CN104616023A - Object outline detection and recognition system and object outline recognition method - Google Patents
Object outline detection and recognition system and object outline recognition method Download PDFInfo
- Publication number
- CN104616023A CN104616023A CN201510064774.5A CN201510064774A CN104616023A CN 104616023 A CN104616023 A CN 104616023A CN 201510064774 A CN201510064774 A CN 201510064774A CN 104616023 A CN104616023 A CN 104616023A
- Authority
- CN
- China
- Prior art keywords
- contour
- recognition system
- anomalous event
- dictionary
- object outline
- 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
-
- 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
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
- G06F18/21345—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis enforcing sparsity or involving a domain transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/513—Sparse representations
Abstract
The invention belongs to the frontier defense supervise and control technical field, and particularly relates to an object outline detection and recognition system and an object outline recognition method. The object outline detection and recognition system comprises a data collection device, a data storage and control device, a wireless reception and transmission device and a power management device, wherein an output end of the data collection device is connected with an input end of the data storage and control device, an output end of the data storage and control device is connected with an input end of the wireless reception and transmission device, and the wireless reception and transmission device is connected with a wireless reception and transmission module of the object outline detection and recognition system in wireless mode. The object outline detection and recognition system and the object outline recognition method collect outline features of different objects through multiple groups of thermopile infrared temperature sensors, send the outline features to a computer in wireless mode, and use an object recognition algorithm based on dictionary learning to perform recognition. The object outline detection and recognition system and the object outline recognition method have the advantages of being wide in detection range, high in concealment performance, strong in reliability and the like, and adopt an anomalous event processing mechanism, and therefore extendibility and adaptability of the object outline detection and recognition system are improved.
Description
Technical field
The present invention relates to frontier defense safety monitoring technology field, especially a kind of contour of object detects recognition system and outline identification method.
Background technology
Realize having great importance to national security to the real-time monitoring in border or depopulated zone.In the age that this takes place frequently across border activity, the effective way improving boundary line safety is all being found by countries all in the world.China's boundary line on land total length about 22, more than 000 kilometer, wherein a lot of place is all unoccupied, if to these local implementation automatic monitorings, will can greatly improve national security prevention ability undoubtedly.
In the current existing supervisory system of China, nearly 95% be all adopt manually monitored by monitor, the Intelligent Measurement to certain event and identification cannot be realized, large to the dependence of people.Due to the factor such as sleepy, tired, monitor staff is difficult to ensure all the period of time effective monitoring, there is information utilization and the deficiency such as system works efficiency is low, poor reliability.In addition, early warning effect and the real-time response performance of existing frontier defense safety monitoring system also fall flat, and the data bulk that wireless video monitoring system collects is very large, for the depopulated zone of very long border or the length and breadth of land, the data transmit in net, stored and receive are considerable and cost is too high, therefore also result in bulk information redundancy and are difficult to intelligentized application.
Summary of the invention
For the problems referred to above, utilize different classes of object appearance profile feature different, in conjunction with compressive sensing theory, provide a kind of contour of object to detect recognition system and outline identification method.Front end data acquisition platform adopts Novel hot pile infrared array sensor and FPGA processor to gather the contour feature of object, has sensing range wide, and disguised high, structure is simple, the features such as reliability is strong.
For achieving the above object, present invention employs following technical scheme:
A kind of contour of object detects recognition system, comprises data collector, data recording control apparatus, wireless transmitter and electric power controller.Data collector, data recording control apparatus, wireless transmitter and electric power controller composition front end data acquisition platform.Described data collector, its output terminal is connected with the input end of data recording control apparatus.Described data recording control apparatus, its output terminal is connected with the input end of wireless transmitter.Described wireless transmitter and outline identification system wireless transmitter between wireless connections.
Described data collector comprises some groups of thermopile IR array of temperature sensor.
Described data recording control apparatus comprises FPGA processor, crystal oscillating circuit, reset circuit and download configuration circuit.
Described wireless transmitter comprises wireless transmitting terminals and wireless interface receiving end.
Described electric power controller is respectively data collector, data recording control apparatus and wireless transmitter and powers.
Described thermopile IR array of temperature sensor adopts MLX90620 module.
Described FPGA processor adopts EP1C3T144 chip.
Described wireless transmitter adopts nRF24L01 radio transmitting and receiving chip.
