CN105488794A - Spatial positioning and clustering based action prediction method and system - Google Patents

Spatial positioning and clustering based action prediction method and system Download PDF

Info

Publication number
CN105488794A
CN105488794A CN201510837116.5A CN201510837116A CN105488794A CN 105488794 A CN105488794 A CN 105488794A CN 201510837116 A CN201510837116 A CN 201510837116A CN 105488794 A CN105488794 A CN 105488794A
Authority
CN
China
Prior art keywords
information
cluster
impact point
model
frame
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.)
Granted
Application number
CN201510837116.5A
Other languages
Chinese (zh)
Other versions
CN105488794B (en
Inventor
周凡
李万华
黄镇业
陈晓燕
曹思琪
陈土丽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sun Yat Sen University
Original Assignee
Sun Yat Sen University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sun Yat Sen University filed Critical Sun Yat Sen University
Priority to CN201510837116.5A priority Critical patent/CN105488794B/en
Publication of CN105488794A publication Critical patent/CN105488794A/en
Application granted granted Critical
Publication of CN105488794B publication Critical patent/CN105488794B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a spatial positioning and clustering based action prediction method and system. The method comprises: performing spatial positioning on target points to obtain position information and motion state information of each frame of the target points; performing information coding according to the position information and the motion state information of at least two frames of continuous target points to establish models of at least two frames of information; clustering the models of the at least two frames of continuous information to obtain a clustering result; establishing a training data set according to the clustering result, and obtaining a working mode according to the training data set; and predicting an action according to the working mode. By implementing embodiments of the invention, the target points are subjected to the spatial positioning and the action is effectively predicted through a clustering technology based on externally input huge data, so that the time delays generated in a signal transmission process are reduced, the subjective delays are effectively reduced, and the user experience is improved.

