METHOD FOR INFRARED SMALL TARGET DETECTION BASED ON DEPTH MAP IN COMPLEX SCENE

Abstract

The present invention discloses a method for infrared small target detection based on a depth map in a complex scene, and belongs to the field of target detection. An infrared image is collected, the image is binarized by using priori knowledge of a to-be-detected target and adopting a pixel value method, the binary image is further limited based on deep priori knowledge, then static and dynamic scoring strategies are formulated to score a candidate connected component in the morphologically processed image, and an infrared small target in a complex scene is detected finally. The method can screen out targets within a specific range, has high reliability; has strong robustness; is simple in program and easy to implement, can be used in sea, land, and air, and has a significant advantage under a complex jungle background.

Claims

1. A method for infrared small target detection based on a depth map in a complex scene, comprising the following steps: 1) image acquisition: acquiring a single-frame or multi-frame infrared image I photographed by a binocular infrared camera and a corresponding depth map dis_I thereof; 2) image binarization: selecting a pixel value K with the maximum edge gradient of a target, binarizing the image by using a pixel value method, obtaining a binary image Binary_I; 3) distance limitation: setting an estimated distance between the target and the infrared camera to d, corresponding a pixel point P(x,y) that is not within a distance range to the binary image Binary_I according to known depth information, Binary_I(x,y) being 0; 4) morphological processing: conducting morphological processing on the binary image including finding connected components, dilation and erosion, wherein the purpose of this step is to extract image information useful for expressing and depicting the shape of the target to be detected from the image; 5) formulation of static and dynamic scoring strategies: using static and dynamic features as decision-making items; ranking the static and dynamic features respectively according to a certain ranking strategy using a weighting scoring mechanism, and finally weighting to obtain scores of all connected components on the image; 6) target screening: screening single target or multiple targets according to the scores of all connected components.

2. The method for infrared small target detection based on a depth map in a complex scene according to claim 1, characterized in that in step 5), the specific process of formulation of static and dynamic scoring strategies includes: 5-1) according to the static features of the target, using rectangularity, aspect ratio, region gray value, variation coefficient of connected component gray value, and circularity as static features, formulating static scoring strategies, wherein the calculation formula of each static feature is: $\hspace{1em}\{\begin{array}{c}\mathrm{Rectangularity}:J_k=\frac{S_k}{S_{\mathrm{rect}}}\\ \mathrm{Aspect}\mathrm{ratio}:R_k=\frac{{\mathrm{width}}_k}{{\mathrm{height}}_k}\\ \mathrm{Region}\mathrm{gray}\mathrm{value}:G_k=\underset{i=1}{\overset{N}{.Math.}}{I}_i*w_i\\ \mathrm{Variation}\mathrm{coefficient}:V_k=\frac{\sqrt{\frac{{.Math.}_1^N{\left(l_i-l_{\mathrm{mean}}\right)}^2}{N-1}}}{I_{\mathrm{mean}}}*100\%\\ \mathrm{Circularity}:C_k=\frac{4{\mathrm{\pi S}}_k}{L_k}\\ {\mathrm{RankS}}_k=\alpha J_k+\beta R_k+\gamma G_k+\delta V_k+{\mathrm{.Math.C}}_k\end{array}$ where S.sub.k represents the area of the k.sup.th connected component, S.sub.rect represents the area of the smallest external rectangle of the k.sup.th connected component, width.sub.k represents the width of the k.sup.th connected component, height.sub.k represents the height of the k.sup.th connected component, I.sub.j. represents the pixel value of the pixel point I(x,y) in the connected component, w.sub.i represents the weight corresponding to the pixel value of the pixel point I(x,y), N represents the number of pixel points in the k.sup.th connected component, I.sub.mean represents the average gray value of the k.sup.th connected component, I.sub.mean=Σ.sub.i=1.sup.NI.sub.i/N, L.sub.k represents the circumference of the k.sup.th connected component, α, β, γ, δ and ε represent weights corresponding to the static features; RankS.sub.k represents a score of a static feature of the k.sup.th connected component; 5-2) according to dynamic features of the target, using area and distance as dynamic features, formulating dynamic scoring strategies: $\{\begin{array}{c}\mathrm{Speed}\mathrm{inequality}\mathrm{Speed}:{\theta }_1*{\mathrm{speed}}_{\min }\le {\mathrm{Speed}}_k\le {\theta }_2*{\mathrm{speed}}_{\max }\\ \mathrm{Speed}\mathrm{inequality}\mathrm{Area}:{\mu }_1*{\mathrm{Area}}_{\min }\le {\mathrm{Area}}_k\le {\mu }_2*{\mathrm{Area}}_{\max }\\ {\mathrm{RankD}}_k=Ϛ{\mathrm{Speed}}_k+\phi {\mathrm{Area}}_k\end{array}\hspace{1em}$ where Speed.sub.k represents the movement speed of the k.sup.th connected component, speed.sub.min represents the minimum known movement speed, speed.sub.max represents the maximum known movement speed, Area.sub.k represents the area of the k.sup.th connected component, Area.sub.min represents the minimum known connected component area, Area.sub.max represents the maximum known connected component area; θ.sub.1, θ.sub.2 represent corresponding speed weights, μ.sub.1, μ.sub.2 represent corresponding area weights, ζ, φ represent weights corresponding to dynamic features, and RankD.sub.k represents a score of a dynamic feature of the k.sup.th connected component.

