CN102538695B - Security detection method and related device thereof - Google Patents
Security detection method and related device thereof Download PDFInfo
- Publication number
- CN102538695B CN102538695B CN201010589176.7A CN201010589176A CN102538695B CN 102538695 B CN102538695 B CN 102538695B CN 201010589176 A CN201010589176 A CN 201010589176A CN 102538695 B CN102538695 B CN 102538695B
- Authority
- CN
- China
- Prior art keywords
- shape information
- distance
- laser
- invader
- parameter
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 30
- 238000006073 displacement reaction Methods 0.000 claims description 15
- 230000010354 integration Effects 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 230000033001 locomotion Effects 0.000 claims description 11
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000017105 transposition Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 description 13
- 238000012360 testing method Methods 0.000 description 6
- 238000009434 installation Methods 0.000 description 4
- 230000009545 invasion Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000001740 anti-invasion Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000004877 mucosa Anatomy 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Burglar Alarm Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The embodiment of the invention discloses a security detection method and a related device thereof, applied to identifiable security detection with wide range and high precision. The security detection method disclosed by the embodiment of the invention comprises the following steps of: emitting at least two beams of laser and scanning a target object; acquiring scanning parameters of the target object, wherein the scanning parameters comprise a distance Z, the distance X and the distance Y; the distance Z is the distance between the target object and a laser emitter; the distance X and the distance Y respectively means a horizontal distance and a vertical distance of the target object on a reference coordinate system; generating shape information of the target object according to the scanning parameters, wherein the shape information is a set of coordinate points of the target object; calculating characteristic parameters of the shape information; and determining the type of the target object according to a preset analysis rule by using the characteristic parameters. The invention further provides a related device for realizing the security detection method.
Description
Technical field
The present invention relates to electronic applications, relate in particular to a kind of security detection method and relevant apparatus.
Background technology
In traditional technology, laser detector is widely used in safety-security area.But traditional Laser Detection Technique recognition function is low, can not distinguish various objects, cause the rate of false alarm of safety-protection system high.
There is in the market a laser curtain detecting devices, the ZM100 laser curtain profile measurer of Wei Zhenshangyou displacement sensing company, this ZM100 measuring instrument uses light emitting diode to form light curtain by optical system, when having invader through search coverage, invader is irradiated and can form shadow image by light curtain, ZM100 measuring instrument obtains this shadow image by telescopic system, and form ccd array signal according to this shadow image, finally by analyzing this ccd array signal, determine the shape of invader.
Although ZM100 measuring instrument has higher recognition capability, because telescopic system in ZM100 measuring instrument is easily blocked the detection visual angle of shadow image, the image that causes getting invader is inaccurate.And because telescopic system cost of manufacture is higher, if will be applied to large-scale anti-invasion security protection, detect, needing more high-precision telescopic system, corresponding production cost is also higher, does not meet economic benefit.
Summary of the invention
The embodiment of the present invention provides a kind of security detection method and relevant apparatus, on a large scale and the high security protection identified of degree of accuracy detect.
Security detection method provided by the invention, comprising: the laser of transmitting at least two bundles, scanning object; Obtain the sweep parameter of object, described sweep parameter comprises: apart from Z, distance X and distance Y, described is the distance of described object and generating laser apart from Z, described distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate; The shape information that generates object according to described sweep parameter, described shape information is the set of the coordinate points of object shape; Calculate the characteristic parameter of described shape information; Utilize described characteristic parameter according to preset analysis rule, to determine the type of described object.
Security protection pick-up unit provided by the invention, comprising: scanning element, and for launching the laser of at least two bundles, scanning object; Acquiring unit, for obtaining the sweep parameter of object, described sweep parameter comprises: apart from Z, and distance X and distance Y, described is the distance of described object and generating laser apart from Z, and described distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate; Generation unit, for generate the shape information of object according to described sweep parameter, described shape information is the set of the coordinate points of object shape; Computing unit, for calculating the characteristic parameter of described shape information; Analytic unit, for utilizing described characteristic parameter to determine the type of described object according to preset analysis rule.
As can be seen from the above technical solutions, the embodiment of the present invention has the following advantages: the present invention is by the laser scanning object of transmitting at least two bundles, obtain the distance of object and generating laser, by this distance, set up the shape information of reference frame evaluating objects thing, reach the effect of accurately determining invader type.What obtain due to the present invention is the shape information that laser reflection returns, and is subject to disturb less extraneously, and degree of accuracy is high; And optical system simple structure of the present invention, by transmitting multiple laser, just can carry out large-scale security protection detection, manufacturing cost is lower.
Accompanying drawing explanation
Fig. 1 is a schematic flow sheet of security detection method in the embodiment of the present invention;
Fig. 2 is another schematic flow sheet of security detection method in the embodiment of the present invention;
Fig. 3 is another schematic flow sheet of security detection method in the embodiment of the present invention;
Fig. 4 is an application examples schematic flow sheet of security detection method in the embodiment of the present invention;
Fig. 5 is a logical organization schematic diagram of security protection pick-up unit in the embodiment of the present invention.
Embodiment
The embodiment of the present invention provides a kind of security detection method and relevant apparatus, on a large scale and the high security protection identified of degree of accuracy detect.
