weight.

[0069] The third step is to determine the candidate viewpoint score corresponding to each candidate transfer position in the above-mentioned candidate transfer position group to obtain a candidate viewpoint score group. Among them, the candidate viewpoint scores in the candidate viewpoint score group can characterize the visual effect when the visitor observes the target exhibit through the VR device at the corresponding candidate transfer position. For each candidate transfer position in the above-mentioned candidate transfer position group, the candidate transfer position can be used as the position to be optimized, and the above-mentioned viewpoint score generation step can be executed to obtain the initial viewpoint score corresponding to the candidate transfer position as the candidate viewpoint score.

[0070] The fourth step is to determine the position to be optimized as the optimized viewing position in response to determining that there is no target viewpoint score in the above-mentioned candidate viewpoint score group. The target viewpoint score can be the maximum value in the above-mentioned candidate viewpoint score group that is greater than the above-mentioned initial viewpoint score.

[0071] Optionally, the above-mentioned execution subject can also execute the following steps:

[0072] The first step is to select the target viewpoint score from the above-mentioned candidate viewpoint score group as the optimized viewpoint score in response to determining that there is a target viewpoint score in the above-mentioned candidate viewpoint score group.

[0073] The second step is to use the candidate transfer position corresponding to the above-mentioned optimized viewpoint score as the position to be optimized and execute the above-mentioned optimized viewing position generation step again.

[0074] As an example, Figure 2 shows a schematic diagram of the scenario of generating an optimized viewing position queue in a circular exhibit area according to the scene-aware automated formation group guidance method of the present disclosure. In Figure 2 it, the target exhibit area is a circular exhibit area,Figure 2 It includes 10 trajectory lines and a group of 10 visitors. The position of one end of each trajectory line far from the target exhibit is the initial visit position, and the position of the other end close to the target exhibit is the optimized visit position. The distribution of the initial visit positions of each trajectory line can be regarded as an approximately uniform circular distribution. Each trajectory line can represent the position optimization process from the initial visit position to the optimized visit position. Each trajectory line can correspond one-to-one with the visitors in the group of visitors. The position where each visitor observes the target exhibit is the optimized visit position after position optimization.

[0075] As an example, Figure 3 Fig. shows a schematic diagram of a scenario for generating an optimized visit position queue in an arc-shaped exhibit area according to the scene-aware automated formation group guidance method of the present disclosure. In Figure 3 it, the target exhibit area is an arc-shaped exhibit area, Figure 3 It includes 16 trajectory lines and a group of 16 visitors. The position of one end of each trajectory line far from the target exhibit is the initial visit position, and the position of the other end close to the target exhibit is the optimized visit position. The distribution of the initial visit positions of each trajectory line can be regarded as an approximately uniform arc-shaped distribution. Each trajectory line can represent the position optimization process from the initial visit position to the optimized visit position. Each trajectory line can correspond one-to-one with the visitors in the group of visitors. The position where each visitor observes the target exhibit is the optimized visit position after position optimization.

[0076] As an example, Figure 4 Fig. shows a schematic diagram of a scenario corresponding to the viewpoint scores of the optimized visit position queue according to the scene-aware automated formation group guidance method of the present disclosure. Among them, Figure 4 It includes 5 sub-figures and a panoramic view of the browsing area. Each sub-figure corresponds one-to-one with the visitors in the panoramic view. Each sub-figure shows the picture seen by the corresponding visitor through the VR glasses at the optimized visit position, as well as the viewpoint score corresponding to the optimized visit position. The viewpoint scores shown in the 5 sub-figures are 0.916, 0.912, 0.930, 0.925, and 0.933 respectively.

[0077] Step 104, based on a preset matching strategy, perform matching processing on the optimized visit position queue and the current visitor position information queue to obtain a target visitor position information queue for guiding each visitor in the group of visitors to perform position jumps and view the target exhibit.