Description

DESCRIPTION OF DRAWINGS

[0019] FIG. 1 is a master flow chart of a method for infrared small target detection based on a depth map in a complex scene;

[0020] FIG. 2 shows a single-frame image of infrared small target detection based on a depth map in a complex scene;

[0021] FIG. 3 shows a target to be detected after being partially enlarged in FIG. 2.

DETAILED DESCRIPTION

[0022] The present invention provides a method for infrared small target detection based on a depth map in a complex scene which realizes the detection of infrared small targets in a complex scene by means of four steps, that is, setting of binary threshold, distance limitation, morphological processing and formulation of static and dynamic scoring strategies. The present invention is further described below in combination with the drawings and the embodiments.

[0023] As shown in FIG. 1, a method tier infrared small target detection based on a depth map in a complex scene, comprising the following steps:

[0024] 1) acquiring single-frame or a multi-frame infrared image I photographed by a binocular infrared camera and a corresponding depth map dis_I thereof, wherein FIG. 2 shows a single-frame image of infrared small target detection based on a depth map in a complex scene;

[0025] 2) FIG. 3 shows a target to be detected after being partially enlarged; selecting a pixel value K with the maximum edge gradient of a target, binarizing the image by using a pixel value method, setting a pixel value of which the value is less than K to 0 and setting a pixel value of which the value is greater than or equal to K to 255, obtaining a binary image Binary_I.

[0026] 3) setting an estimated distance between the target and the infrared camera to d, corresponding a pixel point P(x,y) that is not within a distance range to the binary image Binary_I according to known depth information, Binary_I(x,y) being 0;

[0027] 4) conducting morphological processing on the binary image Binary_I including finding connected components, dilation and erosion; setting an erosion structure element to SE1 and a dilation structure element to SE2; setting the maximum area of a connected component where the target to be detected is located to Area.sub.max and the minimum area to Area.sub.min; if the area of the connected component is Area.sub.k, k represents the serial number of the connected component, only retaining the connected component with Area.sub.min≤Area.sub.k≤Area.sub.max;

[0028] 5) formulation of static and dynamic scoring strategies: using static and dynamic features as decision-making items; ranking the static and dynamic features respectively according to a certain ranking strategy using a weighting scoring mechanism, and finally weighting to obtain scores of all connected components on the image;

[0029] 6) screening single target or multiple targets according to scores.

[0030] In step 5), the specific process of formulation of static and dynamic scoring strategies includes:

[0031] 5-1) According to the static features of the target, using rectangularity, aspect ratio, region gray value, variation coefficient of connected component gray value, and circularity as static features, formulating static scoring strategies, wherein the calculation formula of each static feature is:

[00002]$\hspace{1em}\{\begin{array}{c}\mathrm{Rectangularity}:J_k=\frac{S_k}{S_{\mathrm{rect}}}\\ \mathrm{Aspect}\mathrm{ratio}:R_k=\frac{{\mathrm{width}}_k}{{\mathrm{height}}_k}\\ \mathrm{Region}\mathrm{gray}\mathrm{value}:G_k=\underset{i=1}{\overset{N}{.Math.}}{I}_i*w_i\\ \mathrm{Variation}\mathrm{coefficient}:V_k=\frac{\sqrt{\frac{{.Math.}_1^N{\left(l_i-l_{\mathrm{mean}}\right)}^2}{N-1}}}{I_{\mathrm{mean}}}*100\%\\ \mathrm{Circularity}:C_k=\frac{4{\mathrm{\pi S}}_k}{L_k}\\ {\mathrm{RankS}}_k=\alpha J_k+\beta R_k+\gamma G_k+\delta V_k+{\mathrm{.Math.C}}_k\end{array}$

[0032] where S.sub.k represents the area of the k.sup.th connected component, S.sub.rect represents the area of the smallest external rectangle of the k.sup.th connected component, width.sub.k represents the width of the k.sup.th connected component, height.sub.k represents the height of the k.sup.th connected component, I.sub.i. represents the pixel value of the pixel point I(x,y) in the connected component, w.sub.i represents the weight corresponding to the pixel value of the pixel point I(x,y), N represents the number of pixel points in the k.sup.th connected component, I.sub.mean represents the average gray value of the k.sup.th connected component, I.sub.mean=Σ.sub.i=1.sup.NI.sub.i/N, L.sub.k represents the circumference of the k.sup.th connected component, α, β, γ, δ and ε represent weights corresponding to the static features; RankS.sub.k represents a score of a static feature of the k.sup.th connected component.

[0033] 5-2) According to dynamic features of the target, using area and distance as dynamic features, formulating dynamic scoring strategies:

Speed inequality Speed: θ.sub.1*speed.sub.min≤Speed.sub.k≤θ.sub.2*speed.sub.max

Speed inequality Area: μ.sub.1*Area.sub.min≤Area.sub.k≤μ.sub.2*Area.sub.max

RankD.sub.k=ζSpeed.sub.k+φArea.sub.k

[0034] where Speed.sub.k represents the movement speed of the k.sup.th connected component, speed.sub.min represents the minimum known movement speed, speed.sub.max represents the maximum known movement speed, Area.sub.k represents the area of the connected component, Area.sub.min represents the minimum known connected component area, Area.sub.max represents the maximum known connected component area; θ.sub.1, θ.sub.2 represent corresponding speed weights, μ.sub.1, μ.sub.2 represent corresponding area weights, ζ, φ represent weights corresponding to dynamic features, and RankD.sub.k represents a score of a dynamic feature of the k.sup.th connected component.

[0035] Those skilled in the art can easily understand that the above only describes preferred embodiments of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and the principle of the present invention shall be contained within the protection scope of the present invention.