Refer to Fig. 1, in the embodiment of the present invention, security detection method embodiment comprises:
101, scanning object;
The laser of the generating laser transmitting at least two bundle specific wavelengths of security protection pick-up unit, scanning object; When the Ear Mucosa Treated by He Ne Laser Irradiation of this specific wavelength is during to object, this laser is reflected back in the laser pickoff of security protection pick-up unit by meeting.
Security protection pick-up unit has plural generating laser, and the number of concrete generating laser is determined according to the demand of actual detection scope, does not limit herein.
The specific wavelength of generating laser Emission Lasers can be 532,635,780,905,1064 or the laser of 1550nm, does not specifically limit herein.
102, obtain the sweep parameter of object;
The laser that security protection pick-up unit reflects by reception obtains the distance Z of object and generating laser, then according to setting up reference frame apart from the correlation parameter of Z and generating laser motion scan, determine the sweep parameter of each reflection spot respective coordinates point in reference frame in object.
This sweep parameter comprises: apart from Z, and distance X and distance Y; Wherein, distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate.
This object is a macroscopical concept, on actual object, there are a plurality of laser reflection points, actual apart from Z is the distance that on object, laser reflection is put laser emission point, so security protection pick-up unit can get with laser reflection to count to organize accordingly sweep parameter (apart from Z, distance X and distance Y) information more on same object.
103, generate the shape information of object;
Security protection pick-up unit generates the shape information of object according to sweep parameter (apart from Z, distance X and distance Y), shape information is the set of the coordinate points of object shape.
Take in the reference planes that generating laser is visual angle, security protection pick-up unit has generated the object surface profile image scanning, the coordinate points that these images are formed by numerous laser reflection point forms, and this coordinate points includes this reflection spot in each to the distance Z of laser emission point.
104, calculated characteristics parameter;
After having generated the surface profile image of this object, security protection pick-up unit can be measured calculating to this contour images, extracts the parameters for shape characteristic relevant to object surface configuration; Or in conjunction with the shape information of continuous multiple frames, extract the kinematic feature factor relevant to object motion state.
This characteristic parameter can comprise: the width of object, and the displacement of line segment, the distance of the mid point of continuous two line segments, the translational speed of line segment, the coordinate of each section of object is counted, the curvature of image, boundary length, the linearity of image or standard deviation etc.
Be understandable that, according to actual conditions, security protection pick-up unit can calculate above-mentioned a kind of, or several, or other characteristic parameter, is specifically not construed as limiting herein.
105, the type of evaluating objects thing.
Security protection pick-up unit utilizes the above-mentioned characteristic parameter calculating, and according to the shape facility of preset analysis rule evaluating objects thing, the object of distinguishing invasion is people or other object, avoids leaf or other small size animals to enter sweep limit and causes that mistake is alert.
Security protection pick-up unit of the present invention, by the laser scanning object of transmitting at least two bundles, obtains the distance of object and generating laser, sets up the shape information of reference frame evaluating objects thing by this distance, reaches the effect of accurately determining invader type.What obtain due to the present invention is the shape information that laser reflection returns, and is subject to disturb less extraneously, and degree of accuracy is high; And optical system simple structure of the present invention, by transmitting multiple laser, just can carry out large-scale security protection detection, manufacturing cost is lower.
Security protection pick-up unit, after installation is fixing, can scan the background map in current detection region in advance, to analyze better invader, refers to Fig. 2, and in the embodiment of the present invention, another embodiment of security detection method comprises:
201, scanning background thing;
After the installation of security protection pick-up unit is fixing, scan in advance the still image in current detection region, as the reference background of analyzing invader, this can be preset and upgrade at set intervals run-down with reference to background, to keep the accuracy of context parameter.
202, the sweep parameter of background extraction thing;
The sweep parameter of security protection pick-up unit background extraction thing, sweep parameter is herein mainly the ranging data of current environment.
After getting the sweep parameter of background objects, can carry out filtering processing to this sweep parameter, prevent the noise effect that the situations such as shake or Changes in weather cause.Concrete filtering method can adopt the separated window filtering algorithm of bilateral.
203, set up and store background map;
Security protection pick-up unit, according to the shape information of filtered sweep parameter generation background thing, carries out Background fitting to each target object, sets up background map, and stores this background map into this locality, to call.If background map is predisposed at set intervals, upgrade, after having set up a background map with regard to initialization timing device, enter context update timing next time.
204, scanning object;
The laser of the above specific wavelength of generating laser transmitting two bundle of security protection pick-up unit, scanning object.If current scanning area is all in static state in a period of time, the object of scanning is background objects; If there have object to send in current scanning area to be mobile, the object of scanning is background objects and invader.
According to actual conditions, direction of scanning that can generating laser is set to horizontal scanning or vertical scanning, the invasion that horizontal scanning is moved for detection of object along continuous straight runs (as vehicle enters), the invasion that vertical scanning moves in the vertical direction for detection of object (climbing into as climbed over the walls).
205, obtain the sweep parameter of object;
The content of the step 205 in the present embodiment is identical with the content of step 102 in the embodiment shown in earlier figures 1, repeats no more herein.
206, judge whether to need analyzing and testing;
Security protection pick-up unit is poor by the distance Z of the distance Z of object and background objects, obtains prospect variable.
It can be that average is done poor (this average is the distance of average each reflection spot with laser emission point) that the distance Z of above-mentioned object and the distance Z of background objects make difference, can be also total amount work poor (this total amount be all reflection spots and laser emission point distance with).
