CN102201058A - Cat eye effect object recognition algorithm of active and passive imaging system sharing same aperture - Google Patents

Abstract

The invention provides a cat eye effect object recognition algorithm of active and passive imaging systems sharing a same aperture. The algorithm is suitable for detecting and recognizing optical targets with a characteristic of cat eye effect. The algorithm of the invention improves the cat eye effect object recognition algorithm based on gray scales and shape features. For the active and passive imaging systems sharing the same aperture, differential operation is performed between active and passive images after image registration so that background can be filtered. Rough registering algorithm can be improved. A search scope of matching feature points in a second image can be reduced in horizontal and vertical directions. And algorithm efficiency can be raised. The algorithm possesses good utility value and wide application prospect in the fields of laser imaging and digital image processing technology.

Description

" opal " effect Target Recognition Algorithms of active imaging and passive imaging of common aperture system

(1) technical field

The present invention is for taking aim at the Target Recognition Algorithms of equipment at the optoelectronic device that has optical lens or sight.It is main by motion video and identification " opal " effect target to utilize the active imaging and passive imaging of common aperture system to obtain, and belongs to laser imaging and digital image processing techniques field.

(2) background technology

When one of laser alignment has the optical system of optical lens, optical system can be similar to the combination of regarding lens and a detector focal plane as, laser in its visual field is through the effect of optical system, near the focal plane of optical system, form one " image patch ", this " image patch " is equivalent to a light source, laser reflects back with certain beam divergence angle through optical system, by the light path principle of reversibility, laser beam can be returned along former road, thereby generation good directionality, the reflected in parallel light of concentration of energy, its light intensity substantially exceeds common diffuse reflection light intensity, " opal " effect of Here it is imaging optical system.

" opal " performance characteristic of optical system has very high using value, based on the laser active detection system of " opal " effect, because of its advantage with early warning, has obtained using widely.The active imaging and passive imaging of common aperture system is a kind of of laser active detection system.At present, the LASER Light Source of the laser active detection system of " opal " effect has continuous laser source and two kinds of forms of pulsed laser light source." opal " effect active detection system of pulsed laser light source does not have good dynamic scan characteristic, and the dynamic scan characteristic of continuous laser source " opal " effect active detection system is good, can be used in to carry out the servo-actuated search sweep in the The Cloud Terrace system; Pulsed laser light source " opal " effect active detection system need be gathered video flowing to Same Scene and be carried out subsequent treatment, this algorithm uses continuous laser source " opal " effect active detection system only need gather main passive two width of cloth images to Same Scene and get final product (initiatively image promptly relies on from the main light source emergent light through the formed picture of target reflection to be measured, is promptly relied on the picture of target own radiation light or the formation of reflection natural light by motion video).Domestic to " opal " effect identification of targets, adopt continuous laser source " opal " effect active detection system more, Same Scene is only gathered initiatively image of a width of cloth, and " opal " effect target is determined in the recognition methods of based target gray scale and shape facility.Yet this method is the Target Recognition poor effect in complex background, lacks reliability, and this patent algorithm improves this algorithm, leads passive image difference computing after having added image registration, uses shape to differentiate locking " opal " effect target at last.

The active imaging and passive imaging of common aperture system receives light and at first (adopts Cold Mirrors, i.e. transmitted infrared light through the dichroism spectroscope as shown in Figure 1, reflect visible light) is divided into two-way, transmitted light is through CCD1 (Charge-coupled Device, i.e. charge-coupled image sensor) imaging, for initiatively looking like; Reflected light is passive picture through the CCD2 imaging.

(3) summary of the invention

1, purpose: the present invention is directed to the defective that is unsuitable for Target Recognition in the complex background based on the recognition methods of gray scale and shape facility, propose promptly to carry out the image difference computing after the image registration at the improvement algorithm that is total to the aperture imaging system.The original image that this method is handled is that continuous laser is right by motion video as the master of lighting source collection, utilize main passive image difference computing to realize the background filtering, and this algorithm has added image registration techniques before using main passive image difference computing, reduces the interference noise of not representing the same object point of scene to produce owing to main passive image pixel subtraction point greatly.Use this algorithm identified " opal " effect target precise and high efficiency more.

