CN112069965A - PIR human body tracking method and system based on orientation change - Google Patents

PIR human body tracking method and system based on orientation change Download PDF

Info

Publication number
CN112069965A
CN112069965A CN202010893085.6A CN202010893085A CN112069965A CN 112069965 A CN112069965 A CN 112069965A CN 202010893085 A CN202010893085 A CN 202010893085A CN 112069965 A CN112069965 A CN 112069965A
Authority
CN
China
Prior art keywords
pir
human body
sensor
sensors
output signals
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
Application number
CN202010893085.6A
Other languages
Chinese (zh)
Inventor
杨田野
郭鹏
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.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
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 Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN202010893085.6A priority Critical patent/CN112069965A/en
Publication of CN112069965A publication Critical patent/CN112069965A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V8/00—Prospecting or detecting by optical means
    • G01V8/10—Detecting, e.g. by using light barriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G06F17/12—Simultaneous equations, e.g. systems of linear equations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Photometry And Measurement Of Optical Pulse Characteristics (AREA)

Abstract

The invention discloses a PIR human body tracking method and system based on orientation change, and belongs to the field of signal processing. The method comprises the following steps: collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, wherein the PIR sensor is deployed at different positions in the environment; after denoising processing is carried out on output signals of PIRs through an inverse filter, wave crests and wave troughs of the output signals of the sensors in an observation interval are extracted, and direction changes of a human body relative to the sensors are obtained through the number of the wave crests and the wave troughs of the output signals of the sensors; and establishing a state equation and an observation equation related to the position and the orientation change of the human body, substituting the state equation and the observation equation into the particle filter framework, and estimating the position of the human body. According to the invention, because the personnel position information contained in the PIR sensor original signal is further deeply excavated, the accurate estimation of the direction change of the moving personnel can be obtained, and higher positioning precision can be obtained while the deployment density of the sensor is reduced.