Description

A kind of action prediction method and system based on space orientation and cluster
Technical field
The present invention relates to action prediction technical field, particularly relate to a kind of action prediction method and system based on space orientation and cluster.
Background technology
Space orientation technique is the gordian technique in virtual reality system.In the application of virtual reality, need user and virtual environment to carry out alternately all the time, if continue to use traditional interaction technique, the situation that Consumer's Experience is not good can be caused.Be a kind of better interactive mode alternately with natural body action, this positions the health of user with regard to needing.
Common indoor wireless location technology also has: Wi-Fi, bluetooth, infrared ray, ultra broadband, RFID, ZigBee and ultrasound wave.Current space positioning system utilizes high-speed camera can reach the sample effect of 1000 frames per second, and the switching that user carries out picture is more smooth and fine and smooth.But the general shortcoming of current space positioning system is that time delay is higher.Time delay is high causes the conversion of picture not prompt enough, causes the vertigo symptoms of user to happen occasionally.
Therefore, the time delay reduced in space positioning system is also the key component in this system.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, the invention provides a kind of action prediction method and system based on space orientation and cluster, under space orientation and the huge data based on outside input are carried out to impact point, undertaken by clustering technique effectively predicting the time delay reduced because producing in signals transmission, thus effectively reduce subjective time delay, improve the experience sense of user.
In order to solve the problems of the technologies described above, the invention provides a kind of action prediction method based on space orientation and cluster, described method comprises:
Space orientation is carried out to impact point, obtains positional information and the movement state information of described each frame of impact point;
According at least two frame continuous print, the positional information of impact point and motion state letter carry out information coding, set up the model of at least two frame continuous informations;
Cluster is carried out to the model of described at least two frame continuous informations, obtains cluster result;
Set up training dataset according to described cluster result, and obtain mode of operation according to described training dataset;
According to described mode of operation, action is predicted.
Preferably, described movement state information comprises instantaneous velocity information and acceleration information.
Preferably, positional information and the motion state letter of impact point described in described basis at least two frame continuous print carry out information coding, set up the model of at least two frame continuous informations, comprising:
Record positional information and the movement state information of described impact point in each frame;
Positional information and the motion state of the described impact point of continuous at least two frames of record are believed and carry out information coding, obtaining information coding result;
The information vector of at least bidimensional is built according to described information coding result;
According to the information vector of described at least bidimensional, obtain the model of at least two frame continuous informations.
Preferably, the described model to described at least two frame continuous informations carries out cluster, obtains cluster result, comprising:
The information vector of each at least bidimensional built is carried out category division;
Information vector identical for classification is carried out cluster, obtains cluster result.
Preferably, described mode of operation comprises normal mode of operation and prediction work pattern.
Present invention also offers a kind of action prediction system based on space orientation and cluster, described system comprises:
Locating module: for carrying out space orientation to impact point, obtains positional information and the movement state information of described each frame of impact point;
Model construction module: carry out information coding for the positional information of impact point Gen Ju at least two frame continuous print and motion state letter, sets up the model of at least two frame continuous informations;
Cluster module: for carrying out cluster to the model of described at least two frame continuous informations, obtains cluster result;
Pattern acquiring module: for setting up training dataset according to described cluster result, and obtain mode of operation according to described training dataset;
Prediction module: for predicting action according to described mode of operation.
Preferably, described movement state information comprises instantaneous velocity information and acceleration information.
Preferably, described model construction module comprises:
Information recording unit: for recording positional information and the movement state information of described impact point in each frame;
Information coding unit: positional information and motion state for recording the described impact point of at least two frames are continuously believed and carry out information coding, obtaining information coding result;
Information vector construction unit: for building the information vector of at least bidimensional according to described information coding result;
Model acquiring unit: for the information vector according to described at least bidimensional, obtains the model of at least two frame continuous informations.
Preferably, described cluster module comprises:
Category division unit: for the information vector of each at least bidimensional built is carried out category division;
Cluster cell: for information vector identical for classification is carried out cluster, obtains cluster result.
Preferably, described mode of operation comprises normal mode of operation and prediction work pattern.
In embodiments of the present invention, under impact point being carried out to space orientation and the huge data based on outside input, undertaken by clustering technique effectively predicting the time delay reduced because producing in signals transmission, thus effectively reduce subjective time delay, improve the experience sense of user.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the action prediction method based on space orientation and cluster in the embodiment of the present invention;
Fig. 2 is the schematic flow sheet of the model of foundation at least two frame continuous information in the embodiment of the present invention;
Fig. 3 is the structure composition schematic diagram of the action prediction system based on space orientation and cluster in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the action prediction method based on space orientation and cluster in the embodiment of the present invention, and as shown in Figure 1, the method comprises:
S11: carry out space orientation to impact point, obtains positional information and the movement state information of each frame of impact point;
S12: carry out information coding according to the positional information of at least two frame continuous print impact points and motion state letter, sets up the model of at least two frame continuous informations;
