Scenic route planning method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a scenic route planning method and device, an electronic device and a storage medium. The method comprises: collecting a plurality of frames of to-be-identified images of a pedestrian A by a plurality of image collection devices, wherein the plurality of image collection devices are arranged at an entrance of a scenic spot A and have different snapshot angles; determining an identity recognition mode corresponding to each frame of to-be-identified image in the plurality of frames of to-be-identified images, and performing identity recognition on the pedestrian A according to the identity recognition mode and each frame of to-be-identified image to obtain identity information of the pedestrian A; determining a number of people staying at the scenic spot A according to the identity information of the pedestrian A and a number of tourists leaving the scenic spot A; and planning a route for a tourist entering the scenic area according to the number of people staying at each scenic spot in the scenic area. The embodiments of the present application are beneficial to improving the play experience of tourists.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a scenic area route planning method, device, electronic device and storage medium. Background Art

[0002] Counting passenger flow is very important for some businesses or governments. For example, for bus operation, the passenger flow at each station can be counted, and then the traffic management department can dynamically plan traffic routes based on the passenger flow at each station, providing intelligent bus operation. For another example, in order to improve tourists' travel experience, the passenger flow of scenic spots during peak periods can be counted, and reasonable travel routes can be planned for tourists based on the passenger flow of the scenic spots, and the travel routes can be pushed to tourists to improve their travel experience.

[0003] At present, when counting the number of residents in scenic spots, the identity verification method is relatively simple, resulting in inaccurate statistics of the number of residents, making it difficult to plan the best tour route and reducing the tourists' travel experience. Summary of the Invention

[0004] The embodiments of the present application provide a scenic spot route planning method, device, electronic device and storage medium to improve the statistical accuracy of the number of people staying in the scenic spot, thereby improving the tourists' travel experience.

[0005] In a first aspect, an embodiment of the present application provides a scenic area route planning method, comprising:

[0006] Capturing multiple frames of images of pedestrian A to be identified by using multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of scenic spot A and are captured at different angles, the scenic spot A is any scenic spot in the scenic area, the pedestrian A is any pedestrian entering the scenic spot A, and the multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified;

[0007] Determining an identity recognition pattern corresponding to each frame of the multiple frames of images to be recognized, and performing identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized to obtain identity information of the pedestrian A;

[0008] Determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A;

[0009] According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

[0010] In a second aspect, an embodiment of the present application provides a scenic area route planning device, comprising:

[0011] a collection unit configured to collect multiple frames of images of pedestrian A to be identified using multiple image collection devices, wherein the multiple image collection devices are set at the entrance of scenic spot A and capture images at different angles, the scenic spot A is any scenic spot in the scenic area, and the pedestrian A is any pedestrian entering the scenic spot A, and the multiple image collection devices correspond one-to-one to the multiple frames of images to be identified;

[0012] a processing unit, configured to determine an identity recognition pattern corresponding to each frame of the plurality of frames of images to be recognized, and to perform identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized, thereby obtaining identity information of the pedestrian A;

[0013] Determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A;

[0014] According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, the processor being connected to a memory, the memory being used to store a computer program, the processor being used to execute the computer program stored in the memory, so that the electronic device executes the method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to execute the method described in the first aspect.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to enable the computer to execute the method described in the first aspect.

[0018] The implementation of the embodiments of the present application has the following beneficial effects:

[0019] It can be seen that in the embodiment of the present application, multiple image acquisition devices are set up at each scenic spot in the scenic area, so that multiple frames of images to be identified of pedestrians entering the scenic spot can be captured from multiple angles, so that the characteristics of pedestrians at various angles can be obtained, and the identity of the pedestrians is authenticated according to the identity recognition mode corresponding to each frame of the image to be identified, which improves the comprehensiveness of the identity authentication and makes the identified identity information more accurate, thereby improving the statistical accuracy of the number of residents at each scenic spot, so that better travel routes can be planned for tourists and the user's travel experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 A schematic diagram of the architecture of a scenic area route planning system provided in an embodiment of the present application;

[0022] Figure 2 A flow chart of a scenic area route planning method provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of image stitching provided in an embodiment of the present application;

[0024] Figure 4 A flowchart of another scenic spot route planning method provided in an embodiment of the present application;

[0025] Figure 5 A block diagram of the functional units of a scenic route planning device provided in an embodiment of the present application;