Description

PIR human body tracking method and system based on orientation change
Technical Field
The invention belongs to the field of signal processing, and particularly relates to a PIR human body tracking method and system based on orientation change.
Background
The indoor human body positioning and tracking technology is a key technology of the Internet of things, is also a basic technology related to the fields of intelligent monitoring, human body motion analysis, behavior recognition and the like, and has wide application value in the aspects of medical monitoring, security protection and the like.
At present, most of the traditional human body tracking methods are implemented based on a camera or a radio device. However, these two types of systems are not applicable in some scenarios. In particular, camera-based systems are not suitable for use in private scenes such as bedrooms, because they present a risk of privacy disclosure; radio-based systems are not suitable for scenarios where the radio communication environment is more demanding, as they may interfere with co-band radio communication. In the above scenario, a system based on a PIR sensor (pyroelectric infrared sensor, PIR for short) may meet user requirements. The PIR sensor is a passive infrared detector based on the pyroelectric effect principle, and can detect a moving infrared radiation source in a detection area to realize detection of a moving human body. Due to the characteristics of low cost, low power consumption, strong environmental adaptability and the like, the system is widely applied to security systems, lighting control and auxiliary monitoring of cameras. The PIR sensor can convert the detected infrared radiation of the moving human body into a continuous voltage signal and output the continuous voltage signal, the analog signal contains characteristic information related to the motion form of the human body, and characteristic parameters corresponding to certain specific actions (such as walking, running, jumping and the like) of the human body can be obtained from the characteristic information by utilizing a statistical method or a characteristic extraction algorithm, so that the human body tracking system based on the pyroelectric information is designed and realized.
However, existing PIR Sensor-based positioning schemes, such as that of document 1(S.Narayana, R.V.Prasad, V.S.Rao, T.V.Prabohakar, PIR Sensors: characteristics and Novel Localization technology, International Conference on Information Processing in Sensor Networks, 2015.), require a large number of PIR Sensors to be deployed in the scene, and thus have a high hardware cost. Therefore, it is of great significance to research a PIR sensor positioning scheme which can greatly reduce the deployment density of the sensors.
Disclosure of Invention
Aiming at the defects of the related art, the invention aims to provide a PIR human body tracking method and system based on orientation change, and aims to solve the technical problems of high sensor deployment density and high hardware cost in the conventional PIR sensor positioning scheme.
In order to achieve the above object, an aspect of the present invention provides a PIR human tracking method based on orientation change, including the following steps:
collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, wherein the PIR sensor is deployed at different positions in an environment;
after denoising the output signals of the PIR sensors by using an inverse filter, extracting wave crests and wave troughs of the output signals of the PIR sensors in an observation interval, and acquiring the direction change of a human body relative to each PIR sensor by using the number of the wave crests and the wave troughs of the output signals of the PIR sensors;
and establishing a state equation and an observation equation about the position of the human body and the orientation change, substituting the state equation and the observation equation into a particle filter framework, and executing a particle filter algorithm to estimate the position of the human body.
Further, the inverse filter is obtained by measuring model parameters of the PIR sensor by a unit impulse response method and then designing by using the model parameters.
Further, the acquiring of the orientation change of the human body relative to each PIR sensor by using the number of peaks and troughs of the output signal of each PIR sensor specifically includes:
the change in orientation of the human body relative to the respective PIR sensors is estimated using the following formula:
Figure BDA0002656293580000021
wherein,
Figure BDA0002656293580000022
indicates that the human body is in the observation interval [ tk-1，tk]Estimate of change in orientation with respect to the nth sensor over a period of time，mnThe number of wave crests and wave troughs in the output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor.
Further, the equation of state is expressed as follows:
Figure BDA0002656293580000031
wherein xkAnd ykIndicates that the human body is at tkThe coordinates of the time of day are,
Figure BDA0002656293580000032
and
Figure BDA0002656293580000033
respectively represent the human body tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2);
the observation equation is expressed as follows:
Figure BDA0002656293580000034
Figure BDA0002656293580000035
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
Further, when the PIR sensors are deployed, the number of the PIR sensors is determined according to the positioning area, and the positioning area is ensured to be covered by the PIR sensors.
In another aspect of the present invention, a PIR human tracking system based on orientation change is provided, which comprises
The device comprises a collecting unit, a processing unit and a control unit, wherein the collecting unit is used for collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, and the PIR sensor is deployed at different positions in the environment;
the orientation change acquisition unit is used for extracting wave crests and wave troughs of output signals of all PIR sensors in an observation interval after denoising the output signals of the PIR sensors by using an inverse filter, and acquiring the orientation change of a human body relative to all PIR sensors by using the number of the wave crests and the wave troughs of the output signals of all the PIR sensors;
and a position estimation unit which establishes a state equation and an observation equation regarding the position of the human body and the change of the orientation, substitutes the state equation and the observation equation into a particle filter framework, and executes a particle filter algorithm to estimate the position of the human body.
Further, the inverse filter is obtained by measuring model parameters of the PIR sensor by a unit impulse response method and then designing by using the model parameters.
Further, in the orientation change acquiring unit, acquiring the orientation change of the human body relative to each PIR sensor by using the number of peaks and troughs of the output signal of each PIR sensor specifically includes:
the change in orientation of the human body relative to the respective PIR sensors is estimated using the following formula:
Figure BDA0002656293580000041
wherein,
Figure BDA0002656293580000042
indicates that the human body is in the observation interval [ tk-1，tk]Estimate of the change in orientation with respect to the nth sensor during the time period, mnThe number of wave crests and wave troughs in the output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor.
Further, the equation of state is expressed as follows:
Figure BDA0002656293580000043
wherein xkAnd ykIndicates that the human body is at tkThe coordinates of the time of day are,
Figure BDA0002656293580000044
and
Figure BDA0002656293580000045
respectively represent the human body tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2);
the observation equation is expressed as follows:
Figure BDA0002656293580000051
Figure BDA0002656293580000052
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
Further, when the PIR sensors are deployed, the number of the PIR sensors is determined according to the positioning area, and the positioning area is ensured to be covered by the PIR sensors.
Compared with the prior art, the technical scheme provided by the invention can obtain accurate estimation of the direction change of the moving personnel because the personnel position information contained in the original signal of the PIR sensor is deeper excavated, thereby obtaining higher positioning precision while reducing the deployment density of the sensor.
Drawings
FIG. 1 is a PIR sensor deployment scenario of an embodiment of the invention;
FIG. 2 is a shading layout of a PIR sensor according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of the PIR sensor output signal of the present invention;
FIG. 4 is a schematic diagram comparing the positioning accuracy of the embodiment of the present invention with that of the existing PIR sensor-based positioning method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
One aspect of the embodiments of the present invention provides a novel human body tracking method based on a PIR sensor. The method can judge the position of the human body by measuring the infrared radiation of the human body without arranging any sensor on the human body. The method comprises the following steps:
A) hardware deployment: deploying N PIR sensors equipped with Fresnel lens arrays at different positions in the environment;
B) signal denoising: carrying out denoising processing on the acquired output signals of each path of PIR sensor by using an inverse filter;
C) estimating the azimuth change: extract each PIR sensor at [ tk-1，tk]The peaks and troughs of the signal over the time period and the change in orientation of the person relative to the respective PIR sensor is estimated using the following equation:
Figure BDA0002656293580000061
wherein,
Figure BDA0002656293580000062
indicates that the person is [ t ]k-1，tk]Estimate of the change in orientation with respect to the nth sensor during the time period, mnThe number of wave crests and wave troughs in an output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor;
D) and (3) estimating the position:establish information about the position of a person and
Figure BDA0002656293580000066
and then substituting the state equation and the observation equation into a particle filter framework to estimate the person position. The established state variance and observed variance are as follows:
the state equation is as follows:
Figure BDA0002656293580000063
wherein xkAnd ykIndicates that the person is at tkThe coordinates of the time of day are,
Figure BDA0002656293580000064
and
Figure BDA0002656293580000065
respectively represent persons tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2).
The observation equation:
Figure BDA0002656293580000071
Figure BDA0002656293580000072
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
In another aspect, the present invention further provides a PIR human tracking system based on orientation change, which includes
The device comprises a collecting unit, a processing unit and a control unit, wherein the collecting unit is used for collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, and the PIR sensor is deployed at different positions in the environment;
the orientation change acquisition unit is used for extracting wave crests and wave troughs of output signals of all PIR sensors in an observation interval after denoising the output signals of the PIR sensors by using an inverse filter, and acquiring the orientation change of a human body relative to all PIR sensors by using the number of the wave crests and the wave troughs of the output signals of all the PIR sensors;
and a position estimation unit which establishes a state equation and an observation equation regarding the position of the human body and the change of the orientation, substitutes the state equation and the observation equation into a particle filter framework, and executes a particle filter algorithm to estimate the position of the human body.
The functions of each unit can be referred to the description of the foregoing method embodiments, and are not described herein again.
The contents of the above embodiments will be described with reference to a preferred embodiment.
S1, 4 TRANESEN-2F21 PIR sensors equipped with YUYING-8719 Fresnel lens arrays were deployed in the manner shown in FIG. 1.
When the sensors are deployed, the positioning area is only covered by the sensors, the specific deployment number is determined according to the precision requirement, and the deployed sensor number can be properly increased if the precision is required to be improved.
S2, measuring model parameters of the PIR sensor by using a unit impact response method, and designing a corresponding inverse filter by using the measured model parameters.
And S3, carrying out denoising processing on the collected output signals of each path of PIR sensor by using the designed inverse filter. Wherein the shading layout of the PIR sensor is as shown in figure 2, whilst figure 3 shows the output signal of the PIR sensor when a pedestrian is moving within the PIR sensor.
And S4, finding peak and valley points in each path of signal, and estimating the direction change of the person relative to each sensor according to the PIR signal after denoising. The method specifically comprises the following steps:
setting the length T of the observation interval, and estimating the change of the direction of the person in each observation interval relative to each PIR sensor according to the formula (1):
Figure BDA0002656293580000081
wherein,
Figure BDA0002656293580000082
indicates that the person is [ t ]k-1，tk]Estimate of the change in orientation with respect to the nth sensor during the time period, mnThe number of wave crests and wave troughs in the output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor.
And S5, estimating the absolute position of the person according to the estimated position change of the person relative to each PIR sensor and the absolute position of each PIR sensor. The method specifically comprises the following steps:
establish information about the position of a person and
Figure BDA0002656293580000084
and then substituting the state equation and the observation equation into a particle filter framework to estimate the person position. The established state variance and observed variance are as follows:
the state equation is as follows:
Figure BDA0002656293580000083
wherein xkAnd ykIndicates that the person is at tkThe coordinates of the time of day are,
Figure BDA0002656293580000091
and
Figure BDA0002656293580000092
respectively represent persons tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2).
The observation equation:
Figure BDA0002656293580000093
Figure BDA0002656293580000094
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
The estimation result is substituted into equation (3), and then equations (2) and (3) are substituted into the particle filter algorithm framework. And executing a particle filtering algorithm to obtain the position estimation of the personnel.
Fig. 4 shows the comparison of the positioning accuracy of the method proposed by the present invention and the existing PIR sensor-based positioning method. Moreover, the deployment density of the method is 0.08/square meter, and the comparison method is about 0.2/square meter. Therefore, the invention greatly improves the positioning precision and reduces the deployment density.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. A PIR human body tracking method based on orientation change is characterized by comprising the following steps:
collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, wherein the PIR sensor is deployed at different positions in an environment;
after denoising the output signals of the PIR sensors by using an inverse filter, extracting wave crests and wave troughs of the output signals of the PIR sensors in an observation interval, and acquiring the direction change of a human body relative to each PIR sensor by using the number of the wave crests and the wave troughs of the output signals of the PIR sensors;
and establishing a state equation and an observation equation about the position of the human body and the orientation change, substituting the state equation and the observation equation into a particle filter framework, and executing a particle filter algorithm to estimate the position of the human body.
2. A PIR body tracking method according to claim 1, wherein the inverse filter is designed by measuring model parameters of the PIR sensor by a unit impulse response method and then using the model parameters.
3. A PIR body tracking method according to claim 1, wherein the obtaining of the orientation change of the body with respect to each PIR sensor using the number of peaks and troughs of the output signal of each PIR sensor specifically comprises:
the change in orientation of the human body relative to the respective PIR sensors is estimated using the following formula:
Figure FDA0002656293570000011
wherein,
Figure FDA0002656293570000012
indicates that the human body is in the observation interval [ tk-1，tk]Estimate of the change in orientation with respect to the nth sensor during the time period, mnThe number of wave crests and wave troughs in the output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor.
4. A PIR body tracking method according to claim 3, wherein the equation of state is expressed as follows:
Figure FDA0002656293570000021
wherein xkAnd ykIndicates that the human body is at tkThe coordinates of the time of day are,
Figure FDA0002656293570000022
and
Figure FDA0002656293570000023
respectively represent the human body tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2);
the observation equation is expressed as follows:
Figure FDA0002656293570000024
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
5. A PIR body tracking method according to any of claims 1 to 4, wherein the number of said PIR sensors is determined by the location area when said PIR sensors are deployed, ensuring that the location area is covered by said PIR sensors.
6. A PIR human body tracking system based on orientation change is characterized by comprising
The device comprises a collecting unit, a processing unit and a control unit, wherein the collecting unit is used for collecting a plurality of paths of output signals of a PIR sensor assembled with a Fresnel lens array, and the PIR sensor is deployed at different positions in the environment;
the orientation change acquisition unit is used for extracting wave crests and wave troughs of output signals of all PIR sensors in an observation interval after denoising the output signals of the PIR sensors by using an inverse filter, and acquiring the orientation change of a human body relative to all PIR sensors by using the number of the wave crests and the wave troughs of the output signals of all the PIR sensors;
and a position estimation unit which establishes a state equation and an observation equation regarding the position of the human body and the change of the orientation, substitutes the state equation and the observation equation into a particle filter framework, and executes a particle filter algorithm to estimate the position of the human body.
7. A PIR body tracking system according to claim 6, wherein the inverse filter is designed by measuring model parameters of the PIR sensor by a unit impulse response method and then using the model parameters.
8. A PIR body tracking system according to claim 6, wherein the orientation change obtaining unit, using the number of peaks and troughs of the output signal of each PIR sensor to obtain the orientation change of the body with respect to each PIR sensor, comprises:
the change in orientation of the human body relative to the respective PIR sensors is estimated using the following formula:
Figure FDA0002656293570000031
wherein,
Figure FDA0002656293570000032
indicates that the human body is in the observation interval [ tk-1，tk]Estimate of the change in orientation with respect to the nth sensor during the time period, mnThe number of wave crests and wave troughs in the output signal of the nth sensor is shown, and theta is the mean value of the included angles of symmetrical axes of each pair of adjacent light and dark areas of the PIR sensor.
9. A PIR body tracking system according to claim 8, wherein the equation of state is expressed as follows:
Figure FDA0002656293570000033
wherein xkAnd ykIndicates that the human body is at tkThe coordinates of the time of day are,
Figure FDA0002656293570000034
and
Figure FDA0002656293570000035
respectively represent the human body tkThe speed of the moment in the x and y directions, T being from Tk-1Time tkDuration of time lapse, u denotes a distribution obeying a Gaussian N (0, σ)u) The state noise of (2);
the observation equation is expressed as follows:
Figure FDA0002656293570000041
where h denotes observation noise, anAnd bnThe x and y coordinates of the nth PIR sensor, respectively.
10. A PIR body tracking system according to any of claims 6 to 9, wherein the number of PIR sensors when deployed is determined from the location area, ensuring that the location area is covered by the PIR sensors.
CN202010893085.6A 2020-08-28 2020-08-28 PIR human body tracking method and system based on orientation change Pending CN112069965A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010893085.6A CN112069965A (en) 2020-08-28 2020-08-28 PIR human body tracking method and system based on orientation change

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010893085.6A CN112069965A (en) 2020-08-28 2020-08-28 PIR human body tracking method and system based on orientation change

Publications (1)

Publication Number Publication Date
CN112069965A true CN112069965A (en) 2020-12-11

Family

ID=73664828

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010893085.6A Pending CN112069965A (en) 2020-08-28 2020-08-28 PIR human body tracking method and system based on orientation change

Country Status (1)

Country Link
CN (1) CN112069965A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107148079A (en) * 2017-05-15 2017-09-08 华北电力大学 Three-dimensional alignment by union and method for tracing in movable self-organization sensor network
CN111427007A (en) * 2020-04-24 2020-07-17 山东科技大学 Mine personnel safety state estimation method based on centralized personnel filtering under incomplete measurement

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107148079A (en) * 2017-05-15 2017-09-08 华北电力大学 Three-dimensional alignment by union and method for tracing in movable self-organization sensor network
CN111427007A (en) * 2020-04-24 2020-07-17 山东科技大学 Mine personnel safety state estimation method based on centralized personnel filtering under incomplete measurement

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
XUEFENG LIU等: ""From relative azimuth to absolute location: pushing the limit of PIR sensor based localization"", 《MOBICOM "20: PROCEEDINGS OF THE 26TH ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING》 *

Similar Documents

Publication Publication Date Title
CN107818571B (en) Ship automatic tracking method and system based on deep learning network and average drifting
CN103168467B (en) The security monitoring video camera using heat picture coordinate is followed the trail of and monitoring system and method
US9619999B2 (en) Sensor event assessor input/output controller
CN106600777B (en) Method of counting and device based on infrared array number sensor
Tzannes et al. Detecting small moving objects using temporal hypothesis testing
Xu et al. A people counting system based on head-shoulder detection and tracking in surveillance video
CN101999888B (en) Epidemic preventing and controlling system for detecting and searching people with abnormal temperatures
CN103077539A (en) Moving object tracking method under complicated background and sheltering condition
CN105160649A (en) Multi-target tracking method and system based on kernel function unsupervised clustering
Ahmad et al. A novel method for vegetation encroachment monitoring of transmission lines using a single 2D camera
CN103295221A (en) Water surface target motion detecting method simulating compound eye visual mechanism and polarization imaging
US20130162813A1 (en) Sensor event assessor training and integration
CN115035470A (en) Low, small and slow target identification and positioning method and system based on mixed vision
CN110392218A (en) A kind of infrared imaging identification integration apparatus and working method
Leonida et al. A Motion-Based Tracking System Using the Lucas-Kanade Optical Flow Method
CN113920354A (en) Action recognition method based on event camera
Cerutti et al. Outdoor people detection in low resolution thermal images
CN105890770A (en) Human body state detection device based on pyroelectric technology
Choubisa et al. An optical-camera complement to a PIR sensor array for intrusion detection and classfication in an outdoor environment
CN112069965A (en) PIR human body tracking method and system based on orientation change
Zhou et al. A human body positioning system with pyroelectric infrared sensor
KR101520293B1 (en) Scheduling method for detention of object and of obtaining forensic image by visual attention, and system thereof
Bardas et al. 3D tracking and classification system using a monocular camera
Oppliger et al. Sensor fusion of 3D time-of-flight and thermal infrared camera for presence detection of living beings
CN111476205B (en) Personnel counting method and device based on LSTM model

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20201211