Described thermopile IR array of temperature sensor is arranged on fixed support, and the angular field of view of thermopile IR array of temperature sensor is 60 °.Thermopile IR array of temperature sensor is arranged on fixed support or ties up on certain stable object, and requirement is that visual angle, site is enough wide, and sensor detects visual angle can reach 60 degree.
The invention still further relates to a kind of contour of object and detect recognition methods, the method is based on the Target Recognition Algorithms of line dictionary learning, comprises KPCA Data Dimensionality Reduction, dictionary initialization, rarefaction representation classification, anomalous event treatment mechanism and online dictionary updating.The method comprises KPCA Data Dimensionality Reduction, dictionary initialization, rarefaction representation classification, anomalous event process and online dictionary updating four steps.Specifically, described a kind of contour of object detects recognition methods, and a series of different training sample first front-end acquisition device collected is converted into the proper vector of same dimension by dimensionality reduction.Then eigenvector projection is constructed dictionary to lower dimensional space, by this dictionary, rarefaction representation and identification are carried out to test sample book, whether can belong to anomalous event by discriminating test sample according to sparse coefficient and residual values.If anomalous event, be then classified to anomalous event storehouse; If not, then according to residual error size determination object generic.In anomalous event storehouse, by cluster, anomalous event is classified, after same class anomalous event occurs reaching certain frequency, this class event is removed from abnormal data storehouse, puts into dictionary, realize the online updating of dictionary.
From above technical scheme, front end data acquisition platform of the present invention adopts the object of thermopile infrared sensor array to the region through being provided with this platform to carry out data acquisition, data recording control apparatus is adopted to obtain the contour of object data of sensor array output, and adopt wireless transmitter that the contour of object data of collection are sent to contour of object recognition system, contour of object recognition system judges object classification according to a kind of Target Recognition Algorithms based on online dictionary learning, the method is first to initialization dictionary after training sample dimensionality reduction, by this dictionary, rarefaction representation and identification are carried out to test sample book, and a kind of anomalous event treatment mechanism is proposed, first record is carried out to emerging anomalous event, stored in anomalous event storehouse, and for anomalous event storehouse, when the frequency that a certain class anomalous event occurs is abundant, changed to regular event, realize the online updating of dictionary, and remove from anomalous event storehouse.The benefit done like this is can the different situation of adaptive testing sample dimension, and can process abnormal conditions and judge, improves the extensibility of system, makes algorithm be adaptive to different situations.
Tool of the present invention has the following advantages:
1, adopt thermopile infrared sensor array acquisition data, there is sensing range wide, low-power consumption, good concealment, integrated level high.
2, system identification goes out automatic alarm after specific objective, decreases the human resources of monitor staff, in turn ensure that the effective monitoring of all the period of time while realizing Intelligent Measurement and identification.
3, outline identification algorithm adopts core principle component analysis method dimensionality reduction, will no longer by the constraint of linearly inseparable pattern through nonlinear transformation algorithm, and can the different situation of adaptive testing sample dimension.
4, propose a kind of anomalous event treatment mechanism, can process abnormal conditions and judge, and online updating dictionary in due course, improve the extensibility of system, make algorithm be adaptive to different situations.
Accompanying drawing explanation
Fig. 1 is structural representation of the present invention;
Fig. 2 is data collector and data recording control apparatus wiring schematic diagram;
Fig. 3 is the pin schematic diagram of FPGA processor in data recording control apparatus;
Fig. 4 is the circuit theory diagrams of reset circuit in data recording control apparatus;
Fig. 5 is the circuit theory diagrams of crystal oscillating circuit in data recording control apparatus;
Fig. 6 is the circuit theory diagrams of download configuration circuit in data recording control apparatus;
Fig. 7 is the circuit theory diagrams of wireless transmitter;
Fig. 8 is power circuit principle figure in electric power controller;
Fig. 9 is dictionary initialization flowchart;
Figure 10 is anomalous event treatment mechanism process flow diagram.