[0078] In some embodiments, the above-mentioned execution entity may perform matching processing on the above-mentioned optimized visit location queue and the current visitor location information queue based on a preset matching strategy to obtain a target visitor location information queue for guiding each visitor in the above-mentioned visitor group to perform position jumps and view target exhibits. Among them, the above-mentioned matching strategy may be to minimize the sum of the position deflection angles of each visitor. The position deflection angle may be an angle less than a preset degree between the position orientation before the visitor jumps and the position orientation after the jump. The above-mentioned preset degree may be a preset degree. For example, the above-mentioned preset degree may be 180 degrees. The above-mentioned matching strategy may correspond to a preset objective function. The above-mentioned preset objective function may be a function preset to minimize the sum of the position deflection angles of each visitor before and after the next jump. The above-mentioned current visitor location information queue may be a formation composed of the positions of each visitor at the current moment in the virtual scene. The current visitor location information in the above-mentioned current visitor location information queue may include a visitor identifier and current location information. The above-mentioned visitor identifier may be the unique identifier of the visitor. The above-mentioned current location information may be the information of the position of the corresponding visitor in the browsing area at the current moment before the next jump starts. The target visitor location information in the above-mentioned target visitor location information queue may be the information of the landing position of the corresponding visitor at the next jump. First, the above-mentioned preset objective function may be solved through a preset optimization method to obtain the optimized visit location corresponding to each current visitor location information. Then, for each current visitor location information in the above-mentioned optimized visit location queue, the visitor identifier corresponding to the above-mentioned current visitor location information and the optimized visit location are determined as the target visitor location information. Finally, each visitor uses virtual reality technology to jump to the vicinity of the target exhibit according to the corresponding target visitor location information and observes the target exhibit through a VR device.

[0079] As an example, the above-mentioned optimization method may be, but is not limited to, one of the following: the gradient descent method, the least squares method.

[0080] As an example, Figure 5 shows a comparison schematic diagram before and after the position jump of the scene perception-based automated formation group guidance method according to the present disclosure. Among them, Figure 5 includes a right sub-graph, a left (a) sub-graph, and a left (b) sub-graph, and includes 5 visitors, and the 5 visitors are identified by the serial numbers 1, 2, 3, 4, and 5. The right sub-graph shows the positions and orientations of each visitor before the jump. The left (a) sub-graph and the left (b) sub-graph respectively show the results after the 5 visitors jump using different position matching strategies. Among them, in the left (a) sub-graph and the left (b) sub-graph, the position deflection angles of the 5 visitors before and after the jump can be represented by α 1 、α 2, α 3 , α 4 and α 5 are shown. The left (a) sub - figure shows a random jump result of 5 visitors obtained without using the matching strategy of the present disclosure. The left (b) sub - figure shows the position jump results of 5 visitors obtained after using the matching strategy of the present disclosure. By comparing the position deflection angles of the 5 visitors in the left (a) sub - figure and the left (b) sub - figure, it can be seen that the position deflection angles of the 5 visitors in the left (b) sub - figure using the matching strategy of the present disclosure are relatively small, which can reduce the probability of 3D dizziness of visitors and improve the exhibition viewing experience.

[0081] Optionally, the above - mentioned execution entity can also generate a transition queue based on the above - mentioned jump position information in response to determining that the above - mentioned jump position is not within any exhibit area. Among them, the above - mentioned transition queue can be an ordered queue composed of each transition jump position. Each transition jump position can be a position for visitors to temporarily stay during the process of jumping from near one exhibit to near another exhibit. The above - mentioned transition queue can also meet the above - mentioned preset visitor position condition set. The jump position corresponding to the above - mentioned jump position information can be used as the first element of the ordered queue, and an approximate square matrix method is used to generate a transition queue that meets the above - mentioned preset visitor position condition set according to the above - mentioned social distance threshold and the number of people in the queue. Specifically, the approximate square matrix method can be: generating a formation square array at the transition jump position with a social distance threshold as the interval (a 2*2 array for 1 - 4 people, a 3*3 array for 5 - 9 people, and so on). For example, when the jump position is (x, y) and the social distance threshold is 0.3, for a group of 5 visitors, the jump positions of the 5 visitors can be (x + 0.3, y - 0.3), (x + 0.3, y), (x + 0.3, y + 0.3), (x, y - 0.3), (x, y) respectively.

[0082] Continuing, after generating the transition queue, it is also possible to perform matching processing on the transition queue and the above - mentioned current visitor position information queue based on the above - mentioned matching strategy to obtain a target visitor position information queue for guiding each visitor in the visitor group to jump to the corresponding transition jump position.

[0083] It should be noted that as the guide continuously selects the next jump position through the VR handle, the automated formation group guidance method based on scene perception of the present disclosure can continuously generate a target visitor position information queue for the above - mentioned visitor group to guide each visitor in the visitor group to view each exhibit. In addition, the guide can select the viewing order of the exhibits according to the actual situation and can guide the visitors to visit the exhibits repeatedly.

