Systems and methods for biomechanical evaluation of athletic performances of animals

Abstract

To provide a computer system and method to be used for evaluating biomechanical performances of animals.SOLUTION: A biomechanical evaluation method 700 implemented using a biomechanical evaluation system 100 includes a step 716 of applying, to a biomechanical evaluation model, tracked positions of biomechanical markers on an identified animal and determined biomechanical performance indices to generate an output including at least one biomechanical evaluation index that can be used in assessing the biomechanical performance of the identified animal.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] (Related Applications) This application claims priority to U.S. Provisional Patent Application No. 63 / 517,541, filed August 3, 2023, and U.S. Patent Application No. 18 / 777,671, filed July 19, 2024, the entire disclosures of which are incorporated herein by reference.

[0002] (Technical field) The present invention relates generally to the biomechanical assessment of an animal's athletic performance, and more particularly to a method and system for assessing an animal's biomechanical performance for the purpose of assessing disease or injury. [Background technology]

[0003] With recent advances in technology, it is becoming increasingly common for athletes to be biometrically assessed or monitored by trained medical personnel. Such assessments can, for example, allow for understanding the relationships between body parts and tissues that are overly or underly moving, understand where an athlete is tight and loose, and understand where an athlete is weak and strong. Furthermore, such assessments allow for the development of training methods and movement techniques, which can play an important role in injury prevention as well as athletic performance improvement.

[0004] Similarly, horses, particularly racehorses, can be monitored by animal trainers and veterinarians to ensure that the horse has optimal biomechanical capabilities, to diagnose disease or injury, and / or to evaluate the effectiveness of treatment or intervention protocols. However, the effectiveness of performing biomechanical evaluations on racehorses is limited. For example, in cases where dozens of racehorses are simultaneously exercising, training, and / or running on the track, it is difficult for a person monitoring a particular racehorse to have a view of the particular racehorse in all areas of the racecourse. Furthermore, since monitoring racehorses is time-consuming, animal trainers and veterinarians may not have the time to monitor a particular horse every time the horse is exercising, training, or running on the track. Furthermore, even for experienced animal trainers and veterinarians, the early stages of disease or injury may be difficult to detect visually.

[0005] Therefore, there is a need for a system and method that can be used to assess the biomechanical performance of an animal that overcomes the above-mentioned problems of conventional monitoring methods. Summary of the Invention [Means for solving the problem]

[0006] In one aspect, a computer system for evaluating the biomechanical performance of an animal is provided. The computer system of the present disclosure includes at least one processor in communication with at least one storage device. The processor is programmed to perform the following steps: receive current image data including at least one animal from at least one camera; identify the animal in the received image data based on the specificity of the animal; identify at least one biomechanical marker on the identified animal; track the position of the identified biomechanical marker to determine the tracked position of the biomechanical marker; determine at least one biomechanical performance index based on the tracked position of the identified biomechanical marker; apply (i) the tracked position of the identified biomechanical marker and (ii) the determined biomechanical performance index to a biomechanical evaluation model to generate an output including at least one biomechanical evaluation index used to evaluate the biomechanical performance of the identified animal; and send at least one notification message including the output to at least one computer device.

[0007] In another aspect, a method for assessing the biomechanics of an animal is provided. The method is implemented using a computer device with a processor in communication with a storage device. The method includes the steps of receiving current image data including at least one animal from at least one camera, identifying an animal in the received image data based on a specificity of the animal, identifying at least one biomechanical marker on the identified animal, tracking the position of the identified biomechanical marker to determine a tracked position of the biomechanical marker, determining at least one biomechanical performance index based on the identified biomechanical marker, applying (i) the tracked position of the identified biomechanical marker and (ii) the determined biomechanical performance index to a biomechanical assessment model to generate an output including at least one biomechanical assessment index used to assess the biomechanical performance of the identified animal, and sending at least one notification message including the output to the at least one computer device.

[0008] In another aspect, a non-transitory computer-readable storage medium is provided having computer-executable instructions stored thereon for assessing a biomechanical performance of an animal, the computer-executable instructions being configured, when executed by at least one processor, to cause the processor to perform the following steps: receive current image data from at least one camera, including at least one animal, identify an animal in the received image data based on a specificity of the animal, identify at least one biomechanical marker on the identified animal, track a position of the identified biomechanical marker to determine a tracked position of the biomechanical marker, determine at least one biomechanical performance index based on the tracked position of the identified biomechanical marker, apply (i) the tracked position of the identified biomechanical marker and (ii) the determined biomechanical performance index to a biomechanical assessment model to generate an output including at least one biomechanical assessment index used to assess a biomechanical performance of the identified animal, and send at least one notification message including the output to at least one computing device. [Brief description of the drawings]

[0009] The above and other features, aspects, and advantages of the present disclosure will become better understood from the following detailed description when taken in conjunction with the drawings appended hereto, in which like reference characters represent like parts throughout.

[0010] [Figure 1] FIG. 1 is a schematic diagram of an exemplary biomechanical evaluation system that can be used to evaluate the biomechanical performance of an animal. [Diagram 2] FIG. 2 is a schematic diagram of an exemplary track and camera system that may be used with the biomechanical assessment system shown in FIG. [Diagram 3] FIG. 3 is a first image of a graphical user interface (GUI) that can be used with the biomechanical assessment system shown in FIG. [Figure 4]FIG. 4 is a second image of a graphical user interface (GUI) that can be used with the biomechanical assessment system shown in FIG. [Diagram 5] FIG. 5 is a schematic flow diagram illustrating an exemplary method for assessing the biomechanical performance of an animal that may be implemented using the biomechanical assessment system shown in FIG. [Figure 6] FIG. 6 is a flow diagram illustrating an exemplary method for evaluating the biomechanical performance of an animal that can be implemented using the biomechanical evaluation system shown in FIG. [Figure 7] FIG. 7 is an exemplary graph showing the mean absolute value of head amplitude (normalized) versus the standard deviation of the absolute value of head amplitude (normalized) and the standard deviation of frequency. [Figure 8] FIG. 8 is a diagram illustrating an exemplary configuration of a user computing device, such as the veterinarian computing device shown in FIG. [Figure 9] FIG. 9 is a diagram showing an exemplary configuration of a server system such as the system computer apparatus shown in FIG.

[0011] Unless otherwise indicated, the drawings attached hereto are intended to illustrate features of embodiments of the present disclosure. These features are believed to be applicable to a variety of systems that include one or more embodiments of the present disclosure. Thus, the drawings are not intended to include all conventional features known to those skilled in the art to be required to practice embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] In this specification and the claims, a number of terms will be used, which shall be defined to have the following meanings: The singular forms "a," "an," and "the" include the plural forms unless the context clearly dictates otherwise. The terms "optional" and "optionally" mean that the subsequently described event or circumstance may or may not occur. Furthermore, references to "one embodiment" are not intended to be interpreted as excluding the existence of additional embodiments that incorporate the recited features. Furthermore, unless expressly stated otherwise, embodiments "including" or "having" an element or elements having a particular characteristic may include additional elements that do not have that characteristic.

