Facial orientation system for ride, ride system, method, and readable medium

Abstract

A facial orientation system of a ride includes one or more sensors and a controller. The controller receives, from the one or more sensors, ride vehicle data indicative of the presence and location of a ride vehicle on the ride; determining a ride vehicle orientation based on the ride vehicle data; receiving, from the one or more sensors, location data of the guest indicative of a location of the guest's body, face, or a combination thereof; determining a face orientation, a face rotation, or a combination thereof of the guest based on the ride vehicle orientation and location data; and transmitting data indicative of the determined facial orientation, facial rotation, or a combination thereof to a downstream controller for subsequent control based on the determined facial orientation, facial rotation, or a combination thereof.

Description

This application is a divisional application of a patent application with an application date of February 13, 2020, application number 202080014219.0, and invention name “Facial orientation system for rides, ride system, method and readable medium”. Technical Field

[0001] The present disclosure relates generally to the field of camera-based object detection. More specifically, embodiments of the present disclosure relate to systems and methods for identifying an object orientation using a camera. Background Art

[0002] In many cases, it may be useful to know the orientation of an object. Traditionally, wearable devices or other known features of an object have been used to help facilitate orientation detection of an object. However, the provision and utilization of wearable devices may be expensive and cumbersome. Furthermore, known features may vary from object to object and therefore may be difficult to detect and use as a reference.

[0003] For example, many amusement park-style rides include a ride vehicle that carries passengers along a ride path defined, for example, by a track. During the ride, the ride path may include multiple features, including tunnels, turns, rises, falls, loops, etc. The ride path may also include show scenery features, such as lighting effects, animated characters, or robotic characters, which may provide guests with supplemental content and / or enhance the immersive experience. However, due to the complexity of some amusement rides, it may be difficult to determine the guest's body and / or facial orientation within the ride (such as to activate or deactivate show scenery features along the ride path while the guest is viewing the features) without using wearable ride equipment for the guest. However, providing wearable ride equipment may be expensive and require additional time to implement, as opposed to amusement park-style rides that do not use such equipment. Summary of the invention

[0004] Certain embodiments that are commensurate in scope with the originally claimed subject matter are summarized below. These embodiments are not intended to limit the scope of the present disclosure, but rather these embodiments are intended only to provide a brief summary of certain disclosed embodiments. In fact, the present disclosure may encompass various forms that may be similar or different from the embodiments set forth below.

[0005] Embodiments described herein relate to systems that can track facial orientation and future facial rotation of guests on amusement park rides. As used herein, the term "facial orientation" refers to the position of a guest's head relative to a specific rotation angle. The term "facial rotation" refers to the actual movement or range of movement of the head to achieve a specific rotation angle. In some embodiments, the system can use the orientation of the ride cart on the ride in conjunction with skeletal tracking to determine facial orientation and rotation. In other embodiments, the system can use facial and / or body image detection to determine facial features along with facial orientation and rotation. In addition, machine learning can be used when determining facial orientation based on recurring determinations.

[0006] Although the following discussion focuses primarily on amusement park-style rides, this is not intended to limit the scope of the current invention. In fact, the current object orientation detection system can be used in many different applications that are completely different from amusement park-style rides.

[0007] In an embodiment, a facial orientation system for a ride comprises one or more sensors and a controller. The controller receives ride vehicle data indicating the presence and position of a ride vehicle on the ride from the one or more sensors, determines a ride vehicle orientation based on the ride vehicle data, receives location data of a guest indicating the position of the guest's body, face, or a combination thereof from the one or more sensors, determines a facial orientation, facial rotation, or a combination thereof of the guest based on the ride vehicle orientation and location data, and transmits data indicating the determined facial orientation, facial rotation, or a combination thereof to a downstream controller for subsequent control based on the determined facial orientation, facial rotation, or a combination thereof.

[0008] In an embodiment, a method includes receiving ride vehicle data from one or more sensors indicating the presence and position of a ride vehicle on a ride facility, determining a ride vehicle orientation based on the ride vehicle data, receiving position data of a guest from one or more sensors indicating the position of the guest's body, face, or a combination thereof, determining a facial orientation, facial rotation, or a combination thereof of the guest based on the ride vehicle orientation and position data, and transmitting data indicating the determined facial orientation, facial rotation, or a combination thereof to a downstream controller for subsequent control based on the determined facial orientation, facial rotation, or a combination thereof.

[0009] In an embodiment, a tangible, non-transitory machine-readable medium includes machine-readable instructions that, when executed by one or more processors of the machine, cause the machine to: receive ride vehicle data from one or more sensors indicating the presence and position of a ride vehicle on a ride facility, determine a ride vehicle orientation based on the ride vehicle data, receive position data of a guest from one or more sensors indicating the position of the guest's body, face, or a combination thereof, determine a facial orientation, facial rotation, or a combination thereof of the guest based on the ride vehicle orientation and position data, and transmit data indicating the determined facial orientation, facial rotation, or a combination thereof to a downstream controller for subsequent control based on the determined facial orientation, facial rotation, or a combination thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] These and other features, aspects and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, wherein like characters refer to like parts throughout.

[0011] Figure 1 is a block diagram of an amusement park ride including an attraction having a show scene along a ride path according to an embodiment of the present disclosure; Figure 2 is a schematic diagram of a facial orientation system including a show scene controller for controlling show scene features according to an embodiment; Figure 3 According to the embodiment Figure 2 A block diagram of a facial orientation system of the invention, the facial orientation system using skeletal tracking to determine facial orientation, which is subsequently used to control an animated character; and Figure 4 is a flow chart of a process for determining a guest's facial orientation according to an embodiment. DETAILED DESCRIPTION

[0012] One or more specific embodiments of the present disclosure will be described below. In order to provide a concise description of these embodiments, all features of the actual implementation may not be described in the specification. It should be understood that in the development of any such actual implementation, as in any engineering or design project, many implementation-specific decisions must be made to achieve the developer's specific goals, such as meeting system-related and business-related constraints, which may vary depending on the implementation. In addition, it should be understood that such development work may be complex and time-consuming, but it will still be a routine task of design, production and manufacturing for ordinary technicians who benefit from the present disclosure.

[0013] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that there are one or more elements. The terms "comprising," "including," and "having" are intended to be inclusive, and mean that there may be additional elements in addition to the listed elements. Additionally, it should be understood that reference to an "embodiment" or "embodiments" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the described features.

