CN112465870A - Thermal image alarm intrusion detection method and device under complex background - Google Patents
Thermal image alarm intrusion detection method and device under complex background Download PDFInfo
- Publication number
- CN112465870A CN112465870A CN202011437523.4A CN202011437523A CN112465870A CN 112465870 A CN112465870 A CN 112465870A CN 202011437523 A CN202011437523 A CN 202011437523A CN 112465870 A CN112465870 A CN 112465870A
- Authority
- CN
- China
- Prior art keywords
- target
- motion
- moving
- alarm
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Burglar Alarm Systems (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a thermal image alarm intrusion detection method and a device under a complex background, wherein the method comprises the following steps: s1, acquiring a thermal imaging video frame, creating a motion background model, inputting the thermal imaging video frame into the motion background model, and extracting a motion target; s2, detecting a moving target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the moving target, smoothing the initial track and predicting the moving state of the target by adopting a wave filtering algorithm, completing historical frame matching and generating a moving track; s3, setting sampling points according to the motion tracks, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points; and S4, carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion trail, and outputting a real alarm. The thermal image alarm intrusion detection method and device under the complex background provided by the invention can effectively filter out a large number of false alarms, and realize a smaller false alarm rate while keeping higher sensitivity.
Description
Technical Field
The invention belongs to the technical field of thermal image perimeter intrusion detection, and particularly relates to a thermal image alarm intrusion detection method and device under a complex background.
Background
GMM is a Gaussian Mixture Model, short for Gaussian Mixture Model, and can also be detected as MOG, and the Gaussian Model is a Model which accurately quantifies objects by using a Gaussian probability density function (normal distribution curve) and decomposes one object into a plurality of objects formed based on the Gaussian probability density function (normal distribution curve).
KNN, a short name of K-nearest neighbor, refers to a proximity algorithm, or a K nearest neighbor classification algorithm, and is one of the simplest methods in data mining classification technology.
The frontier defense environment has the characteristics of wide visual field and complex environment, and moving targets are usually very small and are generally below 15 pixels. In order to detect a small moving target, high sensitivity must be maintained, and due to the complexity of the environment, a large number of false alarms can be caused, such as wind blowing, heat waves caused by wheat waves, projection of cloud on the ground, and the like. In the conventional intrusion alarm, generally, GMM-based motion background modeling is performed to detect a moving object, and then the features of a single moving object are extracted and filtered. However, targets in the frontier defense environment are very small and have unobvious characteristics, and the characteristics of a single target have great randomness and cannot be distinguished from a large number of false alarm points.
Therefore, it is very necessary to provide a method and a device for detecting intrusion by thermal imaging alarm under a complex background, aiming at the above-mentioned defects in the prior art.
Disclosure of Invention
The invention provides a thermal image alarm intrusion detection method and device under a complex background, aiming at the defects that in the prior art, targets in the frontier defense environment are very small, the characteristics are not obvious, the characteristics of a single target have great randomness and often cannot be distinguished from a large number of false alarm points.
In a first aspect, the invention provides a thermal imaging alarm intrusion detection method under a complex background, which comprises the following steps:
s1, acquiring a thermal imaging video frame, creating a motion background model, inputting the thermal imaging video frame into the motion background model, and extracting a motion target;
s2, detecting a moving target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the moving target, smoothing the initial track and predicting the moving state of the target by adopting a wave filtering algorithm, completing historical frame matching and generating a moving track;
s3, setting sampling points according to the motion tracks, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points;
and S4, carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion trail, and outputting a real alarm.
Further, the step S1 specifically includes the following steps:
s11, acquiring a thermal imaging video frame through thermal imaging equipment;
s12, modeling the motion background based on a KNN algorithm to generate a KNN motion background model;
and S13, inputting the thermal imaging video frame into the KNN motion background model, and extracting a motion target.
Further, the step S2 specifically includes the following steps:
s21, detecting a moving target by adopting a KNN algorithm;
s22, generating an initial track based on the maximum intersection ratio of the current frame and the historical frame of the moving target;
s23, counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target, and completing initial stage track smoothing and target motion state prediction;
and S24, performing historical frame matching based on the Hungarian algorithm on the smoothed initial track to generate a motion track.