[0013] As used herein, the term "real-time" refers to either the time of occurrence of a relevant event, the time of measuring and collecting certain data, the time of processing the data, or the system response time to events and circumstances. In the embodiments described herein, these activities and events occur substantially instantaneously.

[0014] The embodiments described herein include a biomechanical evaluation system for evaluating the biomechanical performance of an animal, such as a horse. In an exemplary embodiment, the biomechanical evaluation system of the present disclosure includes at least one camera system for collecting image data of an animal moving around a race track, e.g., during a race, training, and / or exercise. Each camera system includes multiple cameras positioned around the track to capture image data of the animal moving around the track. In some embodiments described herein, the biomechanical evaluation system of the present disclosure further includes an identification system that automatically identifies a particular animal in the image data, even when multiple animals are included in the image data. Furthermore, in some embodiments described herein, the biomechanical evaluation system of the present disclosure can automatically identify anatomical markers on an animal included in the image data and track the relative positions and / or displacements of the anatomical markers of the animal as the animal moves around the track. In some embodiments described herein, the biomechanical evaluation system of the present disclosure can use the tracked positions of the anatomical markers to determine one or more biomechanical performance indicators, such as speed, acceleration, stride length, and / or gait type.

[0015] In some embodiments described herein, the biomechanical assessment system of the present disclosure generates a biomechanical assessment model that receives one or more inputs to generate one or more outputs including a biomechanical assessment index. The generated biomechanical assessment index can be used to assess the biomechanical performance of an animal, assess disease or injury of the animal, and / or predict potential disorders of the animal. The biomechanical assessment system of the present disclosure can collect image data of an animal over a period of time, e.g., weeks or months, to determine the normal biomechanical performance of the animal, i.e., a baseline biomechanical performance, e.g., a maximum speed and / or gait pattern characteristic of a particular animal. In this manner, the biomechanical assessment model can be used to detect changes in the normal gait pattern of an animal.

[0016] The biomechanical assessment model can be used, without limitation, to assess an animal's health or biomechanical performance, such as for example, injuries, diseases, or changes in an animal's normal gait, or changes in an animal's behavior or movement patterns, such as changes in head movement.

[0017] 1 is a schematic diagram of an exemplary biomechanical assessment system 100 that may be used to assess the biomechanical performance of an animal 102 or multiple animals 104. In this exemplary embodiment, the biomechanical assessment system 100 is incorporated into a race track 106 on which at least one animal 104 roams, e.g., exercising, training, walking, and / or racing. In other embodiments, the biomechanical assessment system 100 may be incorporated into another type of enclosed area or location, such as a pasture, where the animals 104 are able to roam within the enclosed area.

[0018] In the present exemplary embodiment, the biomechanical assessment system 100 comprises a system computing device 110 communicatively connected to a storage database 112. In some embodiments, the storage database 112 may be a cloud-based database 112. In the embodiments described herein, the biomechanical assessment system 100 comprises a camera system 114 that is used to collect image data, e.g., image frames and / or a series of image frames, such as a video feed, of the animal 104 moving about on the track 106. In the embodiments described herein, the biomechanical assessment system 100 comprises a biomechanical assessment model 116 that is continuously trained and used to determine one or more biomechanical assessment metrics associated with the subject being monitored. For example, the biomechanical assessment metrics can be used to assess the biomechanical performance of the animal 102, predict injury and / or disease progression, predict the likelihood of injury to the animal, track the progression of injury and / or disease, or evaluate the effectiveness of treatment, training, and / or intervention strategies. More details about the biomechanical assessment model 116 and the biomechanical assessment metrics are provided below.

[0019] In the present exemplary embodiment, the animal 102 is a horse, such as a race horse. In other embodiments, the biomechanical evaluation system 100 may be used to evaluate the biomechanical performance of other types of animals 104, such as, but not limited to, dogs, camels, elephants, or animals that are auctioned or used in racing. Additionally, in other embodiments, veterinarians and / or zookeepers may use the biomechanical evaluation system 100 to evaluate animals that are, for example, in captivity or that are difficult or dangerous to access.

[0020] In some embodiments, the system computing device 110 is communicatively connected to one or more other computing devices (e.g., veterinarian computing device 122) associated with one or more stakeholders 120, such as, but not limited to, a veterinarian, an animal trainer, an animal owner, an animal rider, or other interested party. Stakeholder 120 refers to any party interested in receiving information regarding the biomechanical performance of an animal. In some embodiments, stakeholders 120 are required to complete a registration process before being approved to participate in the biomechanical evaluation system 100. Stakeholder 120 is associated with a computing device referred to herein as veterinarian computing device 122. The system computing device 110 and / or veterinarian computing device 122 include a user interface 124, such as, for example, a visual and / or audio display, that enables a graphical user interface (GUI) 126 to present information to stakeholder 120, referred to herein as veterinarian 120. The system computing device 110 may communicate with other computing devices via an application program interface (API) or via an associated, e.g., front-end, graphical user interface (GUI) 126 that enables the exchange of data and / or messages. For example, the system computing device 110 may send one or more messages including video feeds and / or metrics to the other computing devices or cause the other computing devices to display one or more images (views) of the graphical user interface (GUI) 126.

[0021] Computing devices, such as system computing device 110 and veterinarian computing device 122, may be communicatively connected to the Internet via a variety of interfaces, such as, but not limited to, an intranet, a local area network (LAN), a wide area network (WAN), or a network such as an integrated services digital network (ISDN), a dial-up connection, a digital subscriber line (DSL), a cellular connection, and / or a cable modem. System computing device 110 and / or veterinarian computing device 122 may be any device capable of accessing the Internet, such as, but not limited to, a desktop computer, a laptop computer, a personal digital assistant (PDA), a cellular phone connection, a smart phone, a tablet, a phablet, and / or other web-based connectable device.

[0022] The term "database" as used herein refers to a body of data, a relational database management system (RDBMS), or both. A database includes any collection of data, including hierarchical databases, relational databases, flat file databases, object-relational databases, object-oriented databases, and any other structured collection of records or data stored in a computer system. The above examples are merely examples and are not intended to limit the definition and / or meaning of the term database. Examples of RDBMS include Oracle® Database, MySQL®, IBM® DB2, Microsoft® SQL Server, Sybase®, PostgreSQL, and the like. Oracle® is a registered trademark of Oracle Corporation, Redwood Shores, California, USA. IBM® is a registered trademark of International Business Machines Corporation, Armonk, New York, USA. Microsoft® is a registered trademark of Microsoft Corporation, Redmond, Washington, USA. Sybase® is a registered trademark of Sybase, Dublin, California, USA. However, any other database that enables the systems and methods described herein may be used.

[0023] As used herein, the term "processor" refers to a central processing unit, microprocessor, microcontroller, reduced instruction set circuit (RISC), application specific integrated circuit (ASIC), logic circuit, or any other circuit or processor capable of performing the functions described herein.

