CN110503191A - A kind of multilayer neural network model towards video analysis - Google Patents
A kind of multilayer neural network model towards video analysis Download PDFInfo
- Publication number
- CN110503191A CN110503191A CN201910796010.3A CN201910796010A CN110503191A CN 110503191 A CN110503191 A CN 110503191A CN 201910796010 A CN201910796010 A CN 201910796010A CN 110503191 A CN110503191 A CN 110503191A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- layer
- layers
- video analysis
- 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
- 238000003062 neural network model Methods 0.000 title claims abstract description 17
- 238000012216 screening Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims abstract description 18
- 230000004913 activation Effects 0.000 claims abstract description 14
- 210000002569 neuron Anatomy 0.000 claims abstract description 12
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 6
- 238000013459 approach Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of multilayer neural network model towards video analysis, is related to video analysis field, and multilayer neural network model is linked together by multiple neurons and constitutes multitiered network, including acquisition input layer, extract layer, Screening Treatment layer and full articulamentum；The feature vector in video data is extracted by multiple extract layers, multiple Screening Treatment layers carry out further Screening Treatment to multiple feature vectors of extraction respectively, last classification is carried out finally by full articulamentum, the connection relationship established between each layer is used for by activation primitive and network parameter is continuously improved by training algorithm, improve the discrimination of target in video data, new approaches are provided for the design of network model, the selection of training algorithm, can be widely used for video analysis field.
Description
Technical field
The present invention relates to video analysis field more particularly to a kind of multilayer neural network models towards video analysis.
Background technique
Neural network has extensive and attracting prospect in fields such as System Discrimination, pattern-recognition, intelligent controls, especially
In intelligent control, people cherish a special interest to the self-learning function of neural network, and this important feature of neural network
One of the crucial key for regarding this problem of controller adaptability in solving to automatically control as, simulates the practical neural network of the mankind
Mathematical method come out since, people come to terms with this artificial neural network directly referred to as neural network, but due to
The technology is still in infancy at present, and many models can put into the mould of practical application also in abundant and improve at present
Type is more not enough, but there are no the stable multilayer neural network models towards video analysis of performance in the market.
Summary of the invention
The object of the invention is that devising a kind of multilayer nerve net towards video analysis to solve the above-mentioned problems
Network model.
The present invention through the following technical solutions to achieve the above objectives:
A kind of multilayer neural network model towards video analysis, is linked together by multiple neurons and constitutes Multilayer Network
Network, multilayer neural network model include:
Multiple acquisition input layers for being used to acquire inputting video data；
Multiple extract layers, multiple extract layers connect one to one with multiple acquisition input layers, and extract layer is for extracting video
Feature vector in data；
Multiple Screening Treatment layers, multiple Screening Treatment layers connect one to one with multiple extract layers, each Screening Treatment layer
Screening sample processing is acquired to feature vector, obtains sampling feature vectors；
Full articulamentum for finally being classified to multiple sampling feature vectors, extract layer, Screening Treatment layer and Quan Lian
It connects and is linked together between layer by activation primitive.
Further, the wherein model expression of neuron are as follows: Yi=f (Ui)、Wherein YiFor x mind
Output through member, f (Ui) it is activation primitive, w indicates the weight of i-th of input, and θ indicates the threshold value of x neuron.
Further, activation primitive uses ReLU function as activation primitive.
Further, acquisition input layer is web camera, and the signal end of web camera and the signal end of extract layer connect
It connects.
The beneficial effects of the present invention are: feature vector is extracted by multiple extract layers, multiple Screening Treatment layers are right respectively
The multiple feature vectors extracted carry out further Screening Treatment, and last classification is carried out finally by full articulamentum, by swashing
Connection relationship that function living is used to establish between each layer simultaneously continuously improves network parameter by training algorithm, in raising video data
The discrimination of target provides new approaches for the design of network model, the selection of training algorithm, can be widely used for video analysis neck
Domain.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the multilayer neural network model towards video analysis of the present invention；
Fig. 2 is the structural model figure of neuron in a kind of multilayer neural network model towards video analysis of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.Obviously, described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
In the description of the present invention, it is to be understood that, term " on ", "lower", "inner", "outside", "left", "right" etc. indicate
Orientation or positional relationship be based on the orientation or positional relationship shown in the drawings or the invention product using when usually put
Orientation or positional relationship or the orientation or positional relationship that usually understands of those skilled in the art, be merely for convenience of retouching
It states the present invention and simplifies description, rather than the equipment of indication or suggestion meaning or element must have a particular orientation, with specific
Orientation construction and operation, therefore be not considered as limiting the invention.