[0014] Amusement parks feature a wide variety of entertainment, such as amusement park rides, shows, and games. Different types of entertainment can include show scene features that enhance the guests' experience at the amusement park, such as themed scenes along a ride path. Show scene features can include effects, objects, or instruments along the ride path that are activated when guests view a particular show scene. For example, a robotic figure along the ride path can include elements or objects that change or activate based on the detected presence of vehicles and / or guests along the ride path. Show scene changes can include changes in animated machinery and changes in lighting, positioning of ride vehicles, etc.

[0015] Typical show scenery feature (e.g., lighting, animation) activations may be triggered by limited information about the attraction and / or guests viewing the show scenery objects along the ride path. For example, the trigger may be based on the location of the ride vehicle and / or the guest. Thus, show scenery features provided on the ride path may be turned on regardless of the guest location within the ride vehicle. This may result in a less personalized experience that is typically achieved for each loop of the attraction.

[0016] However, it may be desirable to provide more granular triggers that provide more customized scenic spot changes based on the specific features of scenic spot guests. Provided herein is a technique that facilitates determining the facial orientation and facial rotation of guests when they are on a ride without using a guest's facial or head device when the guest is on a ride. The determination of the facial orientation and rotation of the guest can be used to trigger or initialize a show scene feature. For example, a show scene feature, such as an animation or special effect, can be provided in response to the guest's face being oriented to be within the viewing range of a specific object or machinery on a ride path that provides a show scene feature. Typically, a ride moves along a ride path, wherein the guest's body or head moves and rotates to view the features along the ride path. In response to detecting an active ride on a ride, effects and animations can be triggered to initialize. However, providing accurate facial orientation and facial rotation of the guest at a specific location on the ride path (such as within the viewing range of an object or machinery that provides special effects or animations on a ride) may be complex.

[0017] It should be noted that while the examples provided herein may generally be presented in amusement park and ride attraction scenarios, such as using the present guest facial orientation determination technology to facilitate activation of features in a show scene on a ride path, the technology in the present disclosure may be applied to other non-amusement park related conditions and / or scenarios. Therefore, the present example should be understood as merely reflecting a real-world example of a facial orientation system on a ride facility in order to provide a useful context for discussion, and should not be considered to limit the applicability of the present method. Instead, the present method should be understood to be applicable to any situation in which the precise orientation of a moving (e.g., facially turned) person or object can be determined within an environment for commercial purposes, entertainment purposes, etc.

[0018] Considering the foregoing, Figure 1 1 is a block diagram of an amusement park ride 100 that may operate in conjunction with the disclosed facial orientation system according to the present embodiment. In particular, the amusement park ride 100 may include one or more ride vehicles 112 with or without guests, and show scene features along a ride path 108, the show scene features including animated figures 102, lighting effects 104, and displays 106. The show scene features may be activated to change based on the detected orientation of the ride vehicle 112 in conjunction with the facial orientation and / or head rotation of the ride guest.

[0019] As depicted, show scene features such as animated characters 102, lighting effects 104, and displays 106 may be controlled to react via a show scene controller 110. In an embodiment, the show scene controller 110 of the facial orientation system may be centralized and synchronized to at least one or more show scene features located throughout a ride path 108 of an amusement park ride 100 to control one or more show scene features. The show scene controller 110 receives situational positioning information (e.g., ride vehicle 112 position and guest body and / or head position data) via one or more sensors and / or processors located on or around the show scene features, ride vehicles 112, and / or ride path 108. Using this information, facial orientation may be determined by the facial orientation system, such as Figure 2 As described in detail in .

[0020] Once the facial orientation is determined, control signals may be sent to one or more systems that control show scene features to trigger one or more of the show scene features based on the facial orientation. Situational positioning information (e.g., sensory data indicating the position of the ride vehicle 112 on the ride track 116 and the guest body and / or head position) may also be sent to the monitoring system 111. The monitoring system 111 may be a management system that not only monitors show scene changes (such as animation or lighting control signals sent from the show scene controller 110 in response to the ride vehicle 112 orientation and facial orientation), but may also control or reconfigure the show scene controller 110. In this way, the monitoring system 111 may reset show scene feature changes or override animations and effects determined by the show scene controller 110. For example, if Figure 2 As discussed in detail in , the show scene controller 110 can automatically send an animation to the animated character 102 in response to a guest facing the animated character 102. Similarly, if the ride operator 122 finds any problems with the animated character 102 beyond those determined by the show scene controller 110, the ride operator 122 can manually stop the animation via a stop mechanism (e.g., a button) to override the animation. The monitoring system 111 can also be used to recalibrate sensors on or around the show scene. In addition, the monitoring system 111 can be used to reset the facial orientation determination algorithm of the show scene controller 110. In some embodiments, the monitoring system 111 and the show scene controller 110 can be implemented as a single controller.

[0021] As previously described, the show scene controller 110 of the facial orientation system can utilize a combination of sensor data received by sensors on or near show scene features, data from the ride car 112 and / or ride path 108 to detect the positioning of the body / head of the ride car 112 and the guest, and to further determine facial orientation, alignment, and / or estimate facial rotation. This determination can be used to correspondingly control the animations and effects generated throughout the show scene. Based on the orientation of the ride car 112, a 3D map of the guests on the ride facility can be generated. The 3D map generation can be based on the known ride track 116 position and orientation and known features within the ride facility 100 (e.g., the ride track 116 turns to the show scene feature at the midpoint on the ride facility 100). For example, the 3D map can generate the orientation of the ride car 112 based on the ride track 116 positioning. In addition, the guest position data within the 3D map can be based on the ride car 112 orientation and the known ride car 112 structure (e.g., when the ride car 112 moves along the ride path 108, the seats face forward). The 3D map can be used to reconstruct the 3D position of the guest and then accurately determine the facial orientation (particularly relative to known show scene features within the ride path 108). The 3D map can also determine the position where the head may be turning based on the determined facial orientation, such as turning to face the show scene features expected to be viewed by the guest. In addition, machine learning can be used to accurately predict the facial position based on the determination of the reproduction using sensor data. Machine learning can further be used to predict facial orientation based on the facial orientation of the guest learned during a specific point on the ride path 108 (e.g., a face that is generally positioned toward a specific show scene feature).