[0024] As used herein, the terms "software" and "firmware" are used interchangeably and include any computer program stored in memory for execution by a processor, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM) memory. The above memory types are merely examples and are not intended to limit the types of memory that may be used to store computer programs.

[0025] In the embodiments described herein, the biomechanical evaluation system 100 includes or is communicatively connected to an identification system 130 capable of identifying a particular animal 102 in the image data, even when the image data includes multiple animals 104. In some embodiments, the identification system 130 can identify a particular animal 102 in the image data, even when the image data includes, for example, 25 or more different animals, 50 or more different animals, or 100 or more different animals 104. The identification system 130 can be associated with one or more identification computing devices (not shown) that are separate from the system computing device 110, or the identification system 130 can be incorporated within the system computing device 110. In the present exemplary embodiment, the identification system 130 can identify a particular animal 102 even when the animal 102 moves between the fields of view of adjacent cameras 140 (see FIG. 2 ) used in the camera system 114. In some embodiments, the identification system 130 may use identification markers (not shown) attached to, for example, but not limited to, the saddle, saddle cloth, and / or stirrups attached to the animal. In some embodiments, the identification system 130 includes an identification (ID) model that is continually trained to identify a particular animal 102 within the collected image data. In some embodiments, the identification system 130 may use anatomical markers 132, described below, to determine one or more biometric body dimensions to identify a particular animal 102. The identification system 130 may utilize any suitable process or technique to identify a particular animal 102 within the image data. In some embodiments, the identification (ID) model may run on a computing device separate from the system computing device 110, in which case, after identifying an animal 102 with the identification (ID) model, the model results and / or the image data including the identified animal are transmitted to the system computing device 110.Thus, in some embodiments, rather than transmitting all of the collected image data to the system computing device 110, only image data containing the identified animal is transmitted to the biomechanical evaluation system 100 for evaluation, resulting in reduced computation time and improved computational efficiency.

[0026] In the present exemplary embodiment, the system computing device 110 can use image data of the identified animal 102 to identify one or more anatomical markers 132. In the present exemplary embodiment, the anatomical marker 132 refers to one or more locations of particular interest (e.g., position over time, displacement, and / or rotation) that can be tracked using the camera system 114 and / or the system computing device 110. In the present exemplary embodiment, the anatomical marker 132 can include, but is not limited to, a joint center, a limb, a center of mass, and / or an axis of rotation. In the present exemplary embodiment, the at least one anatomical marker 132 can be located, for example, on the horse's leg and / or foot, such as the hoof, heel, talon, and / or spur. In the present exemplary embodiment, the at least one anatomical marker 132 can be located, for example, on the knee, hip, and / or elbow. In some embodiments, the anatomical marker 132 can be located, for example, on the shoulder, mane, withers, and / or head of the animal. Biomechanical assessment system 100 may identify any other suitable anatomical markers 132 that enable biomechanical assessment system 100 to function as described herein.

[0027] The system computing device 110 may identify the anatomical markers 132 in each successive image frame to better track the relative position or displacement of the anatomical markers 132. In some embodiments, the system computing device 110 may track the relative position and / or displacement of the anatomical markers 132 using a global coordinate system established on the track 106. In some embodiments, the system computing device 110 may track the relative position and / or displacement of the anatomical markers 132 relative to a local coordinate system established on the body of the animal. In some alternative embodiments, the system computing device 110 may track the relative position and / or displacement of the anatomical markers 132 relative to one or more other anatomical markers 132, also referred to herein as the relative displacement of the anatomical markers 132. In some alternative embodiments, the anatomical markers 132 may be located, for example, on a person riding a horse and / or on a saddle attached to the animal. In some embodiments, a global positioning system (GPS) may be utilized to detect or locate the animal 102 in the image data to identify the animal 102. For example, GPS data may be obtained using ultra-wideband tags placed on the riders and / or animals, or a phone app that provides GPS data regarding the location of the animal 102.

[0028] In the present exemplary embodiment, the system computing device 110 can determine one or more biomechanical performance indicators based at least in part on the tracked positions or displacements of one or more anatomical markers 132. In the present exemplary embodiment, the biomechanical performance indicator can be, but is not limited to, the velocity, acceleration, and / or jerk (rate of change of acceleration) of one or more individual anatomical markers 132. In some embodiments, the biomechanical performance indicator can be the average velocity, acceleration, and / or jerk of two or more anatomical markers 132. In some embodiments, the biomechanical performance indicator can include the vertical displacement of one or more anatomical markers 132, for example, the vertical displacement or range of displacement of at least one anatomical marker 132 attached to the animal's head.

[0029] In some embodiments, the biomechanical performance indicators may include stride length or gait type, such as, but not limited to, walk, trot, canter, gallop, buck, and / or hand gallop. In some embodiments, the system computing device 110 may determine the gait type based on the tracked position of at least one anatomical marker 132. In some embodiments, the system computing device 110 may determine the gait type based on the displacement of at least one anatomical marker 132 attached to the foot or leg of the animal 102 being evaluated, for example, by detecting when each of the hooves (e.g., left or right front hooves and / or left or right rear hooves) leave and / or contact the ground. For example, the system computing device 110 may detect a pattern in which the anatomical markers 132 of the hooves independently contact the ground in sequential order, with the right hind hoof of the animal contacting the ground first, followed by the right front hoof, the left hind hoof, and the left front hoof, and recognize this pattern as a gait associated with a particular animal. The system computing device 110 may use the tracked positions of the anatomical markers 132 and / or any identifiable pattern of hoof displacement to determine any suitable type of gait. In some alternative embodiments, the type of gait may be determined using the biomechanical assessment model 116.

[0030] 2 is a schematic diagram of a camera system 114 and track 106 that can be used with biomechanical evaluation system 100 (FIG. 1). Camera system 114 can include any device capable of capturing images, including, but not limited to, a camera capable of capturing multiple image frames, a camera capable of capturing a sequence of image frames, a camera capable of capturing a video stream, and the like. Camera system 114 can include, but is not limited to, a neuromorphic camera, a digital camera, an infrared camera, a drone camera, a mirrorless camera, and any other camera that enables biomechanical evaluation system 100 to function as described herein. In the present exemplary embodiment, camera system 114 includes multiple trackside cameras 140 and multiple overhead cameras 142. Alternatively, camera system 114 can include any other camera position that enables biomechanical evaluation system 100 to function as described herein. For example, in some embodiments, camera system 114 can include a perspective camera worn by the rider of the animal being evaluated. The trackside cameras 140 and / or overhead cameras 142 collect image data continuously and / or at set intervals, periodically and / or on-demand, and then transmit the collected image data to the system computing device 110 and / or storage database 112. The image data may be transmitted periodically, for example, every second or minute, at predetermined time intervals, and / or at any suitable time interval that enables the biomechanical assessment system 100 to function as described herein.