Security protection pick-up unit is the size of prospect variable and first threshold (prospect variable computing method are different, and the value size of first threshold setting is also different) relatively, if this prospect variable is greater than first threshold, to triggering step 207.
In order to get rid of the interference of some weather conditions or small size shelter, keeper can set a first threshold, when prospect variable reaches first threshold, just trigger the step of analyzing invader.
Judge whether to trigger analytical procedure except using said method, can also probability of use threshold method: whether the distance Z that judges fixing several impact points in scanning area is greater than a threshold value, if so, corresponding counter adds one; In preset duration, when this counter reaches preset parameter, trigger the step of analyzing invader.
According to actual conditions, judging whether to trigger analytical procedure can also have other method, is specifically not construed as limiting herein.
207, generate the shape information of object;
The content of the step 207 in the present embodiment is identical with the content of step 103 in the embodiment shown in earlier figures 1, repeats no more herein.
208, shape information is carried out to background filtering;
Security protection pick-up unit extracts background map, the shape information of contrast background map and current goal thing, and the part identical with the shape information of background objects in the shape information of removal object, obtains the shape information of invader.
The shape information of current goal thing is carried out after background filtering, and computing machine only needs processing target thing middle distance Z that the information of the part of significant change occurs, and makes to need in frame data the minimizing of counting of subsequent treatment, greatly reduces operand.
209, calculated characteristics parameter;
After having carried out background filtering, the surface profile image of invader is clearer, security protection pick-up unit carries out the measurement calculating of characteristic parameter for the contour images of invader, extract the parameters for shape characteristic relevant to invader surface configuration, and in conjunction with in a certain period, the shape information of the invader of continuous multiple frames, extracts the kinematic feature factor relevant to invader motion state.
210, analyze the type of invader.
Security protection pick-up unit utilizes the above-mentioned characteristic parameter calculating, and analyzes the shape facility of invader according to preset analysis rule, and distinguishing invader is people or other object, avoids leaf or other small size animals to enter sweep limit and causes that mistake is alert.
In the present embodiment, in advance the background of scanning area is scanned, contrast in real time the information of background map and current scanning area, judge whether to change, if so, trigger the step of analyzing and testing, make the analyzing and testing of invader more rationally with accurate; And, in the process of carrying out invader analysis, having added background filtering, counting of making to process in computing greatly reduces, and improved operation efficiency.
In some complex environments, object is more and take on a different character, and now needs the quantity of coordinate points to be processed larger, need to carry out some and cuts apart and merge, and refers to Fig. 3, and in the embodiment of the present invention, another embodiment of security detection method comprises:
301, scanning object;
After having carried out background scans in advance, laser are restrainted in security protection pick-up unit transmitting four, scan respectively the region of current monitoring.The region non-overlapping copies of this four bundles laser scanning, and the scope of this four bundles laser scanning just covers whole guarded region.
302, obtain the sweep parameter of object;
The content of the step 302 in the present embodiment is identical with the content of step 102 in the embodiment shown in earlier figures 1, repeats no more herein.
303, judge whether to need analyzing and testing;
Security protection pick-up unit is poor apart from the average of Z apart from average and the background objects of Z by object, obtains prospect variable.
Security protection pick-up unit compares the size of prospect variable and first threshold, if this prospect variable is greater than first threshold, to triggering step 304.
304～305, the content of the step 304 in the present embodiment to 305 is identical with 207 to 208 content in the embodiment shown in earlier figures 2, repeats no more herein.
306, shape information is carried out to Image Segmentation Methods Based on Features;
Security protection pick-up unit is analyzed the feature of current monitoring environment in advance, tests the characteristic quantity of the various objects that may exist, and calculates and obtain Second Threshold.According to the performance of the needs of current monitoring or treatment facility, Second Threshold can be set to one or more groups, does not do concrete restriction herein.
Suppose that Second Threshold is predisposed to a, after obtaining the shape information of invader, scan successively in the same direction each coordinate points of invader shape information, the coordinate points that continuous 2 distances are no more than to Second Threshold a is classified as a class, the coordinate points that belongs to same object is divided in same one piece of data as far as possible, be convenient to the follow-up feature extraction of carrying out, reduce the complexity of computing.
307, calculated characteristics parameter;
After carrying out Image Segmentation Methods Based on Features, security protection pick-up unit can carry out feature extraction for every one piece of data of invader shape information, extracts the parameters for shape characteristic relevant to object surface configuration (as: distance of the mid point of the width of object, continuous two line segments, the coordinate of each section of object are counted); Or in conjunction with the shape information of continuous multiple frames, extract the kinematic feature factor relevant to object motion state (as: displacement of line segment, the translational speed of line segment).
In parameters for shape characteristic, applying maximum is the feature extraction of straight-line segment, because most object can be combined by comparatively regular straight-line segment, and in monitoring project, need the invasion personnel that survey often to show as upright line segment feature, the emphasis that so linear feature extraction algorithm is for we to be paid close attention to, common line segments extraction algorithm has linear regression, Hough transformation, delta algorithm, greatest hope value-based algorithm etc.
308, shape information is carried out to information fusion;
One, Space integration:
In the shape information of a frame, security protection pick-up unit obtains the distance md of the mid point of continuous two line segments, if be less than the 3rd threshold value apart from md, uses the line segment of the mid point connection of two line segments to replace this two line segments, until all distance md are more than or equal to the 3rd threshold value, Space integration finishes.
