CN104025537A - Apparatus and method for analyzing sensor data - Google Patents
Apparatus and method for analyzing sensor data Download PDFInfo
- Publication number
- CN104025537A CN104025537A CN201180074598.3A CN201180074598A CN104025537A CN 104025537 A CN104025537 A CN 104025537A CN 201180074598 A CN201180074598 A CN 201180074598A CN 104025537 A CN104025537 A CN 104025537A
- Authority
- CN
- China
- Prior art keywords
- event
- primitive
- stream
- observation
- detector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F9/00—Games not otherwise provided for
- A63F9/24—Electric games; Games using electronic circuits not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/131—Protocols for games, networked simulations or virtual reality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Abstract
An apparatus for detecting an event of interest, comprises a first primitive event detector (8b) for generating a stream of first primitive events (10b) using a sensor data stream (4), the sensor data stream (4) carrying raw data at a sensor data rate, the raw data being as- sociated to one or more properties determined for multiple observed objects (72) using one or more sensors, wherein a data rate of the stream of first primitive events (10b) is lower than the sensor data rate as well as a second primitive event detector (8c) for gen not erating a stream of different second primitive events (10c) using the sensor data stream (4), wherein a data rate of the stream of the second primitive events (10c) is lower than the sensor data rate. An event detector (16) is operable to determine the event of interest using the streams (10b, 10c) of the first and second primitive events.
Description
The analysis of embodiments of the present invention relate generally to sensing data, and especially, relate to the apparatus and method for the sensing data providing with high sensing data speed is provided.
Background technology
The wireless sensor network of various technology can be used to locate object, such as location or the tracking mankind and/or other object.Here, " location " means the detection in geographical position or determines, means with short time interval location can follow position and other kinematic variables of the mobile object of observation and follow the tracks of.The location that some are special or positioning control system can be used to locate player and other object (for example, ball) in sport event, and described sport event is such as such as Association football, rugby, rugby, tennis etc.
In the time analyzing the geographical position of collected player and/or ball or locator data, can obtain for example, to whole sport event (Association football match) relevant or with each troop or the relevant statistical information of player.The statistical information obtaining like this may be because of a variety of causes but is interesting.Certain statistical data and their analysis on the one hand, there is various coml interest, because can be correlated with especially for the spectators in stadium and/or before the television set of staying at home.Thereby, provide certain statistical data can improve the larger interest in sport event.On the other hand, the statistics obtaining from original locator data also can be used to training goal.Can analyze oneself the opponent of troop and/or behavior and each player's performance and/or health status here.
Aforesaid location or positioning control system can be based on various technology.For example, can the assessment based on wireless radio signal and/or magnetic field determine locating information.For this purpose, being usually also represented as the transmitter of transducer and/or receiver can be placed on each object (such as player, ball etc.) that system will locate and locate.Corresponding reception and/or dispensing device also can be installed to pays close attention near precalculated position, geographic area (for example, association football pitch).Then the assessment of signal strength signal intensity, signal propagation time and/or signal phase etc. can cause indicating each player or object at not geographical position in the same time or the sensor data stream of location.Locator data sampling can when, object be positioned at timestamp viewed or geographical location that detect and be associated with instruction.As combined information, except comprising the locator data of such as x coordinate, y coordinate and z coordinate, also can provide exercise data (such as speed (speed), acceleration etc.).The location of being sent by alignment sensor system in this manual, and/or exercise data also will be called as original (transducer) data.
In the particular example of radio tracking system, people or object can be equipped with miniature transmitter, and near the many antennas in region (as for example association football pitch) that described miniature transmitter can be embedded in footgear, uniform and ball and its signal is placed under observation pick up.Acceptor unit is processed collected signal and is determined their time of advent (ToA).Based on the calculating of propagation delay differences, the position of each transmitter is determined continuously with all objects in tracing observation.In a particular example, in the 2.4GHz wave band that transmitter exempts to authorize in the whole world, operate, and each transmitter uses CDMA (code division multiple access) technology to distinguish.
But the object of following the tracks of in sports tournament with the accuracy being applicable to easily produces a large amount of sensing datas.For example, the maximal rate of supposing ball is about 150km/h (it is seemingly rational for Association football), and the ball of following the tracks of Association football match with the accuracy of rough 3cm may need about 2000 times of the position of estimation ball per second.But, such as other sports of tennis or baseball undoubtedly by sampling higher needs or estimate speed.And not only ball is tracked during similarly important Association football is competed by following the tracks of therein 22 players.Because following the tracks of in the accuracy situation of 1cm by system above-mentioned is feasible in principle, so also expect to use more than one tracking transducer for each player, to not only obtain his position but also obtain its posture to can judge offside situation etc.Can produce as nearly 50000 position data samples per second or the primary data sample of associated sensor data stream and can there is per second 50000 sensing data speed to the Liang Ge troop of Association football match and the transducer of necessary telecontrol equipment assembling fair amount.