[0026] Figure 6 A schematic diagram of the structure of a scenic area route planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The terms "first," "second," "third," and "fourth," etc., in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, rather than to describe a specific order. In addition, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0029] References herein to "embodiments" mean that a particular feature, result, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] It should be understood that this application uses the example of counting the number of visitors at Scenic Spot A to illustrate the process of counting visitors. Scenic Spot A is any scenic spot in the scenic area. The methods for counting the number of visitors at other scenic spots are similar to those for Scenic Spot A and will not be described further. Furthermore, this application uses the identity information of pedestrians entering Scenic Spot A as an example to illustrate the process of identifying visitors. It should be understood that for Scenic Spot A, the identity information of pedestrians leaving Scenic Spot A also needs to be identified. Identifying the identity information of pedestrians leaving Scenic Spot A is similar to identifying the identity information of pedestrians entering Scenic Spot A and will not be described further. Therefore, counting the number of visitors leaving Scenic Spot A is similar to counting the number of visitors entering Scenic Spot A and will not be described further.

[0031] participate Figure 1 , Figure 1 This is a schematic diagram of the architecture of a scenic route planning system provided in an embodiment of the present application. Figure 1 As shown, the scenic area route planning system includes a scenic area route planning device 10 and multiple image acquisition devices 20, wherein the multiple image acquisition devices are arranged at the entrances of multiple scenic spots in the scenic area, and multiple image acquisition devices 20 are arranged at the entrance of each scenic spot, and the multiple image acquisition devices 20 arranged at the entrance of each scenic spot maintain communication connection with the scenic area route planning device 10; and the multiple image acquisition devices 20 set at each scenic spot are arranged at different positions so that the capturing angles of the multiple image acquisition devices 20 are different.

[0032] based on Figure 1As shown in the system architecture diagram, when pedestrian A enters scenic spot A from the entrance of scenic spot A, multiple frames of images to be identified containing tourists can be collected by multiple image acquisition devices 20 set at the entrance of scenic spot A, wherein each image acquisition device 20 captures one frame of image to be identified, scenic spot A is any scenic spot in the scenic area, and pedestrian A is any scenic spot entering scenic spot A; then, the scenic area route planning device 10 determines the identity recognition mode corresponding to each frame of the multiple frames of images to be identified, and identifies pedestrian A based on the identity recognition mode and each frame of the images to be identified to obtain the identity information of pedestrian A; then, based on the identity information of pedestrian A and the number of tourists leaving scenic spot A, the number of residents in scenic spot A is determined, that is, the number of residents at any scenic spot in the scenic area at the current moment is obtained, that is, the number of residents at each scenic spot at the current moment is obtained; finally, based on the number of residents at each scenic spot in the scenic area at the current moment, a route is planned for tourists entering the scenic area.

[0033] It can be seen that in the embodiment of the present application, multiple image acquisition devices 20 are set at each scenic spot in the scenic area, so that multiple frames of images to be identified of pedestrians entering the scenic spot can be captured from multiple angles, so that the characteristics of pedestrians at various angles can be obtained, and the scenic area route planning device 10 authenticates the pedestrian according to the identity recognition mode corresponding to each frame of the image to be identified, thereby improving the comprehensiveness of the identity authentication and making the identified identity information more accurate, thereby improving the statistical accuracy of the number of residents at each scenic spot, so that a better travel route can be planned for tourists and improving the user's travel experience.

[0034] See Figure 2 , Figure 2 This is a flow chart of a scenic area route planning method provided in an embodiment of the present application. The method is applied to a scenic area route planning device. The method includes the following steps:

[0035] 201: The scenic area route planning device collects multiple frames of images to be identified of pedestrian A through multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of scenic spot A and the capture angles are different. The scenic spot A is any scenic spot in the scenic area, and the pedestrian A is any pedestrian entering the scenic spot A. The multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified.

[0036] For example, when a pedestrian enters scenic spot A, the scenic spot route planning device can control each image acquisition device to capture the pedestrian, thereby obtaining the multiple frames of images to be recognized. For example, the scenic spot route planning device can use infrared to detect whether a person enters the entrance of scenic spot A (an infrared detector can be installed at a designated location at the entrance). If a person is detected entering the designated location, the device controls each image acquisition device to capture the pedestrian, thereby obtaining the multiple frames of images to be recognized.

[0037] Exemplarily, each image acquisition device can be an analog camera, a digital camera, a standard definition camera, a high definition camera, a CCD camera, a COMS camera, or other devices with image capture function. This application does not limit the form of the image acquisition device.

[0038] 202: The scenic area route planning device determines an identity recognition pattern corresponding to each frame of the multiple frames of images to be recognized, and performs identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized to obtain the identity information of the pedestrian A.

