Tackling Performance Measurement System

Abstract

A system for measuring tackling performance, including a cover adapted to fit a tackling dummy, a sensor embedded in the cover and adapted to produce data relating to at least one tackling performance parameter, and electronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data.

Description

FIELD

This invention relates to the field of football tackling performance evaluation. More particularly, this invention relates to real time automatic performance evaluation using tackling dummies.

INTRODUCTION

American professional football is a sport where two teams calmly line up and then explode against each other in what is called a play, which typically lasts no more than a few seconds. The play often ends when a player from one team forcefully hurls himself against a player from the opposing team who is carrying the ball, and forces the ball-carrier to the ground in what is called a tackle. The two teams then line up against each other and do it again. For an hour. Thus, tackling performance by various players is an important aspect of success for one team against another team.

Overall tackling performance is comprised of a combination of a great number of factors, such as approach direction, speed of impact, breadth of impact, force of impact, location of impact, and post impact wrap-up.

Tackling skills are typically developed as a player repeatedly practices tackling a padded apparatus referred to as a tackling dummy, while a coach watches the practice and critiques the player on his technique.

Unfortunately, there are only a few of the tackling performance parameters that are visually observable by a coach, and so the coach can only infer from what he sees in the player's performance how effective the player is in regard to the other parameters, and what the player might need to do to improve.

What is needed, therefore, is a system that tends to reduce issues such as those described above, at least in part.

SUMMARY

The above and other needs are met by a system for measuring tackling performance, including a cover adapted to fit a tackling dummy, a sensor embedded in the cover and adapted to produce data relating to at least one tackling performance parameter, and electronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data.

In some embodiments according to this aspect of the disclosure, the sensor includes at least one of a pressure sensor, a touch sensor, an accelerometer, an inertial measurement unit, a proximity sensor, an LED sensor, and a video camera. In some embodiments the tackling performance parameter includes at least one of approach direction, speed of impact, breadth of impact, force of impact, location of impact, and post impact wrap-up. In some embodiments a first portion of the electronics are disposed in the cover and are in data communication with a second portion of the electronics disposed in a location that is remote from the cover. In some embodiments the data communication is at least one of wired and wireless. In some embodiments the electronics produce a single tackling performance score based on the data. In some embodiments the electronics are adapted to receive input in regard to a player that is using the tackling performance system.

According to another aspect of the disclosure there is described a system for measuring tackling performance, the system including a tackling dummy, a sensor embedded in the tackling dummy and adapted to produce data relating to at least one tackling performance parameter, and electronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data.

According to yet another aspect of the disclosure there is described a system as recited above and including a data center for receiving at least one of the data and the information from a plurality of tackling dummy, sensor, and electronics combinations.

BRIEF DESCRIPTION OF THE DRAWINGS

Further advantages of the invention are apparent by reference to the detailed description when considered in conjunction with the figures, which are not to scale so as to more clearly show the details, wherein like reference numbers indicate like elements throughout the several views, and wherein:

FIG. 1A is a representation of an add-on sensor cover for a tackling performance system according to an embodiment of the present disclosure.

FIG. 1B is a representation of the add-on sensor cover for the tackling performance system as placed over a prior art tackling dummy according to an embodiment of the present disclosure.

FIG. 1C is a representation of electronics associated with the tackling performance system according to an embodiment of the present disclosure.

FIG. 2 is a representation of a tackling performance system according to another embodiment of the present disclosure.

FIG. 3A is a representation of a tackling performance system according to an embodiment of the present disclosure that receives data from several smart tackling performance systems.

FIG. 3B is a representation of a tackling performance system according to an embodiment of the present disclosure that receives data from several smart tackling performance systems.

FIG. 4 is a combination flow chart and functional block diagram of a data analytics software platform for a tackling performance system according to an embodiment of the present disclosure.

FIG. 5 is a combination flow chart and functional block diagram of the data analytics software platform for a tackling performance system according to an embodiment of the present disclosure.

FIG. 6 is a depiction of a bounding box used in a vision-based score, according to an embodiment of the present disclosure.

FIG. 7 is a depiction of field of view angles used in a vision-based score, according to an embodiment of the present disclosure.

FIG. 8 is a functional block diagram of electronics according to an embodiment of the present disclosure.

DESCRIPTION

With reference now to the drawings, there are depicted all of the claimed elements of the various embodiments, although all claimed embodiments might not be depicted in a single drawing. Thus, it is appreciated that not all embodiments include all of the elements as depicted, and that some embodiments include different combinations of the depicted elements. It is further appreciated that the various elements can all have many different configurations, and are not limited to just the configuration of a given element as depicted. As indicated above, the elements of the drawings as depicted are not to scale, even with respect one to another, and relative size or thickness of one element cannot be determined by the aspect ratios of that element or with reference to any dimension of another element.

BRIEF OVERVIEW

FIG. 1A depicts a first embodiment of a tackling performance measurement system 100, in which a smart cover 106 is placed over a prior art tackling dummy 108, as depicted in FIG. 1B. Once the smart cover is united with a tackling dummy 108, the combination becomes a smart dummy 202.

The smart cover 106 includes several pads 104, which include a variety of embedded sensors 102. In this embodiment, the smart covers 106 can be added to existing inventories of tackling dummies 108, thus upgrading the tackling dummies 108 to smart dummies 202, without losing the investment that the team has made in the tackling dummies 108. It is appreciated that the smart covers 106 can be formed into a variety of different shapes and configurations, so as to fit various shapes, sizes, and configurations of tackling dummies 108.

FIG. 1C, depicts additional components of the system 100 for some embodiments, which include electronics 110. In some embodiments, the electronics 110 include at least one of a data acquisition module, a processor, memory, and a data communication interface. The data communication interface enables data communication 114, such as to a user interface 116 and additional electronics. In some embodiments, the user interface 116 displays a video clip of the player drill as well as a player tackling score.

Some embodiments include a display 112, as depicted in FIG. 1C, that is mounted on the smart dummy 202, and which provides timely feedback in regard to the effectiveness of the tackle just performed, such as by displaying a score that is calculated according to a set of metrics, such as predetermined metrics or user-adjustable metrics. This score and other information can also be communicated to the user interface 116. In other embodiments, the raw data is communicated to the user interface 116, and the score is calculated at that location.

FIG. 2 depicts a second embodiment of the system 100, which includes components, such as those described in regard to the smart pad 106, built directly into a tackling dummy 202. Some smart dummies 202 include a balancing weight 210, along with one or more other features as are commonly known in tackling dummy art.

In some embodiments, the system 100 communicates the collected tackling sensor 102 data to a data center 306, as depicted in FIG. 3A, which data is held in records 308. The data center 306 receives tackling data from at least one smart tackling dummy 202, as depicted in FIG. 3B. Each smart tackling dummy 202 may be in a different geographical location, and have its own identification. Each smart tackling dummy 202 sends its data to the data center 306 for storage and processing. The data center system 306 includes a data analytics platform 310 in some embodiments.

In some embodiments, the smart dummy 202 associates tackling data with the player performing the tackle. This can be entered manually, in some embodiments, or it can be determined by the smart dummy 202, such as by a visual identification of the player made by the smart dummy 202 before, during, or after the tackle, or by an electronic identification made by the smart dummy 202, such as by reading an electronic identification of the player, such as an RFID tag worn by the player in some manner.

Detailed Embodiments

FIG. 4 depicts one embodiment of the data analytics platform 310.

In some embodiments, the sensors 102 include at least one of force sensors, pressure sensors, touch sensors, accelerometer sensors, inertial measurement units, proximity sensors, LED sensors, and video cameras.

In some embodiments, the data communication interface enables data communication over at least one of a wired connection and a wireless connection (such as satellite transmission, cellular data, radio, Bluetooth, LAN, WAN, etc.).

In some embodiments, the user interface 116 may include a server, a laptop, a tablet, a cell phone, etc.

In one embodiment, the system 400 comprises eight modules. Module 402 receives data from all the tagged smart dummies 202. Module 404 stores all the received videos. Module 406 puts all the received tackling data in a queue. Every clip of video data and every tackling data is tagged to identify the player and the team he belongs to. Module 408 sends the combined video and tackling data of each player to the data analytics system 500. Module 410 stores the video data of each player for replay purpose and storage for a given amount of time. Module 412 contains the identification data of each player. Such data may include the name, age, height, and weight of the player. Module 414 receives the data from Module 532 of the data analytics system 500. Both data from 412 and 414 is stored in a data base 416.

The query module 418 allows the user to obtain information about a single player or a group of players of similar characteristics. For example, the user may want to know the tackling performance of a single player over time, the average tackling performance score over time, the average tackling performance of all the players in a given age range, or the highest tackling performance score in a group of players with similar age, height, or weight.

With reference now to FIG. 5, module 518 uses the data video cropping module 510 to extract the 11 of the position of the player with respect to the smart tackling dummy 202 position. It converts a drill video from the array of cameras to a 3 by N matrix. The columns of the matrix are time, x-position, and y-position of the player. N depends on the time length of the drill. Module 520 uses the output of Module 510 to extract the tilt, pan, and roll orientation of the player's helmet, and converts a drill video from the array of cameras to a 4 by N matrix. The columns of the matrix are time, tilt, pan, and roll, respectively. The output of modules 518 and 520, stored in database 416, requires reduced storage because the AI based feature-extraction technique of modules 518 and 520.

Module 420 uses the output of Modules 518 and 520 that is stored in database 416 to provide a computer-generated imagery (CGI) video. The CGI video enables the user to replay drills for which videos no longer exist.

In one embodiment, the system 500 comprises eleven modules. The drill video data is extracted from the data center 502 in 504. Module 510 uses AI to crop the drill video data to focus only on the player and reject the remaining information in the video. Module 518 uses the cropped data from Module 512 to extract the running path of the player toward the smart tackling dummy 202. Module 520 uses the same information to extract the orientation of the player's helmet. The information from modules 518 and 520 is used by module 524 to compute a vision based tackling score. For each player, there are two types of scores to be computed to achieve the final tackling score.

The first tackling score uses the sensors data to compute the sensor-based tackling score (T_ss). As an example, the tackling impact force may be provided by a force sensor (F_s), the wrap-up strength (W_s) may be provided by a pressure sensor, the tackling location (T_L) on the dummy may be provided by a proximity sensor. T_L is not a direct numerical value like F_s or W_s. However, a numerical value may be assigned to T_L based on how far from a predetermined ideal location on the dummy 202 the player hits it. This value may range from 0 for a complete miss of the dummy 202 to 1 for a direct hit in the ideal location on the dummy 202.

Let F_Ref and W_Ref be a reference impact force and a wrap up strength, respectively. For example, the reference F_Ref and W_Ref are previously known values or may be provided by the coach. Now define

$F_{s,N}=\frac{F_s}{F_{\mathrm{Ref}}}$ $W_{s,N}=\frac{W_s}{W_{\mathrm{Ref}}}$

• • where F_s,n, W_s,n are the normalized values of F_s, W_s, respectively. The tackling sensor-based score in this example may be computed as follows:

T _ss=(α₁F_s,N+α₂W_s,N)T_L

where α₁, α₂ are coefficients such that α₁+α₂=1. The coefficients are determined based on the priority the coach places on the tackling impact force vs the wrap-up magnitude. In one embodiment, the coefficients are adjustable by coaches by logging into the system and changing the coefficients associated with a profile of the coach.

The second tackling score is a vision-based tackling score (T_vs) that uses the drill video from the cameras 504. The first step is to utilize AI to find and crop the portion of the frame containing the player. The output of the cropping functions gives a bounding box defined by its width w and height h and the position of its center (i,j) in the original frame. For example, given an image of size (w_i,h_i) 1920×1080. Assume that the player is in the center of the image with a size that is 50×100 pixels. In this case, i=960, j=640, w=50, h=100, as depicted in FIG. 6.

In addition, the physical width of the player (W_p) is known. In addition, the player's width will be approximately the width of the bounding box since the player is running toward the dummy. Every camera has a known horizontal field of view (HFoV), which is called θ. For example, θ may be 58 degrees. From i we calculate the angle α at which the center of the player appears, as depicted in FIG. 7, where α=0 represents the center of the HFoV.

$\alpha =\frac{i\theta }{w_i}-\frac{\theta }{2}$

Next, calculate the angular width of the bounding box

$\beta =\frac{w\theta }{w_i}$

Next, using the small angle approximation, W_p may be written as

$w_p=d\beta \to d=\frac{w_p}{\beta }$

Now, using d and a it is possible to calculate the position x, y with respect to the dummy 202

x=d sin(α)

y=d cos(α)

Given x and y over time, the approach path (P_rt) 518 of the player is made up of rows [t_k x_k y_k] where t_k is the time when the frame was taken. In another example, the cameras may include a direct method for measuring distance, such as a stereoscopic camera or a time-of-flight (TOF) camera. For a drill, the coach may assign a target path (P_ref) for players to follow. The path score, (P_s) then corresponds to the similarity between the recorded and reference paths P_rt and P_ref.