Wherein:
1, data collector, 2, data recording control apparatus, 3, wireless transmitter, 4, electric power controller, 5, outline identification system.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described:
As shown in Figure 1, a kind of contour of object detects recognition system, comprises front end data acquisition platform and outline identification system 5.The contour of object data of front end data acquisition platform collection send to outline identification system 5 by wireless transmitter, then adopt a kind of contour of object recognition methods based on online dictionary learning to judge object generic.Front end data acquisition platform comprises data collector 1, data recording control apparatus 2, wireless transmitter 3 and electric power controller 4.Described data collector 1, its output terminal is connected with the input end of data recording control apparatus 2.Described data recording control apparatus 2, its output terminal is connected with the input end of wireless transmitter 3.Wireless connections between described wireless transmitter 3 and the wireless transmitter of outline identification system 5.The wireless transmitter of outline identification system is connected with PC by USB interface.
Described data collector 1, adopts thermopile IR array of temperature sensor and MLX90620 module, for captures object two-dimensional silhouette image information.Described thermopile IR array of temperature sensor is arranged on distance floor level and is about on the fixed support of 1 meter.MLX90620 is whole school's standard 16 × 4 pixel IR array, is integrated in industrial standard four pin TO-39 encapsulation, comprises 64 IR pixels, and each pixel, to having low noise chopper amplifier and high-speed ADC, exports and there is inner RAM, and pass through I
2c communicates acquisition.Thermopile IR array of temperature sensor is the signal perception unit of the non-contact temperature sensor composition of 16 × 4, has VDD, VSS, SDA and SCL tetra-pins.As shown in Figure 2, data collector comprises chip U1, its power pins VDD meets 3.3VCC, the direct ground connection of pin VSS, the indirect electric capacity C1 of power pins VDD and grounding pin VSS, clock pins SCL divide two-way, resistance R1 of leading up to meets 3.3VCC, and another road connects the 141st pin of chip U2D, and data pin SDA also divides two-way, resistance R2 of leading up to meets 3.3VCC, and another road connects the 140th pin of chip U3D.
Described data recording control apparatus 2 comprises FPGA processor, crystal oscillating circuit, reset circuit and download configuration circuit.Described FPGA processor adopts the fpga chip EP1C3T144 chip of CycloneI series.Described crystal oscillating circuit and the output terminal of reset circuit, be connected with the input end of FPGA processor respectively.Data recording control apparatus, for the collection of data, storage, process and transmitting-receiving.The present invention adopts the crystal oscillator of 20MHz as global clock, when other circuit need the clock of different frequency, is obtained by fpga chip frequency division.The structural representation of the structural representation FPGA processor of FPGA processor in data recording control apparatus as shown in Figure 3.FPGA processor comprises U2A, U2B, U2C and U2D tetra-chips.
The circuit theory diagrams of reset circuit in data recording control apparatus as shown in Figure 4.Reset circuit comprise resistance R3 with R4 in parallel after meet 3.3VCC, resistance R3 connects with pushbutton switch S1, and resistance R4 connects with pushbutton switch S2, ground connection after pushbutton switch S1, S2 parallel connection, and the anode of diode D1 is connected between resistance R4 and pushbutton switch S2.Between resistance R3 with pushbutton switch S1, extension line RESET is connected with the 92nd pin of chip U2C, and between resistance R4 with pushbutton switch S2, extension line nCONFIG is connected with the 14th pin of chip U2A.Pushbutton switch S1, as software reset, resets according to personal code work; Pushbutton switch S2 is as hardware reset, and when pressing the button switch S 2, label nCONFIG goes between as low level, and now all FPGA codes are read FPGA processor again inside configuring chip A1, and program restarts to run.
The circuit theory diagrams of crystal oscillating circuit in data recording control apparatus as shown in Figure 5.Described crystal oscillating circuit comprises chip Y1, its 2nd pin ground connection, and its 3rd pin connects the 93rd pin of chip U2C, and its 4th pin divides two-way, leads up to electric capacity C2 ground connection, and another road meets 3.3VCC, and active crystal oscillator provides the global clock of 20MHz for system.