Analyze such sensing data in the time judging at every turn need to about in the initial data of multiple or all the sensors understand because each event by analyzed or because each conclusion to be made need to be about the understanding of the different subsets of transducer initial data.That is to say, in conventional analysis framework, all data need to be distributed to all analysis entities concurrently, if the number of analysis entities increases to analyze data with respect to many aspects, this is not feasible.In order even to realize this task, with in real time or cannot reach completely in those systems close to real-time mode.But, in order to indicate offside position or may to need this in order to answer similar time-critical problem in another sports tournament process in Association football match.
Therefore need to provide for analyte sensors data flow more efficiently to extract the design of concern information.
Summary of the invention
According to the embodiment of the present invention, this is just used for analyzing by utilization and realizes at the analytical framework of the initial data part that sensor data stream was sent with sensing data speed.This analytical framework comprises: input layer, and it comprises for using uniquely sensor data stream as at least two or more primitive event detectors of inputting the first-class and second at least to generate primitive event; And one or more event layers, it comprises for detection of paying close attention to one or more event detector of event, any one in one of them or more event detector only use the stream of the first and second primitive events or by the stream of another other event providing in event detector as input.That is to say, this analytical framework is followed the Hierarchy Analysis Method based on event, wherein determines or detects complementary event the different layers relying on is secondary.
Event can usually can be defined in the instantaneous generation of concern sometime.Generally speaking, event is associated to the change of the relevant amount sensing.Event can be the primitive event obtaining in level basis or input layer, make primitive event directly for example, based on sensing data (exercise data being provided by tracking system) thus and can indicate the change of the relevant amount sensing.Concern event is higher level event, and it depends on other event or primitive event, or more generally depends on other event previously having detected.In another view, event or primitive event comprise by applying to another event or to initial data the information that specific decision criteria obtains.
Method based on event can provide to analyze bottom data with the mode of the multiple processing node parallelizations via network service.This is specially following situation, only need to be provided for the primitive event detector in input layer according to the sensor data stream of speed at a high speed because there is it, in this primitive event detector, they are processed to determine conventionally with the definite primitive event of lower data speed.For more high-rise, primitive event is that the basis of analyzing makes sensor data stream needn't be distributed to all decision entities or event detector.This makes the analysis of the position data of larger group become basic possibility.
And, in higher level layer, for example provide in the analytical framework by comprising some CPU or computing node for the data rate of the reduction of the incoming event of event detector the possibility that event detector and/or primitive event detector is distributed to different CPU or computer and makes to process parallelization.The event data speed reducing even provides when box lunch requires to approach real-time analysis also via the generation of general networks (such as for example by LAN (local area network (LAN)) based on Ethernet) communication event the not possibility of the performance of restriction analysis framework.Compared with initial data, the fact that only decision criteria of event detector is satisfied (, event has occurred) can be used as event information and send between the event detector being relative to each other.This can contribute to make the amount of the data that exchange between event detector to keep low extraly, because the length of the Length Ratio individual data of each single message sampling is short.That is to say, not only can make the number of the packet of per time keep low but also can make the size that has sent packet keep low.In other execution mode, the event data of exchange can also comprise the information about fixed two of event detector, three or more possible states.That is to say, definite event or primitive event can comprise more than one binary Yes/No information.
According to another implementation of the invention, above-mentioned purpose is by realizing for detection of the device of the event of concern, described device comprises the first basis event detector of the stream for generate the former event of first with sensor data stream and for generate the second primitive event detector of stream of the second different primitive events with sensor data stream, wherein the data rate of each in the stream of the first primitive event and the second primitive event is lower than sensing data speed.Event detector can operate determines concern event with the stream of the first and second primitive events.Therefore event detector can make it judge the primitive event based on occurring with lower data speed, and therefore carries out its analysis and without directly accessing high data rate sensor data stream.
In this respect, terminology data speed will be not only interpreted as instantaneous data rates but also be interpreted as mean data rate, and described mean data rate is the mean value during specified time interval as instantaneous data rates.Depend on the group of selected primitive event, specific primitive event can occur and in short time period, determine with sensing data speed.For example, but the mean data rate of primitive event during observing time (Association football fixture) can be lower.
According to certain embodiments of the present invention, primitive event detector can operate and use uniquely exercise data as initial data to the real-time analysis of the tracking data of sport event etc. is provided.Exercise data can be the random subset of positional information, velocity information or the acceleration information of the object of observation.Can in 1 dimension, 2 dimensions or 3 dimension spaces, provide data, make to depend on selected execution mode, kinematic variables used herein will be understood to vector or scalar.In other execution mode, primitive event detector can itself obtain speed and/or acceleration information from provided positional information in addition, and making transducer can be simple tracking or positioner etc.
The suitable selection of step analysis based on basic event, such as judging required any essential information to can obtain for all more high-orders.