S13: carry out cluster to the model of at least two frame continuous informations, obtains cluster result;
S14: set up training dataset according to cluster result, and obtain mode of operation according to training dataset;
S15: action is predicted according to mode of operation.
S11 is described further:
By the mode of camera or gravity sensor, space orientation is carried out to impact point in the present embodiment, obtain the spatial positional information of this impact point; Obtained the movement state information of impact point by instruments such as gyroscope, speed sensor, accelerator and magnetometers, wherein movement state information comprises and is not limited to instantaneous velocity information and acceleration information.
In the present embodiment, adopt mathematical linguistics mode to represent the positional information of the impact point in space and status information, namely the positional information of each impact point adopts position vector the instantaneous velocity information of each impact point adopts instantaneous velocity vector the acceleration information of each impact point adopts vector acceleration
S12 is described further:
Composition graphs 2 couples of S12 are described, and Fig. 2 is the schematic flow sheet of the model of foundation at least two frame continuous information in the embodiment of the present invention, and as shown in Figure 2, this flow process comprises the following steps:
S121: the positional information of record object point and movement state information in each frame;
S122: positional information and the motion state of the impact point of continuous at least two frames of record are believed and carry out information coding, obtaining information coding result;
S123: the information vector building at least bidimensional according to information coding result;
S124: according to the information vector of at least bidimensional, obtains the model of at least two frame continuous informations.
S121 is described further:
In embodiments of the present invention, positional information and the movement state information of each frame impact point is recorded.
S122 is described further:
In the embodiment of the present invention, rank-numeral coding is carried out, wherein N >=2 to the positional information and movement state information recording at least N frame continuous print impact point, by encoding, the positional information after getting coding and movement state information.
S123 is described further:
Vectorization process is carried out to the positional information after coding and movement state information, is converted into the information of vectorization.
S124 is described further:
As follows according to information architecture at least two frame continuous information matrix models of these vectorizations:
x 1 v 1 a 1 x 2 v 2 a 2 . . . x L v L a L . . . x N v N a N ;
Wherein, N >=2 and N >=L, front L vector of definition a series of movements is key value, and N-L vector is below predicted value.
S13 is described further:
By the information vector of each at least bidimensional built is carried out category division, information vector identical for classification carried out regrouping divides a new classification into together, thus obtains cluster result.
S14 is described further
Cluster result is trained, the aiming spot be made up of N number of element moves (action element) for new data item, get the pattern of work according to these data item, wherein mode of operation has normal mode of operation and prediction work pattern, wherein N >=2.
S15 is described further:
First, work as N=L, enter into normal mode of operation, this release; When N >=L enters predictive mode, output be predicted data, carry out action reduction according to these predicted data, obtain prediction action; And compared with the data of prediction being carried out with the data transmitted, the accuracy of verification predicted data, for follow-up providing predicts the outcome more accurately.
Fig. 3 is the structure composition schematic diagram of the action prediction system based on space orientation and cluster in the embodiment of the present invention, and as shown in Figure 3, this system comprises:
Locating module: for carrying out space orientation to impact point, obtains positional information and the movement state information of each frame of impact point;
Model construction module: for carrying out information coding according to the positional information of at least two frame continuous print impact points and motion state letter, the model of foundation at least two frame continuous informations;
Cluster module: for carrying out cluster to the model of at least two frame continuous informations, obtains cluster result;
Pattern acquiring module: for setting up training dataset according to cluster result, and obtain mode of operation according to training dataset;
Prediction module: for predicting action according to mode of operation.
Preferably, movement state information comprises instantaneous velocity information and acceleration information.
Preferably, model construction module comprises:
Information recording unit: for positional information and the movement state information of record object point in each frame;
Information coding unit: positional information and motion state for recording the impact point of at least two frames are continuously believed and carry out information coding, obtaining information coding result;
Information vector construction unit: for building the information vector of at least bidimensional according to information coding result;
Model acquiring unit: for the information vector according at least bidimensional, obtains the model of at least two frame continuous informations.
Preferably, cluster module comprises:
Category division unit: for the information vector of each at least bidimensional built is carried out category division;
Cluster cell: for information vector identical for classification is carried out cluster, obtains cluster result.
Preferably, mode of operation comprises normal mode of operation and prediction work pattern.
Particularly, the principle of work of the system related functions module of the embodiment of the present invention see the associated description of embodiment of the method, can repeat no more here.
In embodiments of the present invention, under impact point being carried out to space orientation and the huge data based on outside input, undertaken by clustering technique effectively predicting the time delay reduced because producing in signals transmission, thus effectively reduce subjective time delay, improve the experience sense of user.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is that the hardware that can carry out instruction relevant by program has come, this program can be stored in a computer-readable recording medium, storage medium can comprise: ROM (read-only memory) (ROM, ReadOnlyMemory), random access memory (RAM, RandomAccessMemory), disk or CD etc.
In addition, above a kind of action prediction method and system based on space orientation and cluster that the embodiment of the present invention provides are described in detail, apply specific case herein to set forth principle of the present invention and embodiment, the explanation of above embodiment just understands method of the present invention and core concept thereof for helping; Meanwhile, for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.