[0039] Exemplarily, the scenic route planning device determines the image acquisition device corresponding to each frame of the multiple images to be identified. For example, a device identifier can be added to each frame of the image to be identified. In this way, the scenic route planning device can obtain the image acquisition device corresponding to each frame of the image to be identified by parsing the device identifier; based on the image acquisition device corresponding to each frame of the image to be identified, the corresponding capture direction of each frame of the image to be identified is determined, wherein the capture direction of each image acquisition device is pre-stored in the scenic route planning device; then, based on the mapping relationship between the capture direction and the identity recognition mode, and the capture direction corresponding to each frame of the image to be identified, the corresponding identity recognition mode of each frame of the image to be identified is determined. For example, when the capture direction is opposite to the entry direction, the corresponding identity recognition mode is face recognition; when the capture direction is the same as or perpendicular to the entry direction, the identity recognition mode is human body recognition.

[0040] Furthermore, the pedestrian A is identified based on the identity recognition pattern corresponding to each frame of the image to be identified and each frame of the image to be identified, and the matching value between each frame of the image to be identified and each preset template is obtained. That is to say, each frame of the image to be identified is identified through the identity recognition pattern corresponding to each frame of the image to be identified; then, the identity information of the pedestrian A is obtained by combining the matching values ​​between the multiple frames of the image to be identified and each preset template. For example, the matching values ​​between each frame of the image to be identified in the multiple frames of the image to be identified and each preset template are weighted to obtain the matching values ​​between the pedestrian A and each preset template. Then, when the maximum matching value is greater than the threshold, the identity information of the pedestrian A is determined to be a staff member of the scenic spot. When the maximum matching value is less than the threshold, the identity information of the pedestrian A is determined to be a tourist, that is, a non-staff member.

[0041] For example, the matching values ​​of the image to be identified 1, the image to be identified 2 and the image to be identified with the preset template 1 are 0.5, 0.2 and 0.8 respectively, and the weight coefficients are 0.6, 0.15 and 0.15 respectively. Then the matching value between the pedestrian A and the preset template 1 is 0.45 (0.5*0.6+0.2*0.15+0.8*0.15=0.45).

[0042] It should be understood that the aforementioned identity recognition modes include face recognition mode and body recognition mode. Each frame of the image to be recognized will only match one identity recognition mode, and this identity recognition mode will be used to perform identity recognition on the image to be recognized. In the face recognition mode, the aforementioned preset templates are face preset templates; in the body recognition mode, the aforementioned preset templates are body preset templates.

[0043] Specifically, when the identity recognition mode is the face recognition mode, face detection is performed on each frame of the image to be recognized to obtain the face area of ​​pedestrian A in each frame of the image to be recognized, and based on the face image in the face area, the matching value between each frame of the image to be recognized and each preset face template is determined. Exemplarily, feature extraction is performed on the face image in the face area to obtain a face feature map; based on the face feature map, a feature vector corresponding to each frame of the image to be recognized is obtained; then, the feature vector corresponding to each frame of the image to be recognized is matched with the feature vector corresponding to each preset face template (for example, Euclidean distance) to obtain the matching value corresponding to each preset face template;

[0044] Specifically, when the identity recognition mode is human recognition mode, human body detection is performed on each frame of the image to be recognized, obtaining a human body frame of pedestrian A in each frame of the image to be recognized. Based on the human body image in the human body frame, the matching value between each frame of the image to be recognized and each preset human body template is determined. Exemplarily, features of the human body in the human body frame are extracted to obtain a human body feature map; based on the human body feature map, a feature vector corresponding to each frame of the image to be recognized is obtained; then, the feature vector corresponding to each frame of the image to be recognized is matched with the feature vector corresponding to each preset human body template to obtain a matching value corresponding to each preset human body template.

[0045] Among them, the above-mentioned face preset templates are the face preset templates of each staff member in the scenic area, and the feature vectors of each face preset template are obtained by feature extraction of the face image of each staff member; the body preset templates are the body preset templates of each staff member in the scenic area, and the feature vectors of each body preset template are obtained by feature extraction of the body image of each staff member.

[0046] In one embodiment of the present application, the human body recognition mode primarily targets situations where the image to be recognized contains the body of pedestrian A but not their face. Generally, such an image to be recognized is captured from the side of the pedestrian (e.g., perpendicular to the entrance), and therefore the human body contained in such an image to be recognized may be a partial human body. Therefore, to improve the accuracy of human body recognition, images of the same pedestrian containing a human body can be spliced ​​together before identity recognition is performed.