The circuit theory diagrams of download configuration circuit in data recording control apparatus as shown in Figure 6.Described download configuration circuit comprises configuring chip A1 and jtag interface JP1, the 1st of JP2, jtag interface JP1, 3, 5, 9 pins respectively with the 88th of chip U2C, 90, 89, 95 pins are connected, the 1st of jtag interface JP2, 5, 7, 9 pins respectively with the 24th of chip U2A, 14, 13, 25 pins are connected, and the 3rd pin of jtag interface JP2 is connected with the 86th pin of chip U2C, the 1st of configuring chip A1, 2, 5, 6 pins respectively with the 12nd of chip U2A, 13, 25, 24 pins are connected, the 3rd of configuring chip A1, 7, 8 pins meet 3.3VCC respectively, and the 7th, 8 pins pass through electric capacity C3 ground connection, its 4th pin ground connection, resistance R8, R9, one end of R13 respectively with the 22nd of chip U2A, 23, 21 pins are connected, resistance R8, R9, ground connection after the other end parallel connection of R13, resistance R10, one end of R11 respectively with the 87th of chip U2C, 86 pins are connected, and one end of resistance R12 is connected with the 14th pin of chip U2A, resistance R10, R11, 3.3VCC is met after the other end parallel connection of R12.If when being downloaded by jtag interface JP1, need after system power failure again to download to FPGA processor, if when being downloaded by jtag interface JP2, user program code will be stored in configuring chip A1, after system powers at every turn, user program code, by automatically reading in FPGA processor from configuring chip A1, then runs.
As the circuit theory diagrams of the wireless transmitter of Fig. 7, described wireless transmitter 3 comprises chip U3, it is the 1st years old, 2, 3, 4, 5, 6 pins respectively with the 60th of chip U2B, 59, 58, 57, 56, 55 pins are connected, it is the 9th years old, the indirect electric capacity X1 of 10 pins and resistance R15, then respectively by electric capacity C10, C11 ground connection, its the 11st pin is by electric capacity C12 ground connection, by C4 ground connection, be connected with the 12nd pin of chip U3 by inductance L 2, its the 12nd pin is connected with the 13rd pin of chip U3 by inductance L 1, its the 13rd pin is by inductance L 3, as RFI/O after electric capacity C5, stable RF can be provided to export to antenna, its the 15th pin and the 18th pin are by C8 ground connection, by C9 ground connection, then power supply 3.3VCC is met, its the 16th pin is by R14 ground connection, its the 19th pin is by electric capacity C7 ground connection.Front-end data acquisition device is collected information data transmission to outline identification system by wireless by wireless transmitter, and outline identification system utilizes according to the digital signal collected again carries out processing, identifying based on the specific objective recognizer of dictionary learning.
Position electric power controller as shown in Figure 8, described electric power controller 4 comprises chip U4, chip U5 and interface J3, the 2nd of interface J3, 3 pin ground connection, 1st pin of interface J3 directly meets 5VCC, the 1st of chip U4, electric capacity C14 and C13 is had between 3 pins, wherein the 3rd pin meets 5VCC, 2nd pin of chip U4 is connected with the 1st pin by electric capacity C15, wherein the 1st pin ground connection, 2nd pin meets 3.3VCC, 3rd pin one tunnel of chip U5 meets 3.3VCC, C16 of separately leading up to is connected with the 1st pin, 2nd pin one tunnel of chip U5 meets 1.5VCC, C17 of separately leading up to is connected with the 1st pin, wherein the 1st pin ground connection, electric capacity C18, C19, C20, C21 is in parallel, one termination 1.5VCC, other end ground connection, electric capacity C22, C23, C24, C25, C26, C27, C28, C29, C30 is in parallel, one termination 3.3VCC, other end ground connection.Described electric power controller 4 is respectively data collector 1, data recording control apparatus 2 and wireless transmitter 3 and powers.
Described front end data acquisition platform comprises data collector 1, data recording control apparatus 2, wireless transmitter 3 and electric power controller 4.In the present invention, front end data acquisition platform is at least 1 group.When supervisory system of the present invention comprises many group thermopile IR array of temperature sensor, front end data acquisition platform composition wireless sensor network will be organized more, carry out collection and the transmission of data.
The invention still further relates to a kind of contour of object recognition methods based on online dictionary learning and comprise KPCA Data Dimensionality Reduction, dictionary initialization, rarefaction representation classification, anomalous event treatment mechanism and online dictionary updating.The detailed process of the method is as follows:
1, KPCA Data Dimensionality Reduction: front end data acquisition platform primary responsibility data acquisition, suppose respectively to a people, a people draws chest, a people squats down through these three kinds of situations collection training samples, each class sample number is N number of, due to the difference of everyone speed of travel, the sample dimension collected is different.By core principle component analysis method (concrete visible list of references: Kernel PCA for Feature Extraction and De-Noising in Non-linear Regression) by 3N training sample respectively by Nonlinear Mapping in nuclear space, and extract major component to eliminate redundant information, be translated into the proper vector of same dimension simultaneously, to facilitate structure dictionary, this method has good robustness to the speed of travel.