Further, the step S3 specifically includes the following steps:
s31, setting an adopted frequency, and extracting a corresponding historical target in the motion trail according to the adopted frequency;
s32, recording morphological characteristics of a historical target, wherein the morphological characteristics comprise an aspect ratio and a target pixel area;
s33, recording the motion characteristics of the historical target, wherein the motion characteristics comprise the moving speed of the target and the moving distance of the target in an adjacent frame;
and S34, after the motion track is generated for a set time period, counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target after the track is finished.
Further, the step S4 specifically includes the following steps:
s41, adjusting the duration of the motion track, and filtering the alarm of which the duration does not meet a threshold value;
s42, adjusting a dispersion threshold value, and filtering alarms with the dispersion of the target morphological characteristics and the target moving speed larger than the dispersion threshold value;
s43, filtering the alarm when the linear pixel distance of the moving target moving is smaller than the threshold value after the track of the moving target is finished;
and S44, setting the filtered alarm as false alarm, and outputting the residual real alarm.
Further, the step S41 specifically includes the following steps:
s411, setting a motion track duration threshold as a first threshold;
s412, judging whether the duration time of the motion track is greater than a first threshold value;
if yes, go to step S413;
if not, go to step S42;
and S413, filtering the alarm corresponding to the motion track.
Further, the step S42 specifically includes the following steps:
s421, calculating the dispersion of the morphological characteristics of the target and the dispersion of the moving speed characteristics of the target according to the historical information of the moving target recorded on the motion track;
s422, setting a dispersion threshold of the morphological characteristics of the target as a second threshold, and setting a dispersion threshold of the moving speed of the target as a third threshold;
s423, judging whether the dispersion of the target morphological characteristics of the motion trail is greater than a second threshold value;
if yes, go to step S424;
if not, go to step S43;
s424, whether the dispersion of the target moving speed is larger than a third threshold value or not;
if yes, go to step S425;
if not, go to step S43;
and S425, filtering the alarm corresponding to the motion track.
Further, the step S43 specifically includes the following steps:
s431, setting the linear pixel distance of the target movement as a fourth threshold value;
s432, after the motion trail is continuously set for a time period, obtaining the linear pixel distance of the motion target;
s433, judging whether the linear pixel distance of the moving target is smaller than a fourth threshold value;
if yes, go to step S434;
if not, go to step S44;
and S434, filtering the alarm corresponding to the motion trail.
In a second aspect, the present invention provides a thermal imaging alarm intrusion detection device under a complex background, including:
the moving object extraction module is used for acquiring thermal imaging video frames, creating a moving background model, inputting the thermal imaging video frames into the moving background model and extracting a moving object;
the motion track generation module is used for detecting a motion target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the motion target, smoothing the initial track and predicting the motion state of the target by using a wave filtering algorithm, completing historical frame matching and generating the motion track;
the motion track characteristic extraction module is used for setting sampling points according to the motion track, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points;
and the false alarm filtering module is used for carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion track and outputting a real alarm.
Further, the moving object extraction module includes:
a thermal imaging video frame acquisition unit for acquiring a thermal imaging video frame by a thermal imaging device;
the motion background model generation unit is used for carrying out motion background modeling based on a KNN algorithm to generate a KNN motion background model;
the moving target extraction unit is used for inputting the thermal imaging video frame into the KNN moving background model and extracting a moving target;
the motion trail generation module comprises:
the moving target detection unit is used for detecting a moving target by adopting a KNN algorithm;
the initial track generating unit is used for generating an initial track based on the maximum intersection ratio of the current frame and the historical frame of the moving target;
the initial track smoothing unit is used for counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target and completing initial track smoothing and target motion state prediction;
a historical frame matching and motion trail generating unit used for carrying out historical frame matching based on Hungary algorithm on the smoothed initial-stage trail to generate a motion trail;
the motion trail feature extraction module comprises:
the historical target extraction unit is used for setting the adoption frequency and extracting the corresponding historical target in the motion trail according to the adoption frequency;
the morphological feature recording unit is used for recording morphological features of the historical target, and the morphological features comprise an aspect ratio and a target pixel area;
the motion characteristic recording unit is used for recording the motion characteristics of the historical target, wherein the motion characteristics comprise the moving speed of the target and the moving distance of the target in an adjacent frame;
the characteristic counting unit is used for counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target moving after the track is finished after the motion track is generated for a set time period;
the false alarm filtering module comprises:
the short-prompt false alarm filtering unit is used for adjusting the duration time of the motion trail and filtering the alarm of which the duration time does not meet a threshold value;
the large-scale false alarm filtering unit is used for adjusting the dispersion threshold value and filtering the alarm of which the dispersion of the target morphological characteristics and the target moving speed is greater than the dispersion threshold value;
the small deformation false alarm filtering unit is used for filtering the alarm that the linear pixel distance of the moving target moving is smaller than the threshold value after the track of the moving target is finished;
and the true alarm output unit is used for setting the filtered alarm as false alarm and outputting the residual true alarm.