[0047] In one embodiment of the present application, Figure 3 As shown, the image to be identified captured from the left side of pedestrian A is called the first image to be identified, and the image to be identified captured from the right side of pedestrian A is called the second image to be identified; then, human body detection is performed on the first image to be identified to obtain a first human body frame and a first human body mask map, and human body detection is performed on the second image to be identified to obtain a second human body frame and a second human body mask map, wherein the first mask map is used to characterize the area of ​​the human body (left half of the human body) belonging to pedestrian A in the first human body frame, and the second mask map is used to characterize the area of ​​the human body (right half of the human body) belonging to pedestrian A in the second human body frame; then, based on the first mask map, the human body is cut out from the first human body frame. A first human body image (i.e., the left half of the human body image) is cut out from the second human body frame based on the second mask image. The first human body image and the second human body image are spliced ​​to obtain a target human body image (a complete human body image). Then, feature extraction is performed on the target human body image to obtain a target feature vector. Finally, the target feature vector is matched with the feature vector of each preset template to obtain a matching value with each preset template, and the matching value with each preset template is used as the matching value between the first image to be identified and each preset template, and the matching value between the second image to be identified and each preset template.

[0048] It can be seen that in this embodiment, the human body images are spliced ​​to obtain a complete human body image, and then the complete human body image is used for human body recognition, which can improve the accuracy of identity recognition.

[0049] It should be understood that for pedestrian A, if the identity recognition mode of a frame of image to be recognized is face recognition and does not contain the face of pedestrian A (for example, pedestrian A is blocked by a pedestrian in front, resulting in the face of pedestrian A not being captured), the matching value between the frame of image to be recognized and each preset template is taken as 0. Similarly, if the identity recognition mode of a frame of image to be recognized is human body recognition and no human body is captured (for example, pedestrian A's body is blocked by an obstacle), the matching value between the frame of image to be recognized and each preset template is also taken as 0.

[0050] 203: The scenic spot route planning device determines the number of people staying at the scenic spot A according to the identity information of the pedestrian A and the number of tourists leaving the scenic spot A.

[0051] For example, based on the identity information of pedestrian A, the identity information of each pedestrian entering the scenic spot A can be obtained; then, based on the identity information of each pedestrian at the scenic spot A and the number of tourists leaving the scenic spot A, the number of people staying at the scenic spot A can be determined. For example, based on the identity information of pedestrian A, the number of new people entering the scenic spot A whose identity information is tourists can be determined; then, based on the number of pedestrians entering the scenic spot A whose identity information is tourists and the number of tourists leaving the scenic spot A, the number of people staying at the scenic spot A, i.e., the number of people staying at the scenic spot at the current moment, can be determined. For example, the difference between the number of tourists entering and leaving can be determined, and combined with the number of people staying at the previous moment, the number of people staying at the scenic spot at the current moment can be determined.

[0052] It should be understood that the method of determining the number of tourists leaving scenic spot A is similar to the method of determining the number of tourists entering scenic spot A. That is, multiple image acquisition devices will also be set up at the exit of scenic spot A to identify the pedestrians leaving the exit, so as to obtain the identity information of each pedestrian leaving the exit, and determine the number of tourists leaving the exit of scenic spot A based on the identity information of each pedestrian leaving the exit.

[0053] 204: The scenic area route planning device plans routes for tourists entering the scenic area according to the number of visitors at each scenic spot in the scenic area.

[0054] Exemplarily, the visiting rules of each scenic spot in the scenic area are obtained (for example, how many people can visit at one time and how long a visit lasts), and based on the visiting rules of each scenic spot, the number of people who visit each scenic spot each time is determined; based on the number of people who visit each scenic spot each time and the number of people staying at each scenic spot, the number of visits to each scenic spot is determined; based on the number of visits to each scenic spot and the time required for a visit, the waiting time for each scenic spot is determined; based on the waiting time for each scenic spot, routes are planned for tourists entering the scenic area. For example, routes can be planned for tourists in ascending order of waiting time, that is, the attractions of the scenic spot are sorted in ascending order of waiting time, and the sorting result is used as the tourist's visiting route.

[0055] It can be seen that in the embodiment of the present application, multiple image acquisition devices are set up at each scenic spot in the scenic area, so that multiple frames of images to be identified of pedestrians entering the scenic spot can be captured from multiple angles, so that the characteristics of pedestrians at various angles can be obtained, and the identity of the pedestrians is authenticated according to the identity recognition mode corresponding to each frame of the image to be identified, which improves the comprehensiveness of the identity authentication and makes the identified identity information more accurate, thereby improving the statistical accuracy of the number of residents at each scenic spot, so that better travel routes can be planned for tourists and the user's travel experience can be improved.