[0022] As shown, the ride vehicle 112 may be detected using a radio frequency identification (RFID) tag 118 incorporated into the ride vehicle 112 or a guest wearable device, a weight sensor 120 along the ride track 116, and / or an infrared (IR) tag 119 located on the ride vehicle 112. The RFID tag 118 may communicate with an electronic reader 123 incorporated at various locations on the ride facility 100, such as on the ride track 116, to indicate the presence of the tag. Thus, the electronic reader 123 placed on the ride path 108 may scan the RFID tag 118 on the ride vehicle 112 as the ride vehicle 112 passes by the electronic reader 123. In addition, the RFID tags 118 may be placed at specific areas of the ride vehicle 112 and / or may be different types of RFID tags 118. In this way, the RFID tag 118 placement and / or type may be used to determine the front and rear of the ride vehicle 112. This information may be used to more accurately predict the location of the guest within the ride vehicle 112, such that the face may be predicted to be facing toward the front of the ride vehicle 112. Similarly, IR tags 119 may also be placed on the ride vehicle 112. The IR tags 119 may include an IR reflective surface that may not be optically visible but may be detected by one or more cameras 114. The cameras 114 may be equipped to detect IR radiation reflected from the tags. In addition, RFID tags or IR tags may be periodically placed on the ride track 116 or ride path 108 at specific intervals or at specific points of interest on the track. The cameras 114, which may be used to detect the body and / or head position of the vehicle 112 and / or the guest, may be configured to activate after the ride vehicle 112 approaches the viewing range of a specific camera, thereby saving power. Similarly, tracking the ride vehicle 112 at specific points on the ride track 116 may be used to activate or deactivate show scene features along the ride path 108. As an example, the RFID tag 118 may indicate that the ride vehicle 112 is at the beginning of its journey, and thus the show scene features located toward the end of the journey may be turned off. When the ride vehicle 112 approaches a point of interest on the ride facility 100, such as a predetermined distance (e.g., 3 meters) from a particular show scene feature that can be determined using a proximity sensor 121 or based on a 3D map, the show scene controller 110 can correspondingly activate such a feature. Additionally or alternatively, an RFID tag 118 or IR marker 119 can be placed so that the position of the ride vehicle 112 on a track (e.g., a straight track or a curve) can be determined.

[0023] In addition, the guest wearable device may also include an RFID tag 118 or an IR marker 119, which may be used to indicate the presence of a guest in the ride vehicle 112 and further trigger a facial orientation determination. As an example, an electronic reader 123 for a guest wearable device may be placed on a seat of the ride vehicle 112 and indicate the presence of a guest when scanned. Additionally or alternatively, the IR marker 119 on the guest wearable device may be detected by a camera using the previously described techniques.

[0024] A weight sensor 120 may also be mounted on the ride track 116 to indicate the presence of a ride vehicle 112 on the ride track 116 based on exceeding a predetermined weight threshold. After determining the location of the ride vehicle 112 using the above-described techniques (e.g., RFID tags 118, IR tags 119) to generate a 3D map, the camera 114 may view an area of ​​interest, such as the location and / or orientation of the ride vehicle 112 within the ride path 108. Thus, capturing guest body and / or head position data may be limited to guests on the ride vehicle 112. Furthermore, since the seat locations of the ride vehicle 112 may be known to the ride facility operator 122, the camera 114 may be configured to narrow the viewing range to focus on a specific area around the seat. Thus, guest positioning may be determined by the ride vehicle 112 location and other sensor mechanisms as described herein to accurately determine facial orientation. Furthermore, facial orientation may be used to determine viewing direction within the ride path 108.

[0025] As shown, a camera 114 or an array of cameras 114 may be installed along the ride path 108 and throughout the amusement park ride 100 to determine the body and / or head orientation of one or more guests. Although an array of cameras 114 is shown and discussed herein to detect guest orientation, a single camera 114 may be used. Furthermore, in some embodiments, a single camera 114 may be used to determine the location and orientation of the ride vehicle 112 for generating a 3D map in addition to or in lieu of the previously described techniques.

[0026] The camera 114 may be disposed at a predetermined distance from a show scene feature, such as from the animated image 102, lighting effects 104, and display 106. Depending on the show scene feature, the predetermined distance may be a distance that may allow for capturing at least the upper half of a guest's head and body, such as to allow for accurate determination of head orientation (e.g., front of head facing toward show scene feature, back of head). For example, the camera 114 may view a 3-meter perimeter around the animated image 102. In this manner, any guest on the ride vehicle 112 near the animated image 102 may be easily detected. Additionally or alternatively, the camera 114 may be integrated into a show scene feature, such as into the body of the animated image 102. The integration may be positioned to allow a clear view of one or more guests to be perceived, whether the guest is positioned in front of the animated image 102 or has passed by the animated image 102 while in the ride vehicle 112. For example, integrating the camera 114 into the eyes of the animated image 102 may allow for detection of guests in front of it. Additionally or alternatively, depending on the expected effect on the guests, the predetermined distance may not be uniform for all show scene features. As an example, the lighting effects 104 along the ride path 108 can be activated before the ride car 112 and / or the guests are positioned in front of it. Therefore, one or more cameras 114 can determine the presence of guests at a distance farther than the animated image 102. In addition, the camera 114 can be positioned in a manner that allows the exclusion of views that may not include interested guests. For example, and as depicted, the ride operator 122 can operate the ride so that guests waiting for the ride 100 in the queue 107 are signaled to enter the ride car 112. Since the ride operator 122 and the guests in the queue 107 are not on the ride 100 or in the ride car 112, their facial orientation relative to the show scene may not be of interest and are therefore excluded from the camera 114 viewing range.

[0027] The camera 114 can also be used to capture data used as input to one or more processes of the facial orientation system as provided herein. In one example, the camera 114 data can be used by the show scene controller 110 to detect the human body. That is, in addition to or in lieu of generating a 3D map of the ride car 112, the presence of the captured image can be used to determine the presence and location of any guest on the ride car 112, and further determine the facial orientation. Skeletal tracking is used at least in part to further determine the guest body and / or facial position on the ride car 112. Skeletal tracking can include using a real-time image or captured image of the guest on the ride car 112 by the camera 114, and comparing the image with the recognized skeletal model to indicate human skeletal detection. For example, the skeletal model can include the relative positioning of the necessary joints, bones, and limbs of the human skeleton. Joints that are closer together on the skeletal model can indicate that the body and / or face are turned in a specific direction. In addition, the skeletal model can be used to predict the future orientation of the guest's face based on the current facial and body position. For example, if the skeletal model indicates that the facial orientation is facing forward based on the body and facial joint positioning (e.g., the shoulder joints are closer together toward the right end of the skeletal body), but the body is slightly turned to the right, then the facial orientation can be predicted to be turned to the right as well. In addition, the ride car 112 data indicating the specific performance scene features at the points along the ride path 108 can be used in conjunction with skeletal tracking to make future facial rotation predictions (e.g., the face is likely to turn toward the known performance scene features). Therefore, comparing the captured guest images and skeletal models can be used for guest detection and body / facial orientation. In some embodiments, the range of facial rotation can be limited based on the ride car 112 orientation and / or body orientation. For example, a typical guest can rotate their head to a maximum head rotation (e.g., 90 degrees) in either direction relative to a known base orientation. Assuming that the user is facing forward in the ride car 112, the ride car 112 orientation can be used as a known base orientation to limit the range of facial rotation. Additionally or alternatively, if the guest's body orientation is known, this can also be used as a known base orientation to limit the range of facial orientation. As an example, when the ride vehicle 112 orientation is used as the known base orientation and the ride vehicle 112 orientation is 45 degrees, the range of the guest's facial rotation can be defined as the known base orientation plus or minus the maximum head rotation. Here, the range of the guest's facial rotation would be 45 degrees plus or minus 90 degrees, resulting in a range of -45 to 135 degrees. Similar calculations can be performed using the guest's body orientation as the known base orientation.

