Scenic spot image generation method based on artificial intelligence and electronic equipment

Abstract

The invention relates to the technical field of image generation, in particular to a tourist attraction image generation method based on artificial intelligence and electronic equipment, and the electronic equipment comprises a data acquisition module, a data transmission and storage module, a data processing and analysis module and an application service and display module. By means of the camera face recognition technology and the electronic equipment, the number of people in each scenic spot can be counted and updated in real time, red, yellow and green three colors are directly displayed on mobile phones of tourists or a map of a large screen of a park in an overlapped mode, the tourists can judge which areas are crowded and which areas are unblocked at a glance without waiting for broadcasting or inquiring workers, and therefore the tourists can judge the crowded areas and the unblocked areas at a glance. Therefore, the sightseeing sequence and direction are automatically adjusted, the queuing time is remarkably shortened, and the sightseeing efficiency and comfort are improved.

Description

Technical Field

[0001] This invention relates to the field of image generation technology, and in particular to a method and electronic device for generating images of tourist attractions based on artificial intelligence. Background Technology

[0002] Currently, most tourist attractions are equipped with static directional maps or electronic guide screens. By marking the location of attractions, service facilities, and recommended routes, these screens provide basic spatial guidance for first-time visitors, enabling them to quickly understand the layout of the scenic area and plan a rough tour route, thereby improving tour efficiency and experience to some extent.

[0003] However, the scenic spots presented by these maps or guide maps are mostly fixed templates and cannot be connected with real-time data. Changes in the flow of people inside the scenic area, instantaneous congestion, and the area's carrying capacity cannot be dynamically reflected on the images. When tourists go to popular attractions based on static scenic pictures, they often get stuck in long queues or high-density gathering areas, which not only wastes valuable sightseeing time but also reduces the overall comfort and even brings safety hazards.

[0004] To address the aforementioned shortcomings, this invention proposes an AI-based method for generating tourist attraction images and an electronic device: A high-precision, full-area digital map is constructed using UAV aerial surveying and BIM technology. Edge computing cameras are integrated to detect real-time facial orientation and entry / exit events, dynamically calculating the number of visitors, hazard level capacity, and visitor dwell time at each attraction. The congestion level is then displayed in real-time on the map using red, yellow, and green overlays. When multiple intersections experience congestion, the electronic device automatically generates a planning arrow indicating the fastest evacuation direction using an "evacuation speed" index. This allows tourists to stay informed about the latest crowd distribution, autonomously avoid peak areas, and achieve safe, efficient, and personalized intelligent tourism. Summary of the Invention

[0005] To achieve the above objectives, this invention proposes an artificial intelligence-based method and electronic device for generating tourist attraction images, comprising the following steps: Step 1: Create a map of the entire scenic area, and label each scenic area. The second step is to detect the flow of people. Cameras are installed at the entrances and exits of the scenic area and at the intersections of the routes. The cameras are used to identify the flow of people and calculate the number of people inside the scenic area. Step 3: Set the capacity of the scenic spot. Determine the number of people that can be accommodated in a single area based on the degree of danger of the scenic spot, and calculate the capacity of the scenic spot area in combination with the area of ​​the scenic spot. Step 4: Determining the length of stay. Using the camera's facial recognition function, the time points when the same face enters and leaves the attraction are recorded. The difference is used to calculate the length of stay. The median of multiple sets of time data is calculated to determine the length of stay at the attraction. Step 5: Route planning. Combine steps 2 and 3 to determine the number of visitors in the scenic area. Based on the visitor capacity in step 3, set a threshold range, classify the visitor capacity of the scenic area according to the threshold range, color-code each category, and display it on the scenic area map created in step 1.

[0006] In one example, the pedestrian flow detection is achieved by installing cameras at the intersections of scenic spots, with each camera corresponding to one fork in the road. The cameras have facial recognition capabilities, identifying the direction of travel through facial features and temporarily storing the faces to ensure that the direction of travel is matched for the next identification. However, the facial information of staff members and all scenic spot operators is not included in the pedestrian flow detection scope.

[0007] In one example, the setting of the tourist attraction's capacity also includes the introduction of a dynamic threshold adjustment mechanism to make capacity management more adaptable. In terms of time, the threshold can be preset and adjusted according to peak and off-peak seasons and holidays. In terms of environment, weather forecast data can be accessed to automatically reduce the capacity of dangerous areas under severe weather conditions such as rain, snow, and fog. In terms of events, the capacity model of relevant areas needs to be temporarily changed when large-scale events are held.

[0008] In one example, the route planning also includes determining the dwell time of two attractions when a fork in the road is marked in red, using the time difference from step four. The dwell time represents the speed at which people leave the attraction. By comparing the two dwell times, an arrow is drawn on the map to indicate the attraction where evacuation is faster.

[0009] In one example, the creation of the global map utilizes aerial photogrammetry by drones to obtain a high-precision digital elevation model and orthophoto map of the scenic area. It also performs detailed measurements and 3D modeling of all buildings, roads, and facilities within the scenic area, and vectorizes all paths and defines key attributes such as width, slope, and hazard level.

[0010] In one example, an AI-based electronic device for generating tourist attraction images includes a data acquisition module, a data transmission and storage module, a data processing and analysis module, and an application service and display module.

[0011] In one example, the data acquisition module is responsible for implementing the map data acquisition in the first step and the real-time pedestrian flow data capture in the second step of the method. The data acquisition module includes a geographic information acquisition unit and an Internet of Things (IoT) sensing network. The geographic information acquisition unit consists of a drone aerial photography electronic device, a 3D laser scanner, and a GPS surveying device, used to acquire multi-source geospatial data of the scenic area. The IoT sensing network consists of smart cameras deployed at key nodes in the scenic area. The cameras are high-definition network cameras with edge computing capabilities and built-in face detection algorithms.

[0012] In one example, the data transmission and storage module includes a network communication module and a data storage and management server. The network communication module adopts a hybrid wired and wireless networking method. The data storage and management server stores the processed high-precision digital map model, regional label library, and anonymized facial feature data, timestamps, and real-time data streams of travel direction events uploaded by the perception network. The streaming data processing engine connects to the real-time data streams passed from the data transmission layer and continuously runs the people counting algorithm.

[0013] In one example, the data processing and analysis module is equipped with a streaming data processing engine, a capacity threshold management module, and a behavior analysis engine. The capacity threshold management module pre-stores and dynamically calculates the capacity thresholds for each area, while the behavior analysis engine calculates the individual's stay time at the attraction by analyzing the timestamps recorded by tourists from different cameras.

[0014] In one example, the application services and display module includes intelligent route planning services, a visual management platform, and a visitor guidance terminal.

[0015] The artificial intelligence-based tourist attraction image generation method and electronic device proposed in this invention can bring the following beneficial effects: 1. This invention utilizes camera facial recognition technology, enabling electronic devices to count and update the number of visitors at each attraction in real time. The data is displayed directly on the map on the visitor's mobile phone or the park's large screen using a combination of red, yellow, and green colors. Visitors do not need to wait for announcements or ask staff; they can immediately determine which areas are crowded and which are unobstructed, thus allowing them to adjust their tour order and direction independently, significantly reducing queuing time and improving tour efficiency and comfort.

[0016] 2. This invention records the time points when the same face enters and leaves a scenic spot. Electronic devices calculate the actual stay time and generate an evacuation speed index. When multiple red congestion points appear at a fork in the road, the map automatically marks dynamic arrows pointing to scenic spots with shorter stay times and faster evacuation. This provides tourists with travel route planning based on real-time data, helps to quickly divert crowds, reduces the risk of local congestion, and ensures the safety and order of scenic area operation. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a schematic diagram of a method for generating images of tourist attractions based on artificial intelligence. Figure 2 A schematic diagram of an electronic device architecture for generating images of tourist attractions based on artificial intelligence. Detailed Implementation

[0018] To more clearly illustrate the overall concept of the present invention, a detailed description will be provided below with reference to the accompanying drawings and examples.

[0019] In the description of this invention, it should be understood that the terms "center," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communication connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0022] In this invention, unless otherwise expressly specified and limited, the first feature "on" or "below" the second feature may be in direct contact with the first and second features, or indirect contact through an intermediate medium. In the description of this specification, references to terms such as "an embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0023] like Figures 1 to 2 As shown, this invention proposes an artificial intelligence-based method for generating images of tourist attractions, comprising the following steps: Step 1: Create a map of the entire scenic area. This involves creating a map of the entire scenic area and labeling each scenic area to facilitate subsequent data statistics.

[0024] The creation of a global map is the cornerstone of the entire electronic system. Its level of detail and data richness directly determine the accuracy of subsequent analysis. This stage is far more than simply drawing a plan; it is a digital process that integrates geographic information electronic equipment, building information modeling, and the Internet of Things.

[0025] First, multi-source data collection is required to build a high-precision map. UAVs are used for aerial photogrammetry to obtain a high-precision digital elevation model and orthophoto map of the scenic area, accurately depicting the terrain undulations and vegetation cover. At the same time, all buildings, roads and facilities in the scenic area are measured and 3D modeled in detail. The model needs to include structural information and basic data for capacity estimation, and all paths are vectorized and key attributes such as width, slope and hazard level are defined.

[0026] Based on this, a multi-level regional labeling system is established, and a multi-level spatial index of "scenic area-region-attraction-sub-region" is constructed to facilitate macro and micro management. Each region is labeled with functional attributes such as sightseeing, cultural heritage, and rest and service, and each area that can stay is labeled with its effective carrying area. Linear areas are labeled with their effective carrying length and reasonable personnel density. These data are the direct basis for subsequent capacity calculations. At the same time, all key points of interest such as entrances and exits, restrooms, and first aid points also need to be marked.

[0027] Finally, the completed digital map will be integrated into a unified management platform. This platform needs to have functions such as map rendering, spatial query, and data visualization to provide core data sources for management decisions and visitor guidance.

[0028] The second step is to detect pedestrian flow using cameras. Cameras are typically installed at intersections of scenic spots, usually near the signs. Each camera corresponds to one fork in the road, and the cameras have facial recognition capabilities. They identify the direction of movement by facial features and temporarily store the faces to ensure accurate identification the next time. However, the facial information of staff and all scenic spot operators is not included in the pedestrian flow detection.

[0029] The specific method for determining visitor flow involves installing cameras at entrances and exits to track the total number of people entering and exiting the scenic area. Cameras at forks in the route identify people passing by, with the direction their faces are facing corresponding to the opposite direction of movement, thus determining their path. This path is then combined with facial recognition from the next camera to determine the number of people in the area between the two cameras. For example, if camera A and camera B are located on opposite sides of the scenic area, and camera A captures a person moving towards the scenic area, the number of people is increased by one; if camera B captures a person moving away from the scenic area, the number of people is decreased by one. By combining the data from cameras A and B, the number of people in the scenic area can be determined. However, there are special cases where a single camera detects a person's face facing the opposite direction from the scenic area, resulting in the opposite trend in the number of people. For example, if camera A detects a face moving away from the scenic area, the number of people in the scenic area is decreased by one; similarly, if camera B detects a face moving towards the scenic area, the number of people in the scenic area is increased by one.

[0030] Step 3: Set the capacity of the scenic spot. Each threshold setting can be set according to the area of ​​the scenic spot. For some mountainous scenic spots or areas with a high degree of danger, the number of people that can be accommodated per area can be divided according to the degree of danger. For example, according to the degree of danger, levels 1-4 can be set. Level 1 corresponds to two people per area. As the degree of danger increases, the number of people that can be accommodated per area decreases. For example, at level 4, one person needs an area of ​​1.5 square meters to ensure safety. The specific capacity can be set by yourself.

[0031] Secondly, a dynamic threshold adjustment mechanism is introduced to make capacity management more adaptable. In terms of time, thresholds can be preset and adjusted according to peak and off-peak seasons and holidays. In terms of environment, weather forecast data can be accessed to automatically reduce the capacity of dangerous areas under severe weather conditions such as rain, snow, and fog. In terms of events, the capacity model of relevant areas needs to be temporarily changed when large-scale events are held.

[0032] Step 4: Determining the duration of stay. Since cameras are installed at the entrance and exit of the attraction, after the camera recognizes a face, it also saves the time point. After leaving the attraction, the camera captures the corresponding face and records the time point. The difference between the two time points represents the duration of stay at that point. All durations are stored in the database. By analyzing the distribution of time differences, the duration of stay for most people can be determined. The average duration of stay for most people is then calculated to determine the basic duration of stay at the attraction.

[0033] Step 5: Route planning. Combining steps 2 and 3, determine the visitor capacity of the scenic area. Based on the visitor capacity determined in step 3, set a threshold range. For example, if the number of visitors is 10%-50% of the threshold range, the scenic area is considered sparsely populated; if the threshold range is 50%-80%, it is considered relatively crowded; and above 80%, it is considered crowded. This percentage range can be manually adjusted. Combined with the scenic area map drawn in step 1, different colors are generated to represent the corresponding scenic spots based on the threshold range determination. For example, green represents sparsely populated areas, yellow represents relatively crowded areas, and red represents crowded areas. Tourists can observe the situation at the scenic spots and choose their routes accordingly.

[0034] Additionally, when a fork in the road occurs and all the attractions are marked in red, the time difference from step four can be used to determine the dwell time at each attraction. Dwell time indicates the speed at which people leave that attraction. By comparing the two dwell times, arrows can be used on the map to indicate the attraction where evacuation is faster, thus providing guidance.

[0035] The electronic device architecture based on the aforementioned artificial intelligence-based method for generating tourist attraction images includes the following modules: The data acquisition module is responsible for implementing the first step of map data acquisition and the second step of real-time pedestrian flow data capture in the method. This layer includes: Geographic information acquisition unit: Composed of UAV aerial photography electronic equipment, 3D laser scanner and GPS mapping equipment, it is used to acquire multi-source geospatial data of the scenic area and provide raw data for the creation of a full-area map.

[0036] The Internet of Things (IoT) sensing network consists of smart cameras deployed at key nodes throughout the scenic area (such as entrances / exits, intersections, and core attractions). These cameras are high-definition network cameras with edge computing capabilities and built-in face detection algorithms to capture video streams and identify faces and their orientation in real time, thus determining the direction of pedestrian movement.

[0037] Data transmission and storage module: This layer is responsible for connecting the data acquisition layer and the upper-layer application. This layer includes: Network communication module: It adopts a hybrid networking method of wired (such as fiber optic) and wireless (such as 5G / Wi-Fi 6) to ensure that the data collected by the front-end sensing device can be transmitted to the data center with low latency and high reliability.

[0038] Data storage and management server: This server stores processed high-precision digital map models, regional label libraries, and real-time data streams such as anonymized facial feature data, timestamps, and movement direction events uploaded by the sensing network. It also establishes a corresponding database to support data analysis.

[0039] Data Processing and Analysis Module: This layer is the core of the electronic device, responsible for implementing the data calculations and logical judgments in the second, third, and fourth steps of the method. This module includes: Streaming data processing engine: This engine interfaces with the real-time data stream from the data transmission layer and continuously runs the people counting algorithm. Based on the "entry" and "departure" events reported by the cameras, this engine aggregates and updates the current number of people in each scenic area in real time.

[0040] Capacity threshold management module: This module pre-stores or dynamically calculates the capacity threshold for each area (as in step 3), and compares it with the real-time number of people obtained by the data processing engine to determine the current congestion level (green, yellow, red).

[0041] Behavioral Analysis Engine: This engine analyzes the timestamps of tourists recorded by different cameras (such as in step four), calculates the individual's stay time at the attraction, and performs big data analysis to derive key indicators such as average stay time and the speed at which people leave.

[0042] Application Services and Display Module: This layer is responsible for implementing the route planning and visualization in step five of the method, directly facing administrators and visitors. This module includes: Intelligent route planning service: This service receives real-time congestion status and pedestrian evacuation speed data from the data processing and analysis layer. When planning routes for tourists, it prioritizes recommending green and unobstructed routes; when route options are limited, it combines the "pedestrian evacuation speed" indicator to guide tourists to areas with faster evacuation.

[0043] Visual management platform: Provides back-end electronic devices for scenic area managers. Based on a full-area map, it renders the colors (green, yellow, red) of each area in real time, displays key statistical data, and provides functions such as threshold configuration and report query.

[0044] Visitor navigation terminals include the scenic area's official mobile app, mini-program, and public information displays within the park. These terminals obtain real-time data from the application service layer, dynamically displaying color maps and recommended routes to visitors, enabling intelligent navigation and visitor flow management.

[0045] Additionally, when a fork in the road occurs and all the attractions are marked in red, the time difference from step four is used to determine the dwell time at each attraction. The dwell time indicates the speed at which people leave the attraction. By comparing the two dwell times, arrows can be used on the map to indicate the attraction with faster evacuation, thus providing guidance. This function is achieved by the intelligent path planning service in the application service and presentation layer calling the behavior analysis engine in the data processing and analysis layer.

[0046] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the electronic device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0047] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for generating tourist attraction images based on artificial intelligence, characterized in that: Includes the following steps: Step 1: Create a map of the entire scenic area, and label each scenic area. The second step is to detect the flow of people. Cameras are installed at the entrances and exits of the scenic area and at the intersections of the routes. The cameras are used to identify the flow of people and calculate the number of people inside the scenic area. Step 3: Set the capacity of the scenic spot. Determine the number of people that can be accommodated in a single area based on the degree of danger of the scenic spot, and calculate the capacity of the scenic spot area in combination with the area of ​​the scenic spot. Step 4: Determining the length of stay. Using the camera's facial recognition function, the time points when the same face enters and leaves the attraction are recorded. The difference is used to calculate the length of stay. The median of multiple sets of time data is calculated to determine the length of stay at the attraction. Step 5: Route planning. Combine steps 2 and 3 to determine the number of visitors in the scenic area. Based on the visitor capacity in step 3, set a threshold range, classify the visitor capacity of the scenic area according to the threshold range, color-code each category, and display it on the scenic area map created in step 1.

2. The method for generating tourist attraction images based on artificial intelligence according to claim 1, characterized in that: The pedestrian flow detection is achieved by installing cameras at the intersections of scenic spots, with each camera corresponding to one fork in the road. The cameras have facial recognition capabilities, identifying the direction of travel through facial features and temporarily storing the faces to ensure that the direction of travel is matched for the next identification. However, the facial information of staff members and all scenic spot operators is not included in the pedestrian flow detection scope.

3. The method for generating tourist attraction images based on artificial intelligence according to claim 1, characterized in that: The setting of tourist attraction capacity also includes the introduction of a dynamic threshold adjustment mechanism to make capacity management more adaptable. In terms of time, the threshold can be preset and adjusted according to peak and off-peak seasons and holidays. In terms of environment, weather forecast data can be connected to automatically reduce the capacity of dangerous areas in severe weather such as rain, snow, and fog. In terms of event, the capacity model of relevant areas needs to be temporarily changed when large-scale events are held.

4. The method for generating tourist attraction images based on artificial intelligence according to claim 1, characterized in that: The route planning also includes determining the dwell time of two attractions when a fork in the road is marked in red, based on the time difference in step four. The dwell time represents the speed at which people leave the attraction. By comparing the two dwell times, an arrow is drawn on the map to indicate the attraction where evacuation is faster.

5. The method for generating tourist attraction images based on artificial intelligence according to claim 1, characterized in that: The creation of the full-area map utilizes drones for aerial photogrammetry to obtain high-precision digital elevation models and orthophoto maps of the scenic area. It also involves detailed measurement and 3D modeling of all buildings, roads, and facilities within the scenic area, vectorizing all paths and defining key attributes such as width, slope, and hazard level.

6. An electronic device applied to the artificial intelligence-based tourist attraction image generation method of claim 1, characterized in that: It includes a data acquisition module, a data transmission and storage module, a data processing and analysis module, and an application service and display module.

7. The electronic device according to claim 6, characterized in that: The data acquisition module is responsible for the first step of map data acquisition and the second step of real-time pedestrian flow data capture in the method. The data acquisition module includes a geographic information acquisition unit and an Internet of Things (IoT) sensing network. The geographic information acquisition unit consists of a drone aerial photography electronic device, a 3D laser scanner and a GPS surveying device, used to acquire multi-source geospatial data of the scenic area. The IoT sensing network consists of smart cameras deployed at key nodes in the scenic area. The cameras are high-definition network cameras with edge computing capabilities and built-in face detection algorithms.

8. The electronic device according to claim 6, characterized in that: The data transmission and storage module includes a network communication module and a data storage and management server. The network communication module adopts a hybrid wired and wireless networking method. The data storage and management server stores the processed high-precision digital map model, regional label library, and anonymized facial feature data, timestamps, and real-time data streams of travel direction events uploaded by the perception network. The streaming data processing engine connects to the real-time data streams input from the data transmission layer and continuously runs the people counting algorithm.

9. The electronic device according to claim 6, characterized in that: The data processing and analysis module is equipped with a streaming data processing engine, a capacity threshold management module, and a behavior analysis engine. The capacity threshold management module pre-stores and dynamically calculates the capacity threshold for each area, while the behavior analysis engine calculates the individual's stay time at the attraction by analyzing the timestamps recorded by tourists from different cameras.

10. The electronic device according to claim 6, characterized in that: The application services and display modules include intelligent route planning services, a visual management platform, and a visitor guidance terminal.

Images