The beneficial effect of the invention is that,
the thermal image alarm intrusion detection method and device under the complex background provided by the invention are used for detecting the moving target based on the KNN algorithm, fusing the Hungarian matching algorithm and the intersection of the front frame and the rear frame of the target to generate the track of the moving target, adopting the Kalman filtering algorithm to carry out track smoothing and target motion state prediction, and simultaneously carrying out characteristic statistics on morphological characteristics and motion characteristics of each historical target forming the track, thereby effectively filtering out a large number of false alarms and realizing smaller false alarm rate while keeping higher sensitivity.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
Therefore, compared with the prior art, the invention has prominent substantive features and remarkable progress, and the beneficial effects of the implementation are also obvious.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a first schematic flow chart of the method of the present invention;
FIG. 2 is a second schematic flow chart of the method of the present invention;
FIG. 3 is a schematic view of the apparatus of the present invention;
in the figure, 1-moving object extraction module; 1.1-a thermal imaging video frame acquisition unit; 1.2-a motion background model generation unit; 1.3-moving object extraction unit; 2-a motion trajectory generation module; 2.1 moving object detection unit-; 2.2-initial trajectory generation unit; 2.3-initial trajectory smoothing unit; 2.4-historical frame matching and motion trail generating unit; 3-a motion track feature extraction module; 3.1-historical target extraction unit; 3.2-morphological feature recording unit; 3.3-a motion characteristics recording unit; 3.4-feature statistics unit; 4-false alarm filtering module; 4.1-short misinformation filtering unit; 4.2-large-scale false alarm filtering unit; 4.3-small deformation false alarm filtering unit; 4.4-true alarm output unit.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in FIG. 1, the invention provides a thermal imaging alarm intrusion detection method under a complex background, which comprises the following steps:
s1, acquiring a thermal imaging video frame, creating a motion background model, inputting the thermal imaging video frame into the motion background model, and extracting a motion target;
s2, detecting a moving target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the moving target, smoothing the initial track and predicting the moving state of the target by adopting a wave filtering algorithm, completing historical frame matching and generating a moving track;
s3, setting sampling points according to the motion tracks, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points;
and S4, carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion trail, and outputting a real alarm.
Example 2:
as shown in FIG. 2, the invention provides a thermal imaging alarm intrusion detection method under a complex background, which comprises the following steps:
s1, acquiring a thermal imaging video frame, creating a motion background model, inputting the thermal imaging video frame into the motion background model, and extracting a motion target; the method comprises the following specific steps:
s11, acquiring a thermal imaging video frame through thermal imaging equipment;
s12, modeling the motion background based on a KNN algorithm to generate a KNN motion background model;
s13, inputting the thermal imaging video frame into a KNN motion background model, and extracting a motion target;
s2, detecting a moving target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the moving target, smoothing the initial track and predicting the moving state of the target by adopting a wave filtering algorithm, completing historical frame matching and generating a moving track; the method comprises the following specific steps:
s21, detecting a moving target by adopting a KNN algorithm;
s22, generating an initial track based on the maximum intersection ratio of the current frame and the historical frame of the moving target; the success rate of late Hungarian matching is improved based on the initial track generated by the maximum intersection ratio;
s23, counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target, and completing initial stage track smoothing and target motion state prediction;
s24, performing historical frame matching based on the Hungarian algorithm on the smoothed initial-stage track to generate a motion track;
s3, setting sampling points according to the motion tracks, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points; the method comprises the following specific steps:
s31, setting an adopted frequency, and extracting a corresponding historical target in the motion trail according to the adopted frequency;
s32, recording morphological characteristics of a historical target, wherein the morphological characteristics comprise an aspect ratio and a target pixel area;
s33, recording the motion characteristics of the historical target, wherein the motion characteristics comprise the moving speed of the target and the moving distance of the target in an adjacent frame;
s34, after the motion track is generated for a set time period, counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target moving after the track is finished;
s4, carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion track, and outputting a real alarm; the method comprises the following specific steps:
s41, adjusting the duration of the motion track, and filtering the alarm of which the duration does not meet a threshold value;
s42, adjusting a dispersion threshold value, and filtering alarms with the dispersion of the target morphological characteristics and the target moving speed larger than the dispersion threshold value;
s43, filtering the alarm when the linear pixel distance of the moving target moving is smaller than the threshold value after the track of the moving target is finished;
and S44, setting the filtered alarm as false alarm, and outputting the residual real alarm.