[0028] In some embodiments, the fast speed ride 100 may use less granular analysis of facial orientation and may use skeletal tracking and ride car 112 data to determine facial orientation. As an example, ride car 112 orientation determination using previously described techniques (e.g., known front and back of ride car 112, ride path 108, ride track 116, and show scenery features 110 on ride path 108) may indicate a possible body position of a guest based on ride car 112 orientation and any show scenery features along ride path 108 that the guest may view. Thus, ride car 112 data may indicate a general position of the guest within ride car 112 and relative position to show scenery features that may be located along ride path 108. In addition, a skeletal model from skeletal tracking may further provide an accurate body and facial orientation of the guest. Positioning of joints closer together toward one end of the skeletal model may indicate that the guest is turning in the same direction as a show scenery feature along ride path 108. Thus, ride car 112 data in conjunction with skeletal tracking may be used for facial orientation determination.

[0029] On the other hand, a slower speed ride 100 may use a relatively more granular analysis of facial orientation, such as to include facial feature analysis. However, the skeletal image provided by skeletal tracking may not indicate precise facial features. Therefore, the skeletal image data may be further processed to identify a face using facial recognition and / or to identify a body shape using body recognition.

[0030] In some embodiments, such as for slower speed rides 100, facial image detection may consider multiple facial features as a whole to determine that a face has been accurately detected. The features considered may be points of interest on the face and their intersections (e.g., two eyes aligned along a horizontal line are adjacent to a nose along a vertical line, and the nose is detected at or near a point between each eye). In addition, the camera 114 may be used for full body detection or upper body detection, depending on the camera 114 viewing range, so that body features may be used to accurately identify the guest orientation (e.g., the guest is facing forward). For example, the body detection feature may consider body features and their intersections, such as the face, arms, and legs. Body detection may also indicate the orientation of the guest's body and predict the guest's facial orientation and / or future facial orientation. As an example, if the guest's face is detected to be facing forward, and the body is detected to be slightly turned to the right, it may be predicted that the facial orientation is also turned to the right. Additionally or alternatively, ride vehicle 112 data indicating the ride vehicle 112 position on the ride path 108 and the relative position to the show scene features may be used in conjunction with body and / or facial image detection to predict the future orientation of facial rotation. In addition, the camera 114 can be used for thermal recognition to detect body heat, which can be used to further accurately predict the presence and orientation of the guest. In addition, the camera 114 can also include infrared (IR) capabilities so that the camera can provide night vision, thereby detecting guests during both day and night. The IR capability can also be used with the IR tag 119 to detect the ride vehicle 112, as discussed above.

[0031] Some of the different types of sensors, such as RFID tags 118, IR tags 119, and / or camera 114 inputs for detecting ride vehicles 112 positioned within the ride facility 100 to generate a 3D map, may be used in conjunction with additional camera 114 inputs for determining the body and / or face of a guest, such as through skeletal tracking. Thus, based on the detection of the current ride vehicle 112 at a particular location within the ride facility 100, the camera 114 may be initialized for skeletal tracking, body detection, and / or facial detection to determine facial orientation. In some embodiments, after determining the facial orientation of the guest, a show scene feature may be initialized to provide entertainment to guests facing the feature within a predetermined range. That is, if the sensing distance is less than a threshold and / or if the guest is within the assumed field of view of the show scene feature and the guest is determined to be facing the feature, an animation or effect may be triggered.

[0032] As previously described, after determining the location of the ride vehicle 112 in conjunction with the guest's body and / or head positioning used to determine the guest's facial orientation (e.g., the face is rotated to the right relative to the body), the algorithm of the facial orientation system can be modified based on machine learning. Specifically, the facial orientation determination algorithm can change in response to ongoing or periodic determinations. As an example, if the guest's facial orientation is determined to be positioned toward a show scene feature at a specific point on the ride path 108, the show scene controller 110 can learn via machine learning to predict the facial orientation at the same location. Similarly, if the facial orientation is determined to be facing forward at a specific point on the ride path 108, the show scene controller 110 can use machine learning to make similar predictions. In addition, machine learning can be used to predict facial rotation when the face is determined to be rotated at a specific point on the ride path 108. Therefore, machine learning can be used to identify patterns of facial orientation and future rotations for accurate facial orientation determination and prediction by the show scene controller 110. According to certain aspects discussed herein, machine learning methods that can be used to make predictions related to facial detection and orientation (such as expected rotation of a face) can be further used to adapt the performance scene animation or effects performed. Based on facial orientation determination using a detection mechanism (e.g., IR tags 119 for detecting ride vehicles 112, skeletal tracking and / or facial recognition for detecting faces), machine learning can update or modify facial orientation algorithms based on updated data, by performing detection and configuration changes, or by other suitable methods.

[0033] As previously mentioned, a combination of detected sensor data indicating the orientation of the ride vehicle 112 and / or the location of the guest within the 3D map of the ride facility 100 may be sent to the show scene controller 110 of the facial orientation system. The facial orientation system may then use the sensor data to determine the facial orientation and subsequently determine any changes to the show scene features. To illustrate, Figure 2A block diagram of a facial orientation system 150 having a show scene controller 110 for controlling show scene features 160 is shown, which may include a display 106, lighting effects 104, and animated characters 102. The show scene controller 110 (e.g., an electronic controller) may include a memory 156, a processor 154, a communication circuit 158, and an input device 152. In some embodiments, the memory 156 is configured to store instructions, data, and / or information, such as a database of images, animations, or effects for show scene features. Additionally or alternatively, the memory 156 may include a user-defined algorithm for generating a 3D map of a ride vehicle within a ride facility and an algorithm for determining facial orientation. It should be noted that although the examples provided herein may explicitly depict and describe show scene features as being limited to the display 106, lighting effects 104, and / or animated characters 102, the disclosed methods may include using facial orientation to control other show scene features or effects on the ride path 108, such as changing the ride track 116 path, character spraying water, etc.