[0031] In the present exemplary embodiment, the trackside cameras 140 are positioned around the perimeter of the truck 106. More specifically, in the present exemplary embodiment, the trackside cameras 140 are oriented in a substantially perpendicular direction relative to the animal 104. In other embodiments, the cameras 140 are oriented in other directions. In some embodiments, each trackside camera 140 can image a side of the animal. For example, the trackside cameras 140 can image image data of the animal at a substantially perpendicular angle relative to the side of the animal. In the present exemplary embodiment, the trackside cameras 140 are positioned at substantially uniform intervals around the perimeter of the truck 106. In some embodiments, the trackside cameras 140 are positioned at non-uniform intervals such that an animal 104 on the truck 106 is always within the field of view of at least one of the trackside cameras 140. For example, in some embodiments, the trackside cameras 140 are positioned at approximately 40 meter intervals. Alternatively, the trackside cameras 140 may be positioned at any location relative to the track 106 and any proximity to the animal on the track, for example, within 500 feet of the animal, such that the trackside cameras 140 can capture highly detailed images of the animal 102 at all locations on the track 106. Positioning the cameras 140 in this manner allows for identification of key points, such as the animal's anatomical markers 132, as described in more detail below. In some embodiments, the camera system 114 includes at least 12 trackside cameras 140. In some embodiments, the trackside cameras 140 may collect images at an imaging rate of between 15 frames / second and 120 frames / second.

[0032] Each of the overhead cameras 142 may include six camera arrays 144 that are controlled independently of one another. In some embodiments, the overhead cameras 142 may be moved (e.g., bent, extended, rotated, or moved) to variably change the field of view of the overhead cameras 142 or any of the six camera arrays 144 that are controlled independently of one another. The overhead cameras 142 are aligned vertically, e.g., above, the trackside cameras 140. The overhead cameras 142 may be used to create an artificial pan-tilt-zoom (PTZ) view of each animal 104. In the present exemplary embodiment, the overhead cameras 142 are oriented to collect isometric images of the top of the animals 102, e.g., the back of the animals 102, and / or the sides of the animals 102. In some embodiments, the overhead cameras 142 are positioned at an end 146 of the track 106 and / or one side 148 of the track 106. The camera system 114 includes a sufficient number of overhead cameras 142 to enable the cameras 142 to image the entirety or a substantial portion of the track 106. The overhead cameras 142 can be positioned to image any area of ​​the track 106 where the animals 104 may be present. In some embodiments, the camera system 114 includes at least four overhead cameras 142. Alternatively, the camera system 114 can include any number of overhead cameras 142 that enable the biomechanical assessment system 100 to function as described herein. The overhead cameras 142 can collect images at an imaging rate of between 15 frames / second and 120 frames / second. The trackside cameras 140 and / or the overhead cameras 142 can collect images at different imaging rates from each other or at the same imaging rate as each other. In some embodiments, the overhead cameras 142 can collect image data that is used to determine position, speed, and / or stride data for each monitored animal 102, as described in more detail below.

[0033] In some embodiments, the system computing device 110 can construct a training dataset that the system computing device 110 can use to generate the biomechanical assessment model 116, e.g., to train and / or tune it. The biomechanical assessment model 116 includes one or more model inputs and one or more model outputs. The training dataset can include one or more of: (i) a plurality of historical image data, (ii) historical anatomical markers 132 identified using the historical image data, (iii) historical biomechanical performance indicators, and / or (iv) historical biomechanical assessment indicators or results, as described below. The system computing device 110 can construct the training dataset by retrieving a reduced data size dataset from a full historical dataset, e.g., all image data collected over a predetermined period of time. Reducing the data size of the training dataset can improve computational efficiency and reduce computational time associated with training the biomechanical assessment model 116 using the training dataset. The system computing device 110 can reduce the data size of the training dataset by filtering the full historical dataset according to one or more criteria, e.g., image quality, animals included in the image data, etc.

[0034] In some embodiments, the biomechanical assessment model 116 may be a single model. In some embodiments, the biomechanical assessment model 116 may be multiple models used in combination with each other and / or individually.

[0035] Model inputs include (i) monitored image data collected by the camera system 114, (ii) identified anatomical markers 132 on the monitored image data, (iii) determined biomechanical performance indices, and / or (iv) one or more biomechanical risk factor indices described below. The model inputs can be applied to the biomechanical assessment model 116 to assess the biomechanical performance of the monitored animals 102 over a period of time. The monitored image data can be collected over a period of time during the assessment of each monitored animal 102. Model outputs include biomechanical assessment indices. The biomechanical assessment indices can include one or more of a risk score, an asymmetry score, and a forelimb lameness score, which indicate a level of injury or disease. In some embodiments, the risk score can be a sum of other determined scores. The forelimb lameness score can be a sum score representing the likelihood of injury to the forelimbs based on the vertical (vertical) displacement, lateral movement, or rate of change of vertical displacement of the horse's head movement, etc. The asymmetry score may be a total score representing the symmetry of the horse's overall movement. For example, a lack of symmetry in the horse's overall gait may indicate an injury to the animal. Alternatively or additionally, another output (biomechanical assessment index) that allows the biomechanical assessment model 116 to assess the animal 102 may be monitored.

[0036] In some embodiments, the system computing device 110 can receive or determine one or more biomechanical risk factor indices. The biomechanical risk factor indices can be indicative of disease or injury for an animal or a group of animals. The biomechanical risk factor indices can be associated with a group of animals or multiple animals and can indicate inter-individual variability in the multiple animals. In some embodiments, the biomechanical risk factor indices can include a mean and / or standard deviation associated with a biomechanical performance index or measurement in multiple animals. In a first example, the biomechanical risk factor indices include a threshold value for vertical (perpendicular) head displacement of the animal 102. For example, if the vertical head displacement of the animal 102 exceeds a predetermined threshold, the animal 102 is determined to be at risk for disease or injury.

[0037] In embodiments described herein, the system computing device 110 can construct a training data set used to train and / or tune the biomechanical assessment model 116. The training data set can include historical image data of one or more animals 104 or a single specific animal collected over a period of time. The system computing device 110 can construct the training data set by storing historical anatomical marker 132 relative positions in the historical image data, historical biomechanical performance indices, predefined biomechanical risk factor indices, and / or historical biomechanical assessment indices. In some embodiments, the system computing device 110 can construct the training data set by using disease or injury history. In some embodiments, the biomechanical assessment model 116 can predict race rankings or results based on biomechanical performance indices, such as average speed, and biomechanical assessment indices.

[0038] In some embodiments, the biomechanical assessment model 116 may be a machine learning model including one or more neural networks, such as a convolutional neural network, a deep learning neural network, etc. The neural network may have one or more layers of nodes, and the model parameters adjusted during training may be weight values ​​respectively applied to one or more inputs to each layer of nodes to generate a node output. In other words, the nodes of each layer may receive one or more inputs and apply weights to each input to generate a node output. The node inputs to the first layer of nodes correspond to model input data fields. And the node output of the final layer of nodes corresponds to at least one model output intended to predict at least one outcome data field. One or more intermediate layers of nodes may be connected between the first layer of nodes and the final layer of nodes.