Due in some complex environments, object takes on a different character, and the complete object that object is comprised of a plurality of parts, now need the quantity of coordinate points to be processed larger, point continuous in the shape information of one frame is merged, contribute to conformity goal thing prototype, reduce operand, be convenient to extract how useful characteristic parameter.Such as people's one leg and a pole, data characteristics in section may be consistent, cannot distinguish, if but in two continuous sections, all found similar feature, be at this moment that a people's the possibility of two legs is just much older.Above-mentioned Space integration method is only to utilize a kind of characteristic parameter to carry out one of information fusion to be understandable that, in practical operation, can also have other Space integration method for example, is specifically not construed as limiting herein.
Two, Fusion in Time:
In the shape information of every two continuous frames, security protection pick-up unit obtains the displacement d of line segment, if be less than the 4th threshold value apart from d, the shape information of this two frame is merged, and obtains the movement locus of this line segment.
Owing to often can not provide enough data analysis in a frame shape information, now need in conjunction with in the same period, the shape information of continuous several frames is analyzed, the shape information with continuous several frames of same motion trajectory is merged, thereby reduced operand and can carry out feature more accurately and describe.Equally, the above-mentioned Fusion in Time method providing is only also a kind of giving an example, and can have other implementation, is specifically not construed as limiting herein.
309, calculated characteristics parameter again;
The invader shape information of security protection pick-up unit after to information fusion calculated, and obtains more accurate characteristic parameter, as: the width W of invader, the displacement D of invader, the translational speed S of invader.
310, analyze the type of invader.
The new characteristic parameter of security protection pick-up unit utilization carries out computing according to the weight proportion of each preset parameter, according to the type of operation result judgement invader.
In the embodiment of the present invention, the shape information of invader has been carried out to Image Segmentation Methods Based on Features and information fusion, reduced the complexity of computing, improved the accuracy of analyzing invader.
Implementation procedure for a better understanding of the present invention, below can be described in detail security detection method of the present invention with a concrete application scenarios, please refer to Fig. 4, is specially:
401, Emission Lasers;
Security protection pick-up unit is by 4 generating laser Emission Lasers, and each generating laser sends by lens the light beam that the angle of divergence is 30 degree, and it is the laser curtain of 120 degree that 4 laser beams form valid analysing range.
Generating laser can be pressed close to the installation of guardrail position, adjusts the position that makes each generating laser during installation, makes the sweep limit non-overlapping copies of each generating laser, and no-raster gap in scanning area.
402, receive return laser light;
The laser pickoff of security protection pick-up unit receives the laser that all objects are reflected back, and the laser signal returning is converted to pulse electrical signal by sensor, this pulse electrical signal is amplified, and set up pulse frequency spectrum image according to time parameter.
403, computing time is poor;
This pulse frequency spectrum image of the analysis of security protection pick-up unit, calculates from Laser emission to the mistiming receiving.The calculating of mistiming and calibration are that time and the digital conversion circuit based on high integration completes.
The optical system of security protection pick-up unit only need comprise Laser emission and receiver module, simple in structure; Signal conversion is that the circuit module by high integration completes, and volume is little and cost is low.
404, obtain the sweep parameter of object;
Security protection pick-up unit first calculates the distance Z of object and generating laser by mistiming and the light velocity, then obtain the deviation angle of corresponding time inner laser transmitter, finally use this apart from Z and deviation angle, utilize polar coordinates to set up reference frame, obtain distance X and the distance Y of each object reflection spot.
405, judge whether to need analyzing and testing;
Security protection pick-up unit is poor apart from the average of Z apart from average and the background objects of Z by object, obtains prospect variable.
Security protection pick-up unit compares the size of prospect variable and first threshold, if this prospect variable is greater than first threshold, to triggering step 406.
406, generate the shape information of object;
The content of the step 406 in the present embodiment is identical with 207 content in the embodiment shown in earlier figures 2, repeats no more herein.
407, shape information is carried out to background filtering;
Security protection pick-up unit extracts background map, the shape information of contrast background map and current goal thing, and the part identical with the shape information of background objects in the shape information of removal object, obtains the shape information of invader.
408, shape information is carried out to Image Segmentation Methods Based on Features;
The content of the step 408 in the present embodiment is identical with 306 content in the embodiment shown in earlier figures 3, repeats no more herein.
409, calculated characteristics parameter;
After carrying out Image Segmentation Methods Based on Features, security protection pick-up unit can carry out feature extraction for every one piece of data of invader shape information, extracts the distance md of the width w of object and the mid point of continuous two line segments; And in conjunction with the shape information of continuous multiple frames, extract the displacement d of line segment and the translational speed s of line segment.
According to following formula, carry out the computing of characteristic parameter:
x
mid＝(x
startx+x
end)/2；
y
mid＝(y
startx+y
end)/2；
s＝d/t；
X
startxand y
startxbe respectively the coordinate figure of an object starting point x axle and y axle, x
endand y
endbe respectively the coordinate figure of an object terminal x axle and y axle, x
midand y
midbe respectively the mid point x axle of a line segment and the coordinate figure of y axle, x
mid 'and y
mid 'be respectively the mid point x axle of another line segment and the coordinate figure of y axle continuously, x
pastmidand y
pastmidbe respectively the mid point x axle of same line segment and the coordinate figure of y axle of another frame shape information continuously, t is the interval time of obtaining the continuous shape information of two frames.