[0034] As discussed in more detail below, in some embodiments, the processor 154 is configured to receive input signals from the input device 152 related to detecting the position of the ride vehicle 112 and / or the orientation of the guest from one or more sensors previously described, which can then be used to determine the facial orientation using the techniques described herein. Subsequently, images, effects, or animations from the database can be provided based on the determined facial orientation and the guest position within the ride facility according to the position of the ride vehicle 112. In this way, when the guest is within a predetermined range of a particular show scene feature and / or when the guest's face is determined to be oriented toward a particular show scene feature, the show scene controller 110 can determine the facial orientation and further control the show scene feature accordingly. As previously described, sensor data can be provided to the input device 152 by (one or more) cameras 114, (one or more) weight sensors 120, IR tags 119, RFID tags 118, and / or (one or more) proximity sensors 121. It should be understood that the illustrated system is intended to be exemplary only, and that certain features and components may be omitted and various other features and components may be added to facilitate the performance according to the disclosed embodiments.

[0035] Based on the sensor data received to the input device 152, the show scene controller 110 can use the processor 154 to facilitate the control of the show scene features 160 to select images to be displayed, animations to be implemented, and special effects that can be stored in a database in the memory 156. The database may include, for example, a list of available images (such as images related to the theme of the ride). As an example, Figure 1The ride 100 depicts a circus theme, and thus, when the guest faces the display 106, a circus image can be displayed on the display 106. The database can also include animations to be performed by the animated character 102 (e.g., a clown). Continuing with the circus theme example, the animations can include, but are not limited to, acrobatics, laughing and waving, greeting, etc. In addition, the lighting effects 104 options can include colored lighting, strobe lighting, shadow lighting, and / or lighting for creating circus-related images displayed throughout the ride path 108 (e.g., the tunnel walls on the ride path 108).

[0036] In the depicted embodiment, the processor 154 of the show scene controller 110 can execute instructions stored in the memory 156 to perform operations such as generating a 3D map, determining a facial orientation based on sensor data received at the input device 152, and selecting or changing a show scene feature 160 (e.g., causing the animated character 102 to juggle when the detected face is oriented toward the animated character 102). Thus, in some embodiments, the processor 154 can be one or more general-purpose microprocessors, one or more application-specific processors (ASICs), one or more field programmable logic arrays (FPGAs), or any combination thereof. Additionally, the memory 156 can be a tangible, non-transitory computer-readable medium that stores instructions executable by the processor 154 and sensor data to be processed by the processor 154. Thus, in some embodiments, the memory 156 can include a random access memory (RAM), a read-only memory (ROM), a rewritable non-volatile memory, a flash memory, a hard drive, an optical disk, etc.

[0037] In addition, the show scene controller 110 can enable the communication circuit 158 ​​to interface with various other electronic devices (such as the monitoring system 111). The monitoring system 111 can use the generated 3D map and / or facial orientation determination for further analysis (e.g., to update the 3D map algorithm). Additionally or alternatively, the show scene controller can enable the communication circuit 158 ​​to interface with components of the show scene feature 160. For example, the communication circuit 158 ​​can allow the show scene controller 110 to be communicatively coupled to a network, such as a personal area network (PAN), a local area network (LAN), and / or a wide area network (WAN). Therefore, in some embodiments, the show scene controller 110 can process data from the input device 152, determine the facial orientation and position of the guest within the 3D map, determine the changes to be implemented (e.g., animation or effect), and transmit the changes to the show scene feature 160 via the communication circuit 158. For example, after processing the sensor data input from the input device 152, the processor 154 can determine a control signal that enables the communication circuit 158 ​​to wirelessly transmit the control data to the performance scene feature 160 to enable the activation of the change. In other embodiments, the communication circuit 158 ​​can be connected to the performance scene feature 160 via a wired connection.

[0038] In some embodiments, once the control signal is sent from the show scene controller 110 to the show scene feature 160, the show scene feature 160 may perform corresponding changes, such as animations implemented by the animated image 102, images to be displayed on the display 106, or visual effects produced using the lighting effect 104. Additionally, although not explicitly shown, the components for implementing changes to the display 106, lighting effects 104, and / or animated image 102 may include corresponding processors, corresponding memories, corresponding communication devices, and one or more actuators.

[0039] Figure 32 is a block diagram 200 of an embodiment using a facial orientation system 150 for detecting facial orientation using skeletal tracking and facial recognition, which is then used to control an animated avatar 102, in accordance with aspects of the present disclosure. The depicted embodiment may include an animated avatar 102 that changes or interacts with a guest when the guest is facing or looking at the animated avatar 102. As shown, a camera 114 is positioned to view both the ride vehicle 112 and guests that may be within a certain range or distance 202 of the animated avatar 102 in the show scene (e.g., as estimated by a proximity sensor 121 or a 3D map), which may trigger animation of the animated avatar 102 when the guest faces the animated avatar 102. Sensory data 203 provided by the camera 114 and / or sensors (such as the depicted RFID tag 118) may be transmitted to the show scene controller 110. Based on an RFID read by the electronic reader 123, one or more cameras 114 may be initialized or turned on to detect the orientation of the ride vehicle 112 and the facial orientation. As previously discussed, an array of ride vehicle 112 presence sensors (e.g., RFID tags 118) strategically placed throughout the ride 100 may be used to activate the cameras 114 sequentially or at specific tracking points along the ride 100 in order to conserve power.

[0040] In this embodiment, the sensory data 203 may be sent to the show scene controller 110 to indicate that the RFID tag 118 associated with the ride vehicle 112 passed by the electronic reader 123, which may indicate the expected position of the ride vehicle 112 on the ride track 116. The determination may indicate the position of the ride vehicle 112 on the ride track 116, such as the ride vehicle 112 is positioned slightly to the left based on the known ride track 116 layout. The determination may be based on a plurality of electronic readers 123, which are placed throughout the ride track 116, such that each electronic reader 123 indicates a corresponding point on the ride track 116. As an example, a particular electronic reader 123 may indicate the midpoint on the ride track 116, and the midpoint may include a ride track 116 that turns, indicating that the ride vehicle 112 on the turning track 116 may also be turning. In addition, the positioning of the ride vehicle 112 within the ride facility 100 and the ride track 116 may indicate a current or expected position next to a show scene feature 160 (such as an animated character 102). The positioning of the ride vehicle 112 can provide context for determining the direction the guest is likely facing. For example, the ride vehicle 112 is facing forward or in line with the ride direction, and therefore, the guest is likely facing forward. Additionally or alternatively, the ride vehicle 112 position can be determined by generating a 3D map using images captured by the camera 114 and / or a known layout of the ride facility 100 (e.g., the ride path 108, the ride track 116, the show scenery features 160, etc.).