2, dictionary initialization: as shown in Figure 9, respectively to a people, a people draws chest, people this three classes event of squatting down prepares several samples, carry out Data Dimensionality Reduction respectively, obtain the proper vector of same dimension in lower dimensional space, form normalized vector as dictionary atom, dictionary atom is pressed row permutation and combination, initialized dictionary can be obtained.
3, rarefaction representation is classified: when having object in sensor array visual field through out-of-date, front-end acquisition device image data, the data collected are test sample book, first Data Dimensionality Reduction is carried out to test sample book and obtain proper vector, and by dictionary, rarefaction representation (concrete visible list of references: Robust face recognition via sparse representation) is carried out to proper vector, reconstruct original signal respectively according to sparse coefficient of all categories and calculate residual error, if the residual error calculated is greater than threshold value between class, be judged to be new events, and be included into anomalous event storehouse, otherwise according to the minimum classification decision principle classification of residual error.
4, anomalous event treatment mechanism and online dictionary updating: as shown in Figure 10, consider the complicacy of reality, all likely occur anomalous event at any time.Anomalous event refers to the new events be not comprised in inside dictionary.For the process of anomalous event, construct an anomalous event storehouse, if judged result is an anomalous event in previous step, then this event is put into anomalous event storehouse; Otherwise kind judging minimum for residual error is the classification of sample and exports.In anomalous event storehouse, by cluster, anomalous event is classified, after same class anomalous event occurs reaching certain frequency, this class event is removed from abnormal data storehouse, puts into dictionary, realize the online updating of dictionary.
When object is through one group of thermopile IR array of temperature sensor or by the wireless sensor network organized thermopile IR array of temperature sensor more and form, thermopile IR array of temperature sensor gathers the two-dimensional silhouette image information of object.Data recording control apparatus gathers the output state of thermopile IR array of temperature sensor at regular intervals, and these states are wirelessly sent to contour of object recognition system.Outline identification system judges object classification according to a kind of Target Recognition Algorithms based on online dictionary learning.In a word, it is wide that the present invention has sensing range, disguised high, and the features such as reliability is strong adopt anomalous event treatment mechanism, improve the extensibility of system, and adaptivity.
Above-described embodiment is only be described the preferred embodiment of the present invention; not scope of the present invention is limited; under not departing from the present invention and designing the prerequisite of spirit; the various distortion that those of ordinary skill in the art make technical scheme of the present invention and improvement, all should fall in protection domain that claims of the present invention determines.
Claims (10)
1. contour of object detects a recognition system, it is characterized in that: comprise data collector, data recording control apparatus, wireless transmitter and electric power controller;
Described data collector, its output terminal is connected with the input end of data recording control apparatus; Described data recording control apparatus, its output terminal is connected with the input end of wireless transmitter; Described wireless transmitter and outline identification system wireless transmitter between wireless connections;
Described data collector comprises some groups of thermopile IR array of temperature sensor;
Described data recording control apparatus comprises FPGA processor, crystal oscillating circuit, reset circuit and download configuration circuit;
Described wireless transmitter comprises wireless transmitting terminals and wireless interface receiving end;
Described electric power controller is respectively data collector, data recording control apparatus and wireless transmitter and powers.
2. a kind of contour of object according to claim 1 detects recognition system, it is characterized in that: described thermopile IR array of temperature sensor adopts MLX90620 module.
3. a kind of contour of object according to claim 1 detects recognition system, it is characterized in that: described FPGA processor adopts EP1C3T144 chip.
4. a kind of contour of object according to claim 1 detects recognition system, it is characterized in that: described wireless transmitter adopts nRF24L01 radio transmitting and receiving chip.
5. a kind of contour of object according to claim 2 detects recognition system, it is characterized in that: described thermopile IR array of temperature sensor is arranged on fixed support, and the angular field of view of thermopile IR array of temperature sensor is 60 °.