[0039] When training the biomechanical assessment model 116 using the training data set, a suitable backpropagation algorithm can be used to adjust the weights assigned to each node layer to reduce the error between the at least one output and its corresponding outcome data field. In this manner, the machine learning model is trained to generate outputs that reliably predict the corresponding outcome data field. Alternatively, the machine learning model may have other suitable structures. In some embodiments, the biomechanical assessment model 116 can be trained by automatically discovering and appropriately weighting complex, second- or third-order, and / or other nonlinear interconnections between the model input data fields and the at least one output. Without the machine learning model, such interconnections cannot be anticipated and / or discovered by a human analyst.

[0040] In some embodiments, the biomechanical assessment system 100 may create two or more biomechanical assessment models 116 that are different from each other. In some embodiments, the system computing device 110 may create a biomechanical assessment model 116 specific to a particular animal, i.e., trained historical image data collected over a predetermined period of time for a particular animal 102. The training data for the biomechanical assessment model 116 specific to a particular animal may have a smaller data size compared to all the training data collected, thereby reducing computation time. The particular biomechanical assessment model 116 may be used to evaluate changes in the biomechanical performance of the particular animal 102. For example, the output of the particular biomechanical assessment model 116 may include an indication that the top speed of the animal 102 has changed, that the normal gait pattern of the animal 102 has changed, etc. In some embodiments, the particular biomechanical assessment model 116 may generate outputs similar or identical to the biomechanical assessment model 116. A particular biomechanical assessment model 116 can be used to create an animal profile representing the animal's normal gait, normal behavior, normal movement patterns, etc., to provide a baseline for detecting changes in the animal's biomechanical performance and health.

[0041] The system computing device 110 can create one or more notification messages that are sent from the system computing device 110 to other computing devices. The notification message can include one or more model outputs. The system computing device 110 may add one or more model inputs to the notification message. In some embodiments, the notification message includes image data, video data, identified anatomical markers 132 (e.g., location), identified anatomical markers 132 superimposed on the image data, determined biomechanical performance indicators (e.g., speed, acceleration, etc.), and / or biomechanical evaluation indicators (e.g., disease or injury warnings). In some embodiments, the notification message includes a recommendation, such as, for example, resting the animal or seeking intervention or medical evaluation by the veterinarian 120. The notification message can include instructions to cause a user interface to display one or more images of a graphical user interface (GUI) 126 (see FIGS. 3 and 4). In some embodiments, the graphical user interface (GUI) 126 can display information included in the notification message.

[0042] 3 and 4, in the present exemplary embodiment, the biomechanical assessment system 100 includes one or more graphical user interfaces (GUIs) 126 displayed on a computing device, such as the system computing device 110 and / or the veterinarian computing device 122, for displaying information, such as determined biomechanical performance indicators and / or biomechanical assessment indicators. In some embodiments, the graphical user interface (GUI) 126 may display images and / or videos, and in some embodiments, the anatomical markers 132 may be superimposed on the images and / or videos. The graphical user interface (GUI) 126 may include one or more different images, such as a first image shown in FIG. 3 and a second image shown in FIG. 4.

[0043] 3, an exemplary image (image) 200 of the graphical user interface (GUI) 126 is shown. The image 200 displays image data collected by the camera system 114. The graphical user interface (GUI) 126 may display a single frame and / or multiple image frames, such as via a video stream. The graphical user interface (GUI) 126 may also overlay one or more anatomical markers 132 on the displayed image data. In some embodiments, the anatomical markers 132 may be color coded to aid in identifying a particular animal 102 included in the image data. In some embodiments, the displayed image data may include multiple animals, and thus each identified animal 102 may be color coded a different color for use as an anatomical marker 132. The displayed exemplary image 200 may include a risk score indicating a level of injury or disease. In some embodiments, the risk score may be a sum of other determined scores. The front leg lameness score may be a total score representing the likelihood of injury to the front legs based on the horse's head movement, etc. The asymmetry score may be a total score representing the symmetry of the horse's overall movement. For example, a lack of symmetry in the horse's overall gait may indicate an injury to the animal. In some embodiments, the magnitude of the score may indicate a level of severity of the identified disease or injury, e.g., a higher score indicates a higher level of severity. The exemplary image 200 may include additional information, such as, for example, the name of the animal, the date and time the image was collected, and / or the location where the image was collected. The image 200 may also include an indication of, for example, speed in miles per hour and / or pace in minutes per mile. The image 200 may also display an overhead schematic of the track 106 and a representative marker indicating the position of the animal 102 relative to the overhead schematic. The image 200 may display determined biomechanical performance indicators, such as, for example, average speed, gait type, stride length, and / or maximum speed.

[0044] 4, an exemplary diagram 300 of a graphical user interface (GUI) 126 is shown. The image 300 may display image data collected by the camera system 114. The image 300 may display a timeline, for example, a timeline of a race, where the timeline shows the speed of the animal 102 over the timeline of the race.

[0045] 5 is a schematic flow diagram illustrating an exemplary method 600 for assessing the biomechanical performance of an animal that may be implemented using the biomechanical evaluation system 100 (FIG. 1). Any portion of the method 600 may be implemented by the system computing device 110. The method 600 includes collecting image data 602 using the trackside camera 140 and the overhead camera 142. The method 600 also includes identifying and / or detecting (or locating) a particular animal 102 within the image data, e.g., within an individual image frame, using the identification system 130, 604. The method 600 also includes storing the collected image data in the database 112 and / or storing the collected image data in the database 112 along with one or more animals 104 identified by the identification system 130, 606.

[0046] In some embodiments, the method 600 further includes analyzing 608 the image data collected by the trackside camera 140. The analyzing 608 includes using one or more image data collected by the trackside camera 140 to identify and / or detect (or locate) a particular animal 102 within the image frame and then identifying anatomical markers 132 on the identified animal 104 within the image frame. The analyzing 608 also includes using one or more image data collected by the trackside camera 140 to classify a gait type or stride length of the identified animal 102 within the image frame and obtain position information of the identified animal 102 in a global coordinate system established for the track 106.

[0047] The method 600 also includes analyzing 610 the image data collected by the overhead camera 142. The analyzing 610 includes the system using one or more image data collected by the overhead camera 142 to identify and / or detect (or locate) a particular animal 102 within the image frames and then obtain location information for the particular animal 102, for example, in a global coordinate system established for the track 106. In some embodiments, the method 600 further includes using one or both of the images collected by the trackside cameras 140 and the image data collected by the overhead camera 142 to classify the stride length of the animal 102, identify anatomical markers 132, and / or obtain location information for the animal 102 on the track 106.

[0048] The method 600 also includes a step 612 of combining or compiling the image data collected by the overhead camera 142, the image data collected by the trackside camera 140, the acquired positional information data, and the identified anatomical markers 132. The method 600 also includes a step 614 of using the combined data to determine a biomechanical performance indicator, such as speed.

[0049] Additionally, the method 600 further includes applying 616 the model inputs to the biomechanical assessment model 116 to cause the biomechanical assessment model 116 to output one or more biomechanical assessment metrics.

[0050] 6 is a flow diagram illustrating an exemplary biomechanical evaluation method 700 that may be implemented using biomechanical evaluation system 100 (FIG. 1) for evaluating the biomechanical performance of an animal 102. The method 700 may be implemented, at least in part, by a computing device, such as system computing device 110 or veterinarian computing device 122.

[0051] In some embodiments, the method 700 includes collecting 702 image data of at least one animal 102 as the animal 102 moves around within the track 106, e.g., as it trains, exercises, or competes. Collecting 702 the image data includes using a camera, such as a trackside camera 140 or an overhead camera 142, to collect the image data and then transmitting the collected image data to the system computing device 110. In some embodiments, collecting 702 the image data includes collecting the image data over a predefined period of time, such as several weeks or months. In some embodiments, collecting 702 the image data includes collecting the image data every time the animal 102 moves around within the track 106, e.g., every time the animal 102 trains, exercises, or competes. In some embodiments, the method 700 includes the system computing device 110 storing the image data in the database 112. This allows the database 112 to be constructed as a historical database. In some embodiments, the method includes the camera transmitting the image data directly to the database 112 .

[0052] In the present exemplary embodiment, the method 700 includes constructing 704 a training data set. The training data set is then used to generate a biomechanical assessment model 116, which is described in more detail below. The constructing 704 training data set includes compiling the collected historical image data using the system computing device 110. The constructing 704 training data set also includes identifying anatomical markers 132 on the historical image data and then adding the identified anatomical markers 132 to the training data set using the system computing device 110. In some embodiments, the method 700 further includes identifying animals 102 in the historical image data and then adding animal identifiers corresponding to the identified animals 102 to the training data set using the system computing device 110. The method 700 also includes determining, using the system computing device 110, one or more historical biomechanical performance indicators based on the historical image data, such as, but not limited to, speed, acceleration, and gait type. The system computing device 110 then adds the determined historical biomechanical performance index to the training data set to continuously update the training data set. In some embodiments, the method 700 further includes the system computing device 110 determining (e.g., receiving and / or calculating) one or more biomechanical risk factor indexes and then adding the determined biomechanical risk factor indexes to the training data set using the system computing device 110. In some embodiments, the method 700 includes receiving one or more biomechanical risk factor indexes from the veterinarian computing device 122. In other embodiments, the biomechanical risk factor indexes may be received / obtained from other sources. Examples of biomechanical risk factor indexes and determined historical biomechanical performance indexes are described above. The step 704 of constructing the training data set further includes the system computing device 110 continuously adding historical biomechanical evaluation indexes or historical results to the training data set. Thus, the training data set includes one or more historical model inputs and one or more historical model outputs.Constructing 704 the training data set includes the system computing device 110 obtaining a reduced data size dataset from the full historical data set, which may include all image data collected over a given period of time.

[0053] In the present exemplary embodiment, the method 700 further includes generating 706 the biomechanical assessment model 116 using the system computing device 110. Generating 706 the biomechanical assessment model 116 includes training the biomechanical assessment model 116 using the constructed training data set. Generating 706 the biomechanical assessment model 116 may include any process, such as training or tuning, to generate a biomechanical assessment model 116 having an error below an acceptable or predetermined threshold. Generating 706 the biomechanical assessment model 116 may include adjusting (e.g., increasing or decreasing) one or more weighting coefficients to adjust the influence of various training model inputs. Generating 706 the biomechanical assessment model 116 may include performing, using the system computing device 110, one or more other suitable processes for adjusting and / or training the biomechanical assessment model 116.

[0054] In the present exemplary embodiment, the method 700 further includes collecting 708 object image data related to a particular animal. Object image data refers to data collected during a particular period of time, such as during training or racing, or any period during which a user desires to evaluate the biomechanical performance of an animal. In some embodiments, the object image data is collected over an extended period of time, such as weeks or days leading up to a racing event. In some embodiments, the system computing device 110 can then add the object image data to the historical image data and / or training data set.

[0055] In the present exemplary embodiment, the method 700 further includes using the system computing device 110 to determine one or more model inputs to be applied to the biomechanical assessment model 116. Determining the model inputs includes identifying 710 a particular animal 102 in the collected target image data. Determining the model inputs further includes identifying 712 anatomical markers 132 of the particular animal 102 in the target image data. In some embodiments, determining the model inputs includes determining 714, using the system computing device 110, one or more biomechanical performance indicators based on the target image data and / or the identified anatomical markers 132. As discussed above, biomechanical performance indicators may include, for example, gait type, speed, and / or acceleration. Inputs to the biomechanical assessment model 116 may include, for example, one or more of: (i) target image data with or without the identified animal 102, (ii) the identified anatomical markers 132, and (iii) the determined biomechanical performance indicators. The method 700 may include determining other appropriate inputs to be applied to the biomechanical assessment model 116 .

[0056] In the present exemplary embodiment, the method 700 includes applying 716, using the system computing device 110, one or more determined model inputs to the biomechanical assessment model 116. Applying 716 the model inputs to the biomechanical assessment model 116 includes the biomechanical assessment model 116 generating one or more model outputs, such as, for example, a disease or injury warning, a recommendation or advice, and / or one or more biomechanical metrics, such as other biomechanical metrics described above.

[0057] In an exemplary embodiment, the method 700 includes generating, using the system computing device 110, one or more notification messages that include one or more of the outputs of the biomechanical assessment model 116, such as biomechanical assessment indices, and the biomechanical performance indices. In some embodiments, the notification messages include subject image data.

[0058] In the present exemplary embodiment, the method 700 further includes a step 718 of using the system computing device 110 to send the notification message to one or more computing devices, such as, for example, the veterinarian computing device 122. The notification message may be viewed and / or analyzed by an interested user, such as, for example, the veterinarian 120, to provide further recommendations or advice regarding, for example, the treatment of the animal.

[0059] In some embodiments, the notification message includes instructions to cause the computing device to display one or more graphical user interfaces (GUIs) 126 for displaying model outputs, subject image data or video, and / or biomechanical performance indicators in a manner that is intuitive and / or easily interpreted by a user.

[0060] In some embodiments, the method 700 further includes the system computing device 110 periodically updating the historical image data, updating the training data set, and / or periodically retraining the model using the updated training data set.

[0061] 7 is an exemplary graph showing the mean absolute value of head amplitude (normalized) versus the standard deviation of the absolute value of head amplitude (normalized) and the standard deviation of frequency. The mean values ​​can be used as model input or model training data. The mean values ​​can also be used to determine a biomechanical risk factor index.