In the above embodiment, the intersection ratio is a concept in target detection, and is the overlapping rate of the generated candidate frame and the original marked frame, i.e. the ratio of their intersection to union, and the optimal case is complete overlap, i.e. the ratio is 1, i.e. the current frame and the historical frame are perfectly matched.
In some embodiments, step S41 includes the following steps:
s411, setting a motion track duration threshold as a first threshold;
s412, judging whether the duration time of the motion track is greater than a first threshold value;
if yes, go to step S413;
if not, go to step S42;
s413, filtering the alarm corresponding to the motion track;
step S41 is to realize the filtering of short false alarm mainly from exposed rock and vibration of vegetation in the sun, and is characterized by short duration, generally in millisecond level, and small target size;
this kind of wrong report can filter through the duration of adjustment orbit, only after the duration reaches certain degree, just can form true police.
In some embodiments, step S42 includes the following steps:
s421, calculating the dispersion of the morphological characteristics of the target and the dispersion of the moving speed characteristics of the target according to the historical information of the moving target recorded on the motion track;
s422, setting a dispersion threshold of the morphological characteristics of the target as a second threshold, and setting a dispersion threshold of the moving speed of the target as a third threshold;
s423, judging whether the dispersion of the target morphological characteristics of the motion trail is greater than a second threshold value;
if yes, go to step S424;
if not, go to step S43;
s424, whether the dispersion of the target moving speed is larger than a third threshold value or not;
if yes, go to step S425;
if not, go to step S43;
s425, filtering the alarm corresponding to the motion track;
step S42 is to filter the large deformation false alarm, which usually has long duration and large deformation scale, and the false alarm mainly comes from wheat wave and cloud shadow, especially in daytime and windy days, one-wave can be formed on thermal images, and a moving target with longer duration is formed after the moving target is processed by KNN algorithm, and the duration is different from 1 second to 8 seconds; in addition, when clouds exist on the mountains, moving objects with long duration can be formed at the edges of the clouds, and the moving objects are characterized by large deformation scale;
according to the historical information of the target recorded on the track, the dispersion of the morphological characteristics and the speed characteristics of the target is calculated, the dispersion of the misinformation is found to be large, and according to the characteristic, the threshold value of the dispersion is adjusted, so that the large-scale misinformation can be filtered.
In some embodiments, step S43 includes the following steps:
s431, setting the linear pixel distance of the target movement as a fourth threshold value;
s432, after the motion trail is continuously set for a time period, obtaining the linear pixel distance of the motion target;
s433, judging whether the linear pixel distance of the moving target is smaller than a fourth threshold value;
if yes, go to step S434;
if not, go to step S44;
s434, filtering the alarm corresponding to the motion track;
step S43 is to filter the small deformation false alarm, which has long duration and small deformation, and the false alarm is less and mostly exists in the wheat wave, and is characterized in that the target often wanders near one point;
after the motion trail continues for a period of time, if the linear distance of the target moving is found to be short or the target does not move, the small deformation false alarm can be judged.
