为提升融合梯度直方图特征和颜色属性特征的有效卷积操作跟踪算法(ECO-HC)的跟踪精度和速度,提出一种融合上下文和重定位的加权相关滤波跟踪方法。根据梯度直方图和颜色属性的不同特性加权融合相关滤波响应值,采用自适应迭代方法预测目标位置;融合多尺度搜索区域,目标上下文特征和目标预测失败时重定位方法进一步提高跟踪精度。在标准数据集OTB-100上进行算法评估,实验结果表明,所提算法的平均距离精度为89.2%,平均重叠率精度为80.6%,比ECO-HC算法分别高3.6%和2.1%。中央处理器的跟踪速度达65.2 frame/s,优于实验中对比的其他跟踪算法。所提算法有效地提高了跟踪精度,在严重遮挡、光照变化等干扰下,仍能较好地跟踪目标。

In order to improve both the tracking accuracy and speed of the efficient convolution operators based tracking algorithm fusing the histogram of oriented gradient and color names features (ECO-HC), a weighted correlation filtering algorithm based on context and relocation is proposed. Considering the differences between the histogram of oriented gradient and color names features, the responses of two features are fused in different weights. The adaptive iterative method is used to predict the position of a target, which combines with the multi-scale search area, the contextual features and the relocation method when the target prediction is failure to further improve the tracking accuracy. The algorithm is evaluated on the OTB-100 dataset. The experimental results show that the average distance accuracy of the proposed algorithm is 89.2% and the average overlap rate is 80.6%, 3.6% and 2.1% higher than those of the ECO-HC method, respectively. In addition, the tracking speed on the central processing unit is 65.2 frame/s, superior to that of the other tracking algorithms compared in the experiments. The proposed algorithm effectively improves the tracking accuracy and can track the objects well under the condition of severe occlusion, illumination variation and other interferences.