充分利用红外图像信息建立有效的观测模型是实现稳健红外目标跟踪的基础。影响红外目标跟踪结果的因素除可见光目标跟踪也会面临的干扰因素之外,还有诸如边缘和纹理信息缺失、信噪比低和背景噪声影响等特有因素。提出基于稀疏编码直方图(HSC)特征和扰动感知模型(DAM)的红外目标跟踪方法,使用K-奇异值分解算法得到过完备字典,利用该字典计算得到每个像素点的稀疏编码,并组成HSC对目标进行表达,同时通过引入DAM增强算法抗背景干扰能力。该方法充分利用了红外图像中运动目标的结构特性,能够有效去除背景干扰。与其他跟踪器相比,在VOT-TIR2015数据集上,该方法的精确度和成功率指标分别获得3.8%和4.4%的提升,具有较高的研究价值和实用价值。 Making full use of infrared image information to establish an effective observational model is the basis for achieving robust infrared target tracking. Factors that affect the results of infrared target tracking In addition to the disturbing factors that visible target tracking can encounter, there are also unique factors such as missing edge and texture information, low signal-to-noise ratios, and background noise effects. An infrared target tracking method based on Sparse Coding Histogram (HSC) and Disturbance Awareness Model (DAM) is proposed. An overcomplete dictionary is obtained by using K-singular value decomposition algorithm. The sparse coding of each pixel is calculated by using this dictionary. HSC expresses the target, and at the same time enhances the algorithm against background interference by introducing DAM. The method takes full advantage of the structural characteristics of the moving target in the infrared image and can effectively remove the background interference. Compared with other tracker, on the VOT-TIR2015 dataset, the accuracy and success rate of this method are improved by 3.8% and 4.4% respectively, which has high research value and practical value.