According to an execution mode, in the positional information of first object of observation and second object of observation is indicated the predetermined neighborhood of second object of observation in first object of observation time, generate and approach event as primitive event.Neighborhood can depend on observation event or sports tournament but the complicated volume being shaped or defined by the distance between first object of observation and second object of observation.Approach and can be used as the input of many other event detection, as for example to answer player/batter or other device possibility and hit the problem of ball or the other object of observation.
According to another execution mode, outside the positional information of first object of observation and second object of observation is indicated the predetermined neighborhood of second object of observation in first object of observation time, generate remote events as primitive event.
According to another execution mode, in the time that the speed (direction or amount) of the object of observation or the change of acceleration exceed predetermined threshold, generate direction and change event as primitive event.This criterion can be useful conventionally in sports or tracking application.But, depending on observed sports, the height of threshold value can be different.Therefore threshold value can be different for different types of motion or even between single game match period, change with the environmental aspect corresponding to changing, for example, occur to rain.
According to another execution mode, it is passive or not when mobile being down to below predetermined threshold with denoted object when the speed of the object of observation, generates idle event as primitive event.According to some execution modes, only keep below and when predetermined threshold reaches at least predetermined minimum duration, generate idle event in the speed of the object of observation.
According to another execution mode, in the time that the speed of the object of observation exceedes predetermined threshold, generate life event as primitive event.According to some execution modes, be only kept above and when predetermined threshold reaches at least predetermined minimum duration, generate life event in the speed of the object of observation.
According to another execution mode, in the time that at least one component of the positional information of the object of observation exceedes or is down to below predetermined threshold, generate cross-line event as primitive event.
Brief description of the drawings
To only hereinafter some execution modes of device and/or method be described by example and with reference to accompanying drawing, in the accompanying drawings
Fig. 1 shows the schematic diagram for the analytical framework of analyte sensors data flow;
Fig. 2 schematically shows the block diagram for detect the execution mode of the method for concern event with sensor data stream;
Fig. 3 schematically shows the example of the available event-detection solutions in order to detect the shooting in Association football match;
Fig. 4 schematically shows the example of the available event-detection solutions in order to detect the one-two in Association football match;
Fig. 5 schematically shows the event that allows to determine efficiently the existence of the object of observation in presumptive area; And
Fig. 6 schematically shows the execution mode of event detector.
Fig. 1 schematically shows for analyzing the initial data part just being sent at sensor data stream 4 with sensing data speed to identify the analytical framework 2 of at least one concern event.Initial data part is associated with the one or more attributes that use one or more sensor tip to determine the object of observation.In current and following execution mode, suppose that initial data only comprises the observation player of Association football match and the kinematic variables of ball.
The input layer 6 of framework 2 comprises for using uniquely sensor data stream 4 to become some primitive event detector 8a-8e of the stream of primitive event next life as input.That is to say to only have the primitive event detector 8a-8e of the input layer of analytical framework 2 to receive initial data as input using high sensing data speed.
The first basis event detector 8b uses sensor data stream 4 to become the first-class 10b of primitive event and the second 10c of primitive event next life as inputting with the second primitive event detector 8c uniquely.Sensor data stream 4 can provide by any applicable technology, and described any applicable technology is such as using standardization or the use copper of custom communication agreement or the ethernet network of optical fiber link or any other wired or wireless technology.
Analytical framework 2 comprises two event layers 12 and 14, eachly comprise that wherein the event detector of event layers 12 and 14 only uses the stream being provided by primitive event detector or other event detector of event layers 12 or 14 as input for detection of paying close attention to the event detector of event.For example, stream 10b and the 10c of event detector 16 use the first basis event detector 8b and the second primitive event detector 8c determine concern event.Stream 10b is also provided for another event detector 18.Self-evident, interdepending arbitrarily is in addition possible.But, for simplicity, illustrate only minority here and rely on or connect.
Link between event detector can connect or realize with any other network link based on any utilization wired ethernet known in the art.Each event detector can be used as that different software process moves on different computing nodes or some in them can be moved on identical node.Event detector can also be implemented as special or programmable hardware or analog.In this respect, the dependence between the event detector shown in Fig. 1 all should be understood to the stream of indication information or each other the dependence to event detector for physical hardware link or for the expression of logical links.
Fig. 2 schematically shows the execution mode that detects the method for concern event with the sensor data stream 4 of sensing data speed carrying initial data for using, and this initial data is associated with the one or more attributes that use one or more sensor tip to determine multiple objects of observation.
Generate in step 20 at the first primitive event, generated the stream 22 of the first primitive event, wherein the data rate of the stream 22 of the first primitive event is lower than sensing data speed.Generate in step 24 at the second primitive event, generated the stream 26 of the second primitive event, wherein the data rate of the stream 26 of the second primitive event is lower than sensing data speed.
Generate in step 28 in event, the stream 22 and 26 of concern event 30 use the first primitive events and the second primitive event is determined.It should be noted in the discussion above that can carry out the first and second events by any random order generates step 20 and 24, that is to say the particular event of first, second stream that not necessarily must create simultaneously or send the primitive event for determining concern event 30.