Example 3:
as shown in fig. 3, the present invention provides a thermal imaging alarm intrusion detection device under a complex background, which includes:
the moving object extraction module 1 is used for acquiring thermal imaging video frames, creating a moving background model, inputting the thermal imaging video frames into the moving background model, and extracting a moving object; the moving object extraction module 1 includes:
a thermal imaging video frame acquisition unit 1.1 for acquiring a thermal imaging video frame by a thermal imaging device;
the motion background model generation unit 1.2 is used for carrying out motion background modeling based on a KNN algorithm to generate a KNN motion background model;
the moving target extraction unit 1.3 is used for inputting the thermal imaging video frame into the KNN moving background model and extracting a moving target;
the motion track generation module 2 is used for detecting a motion target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the motion target, and then performing initial track smoothing and target motion state prediction by using a wave filtering algorithm to complete historical frame matching and generate a motion track; the motion trajectory generation module 2 includes:
a moving target detection unit 2.1, which is used for detecting a moving target by adopting a KNN algorithm;
an initial trajectory generating unit 2.2 for generating an initial trajectory based on a maximum intersection ratio of a current frame and a historical frame of the moving object;
the initial track smoothing unit 2.3 is used for counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target and completing initial track smoothing and target motion state prediction;
a historical frame matching and motion trail generating unit 2.4, which is used for performing historical frame matching based on Hungarian algorithm on the smoothed initial-stage trail to generate a motion trail;
the motion track characteristic extraction module 3 is used for setting sampling points according to the motion track, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points; the motion trajectory feature extraction module 3 includes:
the historical target extracting unit 3.1 is used for setting the adoption frequency and extracting the corresponding historical target in the motion trail according to the adoption frequency;
the morphological feature recording unit 3.2 is used for recording morphological features of the historical target, wherein the morphological features comprise an aspect ratio and a target pixel area;
a motion characteristic recording unit 3.3, configured to record motion characteristics of the historical target, where the motion characteristics include a target moving speed and a moving distance of the target in an adjacent frame;
the characteristic counting unit 3.4 is used for counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target moving after the track is finished after the motion track generates a set time period;
the false alarm filtering module 4 is used for carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion track and outputting a real alarm; the false alarm filtering module 4 comprises:
a short-prompt false alarm filtering unit 4.1, which is used for adjusting the duration time of the motion trail and filtering the alarm of which the duration time does not meet the threshold value;
the large-scale false alarm filtering unit 4.2 is used for adjusting a dispersion threshold value and filtering alarms of which the dispersion of the target morphological characteristics and the target moving speed are both greater than the dispersion threshold value;
the small deformation false alarm filtering unit 4.3 is used for filtering the alarm when the linear pixel distance of the moving target moving is smaller than the threshold value after the track is finished;
and the true alarm output unit 4.4 is used for setting the filtered alarm as false alarm and outputting the residual true alarm.
Although the present invention has been described in detail by referring to the drawings in connection with the preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made on the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and these modifications or substitutions are within the scope of the present invention/any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A thermal imagery alarm intrusion detection method under a complex background is characterized by comprising the following steps:
s1, acquiring a thermal imaging video frame, creating a motion background model, inputting the thermal imaging video frame into the motion background model, and extracting a motion target;
s2, detecting a moving target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the moving target, smoothing the initial track and predicting the moving state of the target by adopting a wave filtering algorithm, completing historical frame matching and generating a moving track;
s3, setting sampling points according to the motion tracks, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points;
and S4, carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion trail, and outputting a real alarm.
2. The method for intrusion detection by thermal imagery alarm under complex background according to claim 1, wherein the step S1 comprises the following steps:
s11, acquiring a thermal imaging video frame through thermal imaging equipment;
s12, modeling a motion background based on a KNN algorithm to generate a KNN motion background model;
and S13, inputting the thermal imaging video frame into a KNN motion background model, and extracting a motion target.
3. The method for intrusion detection by thermal imagery alarm under complex background according to claim 1, wherein the step S2 comprises the following steps:
s21, detecting a moving target by adopting a KNN algorithm;
s22, generating an initial track based on the maximum intersection ratio of the current frame and the historical frame of the moving target;
s23, counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target, and completing initial stage track smoothing and target motion state prediction;
and S24, performing historical frame matching based on the Hungarian algorithm on the smoothed initial track to generate a motion track.