[0062] 8 illustrates an exemplary configuration of a user computing device, such as veterinarian computing device 122 (FIG. 1), configured to transmit and / or receive data from system computing device 110 (FIG. 1). In this exemplary embodiment, user computing device 802 includes a processor 805 for executing instructions. In some embodiments, executable instructions are stored in memory 810 (storage device). Processor 805 may include one or more processing units, such as in a multi-core configuration. Memory 810 is any device that allows for the storage and retrieval of information, such as executable instructions and / or written work instructions. Memory 810 may include one or more computer-readable media.

[0063] The user computing device 802 also includes at least one media output component 815 for presenting information to a user 801, such as, but not limited to, a veterinarian 120. The media output component 815 is any component capable of communicating information to the user 801. For example, the media output component 815 may be a display component configured to display data related to model output, images, or videos, data contained in notification messages, or any other suitable data in the form of reports, dashboards, communications, etc., as described above with reference to FIGS. 1-4. In some embodiments, the media output component 815 includes an output adapter, such as a video adapter or an audio adapter. The output adapter is operably connected to the processor 805. The output adapter is operably connected to an output device, such as a display device, a liquid crystal display (LCD), an organic light emitting diode (OLED) display, or an "electronic ink" display, or an audio output device, speakers, or headphones.

[0064] In some embodiments, the user computing device 802 includes an input device 820 for receiving input from the user 801. The input device 820 may include, for example, a keyboard, a pointing device, a mouse, a stylus, a touch panel, a touch pad, a touch screen, a gyroscope, an accelerometer, a position detector, a voice input device, a fingerprint reader / scanner, a palm print reader / scanner, an iris reader / scanner, a retina reader / scanner, a profile scanner, and the like. A single component, such as a touch screen, can function as both an output device of the media output component 815 and an input device 820. The user computing device 802 also includes a communication interface 825 communicatively connectable to a remote device, such as the system computing device 110 (FIG. 1). The communication interface 825 may include a wired or wireless network adapter or a wireless data transceiver for use with a mobile data network, Global System for Mobile communications (GSM), 3G, or Worldwide Interoperability for Microwave Access (WIMAX), and the like.

[0065] Memory 810 stores computer readable instructions for, for example, providing a user interface to user 801 via media output component 815 and optionally receiving and processing input from input device 820. The user interface includes, among other things, a web browser and a client application. The web browser allows a user, such as user 801, from veterinarian computing device 122 to view and interact with media and other information embedded in web pages or websites. The client application allows user 801 to interact with biomechanical assessment system 100.

[0066] FIG. 9 illustrates an exemplary configuration of a server system 901, such as system computing device 110 (FIG. 1). In some embodiments, server system 901 includes veterinarian computing device 122. Server system 901 includes a processor 905 for executing instructions. The instructions are stored, for example, in memory 910 (storage device). Processor 905 may include one or more processing units (e.g., in a multi-core configuration) for executing instructions. The instructions may be executed on various operating systems on server system 901, such as UNIX, LINUX, Microsoft Windows, etc. More specifically, the instructions may perform various data operations (e.g., create, read, update, delete, etc.) on data stored in storage device 934. It should be understood that various instructions may be executed during initialization at the start of a computer-based method. Some operations may be required to perform one or more processes described herein, while other operations may be more general and / or specific to a particular programming language (e.g., C, C#, C++, Java, or other suitable programming language, etc.).

[0067] The processor 905 is operatively connected to a communications interface 915 such that the server system 901 can communicate with remote devices, such as a user computing device 800 or another server system 901. For example, the communications interface 915 can receive communications from other computing devices of the biomechanical assessment system 100 via multiple network connections, as shown in FIG.

[0068] The processor 905 is operatively connected to a storage device 934. The storage device 934 is any computer operating hardware suitable for storing and / or retrieving data. In some embodiments, the storage device 934 is integrated into the server system 901. In other embodiments, the storage device 934 is external to the server system 901. In other embodiments, the storage device 934 is similar to the database 112 (FIG. 1). For example, the server system 901 may include one or more hard disk drives as the storage device 934. In other embodiments, the storage device 934 is external to the server system 901 and is accessed by multiple server systems 901. For example, the storage device 934 may include multiple storage devices, such as hard disks or solid state disks in a redundant array of inexpensive disks (RAID) configuration. The storage device 934 may include a storage area network (SAN) and / or a network attached storage (NAS) system.

[0069] In some embodiments, the processor 905 is operatively connected to the storage device 934 via a storage interface 920. The storage interface 920 is any component capable of providing the processor 905 with access to the storage device 934. The storage interface 920 may include, for example, an Advanced Technology Attachment (ATA) adapter, a Serial ATA (SATA) adapter, a Small Computer System Interface (SCSI) adapter, a RAID controller, a SAN adapter, a network adapter, and / or any component that provides the processor 905 with access to the storage device 934.

[0070] Memory 910 may include, but is not limited to, random access memory (RAM), such as dynamic RAM (DRAM) and static RAM (SRAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and non-volatile RAM (NVRAM). The above memory types are merely examples and are not intended to limit the types of memory that may be used to store computer programs.

[0071] In the present exemplary embodiment, the biomechanical assessment model 116 allows for the use of historical image data collected over a period of time, e.g., weeks or months, to assess the biomechanical performance of an animal. The trained biomechanical assessment model 116 can detect changes in normal speed (e.g., average speed) for a particular movement, gait pattern, or gait type in a normal animal (e.g., normal inter-individual behavior averaged across multiple animals or normal intra-individual behavior of a single animal), as well as identify disease and / or injury. The biomechanical assessment model 116 is iteratively trained and adjusted using a training data set that includes historical image data and historical outcomes, e.g., historical disease and / or injury. In the present exemplary embodiment, the system includes a camera system having two different sets of cameras, each with a different field of view, which allows the system to identify and track a particular animal regardless of the animal's position on the track and even when there are multiple animals on the track. The system includes an identification system capable of identifying a particular animal even when an image frame captures multiple animals.

[0072] The above description is intended to be merely illustrative, and it will be apparent to those skilled in the art that modifications may be made to the described embodiments without departing from the scope of the invention disclosed. Modifications that are within the scope of the invention will be apparent to those skilled in the art in light of a review of this disclosure, and such modifications are intended to be included within the scope of the appended claims.

[0073] Although specific features of various embodiments of the disclosure may be shown in some drawings and not in others, this is for convenience and in accordance with the principles of the disclosure, any feature of one drawing may be referenced and / or claimed in combination with any feature of any other drawing.

[0074] This specification uses examples to disclose the invention including the best mode and to enable any person skilled in the art to practice the invention, including making and using any device or system, and practicing any method incorporated in the description. The patentable scope of the invention is defined by the claims, and may include other embodiments that occur to those skilled in the art. Such other embodiments are within the scope of the claims if they contain elements that are not different from the language of the claims, or if they contain equivalent elements that are not substantially different from the language of the claims.