Claims (10)

1., based on an action prediction method for space orientation and cluster, it is characterized in that, described method comprises:
Space orientation is carried out to impact point, obtains positional information and the movement state information of described each frame of impact point;
According at least two frame continuous print, the positional information of impact point and motion state letter carry out information coding, set up the model of at least two frame continuous informations;
Cluster is carried out to the model of described at least two frame continuous informations, obtains cluster result;
Set up training dataset according to described cluster result, and obtain mode of operation according to described training dataset;
According to described mode of operation, action is predicted.
2. action prediction method according to claim 1, is characterized in that, described movement state information comprises instantaneous velocity information and acceleration information.
3. action prediction method according to claim 1, is characterized in that, positional information and the motion state letter of impact point described in described basis at least two frame continuous print carry out information coding, sets up the model of at least two frame continuous informations, comprising:
Record positional information and the movement state information of described impact point in each frame;
Positional information and the motion state of the described impact point of continuous at least two frames of record are believed and carry out information coding, obtaining information coding result;
The information vector of at least bidimensional is built according to described information coding result;
According to the information vector of described at least bidimensional, obtain the model of at least two frame continuous informations.
4. action prediction method according to claim 1, is characterized in that, the described model to described at least two frame continuous informations carries out cluster, obtains cluster result, comprising:
The information vector of each at least bidimensional built is carried out category division;
Information vector identical for classification is carried out cluster, obtains cluster result.
5. action prediction method according to claim 1, is characterized in that, described mode of operation comprises normal mode of operation and prediction work pattern.
6., based on an action prediction system for space orientation and cluster, it is characterized in that, described system comprises:
Locating module: for carrying out space orientation to impact point, obtains positional information and the movement state information of described each frame of impact point;
Model construction module: carry out information coding for the positional information of impact point Gen Ju at least two frame continuous print and motion state letter, sets up the model of at least two frame continuous informations;
Cluster module: for carrying out cluster to the model of described at least two frame continuous informations, obtains cluster result;
Pattern acquiring module: for setting up training dataset according to described cluster result, and obtain mode of operation according to described training dataset;
Prediction module: for predicting action according to described mode of operation.
7. action prediction system according to claim 6, is characterized in that, described movement state information comprises instantaneous velocity information and acceleration information.
8. action prediction system according to claim 6, is characterized in that, described model construction module comprises:
Information recording unit: for recording positional information and the movement state information of described impact point in each frame;
Information coding unit: positional information and motion state for recording the described impact point of at least two frames are continuously believed and carry out information coding, obtaining information coding result;
Information vector construction unit: for building the information vector of at least bidimensional according to described information coding result;
Model acquiring unit: for the information vector according to described at least bidimensional, obtains the model of at least two frame continuous informations.
9. action prediction method according to claim 6, is characterized in that, described cluster module comprises:
Category division unit: for the information vector of each at least bidimensional built is carried out category division;
Cluster cell: for information vector identical for classification is carried out cluster, obtains cluster result.
10. action prediction system according to claim 6, is characterized in that, described mode of operation comprises normal mode of operation and prediction work pattern.
CN201510837116.5A 2015-11-26 2015-11-26 A kind of action prediction method and system based on space orientation and cluster Active CN105488794B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510837116.5A CN105488794B (en) 2015-11-26 2015-11-26 A kind of action prediction method and system based on space orientation and cluster

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510837116.5A CN105488794B (en) 2015-11-26 2015-11-26 A kind of action prediction method and system based on space orientation and cluster

Publications (2)

Publication Number Publication Date
CN105488794A true CN105488794A (en) 2016-04-13
CN105488794B CN105488794B (en) 2018-08-24

Family

ID=55675759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510837116.5A Active CN105488794B (en) 2015-11-26 2015-11-26 A kind of action prediction method and system based on space orientation and cluster

Country Status (1)

Country Link
CN (1) CN105488794B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106504266A (en) * 2016-09-29 2017-03-15 北京市商汤科技开发有限公司 The Forecasting Methodology of walking behavior and device, data processing equipment and electronic equipment
CN106644396A (en) * 2016-12-16 2017-05-10 捷开通讯(深圳)有限公司 Device and method for detecting delay time of VR glasses
CN106644397A (en) * 2016-12-16 2017-05-10 捷开通讯(深圳)有限公司 VR device delay time detection device and method
CN109740418A (en) * 2018-11-21 2019-05-10 中山大学 A kind of Yoga action identification method based on multiple acceleration transducers
CN114943936A (en) * 2022-06-17 2022-08-26 北京百度网讯科技有限公司 Target behavior identification method and device, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1212526A (en) * 1997-08-07 1999-03-31 松下电器产业株式会社 Device and method for detecting action vector
CN102427528A (en) * 2011-09-30 2012-04-25 北京航空航天大学 Video motion estimating method based on clustering statistics
CN103661165A (en) * 2012-09-19 2014-03-26 阿尔卑斯电气株式会社 Movement prediction device and input apparatus using the same

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1212526A (en) * 1997-08-07 1999-03-31 松下电器产业株式会社 Device and method for detecting action vector
CN102427528A (en) * 2011-09-30 2012-04-25 北京航空航天大学 Video motion estimating method based on clustering statistics
CN103661165A (en) * 2012-09-19 2014-03-26 阿尔卑斯电气株式会社 Movement prediction device and input apparatus using the same