For this reason, event detector for example may be implemented as state machine, as by below shown in Fig. 6.
The Fig. 3 to 5 being discussed below shows and will be used to compete and obtain more some execution modes of the primitive event of suitably choosing of the concern event of high-order for Association football.
Fig. 3 and 4 shows positional information for analyzing Association football match player and ball to identify the example of analytical framework of many concern events.Can notice, Fig. 3 and 4 illustrated embodiment cannot illustrate institute's correlate and the link between event detector or the decision entities of level at all levels.How Fig. 3 and 4 can be used to analyze data to obtain very complicated information from a small amount of primitive event if being mainly intended to clarify hierarchical method and particularly minority basis event.
The positional information that Fig. 3 shows for analyzing Association football match player and ball is designated the example of the analytical framework of concern event will stop shooting.In the input layer of framework, for example, by by the acceleration providing and threshold or by calculating the single order of position data of ball and second dervative to the direction of ball is changed and inferred, thereby detect " direction change event " 40 for ball.In addition, generate or obtain cross-line event 42, instruction ball has been crossed the predetermined dummy line on court.
Based on cross-line event 42, ball is identified as in specific region, thus formation zone event 44.In the description that is identified in Fig. 5 of specific region, illustrated in more detail.Existence according to ball in inside, court, can infer that observing ball is movable balls 46, and described movable balls 46 is actively for the ball of competing instead of be stored in the spare ball outside court.The close event 48 at player and ball and ball and goal allows to draw the following conclusions: the direction that changes the indicated ball of event 40 by direction change due to specific player hit a ball (this carrys out signaling by corresponding event 50) cause.Infer that by event 52 shooting is for goal in an identical manner.Additional subsequently be that ball and goalkeeper's close event further allows to infer that the player who has been blocked and hit a ball that shoots does not realize goal.As apparent from Figure 3, last complex information is from minority only but the primitive event of suitably choosing is collected.
Fig. 4 shows positional information for analyzing Association football match player and ball to identify the example of analytical framework of two one-twos between player.As illustrated about Fig. 3, carry out definite that specific player hits a ball.In addition, the change of the symbol of the speed of ball or the component of velocity vector can be used to determine peak height event 56 for ball, and this can indicate ball to be shot instead of only ball-handling.Can determine according to instruction ball 58 beginning and the end of occupying of ball close to specific player's the event that approaches 48.As represented by Reference numeral 60, the fact that specific player controls ball can derive from ball and receive in the time that same player controls ball the information of some acceleration.Pass 62 can at ball, by losing ball with a player, another player realizes the information of controlling ball and determines during at intermediary movements, this so that detected by event 56 highly.Finally, one-two 64 can be determined by 2 consecutive passes between identical player.Again, in Fig. 4, determine or the complex information analyzed is based on primitive event that only suitably choose on a small quantity and definition.
Fig. 5 illustrate can as how especially efficiently mode only collect ball 72 and be positioned at the information of the given zone 74 in court from the primitive event of a type.Bottom primitive event is that instruction ball has been crossed and is in fact projected on court to it is subdivided into the cross-line event of the straight line in many regions.Region 72 is by forming with 4 straight lines 76 to 82 that form rectangular area 74 with right angle intersection.Use as cartesian coordinate system indicated in Fig. 5, whether this can be in fact exceeded or is down to predetermined threshold with the realization of getting off by the component of the position vector of definite ball.But, can notice, be possible according to execution mode described herein for other random geometry of observation area equally.Line may need different calculating after whether having been crossed really certainly, such as determining of for example determinant.
Determine by conventional method whether ball 72 is positioned at region 74 and need to spreads all over the All Ranges iteration in court and need to determine the relative position of ball with respect to each edge in region.That is to say, for example, must calculate determinant to infer that ball 72 is in 74 inside, region in the time that all determinants are shared identical symbol for each in an edge, 4 of region 74.To be almost feasible to supposing that 2000 ball positions per second are carried out this analysis in real time.
But, using embodiments of the present invention, determining of the position of ball for example can be, based on for being used for, court being subdivided into each the determined basis " cross-line event " in the line (line 76 to 80 on the border in district 74 is provided) in multiple regions.For each in line, in the time that ball is crossed line, determine cross-line event or relative position event.As illustrated in Figure 5, ball is changed into its current position region 74 by its position from previous position 84.That is to say, the primitive event detector being associated with line 82 will change its output state, or in other words, generates cross-line event.
But, in the time that the primitive event detector being associated with line 82 generates cross-line element, receive the event generating of this event and in addition can generate instruction ball 72 event in region 74 now by the determined event of primitive event detector being associated with line 76,78 and 80.Event detector for example can be implemented as state machine, as illustrated in greater detail in Fig. 6.Compared with conventional method, be used for determining that ball can reduce a great deal of with respect to the calculated load of the position of presumptive area (as for example with respect to penalty area).