6. contour of object detects a recognition methods, it is characterized in that: the method comprises the following steps:
(1) KPCA Data Dimensionality Reduction;
(2) dictionary initialization;
(3) rarefaction representation classification;
(4) anomalous event process and online dictionary updating.
7. a kind of contour of object according to claim 6 detects recognition methods, it is characterized in that: in step (1), described KPCA Data Dimensionality Reduction be a series of different training sample that front-end acquisition device is collected through Nonlinear Mapping in nuclear space, and extract major component to eliminate redundant information, be translated into the proper vector of same dimension simultaneously.
8. a kind of contour of object according to claim 6 detects recognition methods, it is characterized in that: in step (2), described dictionary initialization will carry out Data Dimensionality Reduction respectively for each class event prepares several samples in advance, obtain the proper vector of same dimension in lower dimensional space, initialized dictionary can be obtained by row permutation and combination.
9. a kind of contour of object according to claim 6 detects recognition methods, it is characterized in that: in step (3), described rarefaction representation classification carries out rarefaction representation by after test sample book dimensionality reduction by dictionary, reconstruct original signal respectively according to sparse coefficient of all categories and calculate residual error, realizing anomalous event and other judgement of object type according to residual error size and mutual relationship thereof.
10. a kind of contour of object according to claim 6 detects recognition methods, it is characterized in that: in step (4), described anomalous event process and online dictionary updating first carry out record to emerging anomalous event, stored in anomalous event storehouse, and for anomalous event storehouse, when the frequency that a certain class anomalous event occurs is abundant, changed to regular event, realize the online updating of dictionary, and remove from anomalous event storehouse.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710555808.XA CN107480695A (en) | 2015-02-06 | 2015-02-06 | A kind of contour of object detection recognition method |
| CN201510064774.5A CN104616023A (en) | 2015-02-06 | 2015-02-06 | Object outline detection and recognition system and object outline recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510064774.5A CN104616023A (en) | 2015-02-06 | 2015-02-06 | Object outline detection and recognition system and object outline recognition method |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710555808.XA Division CN107480695A (en) | 2015-02-06 | 2015-02-06 | A kind of contour of object detection recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104616023A true CN104616023A (en) | 2015-05-13 |
Family
ID=53150460
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710555808.XA Pending CN107480695A (en) | 2015-02-06 | 2015-02-06 | A kind of contour of object detection recognition method |
| CN201510064774.5A Pending CN104616023A (en) | 2015-02-06 | 2015-02-06 | Object outline detection and recognition system and object outline recognition method |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710555808.XA Pending CN107480695A (en) | 2015-02-06 | 2015-02-06 | A kind of contour of object detection recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN107480695A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113237567A (en) * | 2021-04-23 | 2021-08-10 | 广州碳思科技有限公司 | Device and method for recognizing object contour based on temperature difference |
| US11350264B2 (en) | 2018-07-25 | 2022-05-31 | Samsung Electronics Co., Ltd. | Method and apparatus for establishing device connection |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280417A (en) * | 2018-01-18 | 2018-07-13 | 苏州折衍光电科技有限公司 | A kind of finger vena method for quickly identifying |
| CN115629783B (en) * | 2022-10-27 | 2023-05-26 | 北方工业大学 | Model updating method for protecting privacy and resisting abnormal data in mobile crowd sensing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11355761A (en) * | 1998-06-10 | 1999-12-24 | Hitachi Ltd | Monitor system |
| CN1389710A (en) * | 2002-07-18 | 2003-01-08 | 上海交通大学 | Multiple-sensor and multiple-object information fusing method |
| CN101017591A (en) * | 2007-02-06 | 2007-08-15 | 重庆大学 | Video safety prevention and monitoring method based on biology sensing and image information fusion |
| CN101236605A (en) * | 2008-02-29 | 2008-08-06 | 重庆大学 | Human body intelligent recognition method and system based on infrared signal |
