基于光谱探测与图像识别的反伪装目标系统研究

Research on Anti-Camouflaged Target System Based on Spectral Detection and Image Recognition

为了在野外环境中快速有效地识别敌方伪装的机动目标,设计了基于光谱探测与视频图像目标识别方法联用的目标识别系统。采用视频图像识别技术获取被测区域的二维影像,再通过光谱探测技术识别目标,最终将目标重建在图像相应位置上从而实现目标识别的可视化。理论推导得到了系统可识别目标的函数关系式,根据该函数关系进行了目标识别的量化实验。实验采用汽车模拟被测机动目标,在不同距离上分别以平坦荒地、灌木丛和废弃建筑物为背景,对明显目标、涂覆迷彩色的目标以及遮挡伪装物的目标分别进行光谱探测。实验结果显示,测试背景对光谱探测效果有一定影响,背景的连续性有利于目标识别;伪装方式以伪装物遮挡最难识别,且随着目标与系统的距离增大而信噪比随之降低。综上所述,采用光谱探测技术克服了传统图像目标识别无法识别伪装目标的缺点,可以实现对伪装目标的有效识别。

To be able to quickly and efficiently identify Enemy camouflaged maneuvering targets in the wild environment,target recognition system was designed based on spectral detection technology and video target recognition method.System was composed of the visible light image acquisition module and static interferometer module.The system used image recognition technology to obtain two dimensional video images of measurement region,and through spectrum detection technology to identify targets.Ultimately,measured target was rebuilt on the corresponding position in the image,so the visual target recognition was realized.After the theoretical derivation,identifiable target function formula of the system was obtained,and based on the functional relationship to complete the quantitative experiments for target recognition.In the experiments,maneuvering target in the battlefield environment was simulated by a car.At different distances,the background was respectively selected to detect a flat wasteland,bushes and abandoned buildings.Obvious target,coated camouflage target and covered disguises target was respectively spectrum detection.Experimental results show that spectrum detection technology can overcome the shortcomings of unrecognized the camouflaged target by traditional image target recognition method.Testing background had some influence on spectrum detection results,and the continuity of the background was conducive to target recognition.Covered disguises target was the hardest to identify in various camouflage mode.As the distance between the target and the system increases,signal to noise ratio of the system was reduced.In summary,the system can achieve effective recognition of camouflaged targets to meet the design requirements.