[0056] In one embodiment of the present application, the personal preferences of tourists entering the scenic area can be first obtained, for example, by obtaining the tourist's access rights. Then, based on the tourist's personal preferences, at least one first attraction matching the tourist's personal preferences is selected from the scenic area. Finally, a route is planned for the tourist based on the waiting time of each of the at least one first attraction in ascending order. It can be seen that incorporating the tourist's personal preferences during route planning further improves the accuracy of route planning and enhances the tourist's travel experience.

[0057] See Figure 4 , Figure 4 A flow chart of another scenic route planning method provided in an embodiment of the present application. The method is applied to a scenic route planning device. Figure 2 The same contents as those in the embodiment shown are not described again here. The method of this embodiment includes the following steps:

[0058] 401: The scenic area route planning device collects multiple frames of images to be identified of pedestrian A through multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of scenic spot A and the capture angles are different. The scenic spot A is any scenic spot in the scenic area, and the pedestrian A is any pedestrian entering the scenic spot A. The multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified.

[0059] 402: The scenic route planning device determines an identity recognition pattern corresponding to each of the multiple frames of images to be recognized, and identifies pedestrian A based on the identity recognition pattern and each frame of images to be recognized, thereby obtaining pedestrian A's identity information.

[0060] 403: The scenic spot route planning device determines the number of people staying at the scenic spot A according to the identity information of the pedestrian A and the number of tourists leaving the scenic spot A.

[0061] 404: The scenic area route planning device determines the waiting time for each scenic spot according to the number of visitors at each scenic spot in the scenic area.

[0062] 405: The scenic area route planning device calculates the waiting time of each scenic spot and the current location of each tourist, and plans a route for each tourist.

[0063] For example, based on each tourist's current geographic location, the time it takes for the tourist to travel to each scenic spot is determined, and the absolute time difference between the time it takes to travel to each scenic spot and the waiting time at the scenic spot is determined, and the scenic spot with the smallest absolute time difference is used as the next scenic spot to be visited (the first scenic spot to be visited); then, the scenic spot to be visited at the next moment is used as the new geographic location of the tourist at the current moment, and then, the absolute time difference between the time it takes for the tourist to travel to other scenic spots and the waiting time at other scenic spots at the next moment is also determined, and the second scenic spot to be visited is selected based on the absolute time difference; and so on, until the last scenic spot to be visited is determined, and the tourist's travel route is obtained.

[0064] 406: The scenic area route planning device pushes the planned travel route for each tourist to each tourist.

[0065] It can be seen that in the embodiment of the present application, multiple image acquisition devices are set at each scenic spot in the scenic area, so that multiple frames of images to be identified of pedestrians entering the scenic spot can be captured from multiple angles, so that the characteristics of pedestrians at various angles can be obtained, and the identity of the pedestrians is authenticated according to the identity recognition mode corresponding to each frame of the image to be identified, which improves the comprehensiveness of the identity authentication and makes the identified identity information more accurate, thereby improving the statistical accuracy of the number of residents at each scenic spot; and, in the process of route planning, the current geographical location of the tourists is also combined, and a route with the shortest travel time is planned as much as possible, which can plan a better travel route for tourists and improve the user's travel experience.

[0066] See Figure 5 , Figure 5 The functional unit composition block diagram of a scenic route planning device provided in an embodiment of the present application. The scenic route planning device 500 includes: a collection unit 501 and a processing unit 502, wherein:

[0067] The acquisition unit 501 is configured to acquire multiple frames of images of a pedestrian A to be identified using multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of a scenic spot A and are captured at different angles. The scenic spot A is any scenic spot in the scenic area, and the pedestrian A is any pedestrian entering the scenic spot A. The multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified.

[0068] The processing unit 502 is configured to determine an identity recognition pattern corresponding to each frame of the plurality of frames of images to be recognized, and to perform identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized, thereby obtaining identity information of the pedestrian A.

[0069] Determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A;

[0070] According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

[0071] In some possible implementations, in determining the identity recognition mode corresponding to each frame of the multiple frames of images to be recognized, the processing unit 502 is specifically configured to:

[0072] Determining an image acquisition device corresponding to each frame of the image to be recognized in the plurality of frames of the image to be recognized;

[0073] Determining a capture direction of each frame of the image to be identified according to an image acquisition device corresponding to each frame of the image to be identified;

[0074] The identity recognition mode corresponding to each frame of the image to be recognized is determined according to the mapping relationship between the capture direction and the identity recognition mode and the capture direction of each frame of the image to be recognized.

[0075] In some possible implementations, in performing identity recognition on the pedestrian A according to the identity recognition mode and each frame of the image to be recognized to obtain the identity information of the pedestrian A, the processing unit 502 is specifically configured to:

[0076] Performing identity recognition on the pedestrian A according to the identity recognition mode corresponding to each frame of the image to be recognized and the image to be recognized, and obtaining a matching value between each frame of the image to be recognized and each preset template;

[0077] The identity information of the pedestrian A is obtained by combining the matching values ​​between each frame of the image to be identified and each preset template.

[0078] In some possible implementations, in performing identity recognition on pedestrian A based on the identity recognition pattern corresponding to each frame of the image to be recognized and each frame of the image to be recognized, and obtaining a matching value between each frame of the image to be recognized and each preset template, the processing unit 502 is specifically configured to:

[0079] When the identity recognition mode is the face recognition mode, face detection is performed on each frame of the image to be recognized to obtain a face region of the pedestrian A in each frame of the image to be recognized, and a matching value between each frame of the image to be recognized and each preset face template is determined based on the face image in the face region;

[0080] When the identity recognition mode is the human body recognition mode, human body detection is performed on each frame of the image to be identified to obtain the human body frame of the pedestrian A in each frame of the image to be identified, and based on the human body image in the human body frame, the matching value between each frame of the image to be identified and each human body preset template is determined.

[0081] In some possible implementations, in determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A, the processing unit 502 is specifically configured to:

[0082] Determining the number of pedestrians entering the scenic spot A whose identity information is tourists based on the identity information of the pedestrian A;

[0083] The number of people staying at the scenic spot A is determined based on the number of pedestrians whose identity information is tourists among the pedestrians entering the scenic spot A and the number of tourists leaving the scenic spot A.

[0084] In some possible implementations, in planning routes for tourists entering the scenic area based on the number of visitors to each scenic spot in the scenic area, the processing unit 502 is specifically configured to:

[0085] Obtain the rules for each scenic spot in the scenic area;

[0086] Determining the number of people who can visit each attraction at each time according to the visiting rules of each attraction;

[0087] Determining the number of visits to each scenic spot according to the number of visitors to each scenic spot each time and the number of residents at each scenic spot;

[0088] Determining the waiting time for each attraction based on the number of visits to each attraction and the time required for one visit;

[0089] According to the waiting time of each scenic spot, a route is planned for tourists entering the scenic spot.

[0090] In some possible implementations, in planning routes for tourists entering the scenic area based on the waiting time at each scenic spot, the processing unit 502 is specifically configured to:

[0091] Obtaining personal preferences of tourists entering the scenic area;

[0092] selecting at least one first scenic spot from the scenic area that matches the personal preference of the tourist;

[0093] Route planning is performed for tourists entering the scenic area according to the waiting time of each first scenic spot in the at least one first scenic spot in ascending order.

[0094] See Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes a transceiver 601, a processor 602, and a memory 603. These are connected via a bus 604. The memory 603 is used to store computer programs and data, and can transmit the data stored in the memory 603 to the processor 602.

[0095] The processor 602 is configured to read the computer program in the memory 603 and perform the following operations:

[0096] Controlling the transceiver 601 to capture multiple frames of images of pedestrian A to be identified through multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of scenic spot A and capture images at different angles, the scenic spot A is any scenic spot in the scenic area, the pedestrian A is any pedestrian entering the scenic spot A, and the multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified;

[0097] Determining an identity recognition pattern corresponding to each frame of the multiple frames of images to be recognized, and performing identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized to obtain identity information of the pedestrian A;

[0098] Determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A;

[0099] According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

[0100] In some possible implementations, in determining the identity recognition mode corresponding to each frame of the multiple frames of images to be recognized, the processor 602 is specifically configured to perform the following operations:

[0101] Determining an image acquisition device corresponding to each frame of the image to be recognized in the plurality of frames of the image to be recognized;

[0102] Determining a capture direction of each frame of the image to be identified according to an image acquisition device corresponding to each frame of the image to be identified;

[0103] The identity recognition mode corresponding to each frame of the image to be recognized is determined according to the mapping relationship between the capture direction and the identity recognition mode and the capture direction of each frame of the image to be recognized.

[0104] In some possible implementations, in terms of performing identity recognition on pedestrian A according to the identity recognition mode and each frame of the image to be recognized to obtain the identity information of pedestrian A, the processor 602 is specifically configured to perform the following operations:

[0105] Performing identity recognition on the pedestrian A according to the identity recognition mode corresponding to each frame of the image to be recognized and the image to be recognized, and obtaining a matching value between each frame of the image to be recognized and each preset template;

[0106] The identity information of the pedestrian A is obtained by combining the matching values ​​between each frame of the image to be identified and each preset template.