| CN204423397U (en) * | 2015-02-06 | 2015-06-24 | 安徽大学 | A kind of contour of object detects recognition system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663425B (en) * | 2012-03-29 | 2014-03-05 | 浙江大学 | Combined target segmentation and identification method based on shape sparse representation |
| CN102938070B (en) * | 2012-09-11 | 2016-05-18 | 广西科技大学 | A kind of behavior recognition methods based on action subspace and weight behavior model of cognition |
| CN103020594B (en) * | 2012-12-03 | 2016-01-20 | 清华大学苏州汽车研究院（吴江） | On-line study is utilized to eliminate the fatigue state detection method of driver individual difference |
| CN104091151A (en) * | 2014-06-30 | 2014-10-08 | 南京信息工程大学 | Vehicle identification method based on Gabor feature extraction and sparse representation |
| CN104156979B (en) * | 2014-07-25 | 2016-09-14 | 南京大学 | Deviant Behavior online test method in a kind of video based on gauss hybrid models |
| CN104268594B (en) * | 2014-09-24 | 2017-12-19 | 中安消技术有限公司 | A kind of video accident detection method and device |
-
2015
- 2015-02-06 CN CN201710555808.XA patent/CN107480695A/en active Pending
- 2015-02-06 CN CN201510064774.5A patent/CN104616023A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11355761A (en) * | 1998-06-10 | 1999-12-24 | Hitachi Ltd | Monitor system |
| CN1389710A (en) * | 2002-07-18 | 2003-01-08 | 上海交通大学 | Multiple-sensor and multiple-object information fusing method |
| CN101017591A (en) * | 2007-02-06 | 2007-08-15 | 重庆大学 | Video safety prevention and monitoring method based on biology sensing and image information fusion |
| CN101236605A (en) * | 2008-02-29 | 2008-08-06 | 重庆大学 | Human body intelligent recognition method and system based on infrared signal |
| CN204423397U (en) * | 2015-02-06 | 2015-06-24 | 安徽大学 | A kind of contour of object detects recognition system |
Non-Patent Citations (1)
| Title |
|---|
| 成雄: "基于分布式红外传感器网络的行为识别定位问题的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11350264B2 (en) | 2018-07-25 | 2022-05-31 | Samsung Electronics Co., Ltd. | Method and apparatus for establishing device connection |
| CN113237567A (en) * | 2021-04-23 | 2021-08-10 | 广州碳思科技有限公司 | Device and method for recognizing object contour based on temperature difference |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107480695A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104616023A (en) | Object outline detection and recognition system and object outline recognition method | |
| CN102283616B (en) | Domestic intelligent cleaning system based on machine vision | |
| CN209186698U (en) | A kind of epilepsy early warning device based on FPGA | |
| CN106153114A (en) | A kind of remotely control intelligent building monitoring system | |
| CN109637102A (en) | A kind of number agricultural land information monitoring system | |
| CN105391732A (en) | Cloud platform and identity identification-based pesticide residue detection supervision system and method | |
| CN113963192A (en) | Fall detection method and device and electronic equipment | |
| CN103824118A (en) | Real-time management system of library seats | |
| CN101882236A (en) | Personnel counting method and equipment based on embedded system | |
| CN205179112U (en) | Host computer and next quick -witted communication system of reservoir detection of water level system | |
| Wang et al. | Real-time monitoring system of landslide based on LoRa architecture | |
| CN204423397U (en) | A kind of contour of object detects recognition system | |
| Zhu et al. | Automated monitoring system of pig behavior based on RFID and ARM-LINUX | |
| CN202562477U (en) | Device for detecting dangerous container stockpiling manner at container terminal storage yard | |
| CN104266634A (en) | On-line monitoring system for non-soluble deposit density of insulator of power transmission line and monitoring method of online monitoring system | |
| CN111429678A (en) | Monitoring system for key population in epidemic situation | |
| CN103761561B (en) | The hyperfrequency Internet of Things chip of compatible ISO18000-6C standard | |
| CN207037394U (en) | A kind of business finance data collecting system based on sensor and Internet of Things | |
| CN202422210U (en) | Embedded integrated information management platform for large warehouse | |
| CN104658175A (en) | Intelligent door mirror system | |
| CN207133608U (en) | The Internet of Things perception terminal that a kind of wrist wearing type is identified based on living body finger print | |
| CN212432347U (en) | Handheld infrared thermometer with information identification function | |
| CN204575122U (en) | Based on the forest environment monitoring system of wireless network | |
| Qiu et al. | Pointer instrument image recognition system for veterinary drug production based on RFID and deep learning | |
| CN201548984U (en) | Personnel counting system based on embedded microprocessor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination |