基于双准则自适应融合的目标跟踪算法

针对单一评判准则较难适应复杂环境下的目标跟踪问题,提出了一种基于双评判准则自适应融合的跟踪算法。在该算法中,空间直方图被用作目标表示模型,候选目标与目标模板之间的相似度、以及候选目标与其邻近背景区域之间的对比度被作为目标评判双准则,而目标函数(或似然函数)则由两个准则的加权融合而成。算法是在粒子滤波框架下实现的目标搜索,并采用了模糊逻辑对相似度和对比度的权值进行自适应调节。对人、动物等多个挑战性运动目标的跟踪结果表明,与增量学习跟踪、ι₁跟踪等最新跟踪器相比,所提算法在处理目标的遮挡、形变、旋转以及表观变化方面的综合性能更好,其成功率和平均重叠率指标分别在80%和0.76以上。

Target tracking approach based on adaptive fusion of dual-criteria

Since the single-criterion-based tracker can not adapt to the complex environment, a tracking approach based on adaptive fusion of dual-criteria was proposed. In the method, the second-order spatiogram was employed to represent the target, the similarity between the target candidate and the target model as well as the contrast between the target candidate and its neighboring background were used to evaluate its reliability, and the objective function (or likelihood function) was established by weighted fusion of the two criteria. The particle filter procedure was used to search the target, and the fuzzy logic was applied to adaptively adjust the weights of the similarity and contrast. Experiments were carried out on several challenging sequences such as person, animal, and the results show that, compared with other trackers such as incremental visual tracker, ι₁ tracker, the proposed algorithm obtains better comprehensive performance in handling occlusion, deformation, rotation, and appearance change, and its success rate and average overlap ratio are respectively more than 80% and 0.76.