A score of 1 indicates the player followed the target path perfectly, while deviating from the path results in a lower score that depends on the severity of deviation. The helmet orientation 520 may be obtained utilizing an artificial neural network (ANN). The score for orientation (H_s) will range from 1 when the player maintains the perfect orientation down to a zero if the player has the helmet oriented such that the tackle could result in the top of the helmet directly striking the dummy. A score of zero indicates a potentially unsafe tackle form. In one example, this will result in a zero score for both T_vs and T_ss. In some embodiments, the vision-based score may be defined as

T _vs =P _s H _s

In one example, the scores T_vs and T_ss are then fused by 530 to form an aggregate score that may be given by

T _TS=(α_FT_ss+β_FT_vs)

• • where α_f and β_f are weighting factors that may be assigned by the coach, depending on the purpose of the drill. These weighting factors are adjustable by the coach via logging into a user profile in the system associated with the coach.

The tackling sensors data in 506 is used to compute the tackling area on the smart tackling dummy, the tackling impact force, and the wrap up strength by Modules 512, 514, and 516, respectively. Module 528 performs sensors data fusion to compute a sensors based tackling score. The vision-based score 524 and the sensor-based score 528 are fused again to determine the final tackling score by Module 532.

In one embodiment, an AI based coach module 526 is used to provide additional information to be used to further improve the tackling score. Module 526 uses the fusion-based and sensor-based tackling scores, as well as input from the human coach 522, to be trained. An example of human coach input may include the score the coach would give after watching the drill of a player. Once trained the AI based coach 526 uses reinforcement learning to generate its own score that is fused with the other two scores.

Electronics Embodiment

Described in this section are various embodiments of the electronics 800, including at least portions of at least one of 110, 114, 116, 306, 400, and 500, as depicted in FIG. 8. Described below are brief descriptions of the types of components that are included in the electronics 800. It is appreciated that in various embodiments of the electronics 800, either a subset of the described components are included, or multiple instances of at least some of the components are included. It is also appreciated that the interconnections depicted in FIG. 8 are representative, and that in some embodiments, various ones of the components are connected directly to one another, and do not have all connections routed through the processor 802.

In various embodiments the electronics 800 includes a processor 802, human interface 804, display 806, memory 808, sensors, 810, sensor inputs 812, communication ports 814, battery 816, power input port 818, outputs 820, and signal processors 822, in a ruggedized housing 824.

The processor 802 controls at least a portion of the operation and communication of the electronics 800, and in various embodiments is at least one of a general purpose processor, an ASIC, and a FPGA. The memory 808 in some embodiments is a DRAM, and contains instructions used by the processor 802 to control the operation of the collection device 800, data collected by the collection device 800, and instructions received from outside the electronics 800. Some embodiments include a removable data bank, such as a micro SD card.

In various embodiments, the display 806 includes a flat panel video screen with a touchscreen. In some embodiments the interface 804 includes one or more of stylus, keyboard, and touch pad input. The battery 816, in some embodiments, includes at least one of a replaceable battery or a rechargeable battery, such as a lithium ion battery. The power input 818, in some embodiments, is used to provide at least one of AC and DC power to the electronics 800, such as for the purposes of at least one of recharging the battery 816 and providing operational power to the collection device 800.

In various embodiments, the sensor inputs 812 include one or more inputs for external sensors 102 that collect a variety of data as described elsewhere herein. In various embodiments, the inputs 812 either receive the raw data from such sensors 102, or data that has been conditioned by an external device and provided in a data stream to the collection device 800. In some embodiments, some sensors 102, such as those previously described, are built in to the electronics 800.

Some embodiments of the electronics 800 include signal processors 822, such as one or more of analog to digital converters for analog data that might be received from either the sensors 102 or the sensor inputs 812, and dedicated signal conditioning circuits such as filters and domain transformers, amplifiers, and so forth.

In some embodiments, the communication ports 814 include components such as wireless Ethernet (such as defined by the various IEEE 802.11 standards), cellular data transceivers (such as defined by IEEE 802.16, 802.20, and other standards), hardwired network connections such as Ethernet, Bluetooth, and other communication protocols. Some embodiments of the electronics 800 include output ports 820, such as video output, signal output (such as from the sensors 810, sensor inputs 812, or otherwise), USB connection, and otherwise.

In various embodiments the ruggedized housing 824 is formed of at least one of metal and plastic. In some embodiments the housing 824 is vented, and in other embodiments the housing 824 provides substantially hermetic protections to the other components disposed within the housing 824. The housing 824 in some embodiments is to at least some degree dust proof, water proof, and shock proof, and provides some degree of thermal insulation to the collection device 800.

The battery 816 is, in some embodiments, sufficient such that the electronics 800 can provide power to the sensors 102, comm ports 814, and other components of the electronics 800 for a length of time that is sufficient to gather data and at least one of store the data and upload it to a central data repository.

As used herein, the word module refers to a combination of both software and hardware that performs one or more designated function. Thus, in different embodiments, various modules might share elements of the hardware as described herein, and in some embodiments might also share portions of the software that interact with the hardware. Further, various modules of the electronics 800, in various embodiments, may be disposed across one or more local and remote locations.

As used herein, the phrase “at least one of A, B, and C” means all possible combinations of none or multiple instances of each of A, B, and C, but at least one A, or one B, or one C. For example, and without limitation: Ax1, Ax2+Bx1, Cx2, Ax1+Bx1+Cx1, Ax7+Bx12+Cx113. It does not mean Ax0+Bx0+Cx0.

The foregoing description of embodiments for this invention has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the invention to the precise form disclosed. Obvious modifications or variations are possible in light of the above teachings. The embodiments are chosen and described in an effort to provide illustrations of the principles of the invention and its practical application, and to thereby enable one of ordinary skill in the art to utilize the invention in various embodiments and with various modifications as are suited to the particular use contemplated. All such modifications and variations are within the scope of the invention as determined by the appended claims when interpreted in accordance with the breadth to which they are fairly, legally, and equitably entitled.

Claims

1. A system for measuring tackling performance, the system comprising: a cover adapted to fit a tackling dummy,a sensor embedded in the cover and adapted to produce data relating to at least one tackling performance parameter, andelectronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data.

2. The system of claim 1, wherein the sensor comprises at least one of a pressure sensor, a touch sensor, an accelerometer, an inertial measurement unit, a proximity sensor, an LED sensor, and a video camera.

3. The system of claim 1, wherein the tackling performance parameter includes at least one of approach direction, speed of impact, breadth of impact, force of impact, location of impact, and post impact wrap-up.

4. The system of claim 1, wherein a first portion of the electronics are disposed in the cover and are in data communication with a second portion of the electronics disposed in a location that is remote from the cover.

5. The system of claim 4, wherein the data communication is at least one of wired and wireless.

6. The system of claim 1, wherein the electronics produce a single tackling performance score based on the data.

7. The system of claim 1, wherein the electronics are adapted to receive input in regard to a player that is using the tackling performance system.

8. A system for measuring tackling performance, the system comprising: a tackling dummy,a sensor embedded in the tackling dummy and adapted to produce data relating to at least one tackling performance parameter, andelectronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data.

9. The system of claim 8, wherein the sensor comprises at least one of a pressure sensor, a touch sensor, an accelerometer, an inertial measurement unit, a proximity sensor, an LED sensor, and a video camera.

10. The system of claim 8, wherein the tackling performance parameter includes at least one of approach direction, speed of impact, breadth of impact, force of impact, location of impact, and post impact wrap-up.

11. The system of claim 8, wherein a first portion of the electronics are disposed in the cover and are in data communication with a second portion of the electronics disposed in a location that is remote from the cover.

12. The system of claim 11, wherein the data communication is at least one of wired and wireless.

13. The system of claim 8, wherein the electronics produce a single tackling performance score based on the data.

14. The system of claim 8, wherein the electronics are adapted to receive input in regard to a player that is using the tackling performance system.

15. A system for measuring tackling performance, the system comprising: a tackling dummy,a sensor embedded in the tackling dummy and adapted to produce data relating to at least one tackling performance parameter,electronics adapted to receive the data from the sensor and at least one of store, analyze, transmit, and display at least one of the data and information derived from the data, anda data center for receiving at least one of the data and the information from a plurality of tackling dummy, sensor, electronics combinations.

16. The system of claim 15, wherein the sensor comprises at least one of a pressure sensor, a touch sensor, an accelerometer, an inertial measurement unit, a proximity sensor, an LED sensor, and a video camera.

17. The system of claim 15, wherein the tackling performance parameter includes at least one of approach direction, speed of impact, breadth of impact, force of impact, location of impact, and post impact wrap-up.

18. The system of claim 15, wherein a first portion of the electronics are disposed in the cover and are in data communication with a second portion of the electronics disposed in a location that is remote from the cover.

19. The system of claim 18, wherein the data communication is at least one of wired and wireless.

20. The system of claim 15, wherein the electronics produce a single tackling performance score based on the data.