[0084] The above embodiments of the present disclosure have the following beneficial effects: Through the method for automated formation group guidance based on scene perception in some embodiments of the present disclosure, the efficiency of group navigation can be improved. Specifically, to solve the technical problem of "reduced group navigation efficiency" mentioned in the background art, in the method for automated formation group guidance based on scene perception in some embodiments of the present disclosure, after the guide determines the next target exhibit to be viewed, first, an initial visit position queue is generated for the visitor group according to the jump position corresponding to the target exhibit selected by the guide. Then, the positions in the initial visit position queue are optimized to obtain an optimized visit position queue. Thus, various viewpoint positions with relatively high view quality when viewing the exhibit can be obtained for subsequent allocation to each visitor. Finally, based on a preset matching strategy, the optimized visit position queue and the current visitor position information queue are matched to obtain a target visitor position information queue for guiding each visitor in the visitor group to perform position jumps and view the target exhibit. Among them, the above matching strategy is to minimize the sum of the position deflection angles before and after the jump for all visitors. Thus, each visitor can match and jump to an optimized visit position with relatively high view quality to observe the target exhibit better. Therefore, in the method for automated formation group guidance based on scene perception in some embodiments of the present disclosure, by automatically generating various jump positions with better viewing effects for the visitor group after the guide selects the jump position, the operations of the guide in planning the navigation route and the viewing positions of users can be simplified, the operation burden and fatigue degree of the guide can be reduced, and the efficiency of group navigation can be improved. Also, because the view quality corresponding to each optimized visit position is relatively high, the viewing experience of visitors when viewing the exhibit can be improved. In addition, by adopting the strategy of minimizing the sum of the position deflection angles before and after the jump for all visitors to match an optimized visit position for each visitor, the probability of visitors experiencing 3D (Three-dimensional) dizziness due to excessive position deflection angles before and after the jump can be significantly reduced, thereby further improving the viewing experience of visitors.

[0085] The technical content not elaborated in detail in the present disclosure belongs to the well-known technology of those skilled in the art.

[0086] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. An automated formation group guidance method based on scene perception, comprising: In response to receiving the jump position information for the browsing area, determining whether the jump position corresponding to the jump position information is within any exhibit area, wherein the browsing area includes a non-exhibit area and at least one exhibit area, and each exhibit area in the at least one exhibit area corresponds to an exhibit; In response to determining that the jump position is in the arbitrary exhibit area, based on a preset social distance threshold and the number of people in the queue, an initial visitor position queue corresponding to the target exhibit is determined, wherein the target exhibit is an exhibit displayed in a target exhibit area, the target exhibit area is an exhibit area including the jump position, the number of people in the queue is the number of each visitor in the visitor group, and the social distance threshold is a lower limit value of the straight-line distance between any two visitors. The initial visitor position queue corresponding to the target exhibit based on the preset social distance threshold and the number of people in the queue is determined, including: Determine whether the shape of the target exhibit area is circular or arc-shaped; In response to determining that the shape of the target exhibit area is circular, determining a radius of the circular area based on a preset social distance threshold and the number of people in the queue; Determine an initial visit position queue corresponding to the target exhibit based on the radius of the circular area and the number of people in the queue; For each initial visit position in the initial visit position queue, in response to determining that an obstacle exists at the initial visit position, iteratively updating the initial visit position; Optimizing the positions of each initial visiting position in the initial visiting position queue to obtain an optimized visiting position queue, wherein each optimized visiting position in the optimized visiting position queue is a viewpoint position with a higher view quality, and the view is an image of an exhibit viewed through a virtual reality device, and optimizing the positions of each initial visiting position in the initial visiting position queue to obtain an optimized visiting position queue includes: For each initial visit position in the initial visit position queue, the following steps are performed: The initial visit position is used as the position to be optimized, and based on the position to be optimized, the following optimized visit position generation steps are performed: Determine a candidate transfer position group corresponding to the position to be optimized; Determine the initial viewpoint score corresponding to the position to be optimized; Determine a candidate viewpoint score corresponding to each candidate transfer position in the candidate transfer position group to obtain a candidate viewpoint score group; In response to determining that the target viewpoint score does not exist in the candidate viewpoint score group, determining the position to be optimized as the optimized visit position; Based on a preset matching strategy, the optimized visiting position queue and the current visitor position information queue are matched to obtain a target visitor position information queue for guiding each visitor in the visitor group to perform position jump and browse target exhibits, wherein the matching strategy is to minimize the sum of the position deflection angles of each visitor, and the position deflection angle is the angle between the position orientation of the visitor before the jump and the position orientation after the jump, which is less than a preset degree.