410, shape information is carried out to information fusion;
In the shape information of a frame, in conjunction with width w with apart from md, the shape information of invader is carried out to Space integration, concrete fusion process can refer step 308;
In the shape information of every two continuous frames, Binding distance d and speed s carry out Fusion in Time to the shape information of invader, and concrete fusion process can refer step 308.
411, calculated characteristics parameter again;
The invader shape information of security protection pick-up unit after to information fusion calculated, and obtains more accurate characteristic parameter: the width W of invader, the displacement D of invader, the translational speed S of invader.
412, analyze the type of invader.
Security protection pick-up unit obtains width W, distance B and the corresponding weight B1 of speed S, B2 and B3;
By parameters value substitution formula: g (x)=B
tx+b
0in calculate, X=(W, D, S...), X is n dimensional feature vector, B=(B
1, B
2, B
3...), B is n dimensional weight vector, B
texpression is carried out transposition, b to matrix B
0for preset human body judgement parameter, g (x) is judged result function, and n is greater than zero integer;
Sorting criterion is: when g (x) is greater than zero, invader is behaved; When g (x) is less than or equal to zero, invader is inhuman.
When g (x) is greater than zero, trigger alarm device is reported to the police.
To describing for carrying out the embodiment of the security protection pick-up unit of the present invention of above-mentioned security detection method, its logical organization please refer to Fig. 5 below, and in the embodiment of the present invention, security protection pick-up unit embodiment comprises:
Scanning element 501, for launching the laser of at least two bundles, scanning object;
Acquiring unit 502, for obtaining the sweep parameter of object, sweep parameter comprises: apart from Z, and distance X and distance Y, apart from Z, be the distance of object and generating laser, distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate;
Generation unit 503, for generate the shape information of object according to this sweep parameter, shape information is the set of the coordinate points of object shape;
Computing unit 504, for calculating the characteristic parameter of this shape information;
Analytic unit 505, for utilizing this characteristic parameter to determine the type of this object according to preset analysis rule.
Security protection pick-up unit in the embodiment of the present invention can further include:
Storage unit 506, for the shape information of pre-stored scanning background thing.
Trigger element 507, for the distance Z of the distance Z of object and background objects is poor, obtains prospect variable, if prospect variable is greater than first threshold, to triggering generation unit.
Background filtering unit 508, for the shape information of object being carried out to background filtering according to the shape information of background objects, obtains the shape information of invader.
Image Segmentation Methods Based on Features unit 509, for according to Second Threshold, the shape information of invader being classified, is classified as a class by the coordinate points that in coordinate points, continuous 2 distances are no more than Second Threshold.
Space integration unit 510, for the shape information at a frame, if the distance md of the mid point of continuous two line segments is less than the 3rd threshold value, use the line segment of the mid point connection of two line segments to replace this two line segments, until all distance md are more than or equal to the 3rd threshold value, Space integration finishes;
And/or,
Fusion in Time unit 511, for the shape information in every two continuous frames, if the displacement d of line segment is less than the 4th threshold value, merges the shape information of this two frame, and obtains the movement locus of line segment.
The scanning element of the security protection pick-up unit in the embodiment of the present invention can comprise:
Laser emitting module 5011, for restrainting laser to object transmitting at least two;
Laser pick-off module 5012, for the laser of receiving target thing reflection;
The acquiring unit of the security protection pick-up unit in the embodiment of the present invention can comprise:
Mistiming detection module 5021, for detection of Emission Lasers and the mistiming that receives reflection laser;
Sweep parameter computing module 5022, for calculating the reflection object of laser and the distance Z of generating laser according to this mistiming, and according to the deviation angle of generating laser with apart from Z, utilize polar coordinates to set up with reference frame, calculate distance X and the distance Y of object.
The concrete reciprocal process of the unit of embodiment of the present invention member terminal is as follows:
Laser emitting module 5011 in scanning element 501 is to object transmitting at least two bundle laser, when laser runs into object by laser reflection, the laser of the laser pick-off module 5012 receiving target thing reflections in scanning element 501 is also converted to pulse electrical signal by the laser signal returning by sensor, this pulse electrical signal is amplified, and set up pulse frequency spectrum image according to time parameter.
Mistiming detection module 5021 in acquiring unit 502 is analyzed this pulse frequency spectrum image, calculates from Laser emission to the mistiming receiving.The calculating of mistiming and calibration are that time and the digital conversion circuit based on high integration completes.Sweep parameter computing module 5022 in acquiring unit 502 is first according to the distance Z of mistiming and light velocity calculating object and generating laser, then obtain the deviation angle of corresponding time inner laser transmitter, finally use this apart from Z and deviation angle, utilize polar coordinates to set up reference frame, obtain distance X and the distance Y of each object reflection spot.
First trigger element 507 extracts the distance Z of background objects, and the distance Z of this background objects is the shape information of the pre-stored background objects of storage unit 506; Then the distance Z of the distance Z of object and background objects is poor, obtain prospect variable, if prospect variable is greater than first threshold, to triggering generation unit 503.