In other words, conventional method need to, the region for each definition:
Each straight flange area under a person's administration for this region:
For the location positioning determinant of the object of observation;
The determinant relatively calculating is to infer that object is whether in region.
On the contrary, use embodiments of the present invention, the number k that people can definition wires is to be subdivided into a number n region by court, as example as illustrated in Figure 5.Then can carry out detection as follows:
Start each k primitive event detector being associated with a line, to determine that ball is that online the first side or the second side are as primitive event.
Start n event detector, to determine that instruction ball is the event in the region of its association, wherein each event detector is connected with the primitive event detector being associated with the line on the border in the region as being associated with event detector.
In the time that the primitive event detector of all connections provides corresponding information, determine event with event detector.
Fig. 6 has schematically illustrated the possible execution mode as the event detector 100 of state machine.4 incoming events or input variable A, B, C and the D that for example can be provided by one or more primitive event detectors are provided state machine.In the time that state machine arrives state 102, state machine or event detector generate or determine the concern event of its association, and this depends on the input of event detector naturally.State machine is by with its initial configuration 104 initialization.In the time of the event of generation A, state machine is transformed into state 106, in the time of the event of generation B, changes state 108 into from state 106.After the event of generation C, state machine changes the event of its last state 102 and definite its association into.Be reinitialized its initial configuration 104 from two states, 106 and 108 machines when the event D, this can be interpreted as reset signal or analog.Should be considerable time, according to the specific implementations of Fig. 6, the order of occurrence of signal A to C importantly arrives final state 102.But, can use the alternate embodiments of state machine, wherein the arrival of incoming event order is incoherent.Usually, state machine can be allowed to realize these with hardware as event detector, this can reduce the calculated load in analytical framework and accelerate overall process.
Although be only described for the subset of the event of concern, can on the basis of primitive event, determine other concern event arbitrarily.Concern event in addition can be for example patrilineal line of descent with only one son in each generation ball, one-two, shooting, ball-handling, free kick from a player to another player, kick off or corner-kick.
Self-evident, although main phase is for Association football, match illustrates, but can in the sports tournament of what its kind in office, use other execution mode of the present invention, described sports tournament is such as for example basketball, handball, volleyball match, rugby, rugby, ice hockey, hockey, polo, baseball, tennis, golf etc.
This description and figure only illustrate principle of the present invention.Therefore will be appreciated that, those skilled in the art can design various layouts, although described various layout is not described clearly in this article or illustrated, specialize principle of the present invention and will be included in its spirit and scope.In addition, in all example principles of recording herein, be intended to clearly for only for teaching purpose to help reader understanding's principle of the present invention and to be contributed to promote the design of this area by (one or more) inventor, and will be interpreted as being not limited to example and the condition recorded particularly like this.And all statements of recording principle of the present invention, aspect and execution mode and particular example thereof are herein intended to comprise its equivalent.
Be expressed as " for ... means " functional block (execution specific function) should be understood to include the functional block that is adapted to respectively the circuit of carrying out specific function.Thereby " for the means of something " also can be understood to " being adapted or can be used to the means of something ".Therefore the means that are adapted to carry out specific function do not imply that such means must carry out described function (at given time).
Comprise any functional block, shown in the figure go out various elements function can by utilize specialized hardware (as for example processor) and can with suitable software explicitly the hardware of executive software provide.In the time being provided by processor, function can be by single application specific processor, provide by single shared processing device or by multiple each processors (wherein some can be shared).And, the explicit use of term " processor " or " controller " should not be interpreted as referring to exclusively hardware that can executive software, and can implicitly include but not limited to digital signal processor (DSP) hardware, network processing unit, application-specific integrated circuit (ASIC) (ASIC), field programmable gate array (FPGA), read-only memory (ROM), random access memory (RAM) and Nonvolatile memory devices for storing software.Can also comprise other hardware (conventional and/or customization).
Those skilled in the art will be appreciated that the conceptual view of the illustrative circuit of the specific principle of the present invention of any block representation herein.Similarly, to be appreciated that, any flow chart, flow graph, state transition diagram, false code etc. represent the various processes that can substantially represent with computer-readable medium and so be carried out by computer or processor, and no matter whether such computer or processor is illustrated by explicitly.
In addition, thus below claim be incorporated in embodiment, wherein each claim can require independent of independent execution mode.Although each claim can require independent of independent execution mode, can also comprise the combination of the theme of dependent claims and each other dependent claims although should be noted that-dependent claims can refer in the claims with particular combinations-other execution mode of one or more other rights.Unless stated that particular combinations is unintentional, otherwise such combination is suggested in the text.In addition,, even if this claim is not directly made to have nothing to do with independent claims, be also intended to the feature of the claim that also comprises any other independent claims.Particularly, when dependent claims is during just at reference encoder device or transmitter, the character pair of relative decoding device or receiver also should be included and be the disclosed part of this description in this.