In addition, term " first ", " second " etc. are only used for distinguishing description, it is not understood to indicate or imply relatively important
Property.
In the description of the present invention, it is also necessary to which explanation is unless specifically defined or limited otherwise, " setting ", " even
Connect " etc. terms shall be understood in a broad sense, for example, " connection " may be a fixed connection, may be a detachable connection, or integrally connect
It connects；It can be mechanical connection, be also possible to be electrically connected；It can be and be directly connected to, can also be indirectly connected with by intermediary, it can
To be the connection inside two elements.For the ordinary skill in the art, can understand as the case may be above-mentioned
The concrete meaning of term in the present invention.
With reference to the accompanying drawing, detailed description of the preferred embodiments.
As shown in Figure 1, a kind of multilayer neural network model towards video analysis, linked together structure by multiple neurons
At multitiered network, multilayer neural network model includes:
Multiple acquisition input layers for being used to acquire inputting video data；
Multiple extract layers, multiple extract layers connect one to one with multiple acquisition input layers, and extract layer is for extracting video
Feature vector in data；
Multiple Screening Treatment layers, multiple Screening Treatment layers connect one to one with multiple extract layers, each Screening Treatment layer
Screening sample processing is acquired to feature vector, obtains sampling feature vectors；
Full articulamentum for finally being classified to multiple sampling feature vectors, extract layer, Screening Treatment layer and Quan Lian
It connects and is linked together between layer by activation primitive.
As shown in Fig. 2, the wherein model expression of neuron are as follows: Yi=f (Ui)、Wherein YiFor x
The output of neuron, f (Ui) it is activation primitive, w indicates the weight of i-th of input, and θ indicates the threshold value of x neuron.
Activation primitive uses ReLU function as activation primitive.
Acquisition input layer is web camera, and the signal end of web camera and the signal end of extract layer connect.
The feature vector in video data is extracted by multiple extract layers, multiple Screening Treatment layers are respectively to the multiple of extraction
Feature vector carries out further Screening Treatment, and last classification is carried out finally by full articulamentum, is used for by activation primitive
The connection relationship established between each layer simultaneously continuously improves network parameter by training algorithm, improves the identification of target in video data
Rate provides new approaches for the design of network model, the selection of training algorithm, can be widely used for video analysis field.
The limitation that technical solution of the present invention is not limited to the above specific embodiments, it is all to do according to the technique and scheme of the present invention
Technology deformation out, falls within the scope of protection of the present invention.
Claims (4)
1. a kind of multilayer neural network model towards video analysis, is linked together by multiple neurons and constitutes multitiered network,
It is characterized in that, multilayer neural network model includes:
Multiple acquisition input layers for being used to acquire inputting video data；
Multiple extract layers, multiple extract layers connect one to one with multiple acquisition input layers, and extract layer is for extracting video data
In feature vector；
Multiple Screening Treatment layers, multiple Screening Treatment layers connect one to one with multiple extract layers, and each Screening Treatment layer is to spy
Sign vector is acquired screening sample processing, obtains sampling feature vectors；
Full articulamentum for finally being classified to multiple sampling feature vectors, extract layer, Screening Treatment layer and full articulamentum
Between linked together by activation primitive.
2. a kind of multilayer neural network model towards video analysis according to claim 1, which is characterized in that wherein refreshing
Model expression through member are as follows: Yi=f (Ui)、Wherein YiFor the output of x neuron, f (Ui) it is activation
Function, w indicate the weight of i-th of input, and θ indicates the threshold value of x neuron.
3. a kind of multilayer neural network model towards video analysis according to claim 2, which is characterized in that activation letter
Number uses ReLU function as activation primitive.
