.png){kind=icon}
返回
Learning Fully Convolutional Network for Visual Tracking With Multi-Layer Feature Fusion
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2899023.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks are powerful models that yield hierarchies of features. In the paper, we present a new approach for general object tracking based on the fully convolutional network with multi-layer feature fusion. The designed network combines semantic information from deep, coarse layers, and appearance information from shallow, fine layers to make accurate pixel-wise objectness prediction. The network is first pretrained offiine using a large set of videos with annotated heatmap groundtruths to obtain a general notion of foreground objects, and later fine-tuned using the first frame to adapt to the particular object instance. In online tracking, the location corresponding to the maximum target objectness in the search image is determined as the new target location, and the scale estimation is handled by incorporating a correlation filter branch into the network. An efficient updating strategy is proposed to further improve tracking performance. The extensive experiments performed on the widely used tracking benchmark OTB100 show that the proposed algorithm outperforms many other state-of-the-art trackers.
Keyword:
FCN
feature fusion
pixel-wise objectness
two-step training
updating strategy
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Object Tracking in Vary Lighting Conditions for Fog Based Intelligent Surveillance of Public Spaces.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Role of Urban Landscapes in Changing the Irrigation Water Requirements in Arid ClimateGeosciences
OAAI
GeosciencesIF0
OAAI分享收藏
查看更多内容