Generation unit 503 generates the shape information of object according to the sweep parameter of object, this shape information is the set of the coordinate points of object shape.The background filtering unit 508 contrast shape information of background objects and the shape informations of current goal thing, the part identical with the shape information of background objects in the shape information of removal object, obtains the shape information of invader.
Classify to the shape information of invader according to Second Threshold in Image Segmentation Methods Based on Features unit 509, the coordinate points that in this coordinate points, continuous 2 distances are no more than Second Threshold is classified as to a class.Computing unit 504 carries out feature extraction for sorted shape information, extracts the parameters for shape characteristic relevant to object surface configuration (as: the width w of object, the distance md of mid point of continuous two line segments be k, the coordinate of each section of object is counted); Or in conjunction with the shape information of continuous multiple frames, extract the kinematic feature factor relevant to object motion state (as: the displacement d of line segment, the translational speed s of line segment).
After carrying out characteristic parameter extraction, first Space integration unit 510 obtains the distance md obtaining after characteristic parameter extraction, then contrast apart from md and the 3rd threshold value, if be less than the 3rd threshold value apart from md, use the line segment of the mid point connection of two line segments to replace this two line segments, until all distance md are more than or equal to the 3rd threshold value, Space integration finishes.Then, Fusion in Time unit 511, in the shape information of every two continuous frames, obtains the displacement d of line segment, if be less than the 4th threshold value apart from d, the shape information of this two frame is merged, and obtains the movement locus of line segment.
Computing unit 504 is the characteristic parameter of the shape information of computing information after merging again, and analytic unit 505 utilizes this characteristic parameter according to preset analysis rule, to determine the type of invader.
Preset analysis rule can be: first obtain characteristic parameter width W, distance B and the corresponding weight B of speed S
1, B
2and B
3; Then by parameters value substitution formula: g (x)=B
tx+b
0in calculate, when g (x) is greater than zero, invader is behaved; When g (x) is less than or equal to zero, invader is inhuman.Above-mentioned analysis rule is only one and is understandable that for example, also has in actual applications other analysis rule, is specifically not construed as limiting herein.
One of ordinary skill in the art will appreciate that all or part of step realizing in above-described embodiment method is to come the hardware that instruction is relevant to complete by program, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium of mentioning can be ROM (read-only memory), disk or CD etc.
Above a kind of security detection method provided by the present invention and relevant apparatus are described in detail, for one of ordinary skill in the art, thought according to the embodiment of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (17)
1. a security detection method, is characterized in that, comprising:
The laser of transmitting at least two bundles, scanning object;
Obtain the sweep parameter of object, described sweep parameter comprises: apart from Z, distance X and distance Y, described is the distance of described object and generating laser apart from Z, described distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate;
The shape information that generates object according to described sweep parameter, described shape information is the set of the coordinate points of object shape;
Calculate the characteristic parameter of described shape information; Described characteristic parameter comprises: the width w of object, the displacement d of line segment, the distance md of the mid point of continuous two line segments, the translational speed s of line segment;
Utilize described characteristic parameter according to preset analysis rule, to determine the type of described object.
2. method according to claim 1, is characterized in that,
Described object comprises: background objects and invader;
Described method also comprises:
The above laser of transmitting two bundle, scanning background thing;
The sweep parameter of background extraction thing;
According to the shape information of described sweep parameter generation background thing;
Store the shape information of described background objects into this locality.
3. method according to claim 2, is characterized in that, described in comprise after obtaining the sweep parameter of object:
The distance Z of the distance Z of described object and background objects is poor, obtain prospect variable;
If described prospect variable is greater than first threshold, to triggering the described step that generates the shape information of object according to sweep parameter.
4. method according to claim 3, is characterized in that, before the characteristic parameter of described calculating shape information, comprises:
According to the shape information of background objects, the shape information of object is carried out to background filtering, obtain the shape information of invader.
5. method according to claim 4, is characterized in that, before the characteristic parameter of described calculating shape information, comprises:
According to Second Threshold, the shape information of invader is classified, the coordinate points that in described coordinate points, continuous 2 distances are no more than Second Threshold is classified as to a class.
6. method according to claim 1, is characterized in that, the characteristic parameter of described calculating shape information comprises:
According to following formula, carry out the computing of characteristic parameter:
X
mid=(X
startx+X
end)／2；
y
mid=(y
startx+y
end)／2；
s=d/t；
Described x
startxand y
startxbe respectively the coordinate figure of an object starting point x axle and y axle, described x
endand y
endbe respectively the coordinate figure of an object terminal x axle and y axle, described x
midand y
midbe respectively the mid point x axle of a line segment and the coordinate figure of y axle, described x
mid'and y
mid'be respectively the mid point x axle of another line segment and the coordinate figure of y axle continuously, described x
pastmidand y
pastmidbe respectively the mid point x axle of same line segment and the coordinate figure of y axle of another frame shape information continuously, t is the interval time of obtaining the continuous shape information of two frames.
7. method according to claim 1, is characterized in that, after the characteristic parameter of described calculating shape information, comprises:
In the shape information of a frame, if the distance md of the mid point of continuous two line segments is less than the 3rd threshold value, use the line segment of the mid point connection of two line segments to replace described two line segments, until all distance md are more than or equal to the 3rd threshold value, Space integration finishes;
And/or,
In the shape information of every two continuous frames, if the displacement d of line segment is less than the 4th threshold value, the shape information of described two frames is merged, and obtain the movement locus of described line segment.
8. method according to claim 7, is characterized in that, the described characteristic parameter that utilizes determines that according to preset analysis rule the type of described invader comprises:
Shape information after information fusion is carried out to the calculating of characteristic parameter, obtain new characteristic parameter and comprise: the width W of invader, the displacement D of invader, the translational speed S of invader;
Utilize new characteristic parameter to carry out computing according to the weight proportion of each preset parameter, according to operation result, judge the type of described invader.
9. method according to claim 8, is characterized in that, the new characteristic parameter of described utilization carries out computing according to the weight proportion of preset each parameter, judges that the type of described invader comprises according to operation result:
By new characteristic parameter substitution formula: g (x)=B
tx+b
0in calculate, described X=(W, D, S...), X is n dimensional feature vector, described B=(B
1, B
2, B
3...), B is n dimensional weight vector, B
1, B
2, B
3represent respectively the weight of each characteristic parameter, B
texpression is carried out transposition to matrix B, described b
0for preset human body judgement parameter, described g (x) is judged result function, and described n is greater than zero integer;
Sorting criterion is: when g (x) is greater than zero, described invader is behaved; When g (x) is less than or equal to zero, described invader is inhuman.
10. according to the method described in claim 1,3,4 or 5, it is characterized in that, described scanning object, the sweep parameter of obtaining object comprises:
The laser of receiving target thing reflection;
Detect Emission Lasers and the mistiming that receives reflection laser;
According to the described mistiming, calculate and reflect the object of laser and the distance of generating laser, obtain apart from Z;
Obtain the deviation angle of generating laser;
According to described deviation angle with apart from Z, utilize polar coordinates to set up with reference frame, calculate distance X and the distance Y of object.
11. 1 kinds of security protection pick-up units, is characterized in that, comprising:
Scanning element, for launching the laser of at least two bundles, scanning object;
Acquiring unit, for obtaining the sweep parameter of object, described sweep parameter comprises: apart from Z, and distance X and distance Y, described is the distance of described object and generating laser apart from Z, and described distance X and distance Y are respectively horizontal range and the vertical range that object is fastened at reference coordinate;
Generation unit, for generate the shape information of object according to described sweep parameter, described shape information is the set of the coordinate points of object shape;
Computing unit, for calculating the characteristic parameter of described shape information; Described characteristic parameter comprises: the width w of object, the displacement d of line segment, the distance md of the mid point of continuous two line segments, the translational speed s of line segment;
Analytic unit, for utilizing described characteristic parameter to determine the type of described object according to preset analysis rule.
12. devices according to claim 11, is characterized in that, described device also comprises:
Storage unit, for storing the shape information of scanning background thing in advance.
13. devices according to claim 12, is characterized in that, described device also comprises:
Trigger element, for the distance Z of the distance Z of described object and background objects is poor, obtains prospect variable, if described prospect variable is greater than first threshold, to triggering generation unit.
14. devices according to claim 12, is characterized in that, described device also comprises:
Background filtering unit, for the shape information of object being carried out to background filtering according to the shape information of background objects, obtains the shape information of invader.
15. devices according to claim 12, is characterized in that, described device also comprises:
Image Segmentation Methods Based on Features unit, for according to Second Threshold, the shape information of invader being classified, is classified as a class by the coordinate points that in described coordinate points, continuous 2 distances are no more than Second Threshold.
16. devices according to claim 15, is characterized in that, described device also comprises:
Space integration unit, for the shape information at a frame, if the distance md of the mid point of continuous two line segments is less than the 3rd threshold value, use the line segment of the mid point connection of two line segments to replace described two line segments, until all distance md are more than or equal to the 3rd threshold value, Space integration finishes;
And/or,
Fusion in Time unit, for the shape information in every two continuous frames, if the displacement d of line segment is less than the 4th threshold value, merges the shape information of described two frames, and obtains the movement locus of described line segment.
17. according to claim 11 to the device described in 15 any one, it is characterized in that, described scanning element comprises:
Laser emitting module, for restrainting laser to object transmitting at least two;
Laser pick-off module, for the laser of receiving target thing reflection;
Described acquiring unit also comprises:
Mistiming detection module, for detection of Emission Lasers and the mistiming that receives reflection laser;
Sweep parameter computing module, for calculating the reflection object of laser and the distance Z of generating laser according to the described mistiming, and according to the deviation angle of generating laser with apart from Z, utilize polar coordinates to set up with reference frame, calculate distance X and the distance Y of object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010589176.7A CN102538695B (en) | 2010-12-15 | 2010-12-15 | Security detection method and related device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010589176.7A CN102538695B (en) | 2010-12-15 | 2010-12-15 | Security detection method and related device thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102538695A CN102538695A (en) | 2012-07-04 |
| CN102538695B true CN102538695B (en) | 2014-03-12 |
Family
ID=46346201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010589176.7A Active CN102538695B (en) | 2010-12-15 | 2010-12-15 | Security detection method and related device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102538695B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152558B (en) * | 2013-03-29 | 2015-10-07 | 西南交通大学 | Based on the intrusion detection method of scene Recognition |
| CN107145823A (en) * | 2017-03-29 | 2017-09-08 | 深圳市元征科技股份有限公司 | A kind of image-recognizing method, pattern recognition device and server |
| CN106940919A (en) * | 2017-04-17 | 2017-07-11 | 三峡大学 | A kind of electric line foreign matter intrusion detection intelligent early-warning method |
| CN109006555B (en) * | 2018-05-22 | 2022-02-11 | 东莞市莱诺实业有限公司 | Work control method and device for pet toy |
| CN109816699B (en) * | 2019-01-30 | 2021-07-27 | 国网智能科技股份有限公司 | Holder angle calculation method based on background suppression interframe difference method |
| CN112116686B (en) * | 2020-09-21 | 2022-04-08 | 猫岐智能科技（上海）有限公司 | Data fusion drawing system and method based on multi-direction light curtain scanning |
| CN112731430B (en) * | 2020-12-15 | 2024-06-11 | 武汉万集光电技术有限公司 | High-altitude parabolic detection method and system based on laser radar |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628237A (en) * | 2002-09-30 | 2005-06-15 | 石川岛播磨重工业株式会社 | Method of measuring object and system for measuring object |
| US7616817B2 (en) * | 2007-04-12 | 2009-11-10 | The United States Of America As Represented By The Secretary Of The Navy | Three dimensional shape correlator |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008158690A (en) * | 2006-12-21 | 2008-07-10 | Sogo Keibi Hosho Co Ltd | Mobile body detection apparatus, security robot, mobile body detection method, and mobile body detection program |
-
2010
- 2010-12-15 CN CN201010589176.7A patent/CN102538695B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628237A (en) * | 2002-09-30 | 2005-06-15 | 石川岛播磨重工业株式会社 | Method of measuring object and system for measuring object |
| US7616817B2 (en) * | 2007-04-12 | 2009-11-10 | The United States Of America As Represented By The Secretary Of The Navy | Three dimensional shape correlator |
Non-Patent Citations (5)
| Title |
|---|
| JP特开2008-158690A 2008.07.10 |
| 一种基于激光雷达和视觉的行人检测方法;钱慧佳等;《上海交通大学学报》;20100731;第44卷(第7期);第946-950页 * |
| 基于激光雷达的车辆跟踪与识别方法;甘志梅等;《上海交通大学学报》;20090630;第43卷(第6期);第923-926页 * |
| 甘志梅等.基于激光雷达的车辆跟踪与识别方法.《上海交通大学学报》.2009,第43卷(第6期),第923-926页. |
| 钱慧佳等.一种基于激光雷达和视觉的行人检测方法.《上海交通大学学报》.2010,第44卷(第7期),第946-950页. |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102538695A (en) | 2012-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102538695B (en) | Security detection method and related device thereof | |
| US10690773B2 (en) | Systems and methods for efficient multi-return light detectors | |
| US9075143B2 (en) | Sparse array RF imaging for surveillance applications | |
| Parrish et al. | Empirical comparison of full-waveform lidar algorithms | |
| US11859976B2 (en) | Automatic locating of target marks | |
| CN112867939B (en) | Real-time estimation of DC offset and noise power for light detection and ranging | |
| Henriksson et al. | Continuously scanning time-correlated single-photon-counting single-pixel 3-D lidar | |
| CN111724558B (en) | Monitoring method, monitoring device and intrusion alarm system | |
| US20180313950A1 (en) | CNN-Based Remote Locating and Tracking of Individuals Through Walls | |
| US20220082659A1 (en) | Echo Signal Processing Method and Apparatus, System, and Storage Medium | |
| CN117269940B (en) | Point cloud data generation method and perception capability verification method of laser radar | |
| CN116547562A (en) | Point cloud noise filtering method, system and movable platform | |
| EP3276576A1 (en) | Disparity estimation by fusion of range data and stereo data | |
| CN105698915B (en) | A kind of optical fiber Recognition of Vibration Sources method and device, system | |
| CN104464055A (en) | PSD linear array and ultrasonic linear array combined passenger flow volume calculation system | |
| BE1025329A9 (en) | Human body recognition method and human body recognition sensor | |
| US6616044B1 (en) | Methods and apparatus for obtaining imaging information in bar code scanners | |
| EP3834125A1 (en) | System and method for detecting, tracking and counting human objects of interest with an improved height calculation | |
| KR102120812B1 (en) | Target recognition and classification system based on probability fusion of camera-radar and method thereof | |
| US20220334264A1 (en) | Computer implemented method for identifying transparent and/or mirroring plane candidates and uav using the same | |
| US20090153326A1 (en) | Method for locating intruder | |
| CN108919236A (en) | A kind of space junk laser ranging effect emulation analysis method and device | |
| CN111213069B (en) | Obstacle avoidance device and method based on coherent light | |
| Ronnback et al. | On filtering of laser range data in snowfall | |
| CN117332585B (en) | Simulation model modeling method and system for time-of-flight ranging laser radar |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PP01 | Preservation of patent right | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20201119 Granted publication date: 20140312 |
|
| PD01 | Discharge of preservation of patent |
Date of cancellation: 20210112 Granted publication date: 20140312 |
|
| PD01 | Discharge of preservation of patent | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20210112 Granted publication date: 20140312 |
|
| PP01 | Preservation of patent right | ||
| PD01 | Discharge of preservation of patent |
Date of cancellation: 20230509 Granted publication date: 20140312 |
|
| PD01 | Discharge of preservation of patent |