首页|多特征融合的无人艇视觉小目标鲁棒跟踪

多特征融合的无人艇视觉小目标鲁棒跟踪

扫码查看
[目的]针对低特征分辨率、相似环境信息引起的无人艇视觉小目标跟踪混淆问题,提出一种多特征融合的连续卷积算子跟踪算法.[方法]首先,采用双三次插值技术,提高多特征图分辨率,实现亚像素级定位;其次,利用特征投影和生成样本空间,提高目标跟踪的效率,避免滤波器过拟合;最后,设计高置信度模型更新策略,解决相似环境信息对滤波器的干扰问题.[结果]结果表明:相较于传统的连续卷积算子跟踪算法,平均成功率提升 17.4%,平均距离精度指标提升 17.8%,期望平均覆盖率提升 5.1%.[结论]该算法法能够处理海洋环境下的小目标跟踪混淆问题,为提升无人艇及海洋机器人的智能感知能力,提供关键技术支撑.
Multi-feature fusion-based robust tracking of small targets in unmanned surface vehicle vision
[Objectives]To overcome the challenges of tracking small targets in unmanned surface vehicle vision under the conditions of low feature resolution and similar environmental information,a multi-feature fu-sion-based continuous convolution operator tracking(MCCOT)algorithm is proposed.[Methods]The res-olution of multi-feature maps is enhanced using bicubic interpolation techniques to enable sub-pixel-level loc-alization.Efficiencies in target tracking are achieved through feature projection and sample space generation to mitigate filter overfitting.Furthermore,interference arising from similar environmental features on the filter is addressed by developing an update strategy for high-confidence models.[Results]As the experimental res-ults show,compared to traditional continuous convolution operator tracking algorithms,the proposed al-gorithm achieves an average success rate increase of 17.4%,average distance precision increase of 17.8%,and expected average overlap rate increase of 5.1%.[Conclusions]The proposed algorithm can deal with the problem of small target tracking confusion in marine environments,providing key technical support for im-proving the intelligent sensing capability of unmanned boats and marine robots.

robust tracking of small targets at seamulti-feature fusioncontinuous convolutional operat-orunmanned surface vehicle vision

王宁、吴伟、王元元、孙赫男、冯远

展开 >

大连海事大学 轮机工程学院,辽宁 大连 116026

水路交通控制全国重点实验室,辽宁 大连 116026

大连市智能船舶绿色动力控制与测试重点实验室,辽宁 大连 116026

大连海事大学 船舶电气工程学院,辽宁 大连 116026

大连海事局 甘井子海事处,辽宁 大连 116031

展开 >

海上小目标鲁棒跟踪 多特征融合 连续卷积算子 无人艇视觉

国家自然科学基金资助项目国家自然科学基金资助项目国家高层次人才支持计划国防基础科研计划资助项目辽宁省"兴辽英才计划"领军人才项目大连市科技创新基金重大基础研究项目中央高校基本科研业务费专项资金项目

U23A2068052271306SQ2022QB00329JCKY2022410C013XLYC22020052023JJ11CG0093132023501

2024

中国舰船研究
中国舰船研究设计中心

中国舰船研究

CSTPCD北大核心
影响因子:0.496
ISSN:1673-3185
年,卷(期):2024.19(5)