[0041] Once the ride vehicle 112 positioning has been determined and the camera 114 is activated, the camera 114 can focus on the view of the ride vehicle 112 to detect the guest body and / or head position and determine their facial orientation. Using different recognition technologies, such as but not limited to skeletal tracking and / or facial recognition, as previously discussed, the show scene controller can determine facial orientation. As depicted, multiple guests can be in the ride vehicle 112, and the camera 114 can observe each guest simultaneously or individually. Therefore, the show scene controller 110 can use skeletal tracking for detecting skeletal body features (such as skeletal head and / or body) to detect and track the presence of multiple guests. In some embodiments, the skeletal reading 204 sent to the show scene controller 110 can then trigger facial detection. Facial recognition technology can use skeletal tracking readings to focus on skeletal images and find arms, chests, eyes, noses, etc. to generate facial images 206. In this way, the show scene controller can use the ride vehicle 112 orientation in the ride facility 100 in combination with the body / facial orientation technology described previously to determine and generate facial orientation images 208. Additionally or alternatively, facial orientation image 208 may include additional images indicating predicted facial rotation or positioning. Further, show scene controller 110 may use machine learning to update its facial orientation detection determinations and predictions for guests at specific locations within ride 100 based on reproduced body and facial positions and their resulting facial orientation determinations.

[0042] In addition, the facial orientation determination of one or more guests in the ride vehicle 112 can be used to initialize or change the performance scene features 160, such as the animated image 102 and lighting effects 104 in the depicted embodiment. As shown, the first guest 210 and the second guest 212 can be positioned closest to the animated image 102. Based on the predefined settings of the performance scene controller 110 (e.g., the settings defined by the designer or operator), the animated image 102 can be instructed to react to guests within a specific distance 202 (e.g., 3 meters) and facing its direction. Here, although the faces of both the first guest 210 and the second guest 212 are turned to face the animated image 102, the first guest is within the specific distance 202 for the animated image 102 to interact with the first guest 210, while the second guest 212 is out of range. Specifically, the first guest 210 is in a distance 203A of 3 meters from the animated image 102, which is within the specific distance 202 of 3 meters. However, the second guest 212 is in a 26-meter distance 203B from the animated character 102 and is therefore not within the specific distance 202. In addition, the third guest 214 is in a 2-meter distance 203C, which is within the 3-meter specific distance 202 from the lighting effect 104 surrounding the circus tent feature. Although the third guest 214 is within the specific distance 202, the guest's face is determined to be oriented to the left and away from the lighting effect 104. Therefore, the show scene feature can be triggered in response to the guest being determined to be within the specific distance 202 and facing the show scene feature. In the case of using the facial orientation technology described herein, the show scene features such as the lighting effect 104 can save power and continue to be powered off in response to no guests being determined to be facing the show scene feature within the specific distance 202.

[0043] In addition, in some cases, there may be an empty ride car (e.g., no guests in the ride car) or a ride car with less than the maximum number of guests. As described in the current embodiment, as the car continues to move forward within the ride facility 100, an empty subsequent ride car 218 follows the ride car 112. The subsequent car 218 may also include an RFID tag 118, which may be used to indicate the presence of the subsequent ride car 218. In some embodiments, the detection of the subsequent ride car 218 may cause the camera 114 to generate a 3D map of the ride car 112 and further initialize skeletal tracking. However, skeletal tracking will generate a result indicating that no human skeleton is detected. Since no guests are detected, show scene features such as animated characters 102 and lighting effects 104 can remain powered off, thereby saving power.

[0044] Figure 4 Is used for Figure 2 and 310 is a process flow diagram of a method 250 for generating facial orientation determination by a show scene controller 110 of a facial orientation system 150. It should be noted that the method 250 can be performed by a system (such as a facial orientation system 150 including a show scene controller 110 and / or a show scene feature 160) as an automated process. Although shown in a particular order, it should be noted that the operations described with respect to the method 250 can be performed in an order different from that shown and described, and indeed, such an arrangement of the method 250 is covered by the present disclosure. In addition, certain steps or portions of the method 250 can be omitted, and other steps can be added. The method 250 can be performed in response to a guest on the ride facility.

[0045] In some embodiments, the show scene controller may receive an indication that the ride vehicle 112 is present at a location of interest (block 252). The location of interest may be a specific range in front of, behind, or near a show scene feature 160, such as an animated character 102. Additionally or alternatively, the location may be based on the ride path 108 data. Figure 2 The memory 156 of the ride path 108 may store ride path 108 data including information about the position of the ride vehicle 112 along the ride path 108 as a function of time and / or other factors, which may be used to determine whether the ride vehicle 112 is present at a location of interest. In an embodiment, an electronic reader 123 associated with the ride vehicle 112 may be scanned as the ride vehicle 112 traverses the ride path 108. RFID signals observed along the ride path 108 may provide an indication of the location of the ride vehicle 112. Further, in some embodiments, the amount of time that has passed and / or other factors may be used to identify the location of the ride vehicle 112, enabling the show scene controller 110 to determine when the ride vehicle 112 has arrived at a location of interest. In some embodiments, sensor data input (e.g., via a camera 114, a weight sensor 120, an IR tag 119, and / or an RFID tag 118) and the like may be used to identify the location of the ride vehicle 112, and therefore identify whether the ride vehicle 112 is at a location of interest.

[0046] In addition, the show scene controller 110 can use the sensor data input to determine (block 254) the location of the ride vehicle 112 within the ride facility 100 (e.g., the ride path 108 or the ride track 116) by generating a 3D map of the location of the ride vehicle 112 using the previously described techniques. As previously described, the 3D map generation can be based on the known ride track 116 location and orientation and known features within the ride facility 100 (e.g., the ride track 116 turns toward a show scene feature at a midpoint on the ride facility). For example, the 3D map can generate the orientation of the ride vehicle 112 based on the ride track 116 positioning, such as the angle of a turn or bank. In addition, the guest position data within the 3D map can be based on the ride vehicle 112 orientation and the known ride vehicle 112 (e.g., the seats face forward as the ride vehicle 112 moves along the ride path 108). Therefore, the ride vehicle 112 location can also indicate the guest location within the ride facility 100.