Claims

1. 1. A computer system for assessing the biomechanical performance of an animal, comprising: at least one processor in communication with at least one storage device; The processor, receiving current image data from at least one camera, the image data including at least one animal; identifying the animals in the received image data based on a distinctiveness of the animals; identifying at least one biomechanical marker on the identified animal; tracking the positions of the identified biomechanical markers to determine tracked positions of the biomechanical markers; determining at least one biomechanical performance index based on the tracked positions of the identified biomechanical markers; applying (i) the tracked positions of the identified biomechanical markers, and (ii) the determined biomechanical performance indexes to a biomechanical assessment model to generate an output including at least one biomechanical assessment index used to assess the biomechanical performance of the identified animal; sending at least one notification message including said output to at least one computing device.

2. 2. The computer system of claim 1, The processor, Reading out historical image data; identifying at least one animal within the historical image data; identifying at least one historical biomechanical marker on the identified animal in the historical image data; tracking the positions of the identified historical biomechanical markers to determine historical tracked positions of the biomechanical markers; determining at least one historical biomechanical performance index based on the historical tracking positions of the identified historical biomechanical markers; (i) generating a training data set including at least one of the historical tracking positions of the identified historical biomechanical markers, (ii) the determined historical biomechanical performance index, and (iii) at least one biomechanical risk factor index.

3. 3. The computer system of claim 2, The processor, The computer system is further programmed to perform the step of using the training data set to train the biomechanical assessment model to receive inputs including at least one of (i) the current tracking positions of the identified biomechanical markers, and (ii) the determined biomechanical performance indexes, and output the biomechanical assessment index.

4. 2. The computer system of claim 1, The step of determining the biomechanical performance index includes determining at least one of the following: a velocity of the biomechanical marker on the identified animal, an acceleration of the biomechanical marker on the identified animal, a gait type of the identified animal, a stride length of the identified animal, an average speed of the identified animal, a maximum speed of the identified animal, a center of mass of an anatomical part of the identified animal, a velocity of an anatomical part of the identified animal, an acceleration of an anatomical part of the identified animal, a relative position of two or more of the biomechanical markers on the identified animal, and a vertical displacement of the biomechanical marker on the identified animal.

5. 2. The computer system of claim 1, The step of identifying the biomechanical markers on the identified animal comprises: A computer system comprising at least one of the steps of identifying joint anatomical markers on the identified animal and identifying body part markers on the identified animal.

6. 2. The computer system of claim 1, The step of receiving the image data includes: receiving at least one first image data including the animal from at least one first camera oriented in a first viewing direction towards the animal in the image data; and receiving at least one second image data including the animal from at least one second camera oriented in a second viewing direction that is vertically displaced relative to the first viewing direction.

7. 2. The computer system of claim 1, The step of generating the output including the biomechanical assessment index comprises: A computer system comprising at least one of a risk score, a lameness score, and an asymmetry score.

8. 3. The computer system of claim 2, The biomechanical risk factor index comprises at least one vertical displacement threshold of an anatomical marker located proximate to the animal's head.

9. 2. The computer system of claim 1, The computer system of claim 1 , wherein the biomechanical index of the animal comprises a biomechanical index of a horse.

10. 2. The computer system of claim 1, The step of transmitting the notification message to the computer device further comprises: The computer system includes the step of transmitting the notification message to a computer device associated with a veterinarian.

11. 2. The computer system of claim 1, A computer system, wherein the step of sending the notification message to the computer device includes a step of sending the determined biomechanical performance index to the computer device.

12. 2. The computer system of claim 1, The processor, The computer system is further programmed to execute a step of causing the computer device to display the identified biomechanical markers superimposed on at least one of the image data including the identified animal.

13. 1. A method for assessing a biomechanical performance of an animal, implemented using a computing device having a processor in communication with a storage device, comprising: receiving current image data from at least one camera, the image data including at least one animal; identifying animals in the received image data based on a distinctiveness of the animals; identifying at least one biomechanical marker on the identified animal; tracking the positions of the identified biomechanical markers to determine tracked positions of the biomechanical markers; determining at least one biomechanical performance index based on the identified biomechanical markers; applying (i) the tracked positions of the identified biomechanical markers, and (ii) the determined biomechanical performance indexes to a biomechanical assessment model to generate an output including at least one biomechanical assessment index used to assess the biomechanical performance of the identified animal; sending at least one notification message including said output to at least one computing device.

14. 14. The method of claim 13, Reading out historical image data; identifying at least one animal within the historical image data; identifying at least one historical biomechanical marker on the identified animal in the historical image data; tracking the positions of the identified historical biomechanical markers to determine historical tracked positions of the biomechanical markers; determining at least one historical biomechanical performance index based on the historical tracking positions of the identified historical biomechanical markers; (i) generating a training data set including at least one of the historical tracking positions of the identified historical biomechanical markers, (ii) the determined historical biomechanical performance index, and (iii) at least one biomechanical risk factor index.

15. 15. The method of claim 14, The method further comprises using the training data set to train the biomechanical assessment model to receive inputs including at least one of (i) the current tracking positions of the identified biomechanical markers, and (ii) the determined biomechanical performance index, and to output the biomechanical assessment index.

16. 14. The method of claim 13, The step of identifying the biomechanical markers on the identified animal comprises: The method includes at least one of identifying joint anatomical markers on the identified animal and identifying body part markers on the identified animal.

17. 14. The method of claim 13, The step of receiving the image data includes: receiving at least one first image data including the animal from at least one first camera oriented in a first viewing direction towards the animal in the image data; and receiving at least one second image data including the animal from at least one second camera oriented in a second viewing direction that is vertically displaced relative to the first viewing direction.

18. 14. The method of claim 13, The step of generating the output including the biomechanical assessment index comprises: The method includes at least one of a risk score, a lameness score, and an asymmetry score.

19. 1. A non-transitory computer readable storage medium having stored thereon computer executable instructions for assessing a biomechanical performance of an animal, comprising: The computer-executable instructions, when executed by at least one processor, cause the processor to: receiving current image data from at least one camera, the image data including at least one animal; identifying the animals in the received image data based on a distinctiveness of the animals; identifying at least one biomechanical marker on the identified animal; tracking the positions of the identified biomechanical markers to determine tracked positions of the biomechanical markers; determining at least one biomechanical performance index based on the tracked positions of the identified biomechanical markers; applying (i) the tracked positions of the identified biomechanical markers, and (ii) the determined biomechanical performance indexes to a biomechanical assessment model to generate an output including at least one biomechanical assessment index used to assess the biomechanical performance of the identified animal; and transmitting at least one notification message including the output to at least one computing device.

20. 20. The non-transitory computer readable medium of claim 19, The computer-executable instructions, when executed by at least one processor, cause the processor to: Reading out historical image data; identifying at least one animal within the historical image data; identifying at least one historical biomechanical marker on the identified animal in the historical image data; tracking the positions of the identified historical biomechanical markers to determine historical tracked positions of the biomechanical markers; determining at least one historical biomechanical performance index based on the historical tracking positions of the identified historical biomechanical markers; (i) generating a training data set including at least one of the historical tracking positions of the identified historical biomechanical markers, (ii) the determined historical biomechanical performance index, and (iii) at least one biomechanical risk factor index.

Images