Using wavelet - based multi - scale transform to detect infrared target , it is possible to acquire modulus image to segment citrus from background under direct sunlight conditions , whereas it is difficulty to identification because of the confusion of the reflected light from leaves under backlighting . the method is very sensitive to the ambient air condition , such as in condition b or c , the identification is very difficult 用该方法可以较好地识别顺光条件下采集的红外热图像中的果实，而在背光条件下，由于位于树冠边缘的树叶反射光较强或穿过树冠的光使周围的树叶光反射较强，使果实在红外热图像中的温度或灰度低于反射光强的树叶等部分，则不能识别。
In this paper , firstly , three - dimensional geometrical models of the target and ir flares are established and by using the software vega missile attacking process is real - time simulated visually . secondly , the ir radiation characteristic of the target , background and the ir flares are analyzed , in which the wave radiation of the sun at different time , wind speed , the relative humidity and ir radiation attenuation characteristic of the atmosphere is under consideration . from above the ir image of the target , ir flare and the background are got and then are normalized to gray color image that will be showed in a child window in real time 本文通过三维建模工具creator建立目标、背景和干扰的三维模型，再通过视景仿真软件vega生成载机、导弹和目标飞机的可见光场景图像，实时地对导弹攻击工程进行可视化仿真；并分析了目标、背景和干扰的红外辐射特性，计算出传感器路径上大气衰减等等，将经过衰减的目标、背景和干扰的辐射强度量化为灰度图，以子窗口形式实时显示；进一步可以使目标和干扰按照各自的运动轨迹运动，便可产生动态的红外热图像序列。
The unique heat radiation of infrared image is generated from subcomponents . this paper analyses the natural feature of infrared image and the relationship between the shape and orientation with eigen vectors , gives the measure to classify infrared image based on object position to improve ability of compatibility in object recognition , moreover , applies the independent component for sub - region segmentation to construct new infrared image eigen vectors . the image features are processed by a support vector machine , and transform the binary svm to multi - object classifier 文中在传统红外热图像特征量的基础之上，通过分析红外热图像自身特性以及它的形成与其自身姿态的关系，提出了对目标物体红外热图像基于目标姿态的子分类，来提高目标识别中对姿态的容忍度；同时根据红外目标子部件对图像影响的统计独立性，使用独立元的方法对目标红外热图像进行了子区域分割，形成了新的红外图像特征量。