[0047] After receiving an indication that the ride vehicle 112 is positioned in the area of ​​interest and determining the location of the ride vehicle 112, the show scene controller 110 may initialize (block 256) sensors to detect one or more guests in the ride vehicle 112. For example, the show scene controller 110 may output one or more signals to activate the camera 114 for skeletal tracking, facial recognition, and / or body recognition to begin detecting the facial location of the guest in the ride vehicle 112. For example, the presence of a guest may be detected by a discernible pattern (e.g., a continuous solid color or design) on the back of a seat of the ride vehicle 112 in an image captured by the camera 114. In response to a guest in the seat, the pattern may not be visible (e.g., a continuous solid color or design interrupted by a guest covering a portion of the pattern), thereby indicating the presence of a guest. On the other hand, when the seat is visible and the pattern is detectable, then the show scene controller 110 may determine that the guest is not present in the ride vehicle 112. This indicates that no one is present in the seat. Additionally, skeletal tracking can be used to determine the guest's presence, such that when the intersections of the necessary joints, bones, and limbs of the human skeleton are determined, the guest may be present in the ride vehicle 112. On the other hand, if skeletal tracking does not determine the intersections of the skeletal joints, the guest may not be present.

[0048] The show scene controller 110 may determine (decision box 258) whether the input received from the camera 114 indicates the presence of a guest in the ride car 112 within the viewing range. In addition to the presence of a guest determined using the camera 114 for pattern recognition or skeleton recognition on the seat, when the guest sits in the ride car 112, an RFID tag 118 in the guest's wearable item may be scanned to indicate the guest's presence.

[0049] If the show scene controller 110 receives an indication that a guest is vacant (e.g., when performing skeletal recognition, the camera 114 captures an image of an empty car), then no further facial orientation detection is required, at least for the particular seat in the ride car. Therefore, the show scene controller 110 may cause (block 260) the guest detection sensor to stop detecting and / or stop processing guests in the portion of the ride car 112 that is indicated to be vacant.

[0050] However, if the signal indicates that the guest is present in a ride car 112 seat, the show scene controller 110 may continue to perform skeletal tracking identification or tracking to detect (box 262) the guest's body and / or head. For example, skeletal tracking may take into account the relative positioning of the necessary joints, bones, and limbs of the human skeleton to generate a skeletal model. As previously described, joints that are closer together on the skeletal model may indicate that the body and / or head are turned in a particular direction. In addition, ride car 112 data that may take into account specific points on the ride track 116 and show scene features along the ride path 108 may be used in conjunction with skeletal tracking to determine facial orientation and make future facial rotation predictions.

[0051] In addition to or in lieu of skeletal tracking for generating a skeletal image of a guest, facial and / or body recognition (as indicated by dashed lines) may optionally be performed to detect (box 264) facial features of guests of a ride facility such as for a more granular analysis using facial orientation. As previously described, facial recognition may include consideration of points of interest on the face and their intersections (e.g., two eyes aligned along a horizontal line are adjacent to a nose along a vertical line, with the nose detected at or near a point between each eye). Similarly, body detection may consider body features and their intersections, such as a face, arms and legs, or an upper body. Both facial and body recognition may allow for more accurate facial features and / or body determination, which may be used for facial orientation and future rotation determination. As an example, a slow-speed standing ride facility in which a guest stands in a ride vehicle 112 may utilize both body and facial recognition techniques.

[0052] For example, in some embodiments, a skeletal image algorithm can indicate the body orientation of a guest within the ride vehicle 112 by observing the relative proximity of skeletal joints. This information can provide an indication of the likely body and, therefore, facial orientation. As an example, knee joints that are close together and turned toward a particular side of the ride vehicle 112 (e.g., the left side) can indicate that the guest's body and head are turned in that orientation (e.g., to the left).

[0053] Similarly, facial recognition algorithms can indicate the orientation of a face based on the proximity of detected facial features. For example, when a facial feature (e.g., an eye) is detected toward one side of the face, this can indicate that the face is turned in the direction corresponding to that side of the face (e.g., detecting an eye toward the left side of the face can indicate that the guest is facing left).

[0054] The show scene controller 110 may determine (block 266) the guest's facial orientation by using both skeletal tracking and facial and / or body recognition in conjunction with the previously determined presence and location of the ride vehicle 112 within the ride facility 100. Specifically, the ride vehicle orientation is used as a baseline orientation of the guest's body, which may then be combined with the skeletal and / or facial and body data to find the precise orientation of the face.

[0055] Additionally, in some embodiments, machine learning may be used to determine (block 267) how the face may be turning based on reoccurring facial orientation determinations made for the guest at a particular location within the ride 100. As an example, if the guest's facial orientation is determined to be positioned to the left (e.g., toward a show scene feature) at a particular point on the ride path 108, the show scene controller 110 may learn via machine learning to predict the facial orientation as the same orientation for that location on the ride path 108. Additionally, the facial orientation algorithm of the show scene controller 110 may be updated using machine learning for previously determined skeletal tracking and facial and / or body recognition data and a confirmation indication of the guest's actual facial orientation associated with the previously determined skeletal tracking and facial and / or body recognition data. The facial orientation algorithm may be updated to predict or determine a more accurate facial orientation, as well as where the facial orientation may be turning given the guest's positioning within the ride 100.

[0056] Next, the facial orientation determination may be used to control show scene features 160 along the ride path 108. The show scene controller 110 may determine whether the guest's facial orientation is within a certain distance from the show scene feature 160 (decision block 268). In other words, the show scene controller 110 may determine that the guest's facial orientation is within a certain distance from the show scene feature when the guest's face is not only within the certain distance of the show scene feature but also when the guest's face is determined to be oriented within the viewing range of the show scene feature.

[0057] If the facial orientation is within a certain distance (e.g., within a 3-meter perimeter from the animated avatar 102) and the user's facial orientation is within the viewing range of the show scene feature, the show scene feature can be activated (block 270) or updated to reflect the change, as previously described. As an example, the guest's facial orientation can be facing the animated avatar 102 within a certain range of the guest, and the show scene controller 110 can send an animation control signal to the animated avatar 102. The animation control signal can be processed by the processor of the animated avatar 102 and cause the animated avatar 102 to change, such as by using an actuator to smile or wave, as described above.

[0058] However, if the guest's face is not oriented within a certain distance of the show scene feature 160 or is not oriented within the viewing range of the show scene feature 160, the show scene feature is not activated. This provides a more personalized experience, which can reduce power usage and / or wear on the show scene feature.

[0059] In some cases, after initially detecting that the guest's orientation is not within a predetermined distance of a show scene feature, the guest may be oriented toward the show scene feature. Thus, an additional orientation determination may be performed. In this case, as the ride vehicle 112 moves along the ride path 108, the show scene controller 110 may determine (decision block 272) whether the ride vehicle 112 is still present at the location of interest. Continuing with the animated character 102 example, if the animated character 102 is no longer within a specific distance 202 from the guest facing the animated character 102, the show scene controller 110 may cause (block 260) the sensor (e.g., camera 114) to stop detecting the guest on the ride vehicle 112.

[0060] However, if the ride vehicle 112 continues to be positioned at the point of interest, the show scene controller 110 may receive (box 252) an indication that the ride vehicle 112 is present at the point of interest and take subsequent steps of determining the location of the ride vehicle 112, initializing sensors to detect guests on the ride vehicle 112, etc.

[0061] As can be appreciated, current techniques involving facial orientation detection based on contextual data associated with the ride and / or the guest's body can provide significant benefits. For example, less granular analysis of facial orientation can provide increased efficiency in orientation processing, which can be particularly useful in high-speed amusement rides. Additionally, triggering show scene features based on detected facial orientation can provide increased power utilization efficiency, can reduce wear on show scene features, and / or can provide a more personalized ride experience.

[0062] Although only certain features of the present disclosure have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. Therefore, it is to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the present disclosure. It should be understood that any features illustrated or described with respect to the drawings discussed above may be combined in any suitable manner.

[0063] The technology presented and claimed herein is cited and applied to substantial objects and specific examples of a practical nature that demonstrably improve the art and is therefore not abstract, intangible, or purely theoretical. In addition, if any claim appended to the end of this specification contains one or more elements designated as "means for [performing] ... [function]" or "steps for [performing] ... [function]," it is intended that such elements be interpreted in accordance with 35 U.S.C. § 112(f). However, for any claim containing elements designated in any other manner, it is intended that such elements not be interpreted in accordance with 35 U.S.C. § 112(f).

Claims

1. A riding system, comprising: one or more sensors; as well as One or more controllers configured to: receiving location data of a guest from the one or more sensors, the location data indicating a location of the guest's body, face, or a combination thereof on the ride; determining a facial orientation, facial rotation, or a combination thereof of the guest based at least in part on the position data, independent of sensor observations of the facial orientation and facial rotation; and One or more features of the ride are controlled based on the determined facial orientation, facial rotation, or a combination thereof.

2. The ride system of claim 1, wherein the position data comprises a skeletal image determined by skeletal tracking.

3. The ride system of claim 2, wherein the facial orientation, the facial rotation, or the combination thereof is based at least in part on a first position of a first body joint of the guest on the skeletal image being within a threshold distance of a second position of a second body joint of the guest.

4. The ride system according to claim 1, wherein: The one or more controllers are configured to: A facial orientation, facial rotation, or a combination thereof of the guest is determined using a machine learning model that recognizes patterns of previous guests on the ride.

5. The ride system of claim 1 , wherein the one or more controllers are configured to: A facial orientation, a facial rotation, or a combination thereof is determined based at least in part on a first position of a first facial feature of the guest being within a threshold distance from a second facial feature of the guest.

6. The ride system of claim 5, wherein the threshold distance indicates a direction of a first side of the face of the guest, a second side of the face opposite the first side, or a center of the face.

7. The ride system of claim 1 , wherein the ride facility includes a ride vehicle, and the one or more controllers are configured to determine the guest's facial orientation, facial rotation, or a combination thereof based on the position of the body, face, or a combination thereof within the ride vehicle.

8. The ride system of claim 1 , wherein the ride comprises a ride vehicle and the one or more controllers are configured to: receiving an indication of a ride vehicle position along a path of the ride from the one or more sensors; and The facial orientation, facial rotation, or a combination thereof is determined based at least in part on the passenger vehicle position.

9. The ride system of claim 8, wherein ride vehicle position is based at least in part on a structure of the ride vehicle, a known ride path of the ride, or a combination thereof.

10. The ride system of claim 1 , wherein controlling the one or more features comprises: causing actuation of the one or more features when the determined facial orientation, facial rotation, or a combination thereof is oriented toward the one or more features; as well as When the determined facial direction, facial rotation, or a combination thereof is oriented away from the one or more features, actuation of the one or more features is inhibited.

11. The ride system of claim 10, wherein actuation of the one or more features comprises: Animating an animated character, displaying an image on a display, generating lighting effects, or a combination thereof.

12. A method comprising: receiving location data of a guest from one or more sensors, the location data indicating a location of the guest's body, face, or a combination thereof on the ride; determining a facial orientation, facial rotation, or a combination thereof of the guest based at least in part on the position data, independent of sensor observations of the facial orientation and facial rotation; and One or more features of the ride are controlled based on the determined facial orientation, facial rotation, or a combination thereof.

13. The method of claim 12, wherein the position data comprises a skeleton tracking image, a facial recognition image, a body recognition image, or a combination thereof.

14. The method of claim 12, wherein the one or more sensors include a radio frequency identification (RFID) tag, a proximity sensor, an infrared (IR) tag, a weight sensor, a camera, or any combination thereof; Wherein the RFID tags, the proximity sensors, the IR tags, the weight sensors, the cameras, or any combination thereof are placed on a ride path of the ride at one or more points of interest to track or predict the positions of the guests on the ride within the ride path.

15. The method according to claim 14, comprising: The facial orientation, facial rotation, or a combination thereof of the guest is determined using a machine learning model that identifies patterns of previous guests on the ride at the predicted location of the guest on the ride within the ride path.

16. A tangible, non-transitory machine-readable medium comprising machine-readable instructions that, when executed by one or more processors of a machine, cause the machine to: receiving location data of a guest from one or more sensors, the location data indicating a location of the guest's body, face, or a combination thereof on the ride; determining a facial rotation, facial orientation, or a combination thereof of the guest based at least in part on the position data, independent of sensor observations of the facial orientation and facial rotation; and One or more features of the ride are controlled based on the determined facial orientation, facial rotation, or a combination thereof.

17. The machine-readable medium of claim 16, wherein the location data comprises an orientation of the guest's ride vehicle, the machine-readable medium comprising machine-readable instructions that, when executed by one or more processors of a machine, cause the machine to: A body position is determined based at least in part on the orientation of the passenger vehicle.

18. The machine-readable medium of claim 16, comprising machine-readable instructions that, when executed by one or more processors of a machine, cause the machine to: The facial rotation, facial orientation, or combination thereof is determined as a prediction of a future facial rotation, facial orientation, or combination thereof before the facial rotation, facial orientation, or combination thereof occurs.

19. The machine-readable medium of claim 16, wherein a three-dimensional (3D) map of the guest on the ride is generated based on the position data and the position of the ride vehicles on the ride, wherein the 3D map indicates a determined facial rotation of the guest relative to one or more features of the ride.

20. The machine-readable medium of claim 19, wherein the determined facial rotation uses machine learning to accurately predict facial position based on reproduced facial orientation determinations for specific portions of the ride within the 3D map.

Images