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CRISTIAN SMINCHISESCU ET AL.: "《Discriminative Density Propagation for 3D Human Motion Estimation》", 《PROCEEDINGS OF THE 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 *
马红星等: "《基于聚类的相位相关运动估计方法》", 《光学与光电技术》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106504266A (en) * 2016-09-29 2017-03-15 北京市商汤科技开发有限公司 The Forecasting Methodology of walking behavior and device, data processing equipment and electronic equipment
WO2018059300A1 (en) * 2016-09-29 2018-04-05 北京市商汤科技开发有限公司 Method and device for predicting walking behaviour, data processing device and electronic apparatus
CN106504266B (en) * 2016-09-29 2019-06-14 北京市商汤科技开发有限公司 The prediction technique and device of walking behavior, data processing equipment and electronic equipment
US10817714B2 (en) 2016-09-29 2020-10-27 Beijing Sensetime Technology Development Co., Ltd Method and apparatus for predicting walking behaviors, data processing apparatus, and electronic device
CN106644396A (en) * 2016-12-16 2017-05-10 捷开通讯(深圳)有限公司 Device and method for detecting delay time of VR glasses
CN106644397A (en) * 2016-12-16 2017-05-10 捷开通讯(深圳)有限公司 VR device delay time detection device and method
CN109740418A (en) * 2018-11-21 2019-05-10 中山大学 A kind of Yoga action identification method based on multiple acceleration transducers
CN109740418B (en) * 2018-11-21 2022-10-14 中山大学 Yoga action identification method based on multiple acceleration sensors
CN114943936A (en) * 2022-06-17 2022-08-26 北京百度网讯科技有限公司 Target behavior identification method and device, electronic equipment and storage medium
CN114943936B (en) * 2022-06-17 2023-06-20 北京百度网讯科技有限公司 Target behavior recognition method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN105488794B (en) 2018-08-24

Similar Documents

Publication Publication Date Title
JP6972319B2 (en) Image recognition method, terminal and storage medium
US20210201147A1 (en) Model training method, machine translation method, computer device, and storage medium
CN105488794A (en) Spatial positioning and clustering based action prediction method and system
CN110472531B (en) Video processing method, device, electronic equipment and storage medium
Ma et al. An artificial intelligence-based approach for simulating pedestrian movement
CN110347873A (en) Video classification methods, device, electronic equipment and storage medium
Cheng et al. Pedestrian trajectory prediction via the Social‐Grid LSTM model
US11351458B2 (en) Method for controlling target object, apparatus, device, and storage medium
Wei et al. Learning motion rules from real data: Neural network for crowd simulation
CN113821720A (en) Behavior prediction method and device and related product
CN113723378B (en) Model training method and device, computer equipment and storage medium
CN110168542A (en) For compressing the electronic equipment of language model, for providing the electronic equipment and its operating method of recommending word
CN108604312A (en) Information processing unit, the information processing method of time series data and program
CN110955965A (en) Pedestrian motion prediction method and system considering interaction
CN109902876A (en) A kind of method, apparatus and path planning system of determining smart machine moving direction
EP4111360A1 (en) System and method for real-time interaction and coaching
Qureshi et al. Neurocomputing for internet of things: object recognition and detection strategy
Huang et al. Real-time radar gesture classification with spiking neural network on SpiNNaker 2 prototype
Artemov et al. Subsystem for simple dynamic gesture recognition using 3DCNNLSTM
Bai et al. Deep virtual-to-real distillation for pedestrian crossing prediction
CN115909465A (en) Face positioning detection method, image processing device and readable storage medium
Mai et al. From Efficient Multimodal Models to World Models: A Survey
CN113495767A (en) Interactive scene generation method and device and electronic equipment
Yang et al. Workload allocation based on user mobility in mobile edge computing
Wang et al. Data‐Driven Simulation of Pedestrian Movement with Artificial Neural Network

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Zhou Fan

Inventor after: Chen Xiaoyan

Inventor after: Zheng Guifeng

Inventor before: Zhou Fan

Inventor before: Li Wanhua

Inventor before: Huang Zhenye

Inventor before: Chen Xiaoyan

Inventor before: Cao Siqi

Inventor before: Chen Tuli

GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20160413

Assignee: LONGSE TECHNOLOGY Co.,Ltd.

Assignor: SUN YAT-SEN University

Contract record no.: X2020440000043

Denomination of invention: Spatial positioning and clustering based action prediction method and system

Granted publication date: 20180824

License type: Common License

Record date: 20200320