Should further note, in this manual or in the claims disclosed method can be realized by each the device of means with corresponding steps for carrying out these methods.
Further, should be understood that, in this specification or claim, disclosed multiple steps or function openly cannot be interpreted as in particular order.Therefore, unless such step or function due to technical reason instead of interchangeable, otherwise multiple step or function openly will or not be limited to particular order these.
In addition, single step can comprise or can be broken down into multiple sub-steps in some embodiments.Unless explicitly is got rid of, otherwise such sub-step can be included and be a disclosed part for this single step.
Claims (26)
1. one kind for detection of concern event (30; 102) device, described device comprises:
The first basis event detector (8b), described the first basis event detector is used for using sensor data stream (4) to generate the stream (10b) of the former event of first, described sensor data stream (4) is with sensing data speed carrying initial data, described initial data is associated to the determined one or more attributes of multiple objects of observation (72) with using one or more sensor tip, wherein, the data rate of the stream of the first primitive event (10b) is lower than described sensing data speed;
The second primitive event detector (8c), described the second primitive event detector is used for using described sensor data stream (4) to generate the stream (10c) of the second different primitive events, wherein, the data rate of the stream of described the second primitive event (10c) is lower than described sensing data speed; And
Event detector (16; 100), described event detector can operate to use the stream of described the first primitive event and the stream (10b, 10c) of described the second primitive event to determine concern event (30; 102).
2. device according to claim 1, wherein, described the first and second primitive event detectors (8b, 8c) can operate to use uniquely exercise data as described initial data.
3. device according to claim 2, wherein, described exercise data comprises positional information, velocity information and the acceleration information of the object of observation.
4. according to device in any one of the preceding claims wherein, wherein, described the first and second primitive event detectors (8b, 8c) can operate to use uniquely described sensor data stream (4) as input.
5. according to device in any one of the preceding claims wherein, wherein, in the positional information of first object of observation and second object of observation is indicated the predetermined neighborhood of described second object of observation in described first object of observation time, generate and approach event as described the first primitive event or described the second primitive event.
6. device according to claim 5, wherein, described predetermined neighborhood is defined by the predetermined maximal distance between described first object of observation and described second object of observation.
7. according to device in any one of the preceding claims wherein, wherein, outside the positional information of first object of observation and second object of observation is indicated the predetermined neighborhood of described second object of observation in described first object of observation time, generate remote events as described the first primitive event or described the second primitive event.
8. according to device in any one of the preceding claims wherein, wherein, in the time that the speed of the object of observation or the change of acceleration exceed predetermined threshold, generate direction and change event as described the first primitive event or described the second primitive event.
9. according to device in any one of the preceding claims wherein, wherein, in the time that the speed of the object of observation is down to below predetermined threshold, generate idle event as described the first primitive event or described the second primitive event.
10. device according to claim 9, wherein, is down to described predetermined threshold when assigning at least predetermined minimum duration when the speed of the described object of observation, only generates described idle event.
11. according to device in any one of the preceding claims wherein, wherein, in the time that the speed of the object of observation exceedes predetermined threshold, generates life event as described the first primitive event or described the second primitive event.
12. devices according to claim 11, wherein, in the time that the speed of the described object of observation exceedes described predetermined threshold and reaches at least predetermined minimum duration, only generate described life event.
13. according to device in any one of the preceding claims wherein, wherein, in the time that the component of the positional information of described first object of observation or described second object of observation exceedes predetermined threshold or is down to below predetermined threshold, generate cross-line event as described the first primitive event or described the second primitive event.
14. according to device in any one of the preceding claims wherein, wherein, when described the first basis event detector (8b) detect described the first object and described second object approach event time and change when event when described the second primitive event detector (8c) detects the direction of described second object, detect that the event of hitting is as described concern event (30; 102) event of hitting, indicates described second object to be hit by described the first object.
15. according to device in any one of the preceding claims wherein, and described device further comprises for detecting another concern event (30 by described the first primitive event and described concern event; 102) another event detector (18).
16. devices according to claim 15, wherein, when described the first basis event detector (8b) detects while approaching event and detects that while hitting event, formation object occupies event as described another concern event (30 when described event detector (16); 102).
17. devices according to claim 15, wherein, in the time that described the first basis event detector (8b) detects remote events and when described event detector (16), detect while hitting event, formation object is lost event as described another concern event (30; 102).
18. according to device in any one of the preceding claims wherein, wherein, and described event detector (16; 100) be implemented as state machine (100).
19. 1 kinds for detection of concern event (30; 102) method, described method comprises:
Use sensor data stream (4) to generate the stream (10b of the former event of first; 20), described sensor data stream (4) is with sensing data speed carrying initial data, described initial data is associated with the one or more attributes that use one or more sensor tip to determine multiple objects of observation, wherein, and the stream (10b of described the first primitive event; 20) data rate is lower than described sensing data speed;
Use described sensor data stream (4) to generate the stream (10c of the second different primitive events; 26), wherein, the stream (10c of described the second primitive event; 26) data rate is lower than described sensing data speed; And
Determine described concern event (30 with the stream of described the first primitive event and the stream of described the second primitive event; 102).
