针对远距离低信噪比条件下目标检测难的实际问题,提出采用D-S证据理论的双色红外小目标融合检测方法。该方法首先采用统计检测方法对各传感器图像进行目标检测处理;接着采用“或”逻辑对各传感器的目标检测结果进行融合,以降低目标漏检的可能性;然后在各传感器图像中提取融合检测结果中各候选目标区域的多个图像特征作为进一步消除虚警的证据;最后采用D-S证据理论对各候选目标区进行基于多特征的目标融合识别处理,并将识别结果作为整个系统最终的目标检测输出。实验结果证明了该算法的有效性。 Aiming at the practical problem of difficult target detection under long distance and low signal-to-noise ratio conditions, a two-color infrared small target fusion detection method based on D-S evidence theory is proposed. The method first uses the statistical detection method to detect the target of each sensor image, and then uses the OR logic to fuse the target detection results of each sensor to reduce the possibility of missing detection. Then, the fusion detection is extracted from each sensor image In the end, the DS evidence theory is used to carry out target fusion recognition processing based on multiple features for each candidate target area, and the recognition result is used as the final target detection of the whole system Output. Experimental results show the effectiveness of the algorithm.