2. The method according to claim 1, wherein: The method further comprises: In response to determining that the jump position is not within any exhibit area, a transition queue is generated based on the jump position information, wherein the transition queue is a sequential queue composed of various transition jump positions, and each transition jump position is a position for visitors to temporarily stay in the process of jumping from one exhibit to another exhibit.

3. The method according to any one of claims 1-2, wherein: Each visitor in the visitor group satisfies a preset visitor position condition set, wherein the preset visitor position condition set includes: Condition 1: in response to determining that the jump position is within the arbitrary exhibit area, each visitor in the visitor group faces the centroid of the target exhibit; Condition 2: The straight-line distance between the locations of any two visitors in the visitor group is not less than the social distance threshold; Condition 3: Each visitor in the visitor group does not collide with any obstacle.

4. The method according to claim 3, wherein: The radius of the circular area is generated by the following formula: r1=d / 2sin(π / n), Among them, r1 represents the radius of the circular area, d represents the social distance threshold, n represents the number of visiting positions corresponding to the number of people in the queue, and sin(·) represents the sine function; The initial visit position in the initial visit position queue is generated by the following formula: P[i]=e.p+r1·(cos(2π×i / n), sin(2π×i / n)), Wherein, P represents the initial visit position queue, i represents the sequence number of the initial visit position in the initial visit position queue, P[i] represents the i-th initial visit position in the initial visit position queue, e represents the target exhibit, p represents the position point, ep represents the position of the exhibit, and cos(·) represents the cosine function; The initial visit position is iteratively updated by the following formula to obtain the initial visit position that satisfies the third condition: Among them, δ represents the change in the distance moved by the initial visit position toward the target exhibit at each iterative update, and Δ represents the cumulative distance moved by the initial visit position toward the target exhibit after each iterative update.

5. The method according to claim 4, wherein: The method further comprises: In response to determining that the shape of the target exhibit area is an arc, the arc area radius is determined based on the social distance threshold and the number of people in the queue, wherein the arc area radius is generated by the following formula: Among them, r2 represents the radius of the arc area, Indicates the angle, in the target exhibit area, It indicates the obtuse angle or right angle formed by the wall on one side of the target exhibit and the plane where the center of mass of the target exhibit is located. It indicates the acute angle formed by the wall on the other side of the target exhibit and the plane where the center of mass of the target exhibit is located. Indicates the angle between the two side walls of the target exhibit; Based on the radius of the arc area and the number of people in the queue, an initial visiting position queue corresponding to the target exhibit is determined, wherein the initial visiting position in the initial visiting position queue is generated by the following formula: For each initial visit position in the initial visit position queue, in response to determining that an obstacle exists at the initial visit position, the initial visit position is iteratively updated by the following formula to obtain an initial visit position that satisfies the third condition:

6. The method according to claim 3, wherein: The target viewpoint score is a maximum value in the candidate viewpoint score group that is greater than the initial viewpoint score.

7. The method according to claim 6, wherein: The method further comprises: In response to determining that there is a target viewpoint score in the candidate viewpoint score group, selecting the target viewpoint score from the candidate viewpoint score group as the optimized viewpoint score; The candidate transfer position corresponding to the optimized viewpoint score is used as the position to be optimized, and the optimized visit position generation step is performed again.

8. The method according to claim 7, wherein: The determining of the initial viewpoint score corresponding to the position to be optimized includes: Determine the exhibit observation plane corresponding to the position to be optimized; Determine the visitor's device field of view area, the exhibit projection area and the field of view obstruction area corresponding to the exhibit observation plane; Determine the overlapping area between the field of view area of ​​the visitor's device and the exhibit projection area as the exhibit area within the field of view; Determine the ratio between the area of ​​the exhibit area within the field of view and the area of ​​the field of view of the visitor device as the exhibit field of view area ratio; Determine the ratio between the area of ​​the exhibit area within the field of view and the area of ​​the exhibit projection area as the exhibit visible area ratio; Determine an overlapping area between the visual field blocking area and the exhibit area within the visual field as the exhibit blocking area; Determine the difference between the area of ​​the exhibit area in the field of view and the area of ​​the exhibit blocked area as the unblocked exhibit area; Determine the ratio between the unobstructed exhibit area and the area of ​​the exhibit area within the field of view as the unobstructed exhibit area ratio; Determining the visual field color quality of the target exhibit; Determining the depth of field quality of the target exhibit; The proportion of the exhibit field of view area, the proportion of the exhibit visible area, the proportion of the unobstructed exhibit area, the field of view color quality and the field of view depth quality are weightedly summed to obtain an initial viewpoint score corresponding to the position to be optimized.

Images