4. The method for intrusion detection by thermal imagery alarm under complex background according to claim 1, wherein the step S3 comprises the following steps:
s31, setting an adopted frequency, and extracting a corresponding historical target in the motion trail according to the adopted frequency;
s32, recording morphological characteristics of a historical target, wherein the morphological characteristics comprise an aspect ratio and a target pixel area;
s33, recording the motion characteristics of the historical target, wherein the motion characteristics comprise the moving speed of the target and the moving distance of the target in an adjacent frame;
and S34, after the motion track is generated for a set time period, counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target after the track is finished.
5. The method for intrusion detection by thermal imagery alarm under complex background according to claim 4, wherein the step S4 comprises the following steps:
s41, adjusting the duration of the motion track, and filtering the alarm of which the duration does not meet a threshold value;
s42, adjusting a dispersion threshold value, and filtering alarms with the dispersion of the target morphological characteristics and the target moving speed larger than the dispersion threshold value;
s43, filtering the alarm when the linear pixel distance of the moving target moving is smaller than the threshold value after the track of the moving target is finished;
and S44, setting the filtered alarm as false alarm, and outputting the residual real alarm.
6. The method for intrusion detection by thermal imagery alarm under complex background according to claim 5, wherein the step S41 comprises the following steps:
s411, setting a motion track duration threshold as a first threshold;
s412, judging whether the duration time of the motion track is greater than a first threshold value;
if yes, go to step S413;
if not, go to step S42;
and S413, filtering the alarm corresponding to the motion track.
7. The method for intrusion detection by thermal imagery alarm under complex background according to claim 5, wherein the step S42 comprises the following steps:
s421, calculating the dispersion of the morphological characteristics of the target and the dispersion of the moving speed characteristics of the target according to the historical information of the moving target recorded on the motion track;
s422, setting a dispersion threshold of the morphological characteristics of the target as a second threshold, and setting a dispersion threshold of the moving speed of the target as a third threshold;
s423, judging whether the dispersion of the target morphological characteristics of the motion trail is greater than a second threshold value;
if yes, go to step S424;
if not, go to step S43;
s424, whether the dispersion of the target moving speed is larger than a third threshold value or not;
if yes, go to step S425;
if not, go to step S43;
and S425, filtering the alarm corresponding to the motion track.
8. The method for intrusion detection by thermal imagery alarm under complex background according to claim 7, wherein the step S43 comprises the following steps:
s431, setting the linear pixel distance of the target movement as a fourth threshold value;
s432, after the motion trail is continuously set for a time period, obtaining the linear pixel distance of the motion target;
s433, judging whether the linear pixel distance of the moving target is smaller than a fourth threshold value;
if yes, go to step S434;
if not, go to step S44;
and S434, filtering the alarm corresponding to the motion trail.
9. The utility model provides a thermal imagery warning intrusion detection device under complicated background which characterized in that includes:
the moving object extraction module (1) is used for acquiring thermal imaging video frames, creating a moving background model, inputting the thermal imaging video frames into the moving background model and extracting a moving object;
the motion track generation module (2) is used for detecting a motion target by adopting a KNN algorithm, generating an initial track according to the intersection ratio of a current frame and a historical frame of the motion target, and then performing initial track smoothing and target motion state prediction by using a wave filtering algorithm to complete historical frame matching and generate a motion track;
the motion track characteristic extraction module (3) is used for setting sampling points according to the motion track, and extracting and counting morphological characteristics and motion characteristics of historical targets of the sampling points;
and the false alarm filtering module (4) is used for carrying out false alarm filtering according to the morphological characteristics and the motion characteristics of the motion track and outputting a real alarm.