20. 1 kinds of analytical frameworks, described analytical framework is for analyzing the initial data part just sending at sensor data stream (4) with sensing data speed to identify at least one concern event (30; 102), each initial data part is associated with the one or more attributes that use one or more sensor tip to determine the object of observation, and described analytical framework comprises:
Input layer (6), described input layer comprises for using uniquely described sensor data stream (4) to generate at least first-class (10b) of primitive event and at least two or more primitive event detectors (8a-8e) of second (10c) as input; And
One or more event layers (12,14), described event layers comprises for detection of concern event (30; 102) one or more event detectors (16,18), wherein, described one or more event detector (16,18) any in only use the stream of described the first primitive event and the stream (18b, 10c) of described the second primitive event or by the stream of another other event providing in described event detector (16) as input.
21. analytical frameworks according to claim 20, wherein, described one or more event layers (12,14) described one or more event detectors connect via at least two or more primitive event detectors (8b, 8c) of network and described input layer (6).
22. analytical frameworks according to claim 21, wherein, described network is cable network.
23. according to the analytical framework described in claim 21 or 22, and wherein, the communication in described network is based on Internet protocol.
24. according to the analytical framework described in any one in claim 20 to 24, and wherein, the data rate of described first and described second (10b, 10c) of described primitive event is lower than described sensing data speed.
25. according to the analytical framework described in any one in claim 20 to 24, and wherein, the first and second primitive event detectors (8b, 8c) can operate to use uniquely the exercise data of the object of observation as described initial data.
26. 1 kinds of computer programs, described computer program for carrying out method according to claim 19 in the time moving on computers.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/EP2011/069166 WO2013064174A1 (en) | 2011-10-31 | 2011-10-31 | Apparatus and method for analyzing sensor data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104025537A true CN104025537A (en) | 2014-09-03 |
Family
ID=44925518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201180074598.3A Pending CN104025537A (en) | 2011-10-31 | 2011-10-31 | Apparatus and method for analyzing sensor data |
Country Status (7)
| Country | Link |
|---|---|
| US (1) | US20150051719A1 (en) |
| EP (1) | EP2774339A1 (en) |
| JP (1) | JP5970074B2 (en) |
| CN (1) | CN104025537A (en) |
| AU (1) | AU2011380291B2 (en) |
| BR (1) | BR112014010332A2 (en) |
| WO (1) | WO2013064174A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110235191A (en) * | 2017-01-26 | 2019-09-13 | 瑞典爱立信有限公司 | Detection system and method |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102013112317A1 (en) * | 2013-11-08 | 2015-05-13 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Apparatus and method for automatically evaluating a course of a training exercise |
| US9824112B1 (en) * | 2014-02-18 | 2017-11-21 | Google Inc. | Creating event streams from raw data |
| CN112262417B (en) * | 2018-06-14 | 2022-09-20 | 住友电气工业株式会社 | Wireless sensor system, wireless terminal device, communication control method, and communication control program |
| CN112739436A (en) * | 2018-09-27 | 2021-04-30 | 英特尔公司 | Highlight identification technique in a volumetric content creation system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001104533A (en) * | 1999-10-05 | 2001-04-17 | Mitsubishi Electric Corp | Device for aiding to judge offside |
| JP2003000788A (en) * | 2001-06-25 | 2003-01-07 | It Gem:Kk | Golf playing system by ball position information and managing the information, and method for playing golf |
| US20070043803A1 (en) * | 2005-07-29 | 2007-02-22 | Microsoft Corporation | Automatic specification of semantic services in response to declarative queries of sensor networks |
| US20080059060A1 (en) * | 2002-09-09 | 2008-03-06 | Jeremy Irish | Method For Executing User Navigational Events Triggered Through Geolocational Data Describing Zones Of Influence |
| WO2008033338A2 (en) * | 2006-09-11 | 2008-03-20 | Aman James A | System and methods for translating sports tracking data into statistics and performance measurements |
| CN101835513A (en) * | 2007-09-14 | 2010-09-15 | 克里斯蒂安·齐格 | The system that is used for capturing tennis match data |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ITRM20010045A1 (en) * | 2001-01-29 | 2002-07-29 | Consiglio Nazionale Ricerche | SYSTEM AND METHOD FOR DETECTING THE RELATIVE POSITION OF AN OBJECT COMPARED TO A REFERENCE POINT. |
