用于目标跟踪的孪生渐进注意引导融合网络

针对基于孪生网络的目标跟踪中大部分方法是利用主干网络的最后一层语义特征来计算相似度,而单一地利用深层特征空间往往是不够的问题,提出基于孪生网络的渐进注意引导融合跟踪方法.首先采用主干网络提取深层和浅层特征信息;然后通过特征聚合模块,以自顶向下的方法去编码融合深层语义信息以及浅层空间结构信息,并利用注意力模块减少融合产生的特征冗余;最后计算目标和搜索区域的匹配相似度,以进行目标跟踪.在加入注意力模块后,跟踪器可以选择性地整合多层特征信息,提升了跟踪器的性能.在OTB2013,OTB50,OTB2015,VOT2016以及VOT2017这5个公共基准数据库上,与SiamDW等方法进行实验的结果表明,文中方法能够有效地提升跟踪的精度及成功率.

Siamese Progressive Attention-Guided Fusion Network for Object Tracking

For the most of object tracking algorithms using siamese networks,the semantic feature derived from the last layer of the backbone network is used to calculate the similarity.However,the use of single deep feature space often leads to partial loss of effective information.To address this issue,the siamese progressive attention-guided fusion network is proposed.First,the deep and shallow feature information is simultaneously extracted using the backbone network.Second,a top-down strategy is adopted to gradually encode and fuse deep semantic information,as well as shallow spatial structure information is obtained from the progressive feature aggregation module.We then use attention module to reduce feature redundancy that generated by fusion.Last,the optimal solution of object tracking is formed by calculating the similarity between the target and search area.By means of attention module,the tracker can selectively integrate multi-level features information to enhance the performance of the applications.As compared with SiamDW and other traditional methods,experimental results conducted on the five common tracking benchmarks including OTB2013,OTB50,OTB2015,VOT2016 and VOT2017,demonstrate that the effectiveness of the proposed algorithm in terms of tracking accuracy and success rate.