10. The thermographic alarm intrusion detection device under complex background of claim 9, wherein the moving object extraction module (1) comprises:
a thermal imaging video frame acquisition unit (1.1) for acquiring a thermal imaging video frame by a thermal imaging device;
the motion background model generation unit (1.2) is used for carrying out motion background modeling based on a KNN algorithm to generate a KNN motion background model;
the moving target extraction unit (1.3) is used for inputting the thermal imaging video frame into the KNN moving background model and extracting a moving target;
the motion trail generation module (2) comprises:
a moving target detection unit (2.1) for detecting a moving target by using a KNN algorithm;
an initial track generation unit (2.2) for generating an initial track based on the maximum intersection ratio of the current frame and the historical frame of the moving object;
the initial track smoothing unit (2.3) is used for counting the speed information of the moving target, constructing an initial state matrix and a motion equation of a Kalman filtering algorithm according to the speed information of the moving target and finishing initial track smoothing and target motion state prediction;
a historical frame matching and motion trail generating unit (2.4) for performing historical frame matching based on Hungarian algorithm on the smoothed initial-stage trail to generate a motion trail;
the motion track feature extraction module (3) comprises:
the history target extraction unit (3.1) is used for setting the adoption frequency and extracting the corresponding history target in the motion trail according to the adoption frequency;
a morphological feature recording unit (3.2) for recording morphological features of the historical object, the morphological features comprising an aspect ratio and an object pixel area;
a motion characteristic recording unit (3.3) for recording motion characteristics of the historical target, wherein the motion characteristics comprise target moving speed and moving distance of the target in adjacent frames;
the characteristic counting unit (3.4) is used for counting the speed, the aspect ratio, the target pixel area, the dispersion of the target moving speed and the linear pixel distance of the moving target moving after the track is finished after the motion track is generated for a set time period;
the false alarm filtering module (4) comprises:
a short-prompt false alarm filtering unit (4.1) for adjusting the duration time of the motion trail and filtering the alarm of which the duration time does not meet the threshold value;
the large-scale false alarm filtering unit (4.2) is used for adjusting the dispersion threshold value and filtering the alarm of which the dispersion of the target morphological characteristics and the target moving speed is greater than the dispersion threshold value;
a small deformation false alarm filtering unit (4.3) for filtering the alarm when the linear pixel distance of the moving target moving is less than the threshold value after the track is finished;
and the true alarm output unit (4.4) is used for setting the filtered alarm as false alarm and outputting the residual true alarm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011437523.4A CN112465870B (en) | 2020-12-10 | 2020-12-10 | Thermal image alarm intrusion detection method and device under complex background |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011437523.4A CN112465870B (en) | 2020-12-10 | 2020-12-10 | Thermal image alarm intrusion detection method and device under complex background |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465870A true CN112465870A (en) | 2021-03-09 |
| CN112465870B CN112465870B (en) | 2023-07-14 |
Family
ID=74800793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011437523.4A Active CN112465870B (en) | 2020-12-10 | 2020-12-10 | Thermal image alarm intrusion detection method and device under complex background |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465870B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238214A (en) * | 2021-04-14 | 2021-08-10 | 杭州萤石软件有限公司 | Target object detection method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739691A (en) * | 2009-12-04 | 2010-06-16 | 北京智安邦科技有限公司 | Method and device for detecting video false alarm target |
| CN103413330A (en) * | 2013-08-30 | 2013-11-27 | 中国科学院自动化研究所 | Method for reliably generating video abstraction in complex scene |
| CN103489202A (en) * | 2013-01-15 | 2014-01-01 | 上海盈觉智能科技有限公司 | Intrusion detection method based on videos |
| CN104574340A (en) * | 2013-10-18 | 2015-04-29 | 上海睿穹信息科技有限公司 | Video intrusion detection method based on historical images |
| CN105141903A (en) * | 2015-08-13 | 2015-12-09 | 中国科学院自动化研究所 | Method for retrieving object in video based on color information |
| CN110866943A (en) * | 2019-11-21 | 2020-03-06 | 无锡中科水质环境技术有限公司 | Fish position tracking method for water quality monitoring |
| CN111507235A (en) * | 2020-04-13 | 2020-08-07 | 北京交通大学 | Video-based railway perimeter foreign matter intrusion detection method |