| US8614741B2 (en) * | 2003-03-31 | 2013-12-24 | Alcatel Lucent | Method and apparatus for intelligent and automatic sensor control using multimedia database system |
| US9094615B2 (en) * | 2004-04-16 | 2015-07-28 | Intheplay, Inc. | Automatic event videoing, tracking and content generation |
| US20070015583A1 (en) * | 2005-05-19 | 2007-01-18 | Louis Tran | Remote gaming with live table games |
| ITRM20060110A1 (en) * | 2006-03-03 | 2007-09-04 | Cnr Consiglio Naz Delle Ricerche | METHOD AND SYSTEM FOR THE AUTOMATIC DETECTION OF EVENTS IN SPORTS ENVIRONMENT |
| NZ571953A (en) * | 2006-03-20 | 2011-10-28 | Riform Pty Ltd | A system to determine the relationship between animals based on the time they spend close to each other |
| US7508335B2 (en) * | 2006-12-20 | 2009-03-24 | Raytheon Company | Multiple sensor processing |
| JP2008211781A (en) * | 2007-02-05 | 2008-09-11 | Mitsubishi Electric Research Laboratories Inc | System for modeling movement of objects in certain environment and method executed by computer |
| US8013738B2 (en) * | 2007-10-04 | 2011-09-06 | Kd Secure, Llc | Hierarchical storage manager (HSM) for intelligent storage of large volumes of data |
| US20090262137A1 (en) * | 2008-01-10 | 2009-10-22 | Walker Jay S | Systems and methods for presenting prediction in a broadcast |
| US7671802B2 (en) * | 2008-03-17 | 2010-03-02 | Disney Enterprises, Inc. | Active player tracking |
| US8231506B2 (en) * | 2008-12-05 | 2012-07-31 | Nike, Inc. | Athletic performance monitoring systems and methods in a team sports environment |
-
2011
- 2011-10-31 EP EP11781484.8A patent/EP2774339A1/en not_active Ceased
- 2011-10-31 BR BR112014010332A patent/BR112014010332A2/en not_active Application Discontinuation
- 2011-10-31 CN CN201180074598.3A patent/CN104025537A/en active Pending
- 2011-10-31 US US14/355,109 patent/US20150051719A1/en not_active Abandoned
- 2011-10-31 JP JP2014539247A patent/JP5970074B2/en active Active
- 2011-10-31 WO PCT/EP2011/069166 patent/WO2013064174A1/en active Application Filing
- 2011-10-31 AU AU2011380291A patent/AU2011380291B2/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001104533A (en) * | 1999-10-05 | 2001-04-17 | Mitsubishi Electric Corp | Device for aiding to judge offside |
| JP2003000788A (en) * | 2001-06-25 | 2003-01-07 | It Gem:Kk | Golf playing system by ball position information and managing the information, and method for playing golf |
| US20080059060A1 (en) * | 2002-09-09 | 2008-03-06 | Jeremy Irish | Method For Executing User Navigational Events Triggered Through Geolocational Data Describing Zones Of Influence |
| US20070043803A1 (en) * | 2005-07-29 | 2007-02-22 | Microsoft Corporation | Automatic specification of semantic services in response to declarative queries of sensor networks |
| WO2008033338A2 (en) * | 2006-09-11 | 2008-03-20 | Aman James A | System and methods for translating sports tracking data into statistics and performance measurements |
| CN101835513A (en) * | 2007-09-14 | 2010-09-15 | 克里斯蒂安·齐格 | The system that is used for capturing tennis match data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110235191A (en) * | 2017-01-26 | 2019-09-13 | 瑞典爱立信有限公司 | Detection system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| BR112014010332A2 (en) | 2017-04-18 |
| EP2774339A1 (en) | 2014-09-10 |
| US20150051719A1 (en) | 2015-02-19 |
| AU2011380291B2 (en) | 2015-03-12 |
| WO2013064174A1 (en) | 2013-05-10 |
| AU2011380291A1 (en) | 2014-04-17 |
| JP5970074B2 (en) | 2016-08-17 |
| JP2015505681A (en) | 2015-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10707908B2 (en) | Method, apparatus, and computer program product for evaluating performance based on real-time data for proximity and movement of objects | |
| CN109862949B (en) | System for evaluating basketball projection performance | |
| KR101800795B1 (en) | Web-based game platform with mobile device motion sensor input | |
| CN104025537A (en) | Apparatus and method for analyzing sensor data | |
| JPWO2019225415A1 (en) | Ball game video analysis device and ball game video analysis method | |
| US20220051419A1 (en) | System and method for object tracking | |
| WO2015098420A1 (en) | Image processing device and image processing method | |
| US11710316B2 (en) | System and method for object tracking and metric generation | |
| JP7118253B2 (en) | A system for determining game scenarios in sports games | |
| CN112437487A (en) | Position positioning method, event identification method, device and computer equipment | |
| TW201723971A (en) | Method and system for live determining of a sports device | |
| RU2566942C2 (en) | Control system of tactical actions of sports team in real time | |
| WO2022035471A1 (en) | System and method for object tracking and metric generation | |
| JP2021022153A (en) | Data processor, method for processing data, and program | |
| Burkett | Technologies for Monitoring Human Player Activity Within a Competition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140903 |
|
| RJ01 | Rejection of invention patent application after publication |