2, technical scheme: the present invention by two CCD cameras gather respectively main, by motion video, at first the image that one of them CCD camera is taken carries out horizontal mirror image switch and handles, and again image is carried out gaussian filtering, carries out image registration then.Image registration comprises feature point detection and Feature Points Matching two parts, wherein, the coupling of unique point at first adopts the Euclidean distance of proper vector as similarity measurement, the feature point set that is slightly mated, adopt the RANSAC (abbreviation of RANdom SAmpleConsensus of high robust again, being the random sampling unification algorism) algorithm iteration purification match point is to data, and calculate the transformation relation of two width of cloth images in conjunction with least square method, obtain perspective transformation matrix.Utilize the perspective transformation matrix that obtains in the Feature Points Matching process, piece image is mapped on the matched position of another width of cloth image, carry out the image difference computing again.Differentiate locking " opal " effect target by shape at last.

Fig. 2 is the process flow diagram of this algorithm, and the specific implementation step is as follows:

Step 1: image level mirror image switch and gaussian filtering;

Step 2: image registration;

Step 3: image transformation;

Step 4: image difference;

Step 5: image binaryzation;

Step 6: zone marker;

Step 7: shape facility is differentiated;

Step 8: target area locking.

3, advantage and effect: advantage of the present invention is to lead passive image difference computing again after adopting image registration, realizes the background filtering.Because two CCD put error, mainly during without the computing of images match direct differential, subtracted each other pixel and do not necessarily represent same object point in the scene by motion video, this algorithm has overcome this drawback, has improved the accuracy of identification " opal " effect target.

(4) description of drawings

Fig. 1 is an active imaging and passive imaging of common aperture system architecture synoptic diagram.This system architecture is mainly by continuous semiconductor laser instrument (CWLASER), Laser emission and receiving optics, dichroism spectroscope, two compositions such as CCD camera, DSP (DigitalSignal Processing, digital signal processing) processing unit and display module.Lasing light emitter is made of semiconductor laser, exports continuous infrared laser; The optical axis of CCD1, CCD2 camera lens orthogonal and all with dichroism spectroscope angle at 45; After the processing unit processes conversion of image through digital signal processor DSP, show by display module.

Fig. 2 is an algorithm flow chart.

(5) embodiment

The present invention adopts continuous laser as the active light source, can realize round-the-clock Target Recognition, uses the dichroism spectroscope to see through the infrared light reflection visible light, and it is main by motion video to use two CCD cameras to obtain respectively.

Fig. 2 is an algorithm flow chart of the present invention, and these algorithm concrete steps are as follows:

1, image level mirror image switch and gaussian filtering: obtain the master of Same Scene by motion video by two CCD, system architecture decision CCD1 and CCD2 are imaged as horizontal mirror, need carry out horizontal mirror image switch to piece image wherein, re-use Gaussian filter master, passive image filtering;

2, image registration: image registration comprises feature point detection and Feature Points Matching two parts.Use SIFT (Scale-InvariantFeature Transform, i.e. yardstick invariant features conversion) algorithm to carry out feature point detection, to image I ₁, I ₂Detect N respectively ₁, N ₂Individual unique point.The SIFT algorithm is a kind of algorithm that extracts local feature, search out extreme point at metric space, extracting position, yardstick, invariable rotary characteristic quantity are so the SIFT feature descriptor has good robustness to illumination variation, image rotation, proportional zoom, geometry deformation, fuzzy and compression of images.

The coupling of unique point at first adopts the Euclidean distance of proper vector as similarity measurement, the feature point set that is slightly mated.Get image I ₁In certain unique point, in image I ₂The middle searching and the nearest and inferior two near unique points of its Euclidean distance if minimum distance removes in proper order closely less than certain threshold value, thinks that then this is a pair of match point.More than thick matching result have the mistake coupling unavoidably, adopt RANSAC algorithm iteration purification match point again.The RANSAC algorithm is a kind of robust Model algorithm for estimating of widespread use, main thought is: the as far as possible little sampling set of initial utilization, estimate model parameter, then under estimated parameter, select the data point of data centralization to enlarge initial sampling set as far as possible, iteration produces maximum consistance data set, utilizes maximum consistance data set at last, carries out the estimation of model parameter again.The model parameter of determining constitutes perspective transition matrix H at last, and the unique point of consistance data centralization is to satisfying:

$\left(\begin{array}{c}{x}_i\\ y_i\\ 1\end{array}\right)=H*\left(\begin{array}{c}{x}_i^{\′}\\ y_i^{\′}\\ 1\end{array}\right)$

(x wherein _i, y _i) be I ₁In i (1≤i≤N ₁) individual unique point coordinate, (x ' _i, y ' _i) be image I ₂In characteristic of correspondence point coordinate with it.Not right to the point of thinking matching error at the match point of maximum consistance data centralization.