4. a kind of multilayer neural network model towards video analysis according to claim 1, which is characterized in that acquisition is defeated
Entering layer is web camera, and the signal end of web camera and the signal end of extract layer connect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910796010.3A CN110503191A (en) | 2019-08-27 | 2019-08-27 | A kind of multilayer neural network model towards video analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910796010.3A CN110503191A (en) | 2019-08-27 | 2019-08-27 | A kind of multilayer neural network model towards video analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110503191A true CN110503191A (en) | 2019-11-26 |
Family
ID=68588429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910796010.3A Pending CN110503191A (en) | 2019-08-27 | 2019-08-27 | A kind of multilayer neural network model towards video analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110503191A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090447A (en) * | 2017-12-19 | 2018-05-29 | 青岛理工大学 | Hyperspectral image classification method and device under double branch's deep structures |
| CN108875912A (en) * | 2018-05-29 | 2018-11-23 | 天津科技大学 | A kind of neural network model for image recognition |
| CN109447977A (en) * | 2018-11-02 | 2019-03-08 | 河北工业大学 | A kind of defects of vision detection method based on multispectral depth convolutional neural networks |
| CN109993220A (en) * | 2019-03-23 | 2019-07-09 | 西安电子科技大学 | Multi-source Remote Sensing Images Classification method based on two-way attention fused neural network |
| US20190236454A1 (en) * | 2018-01-24 | 2019-08-01 | Wai Kit Ricky FOK | Parallel residual neural network architecture and system and method for training a residual neural network |
| CN110083700A (en) * | 2019-03-19 | 2019-08-02 | 北京中兴通网络科技股份有限公司 | A kind of enterprise's public sentiment sensibility classification method and system based on convolutional neural networks |
-
2019
- 2019-08-27 CN CN201910796010.3A patent/CN110503191A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090447A (en) * | 2017-12-19 | 2018-05-29 | 青岛理工大学 | Hyperspectral image classification method and device under double branch's deep structures |
| US20190236454A1 (en) * | 2018-01-24 | 2019-08-01 | Wai Kit Ricky FOK | Parallel residual neural network architecture and system and method for training a residual neural network |
| CN108875912A (en) * | 2018-05-29 | 2018-11-23 | 天津科技大学 | A kind of neural network model for image recognition |
| CN109447977A (en) * | 2018-11-02 | 2019-03-08 | 河北工业大学 | A kind of defects of vision detection method based on multispectral depth convolutional neural networks |
| CN110083700A (en) * | 2019-03-19 | 2019-08-02 | 北京中兴通网络科技股份有限公司 | A kind of enterprise's public sentiment sensibility classification method and system based on convolutional neural networks |
| CN109993220A (en) * | 2019-03-23 | 2019-07-09 | 西安电子科技大学 | Multi-source Remote Sensing Images Classification method based on two-way attention fused neural network |
Non-Patent Citations (3)
| Title |
|---|
| 戴凤智等: "基于深度学习的视频跟踪研究进展综述", 《计算机工程与应用》 * |
| 杨远飞等: "改进的深度卷积网络在交通标志识别中的应用", 《电视技术》 * |
| 郑卓等: "高分辨率遥感影像场景的多尺度神经网络分类法", 《测绘学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lv et al. | Generative adversarial networks for parallel transportation systems | |
| CN106295568B (en) | The mankind's nature emotion identification method combined based on expression and behavior bimodal | |
| CN108764059B (en) | Human behavior recognition method and system based on neural network | |
| CN104992223B (en) | Intensive Population size estimation method based on deep learning | |
| CN108764207A (en) | A kind of facial expression recognizing method based on multitask convolutional neural networks | |
| CN109101865A (en) | A kind of recognition methods again of the pedestrian based on deep learning | |
| CN106803301A (en) | A kind of recognition of face guard method and system based on deep learning | |
| CN110287805A (en) | Micro- expression recognition method and system based on three stream convolutional neural networks | |
| CN104063719A (en) | Method and device for pedestrian detection based on depth convolutional network | |
| CN105701467A (en) | Many-people abnormal behavior identification method based on human body shape characteristic | |
| CN103955671B (en) | Human behavior recognition method based on rapid discriminant common vector algorithm | |
| CN109190561A (en) | Face identification method and system in a kind of video playing | |
| Jiang et al. | A cross-modal multi-granularity attention network for RGB-IR person re-identification | |
| CN109376613A (en) | Video brainpower watch and control system based on big data and depth learning technology | |
| CN105590099A (en) | Multi-user behavior identification method based on improved convolutional neural network | |
| Rabiee et al. | Crowd behavior representation: an attribute-based approach | |
| CN109271912A (en) | Video classification methods, device, electronic equipment and storage medium | |
| Cai et al. | A robust interclass and intraclass loss function for deep learning based tongue segmentation | |
| CN107341471B (en) | A kind of Human bodys' response method based on Bilayer condition random field | |
| Lee et al. | Fast object localization using a CNN feature map based multi-scale search | |
| CN114937298A (en) | Micro-expression recognition method based on feature decoupling | |
| CN106991400A (en) | A kind of fire hazard smoke detecting method and device | |
| CN113705384A (en) | Facial expression recognition method considering local space-time characteristics and global time sequence clues | |
| CN113343927A (en) | Intelligent face recognition method and system suitable for facial paralysis patient | |
| CN105809200A (en) | Biologically-inspired image meaning information autonomous extraction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191126 |
|
| RJ01 | Rejection of invention patent application after publication |