期刊文献+
共找到4篇文章
< 1 >
每页显示 20 50 100
Fast-armored target detection based on multi-scale representation and guided anchor 被引量:5
1
作者 Fan-jie Meng Xin-qing Wang +2 位作者 Fa-ming Shao Dong Wang Xiao-dong Hu 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2020年第4期922-932,共11页
Focused on the task of fast and accurate armored target detection in ground battlefield,a detection method based on multi-scale representation network(MS-RN) and shape-fixed Guided Anchor(SF-GA)scheme is proposed.Firs... Focused on the task of fast and accurate armored target detection in ground battlefield,a detection method based on multi-scale representation network(MS-RN) and shape-fixed Guided Anchor(SF-GA)scheme is proposed.Firstly,considering the large-scale variation and camouflage of armored target,a new MS-RN integrating contextual information in battlefield environment is designed.The MS-RN extracts deep features from templates with different scales and strengthens the detection ability of small targets.Armored targets of different sizes are detected on different representation features.Secondly,aiming at the accuracy and real-time detection requirements,improved shape-fixed Guided Anchor is used on feature maps of different scales to recommend regions of interests(ROIs).Different from sliding or random anchor,the SF-GA can filter out 80% of the regions while still improving the recall.A special detection dataset for armored target,named Armored Target Dataset(ARTD),is constructed,based on which the comparable experiments with state-of-art detection methods are conducted.Experimental results show that the proposed method achieves outstanding performance in detection accuracy and efficiency,especially when small armored targets are involved. 展开更多
关键词 RED image RPN Fast-armored target detection based on multi-scale representation and guided anchor
下载PDF
A simple practical balloon anchoring technique within the guide catheter for chronic total occlusion (CTO) of the coronary artery
2
作者 Leilei Chen Yi Cheng +3 位作者 Yang Yang Zhen Zhang Dingguo Zhang Liansheng Wang 《The Journal of Biomedical Research》 CAS CSCD 2015年第5期423-425,共3页
Dear Editor: Chronic total occlusions (CTOs) of the coronary artery are commonly encountered complex lesionst11. Percutaneous coronary intervention (PCI) for CTO is technically challenging due to low procedural ... Dear Editor: Chronic total occlusions (CTOs) of the coronary artery are commonly encountered complex lesionst11. Percutaneous coronary intervention (PCI) for CTO is technically challenging due to low procedural success ratesTM. Microcatheter is one of the important devices for treatment of CTOTM. It has been widely used attributed to the excellent crossability whenever angula- tion and tortuousity of the coronary artery is encoun- tered. In the process, the microcatheter has to be withdrawn from the guide wire after the wire is proved to locate in the true lumen. 展开更多
关键词 of the coronary artery A simple practical balloon anchoring technique within the guide catheter for chronic total occlusion PCI CTO
下载PDF
基于改进RetinaNet的行人检测算法 被引量:5
3
作者 刘晋川 黎向锋 +3 位作者 叶磊 刘安旭 赵康 左敦稳 《科学技术与工程》 北大核心 2022年第10期4019-4025,共7页
为提高实际应用场景中行人的检测精度,提出了使用高分辨率特征提取网络HRNet(high-resolution representation network)并引入Guided Anchoring机制对RetinaNet算法进行改进,维持了特征图在特征提取过程中的高分辨率信息,同时使网络中... 为提高实际应用场景中行人的检测精度,提出了使用高分辨率特征提取网络HRNet(high-resolution representation network)并引入Guided Anchoring机制对RetinaNet算法进行改进,维持了特征图在特征提取过程中的高分辨率信息,同时使网络中的锚框自适应生成,提高了算法的检测精度。结果表明:该改进算法在Caltech行人数据集上取得了0.905的平均精度均值(mean average precision,mAP),相比于标准的RetinaNet算法提高了6.0%,在每帧图像尺寸为1280×720像素的视频上检测速度达到了19 FPS(FPS为每秒检测帧数),达到了检测精度与检测速度的均衡。 展开更多
关键词 行人检测 卷积神经网络 RetinaNet 高分辨率网络 guided anchoring
下载PDF
一种基于特征引导的电力施工场景工装合规穿戴二阶段检测算法 被引量:3
4
作者 林其雄 陈畅 +1 位作者 闫云凤 齐冬莲 《浙江电力》 2022年第4期44-50,共7页
现有电力施工场景下关于工装穿戴的智能监管方案主要是针对安全帽,少有针对作业人员整体合规穿戴的相关方案。基于更细致的作业人员工装合规穿戴监管需求,提出一种二阶段的工装合规穿戴检测算法,包括人员定位阶段和人体区域工装合规检... 现有电力施工场景下关于工装穿戴的智能监管方案主要是针对安全帽,少有针对作业人员整体合规穿戴的相关方案。基于更细致的作业人员工装合规穿戴监管需求,提出一种二阶段的工装合规穿戴检测算法,包括人员定位阶段和人体区域工装合规检测阶段。针对现场人员工作姿态复杂的情况,结合特征金字塔网络和Guided Anchor提出一种基于Faster R-CNN优化的人员定位算法,在15000余张现场采集样本构成的数据集上获得了91.1%的人员定位准确率,相比普通Faster R-CNN算法提升6.0%。二阶段检测算法在人体区域工装检测任务上获得92.9%的准确率,相比单阶段Faster R-CNN算法提升11.4%。 展开更多
关键词 合规穿戴 guided anchor 二阶段检测 人员定位 人体区域工装检测
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部