This patent improves thick matching algorithm in process of image registration.To leading by behind the motion video use SIFT feature point detection algorithm image I ₁, I ₂N is arranged respectively ₁, N ₂Individual unique point is judged image I in the former thick matching process ₁In i unique point whether with image I ₂In certain Feature Points Matching the time, computed image I ₁In i the point and I ₂All N ₂The Euclidean distance of individual unique point and ordering.When calculating I ₁In all N ₁During the matching relationship of individual unique point, need repetitive operation N ₁Inferior, work as N ₁And N ₂When all very big, calculate very consuming timely, efficiency of algorithm is low.At the active imaging and passive imaging of common aperture system, by to the images after registration computational analysis, knowing that two width of cloth image corresponding point row pixels and row pixel coordinate do not differ can surpass 50.If so I ₁In the pixel coordinate of unique point i be (a, b), then at I ₂In the search i corresponding point the time, the hunting zone can be restricted to, row-coordinate at a-50 between the a+50, the row coordinate at b-50 to the unique point between the b+50.

3, image transformation: utilize the perspective transformation matrix that obtains in the Feature Points Matching process, piece image is mapped on the matched position of another width of cloth image.

$\left[\begin{array}{c}{x}^{\′}\\ y^{\′}\\ 1\end{array}\right]~H*\left[\begin{array}{c}x\\ y\\ 1\end{array}\right]$

Formulate be with image I ₂Be mapped to image I ₁Matched position on, [x y 1] is I ₂The homogeneous coordinates of middle pixel, [x ' y ' 1] is I ₂The homogeneous coordinates of the pixel after the projective transformation.

4, image difference: with image I ₁With image I ₂Image after the projective transformation carries out the image difference computing;

5, image binaryzation: the utilization self-adaption thresholding method, carry out binary conversion treatment to image behind the calculus of differences;

6, zone marker: have a plurality of connected domains in the binary image,, need carry out zone marker for extracting its feature;

7, shape facility is differentiated: pass through comprehensive criterion again

Metric＝|1-Metric _r|+|1-Metric _e|

Further lock onto target region.Wherein

Represent the circularity of cut zone,

Represent the excentricity of cut zone, A is the area of cut zone, and P is the girth of cut zone, and a is the major axis of cut zone, and b is the minor axis of cut zone.The approaching more circle of the approaching more zero explanation critical region of the value of Metric;

8, lock onto target zone: realized the target area locking by above flow process.

Advantage of the present invention is to introduce image registration techniques to lead the filtering of passive image difference computing realization background, has improved the reliability of " opal " effect target identification. In process of image registration, thick matching algorithm is improved, for the active imaging and passive imaging of common aperture system, dwindled the hunting zone of second width of cloth image, seeking characteristic point to be matched from the ranks both direction, improved efficiency of algorithm.

Claims (3)

1. " opal " effect Target Recognition Algorithms of active imaging and passive imaging of common aperture system, lead the filtering of passive image difference computing realization background after adopting image registration techniques, improve the reliability of " opal " effect Target Recognition, can accurate recognition have gone out " opal " effect target in the complex background.Algorithm flow is summarised as following key step:

(1) image that CCD in the system is taken carries out horizontal mirror image switch and handles, again to the master, carried out gaussian filtering by motion video;

(2) carry out image registration after the filtering, removed because main passive image pixel subtraction point is not represented the interference noise that same object point brings in the scene.In process of image registration, thick matching algorithm is improved,, dwindled the hunting zone of second width of cloth image, seeking unique point to be matched from the ranks both direction at the active imaging and passive imaging of common aperture system;

(3) utilize the perspective transformation matrix that obtains in the Feature Points Matching process, piece image is mapped on the matched position of another width of cloth image;

(4) with image I ₁With image I ₂Image after the projective transformation carries out the image difference computing;

(5) the utilization self-adaption thresholding method carries out binary conversion treatment to image behind the calculus of differences;

(6) there are a plurality of connected domains in the binary image,, carry out zone marker for extracting its feature;

(7) at last by shape criterion locking " opal " effect target.

2. " opal " effect Target Recognition Algorithms of active imaging and passive imaging of common aperture as claimed in claim 1 system, it is characterized in that: used image registration techniques before the main passive image difference computing, removed because main passive image pixel subtraction point is not represented the interference noise that same object point brings in the scene.

3. " opal " effect Target Recognition Algorithms of active imaging and passive imaging of common aperture as claimed in claim 1 system, it is characterized in that:, dwindled the hunting zone of second width of cloth image, seeking unique point to be matched from the ranks both direction at the active imaging and passive imaging of common aperture system.

Images