[0107] In some possible implementations, in terms of performing identity recognition on pedestrian A based on the identity recognition pattern corresponding to each frame of the image to be recognized and each frame of the image to be recognized, and obtaining a matching value between each frame of the image to be recognized and each preset template, the processor 602 is specifically configured to perform the following operations:

[0108] When the identity recognition mode is the face recognition mode, face detection is performed on each frame of the image to be recognized to obtain a face region of the pedestrian A in each frame of the image to be recognized, and a matching value between each frame of the image to be recognized and each preset face template is determined based on the face image in the face region;

[0109] When the identity recognition mode is the human body recognition mode, human body detection is performed on each frame of the image to be identified to obtain the human body frame of the pedestrian A in each frame of the image to be identified, and based on the human body image in the human body frame, the matching value between each frame of the image to be identified and each human body preset template is determined.

[0110] In some possible implementations, in determining the number of people staying at the scenic spot A based on the identity information of the pedestrian A and the number of tourists leaving the scenic spot A, the processor 602 is specifically configured to perform the following operations:

[0111] Determining the number of pedestrians entering the scenic spot A whose identity information is tourists based on the identity information of the pedestrian A;

[0112] The number of people staying at the scenic spot A is determined based on the number of pedestrians whose identity information is tourists among the pedestrians entering the scenic spot A and the number of tourists leaving the scenic spot A.

[0113] In some possible implementations, in planning routes for tourists entering the scenic area based on the number of visitors to each scenic spot in the scenic area, the processor 602 is specifically configured to perform the following operations:

[0114] Obtain the rules for each scenic spot in the scenic area;

[0115] Determining the number of people who can visit each attraction at each time according to the visiting rules of each attraction;

[0116] Determining the number of visits to each scenic spot according to the number of visitors to each scenic spot each time and the number of residents at each scenic spot;

[0117] Determining the waiting time for each attraction based on the number of visits to each attraction and the time required for one visit;

[0118] According to the waiting time of each scenic spot, a route is planned for tourists entering the scenic spot.

[0119] In some possible implementations, in planning routes for tourists entering the scenic area based on the waiting time at each scenic spot, the processor 602 is specifically configured to perform the following operations:

[0120] Obtaining personal preferences of tourists entering the scenic area;

[0121] selecting at least one first scenic spot from the scenic area that matches the personal preference of the tourist;

[0122] Route planning is performed for tourists entering the scenic area according to the waiting time of each first scenic spot in the at least one first scenic spot in ascending order.

[0123] Specifically, the transceiver 601 may be Figure 5 The acquisition unit 501 of the scenic route planning device 500 of the embodiment described above, the processor 602 may be Figure 5 The processing unit 502 of the scenic route planning device 500 of the embodiment.

[0124] It should be understood that the scenic area route planning device in this application may include a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a PDA, a laptop computer, a mobile Internet device MID (Mobile Internet Devices, abbreviated as: MID) or a wearable device, etc. The above-mentioned scenic area route planning device is only an example, not an exhaustive list, and includes but is not limited to the above-mentioned electronic devices. In actual applications, the above-mentioned scenic area route planning device may also include: an intelligent vehicle-mounted terminal, a computer device, etc.

[0125] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0126] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods described in the above method embodiments.

[0127] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0128] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0131] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0132] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0133] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0134] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A scenic area route planning method, characterized in that: include: Capturing multiple frames of images of pedestrian A to be identified by using multiple image acquisition devices, wherein the multiple image acquisition devices are set at the entrance of scenic spot A and are captured at different angles, the scenic spot A is any scenic spot in the scenic area, the pedestrian A is any pedestrian entering the scenic spot A, and the multiple image acquisition devices correspond one-to-one to the multiple frames of images to be identified; Determining an identity recognition pattern corresponding to each frame of the multiple frames of images to be recognized, and performing identity recognition on the pedestrian A based on the identity recognition pattern and each frame of the images to be recognized to obtain identity information of the pedestrian A, including: In the case where the identity recognition mode is a human body recognition mode, the multiple frames of images to be recognized include a first image to be recognized captured from the left side of the pedestrian A, and a second image to be recognized captured from the right side of the pedestrian A; human body detection is performed on the first image to be recognized to obtain a first human body frame and a first human body mask map, and human body detection is performed on the second image to be recognized to obtain a second human body frame and a second human body mask map; a first human body image is cut out from the first human body frame based on the first mask map, and a second human body image is cut out from the second human body frame based on the second mask map, and the first human body image and the second human body image are spliced ​​to obtain a target human body image; feature extraction is performed on the target human body image to obtain a target feature vector; the target feature vector is matched with the feature vector of each human body preset template to obtain a matching value with each human body preset template, and the matching value with each preset template is used as the matching value between the first image to be recognized and the second image to be recognized and each human body preset template; the identity information of the pedestrian A is determined by combining the matching values ​​between the first image to be recognized and the second image to be recognized and each human body preset template; Determine the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A; According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

2. The method according to claim 1, characterized in that The determining of the identity recognition mode corresponding to each frame of the image to be recognized in the plurality of frames of the image to be recognized includes: Determining an image acquisition device corresponding to each frame of the plurality of frames of images to be recognized; Determining a capture direction of each frame of the image to be identified according to an image acquisition device corresponding to each frame of the image to be identified; The identity recognition mode corresponding to each frame of the image to be recognized is determined according to the mapping relationship between the capture direction and the identity recognition mode and the capture direction of each frame of the image to be recognized.

3. The method according to claim 1 or 2, characterized in that The step of performing identity recognition on the pedestrian A according to the identity recognition mode and each frame of the image to be recognized to obtain the identity information of the pedestrian A includes: When the identity recognition mode is the face recognition mode, face detection is performed on each frame of the image to be recognized to obtain the face area of ​​the pedestrian A in each frame of the image to be recognized, and based on the face image in the face area, the matching value between each frame of the image to be recognized and each preset face template is determined. The identity information of the pedestrian A is determined by combining the matching values ​​between each frame of the image to be recognized and each preset face template.

4. The method according to claim 3, characterized in that The step of determining the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A includes: Determining the number of pedestrians entering the scenic spot A whose identity information is tourists based on the identity information of the pedestrian A; The number of people staying at the scenic spot A is determined based on the number of pedestrians whose identity information is tourists among the pedestrians entering the scenic spot A and the number of tourists leaving the scenic spot A.

5. The method according to claim 4, characterized in that The method of planning routes for tourists entering the scenic area according to the number of visitors to each scenic spot in the scenic area includes: Obtain the rules for each scenic spot in the scenic area; Determining the number of people who can visit each attraction at each time according to the visiting rules of each attraction; Determining the number of visits to each scenic spot according to the number of visitors to each scenic spot each time and the number of residents at each scenic spot; Determining the waiting time for each attraction based on the number of visits to each attraction and the time required for one visit; According to the waiting time of each scenic spot, a route is planned for tourists entering the scenic spot.

6. The method according to claim 5, characterized in that The route planning for tourists entering the scenic area according to the waiting time of each scenic spot includes: Obtaining personal preferences of tourists entering the scenic area; selecting at least one first scenic spot from the scenic area that matches the personal preference of the tourist; Route planning is performed for tourists entering the scenic area according to the waiting time of each first scenic spot in the at least one first scenic spot in ascending order.

7. A scenic area route planning device, characterized in that: include: a collection unit configured to collect multiple frames of images of pedestrian A to be identified using multiple image collection devices, wherein the multiple image collection devices are set at the entrance of scenic spot A and capture images at different angles, the scenic spot A is any scenic spot in the scenic area, and the pedestrian A is any pedestrian entering the scenic spot A, and the multiple image collection devices correspond one-to-one to the multiple frames of images to be identified; A processing unit, configured to determine an identity recognition pattern corresponding to each frame of the plurality of images to be recognized, and to perform identity recognition on pedestrian A based on the identity recognition pattern and each frame of the images to be recognized, to obtain identity information of pedestrian A, including: In the case where the identity recognition mode is a human body recognition mode, the multiple frames of images to be recognized include a first image to be recognized captured from the left side of the pedestrian A, and a second image to be recognized captured from the right side of the pedestrian A; human body detection is performed on the first image to be recognized to obtain a first human body frame and a first human body mask map, and human body detection is performed on the second image to be recognized to obtain a second human body frame and a second human body mask map; a first human body image is cut out from the first human body frame based on the first mask map, and a second human body image is cut out from the second human body frame based on the second mask map, and the first human body image and the second human body image are spliced ​​to obtain a target human body image; feature extraction is performed on the target human body image to obtain a target feature vector; the target feature vector is matched with the feature vector of each human body preset template to obtain a matching value with each human body preset template, and the matching value with each preset template is used as the matching value between the first image to be recognized and the second image to be recognized and each human body preset template; the identity information of the pedestrian A is determined by combining the matching values ​​between the first image to be recognized and the second image to be recognized and each human body preset template; Determine the number of visitors to the scenic spot A based on the identity information of the pedestrian A and the number of visitors leaving the scenic spot A; According to the number of visitors to each scenic spot in the scenic area, route planning is performed for tourists entering the scenic area.

8. An electronic device, characterized in that: include: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

Images