| CN111582060A (en) * | 2020-04-20 | 2020-08-25 | 浙江大华技术股份有限公司 | Automatic line drawing perimeter alarm method, computer equipment and storage device |
| CN111932580A (en) * | 2020-07-03 | 2020-11-13 | 江苏大学 | Road 3D vehicle tracking method and system based on Kalman filtering and Hungary algorithm |
-
2020
- 2020-12-10 CN CN202011437523.4A patent/CN112465870B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739691A (en) * | 2009-12-04 | 2010-06-16 | 北京智安邦科技有限公司 | Method and device for detecting video false alarm target |
| CN103489202A (en) * | 2013-01-15 | 2014-01-01 | 上海盈觉智能科技有限公司 | Intrusion detection method based on videos |
| CN103413330A (en) * | 2013-08-30 | 2013-11-27 | 中国科学院自动化研究所 | Method for reliably generating video abstraction in complex scene |
| CN104574340A (en) * | 2013-10-18 | 2015-04-29 | 上海睿穹信息科技有限公司 | Video intrusion detection method based on historical images |
| CN105141903A (en) * | 2015-08-13 | 2015-12-09 | 中国科学院自动化研究所 | Method for retrieving object in video based on color information |
| CN110866943A (en) * | 2019-11-21 | 2020-03-06 | 无锡中科水质环境技术有限公司 | Fish position tracking method for water quality monitoring |
| CN111507235A (en) * | 2020-04-13 | 2020-08-07 | 北京交通大学 | Video-based railway perimeter foreign matter intrusion detection method |
| CN111582060A (en) * | 2020-04-20 | 2020-08-25 | 浙江大华技术股份有限公司 | Automatic line drawing perimeter alarm method, computer equipment and storage device |
| CN111932580A (en) * | 2020-07-03 | 2020-11-13 | 江苏大学 | Road 3D vehicle tracking method and system based on Kalman filtering and Hungary algorithm |
Non-Patent Citations (4)
| Title |
|---|
| RAVI VAISHNAVI.ET AL: "Implementation of algorithms for Point target detection and tracking in Infrared image sequences", 《IEEE》 * |
| 任珈民等: "基于YOLOv3与卡尔曼滤波的多目标跟踪算法", 计算机应用与软件, no. 05 * |
| 刘峰等: "一种低复杂度的监控视频异物入侵检测算法", 南京邮电大学学报(自然科学版), no. 01 * |
| 诸葛琳娜: "基于移动平台热成像的行人检测与跟踪研究", 《中国优秀硕士学位论文全文数据库 信息科技》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113238214A (en) * | 2021-04-14 | 2021-08-10 | 杭州萤石软件有限公司 | Target object detection method and device, electronic equipment and storage medium |
| CN113238214B (en) * | 2021-04-14 | 2024-03-19 | 杭州萤石软件有限公司 | Target object detection method, target object detection device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465870B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872483B (en) | Intrusion alert photoelectric monitoring system and method | |
| CN110853295A (en) | High-altitude parabolic early warning method and device | |
| CN109101944B (en) | Real-time video monitoring method for identifying garbage thrown into river channel | |
| CN109905675A (en) | A kind of mine personnel monitoring system based on computer vision and method | |
| CN101167086A (en) | Human detection and tracking for security applications | |
| Kato et al. | An HMM/MRF-based stochastic framework for robust vehicle tracking | |
| CN110490043A (en) | A kind of forest rocket detection method based on region division and feature extraction | |
| CN113362374A (en) | High-altitude parabolic detection method and system based on target tracking network | |
| CN106709938A (en) | Multi-target tracking method based on improved TLD (tracking-learning-detected) | |
| CN103714319A (en) | Video intrusion detection method used for power line external force damage-prevention system | |
| CN111814635A (en) | Smoke and fire identification model establishing method and smoke and fire identification method based on deep learning | |
| CN112465870B (en) | Thermal image alarm intrusion detection method and device under complex background | |
| CN114373130A (en) | Space-based infrared dark and weak moving target detection method | |
| CN108921826A (en) | The transmission line of electricity that super-pixel segmentation is combined with deep learning invades object detecting method | |
| Tang et al. | Background subtraction using running Gaussian average and frame difference | |
| CN110796682A (en) | Detection and identification method and detection and identification system for moving target | |
| CN103679172A (en) | Method for detecting long-distance ground moving object via rotary infrared detector | |
| CN106842349A (en) | Transmission line of electricity external force damage prevention detection method and device | |
| CN113283330A (en) | Video SAR moving target detection method based on deep learning and multi-target tracking algorithm | |
| Wei et al. | A Markov random field approach for sidescan sonar change detection | |
| Batista et al. | Improved real-time wildfire detection using a surveillance system | |
| Kim et al. | Three plot correlation-based small infrared target detection in dense sun-glint environment for infrared search and track | |
| Archana et al. | To detect abnormal event at ATM system by using image processing based on IOT technologies | |
| CN115394065A (en) | AI-based automatic identification packet loss behavior alarm method and device | |
| Wei et al. | Birds/bats movement tracking with IR camera for wind farm applications |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |