ICCV 2019视频目标跟踪算法Pipeline集合

最新推荐文章于 2024-09-20 21:09:19 发布

越野者

最新推荐文章于 2024-09-20 21:09:19 发布

阅读量5.5k

点赞数 4

分类专栏：视频目标跟踪（Visual tracking）论文笔记（Paper notes）文章标签：视频目标跟踪 ICCV 论文笔记

本文链接：https://blog.csdn.net/discoverer100/article/details/101347018

版权

这篇博客介绍了ICCV 2019会议上关于视频目标跟踪的多个算法，包括ARCF、MLT、DiMP等。这些算法涉及实时无人机跟踪、深度学习、元学习、3D车辆检测与跟踪等方面，旨在提升视觉跟踪的实时性和鲁棒性。通过学习适应性特征、抑制异常和联合检测与跟踪等方法，这些研究为视觉对象跟踪提供了新的解决方案。

摘要由CSDN通过智能技术生成

文章目录

1. ARCF: "Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking"
2. MLT: "Deep Meta Learning for Real-Time Target-Aware Visual Tracking"
3. : "Joint Monocular 3D Vehicle Detection and Tracking"
4. : "`Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking"
5. DiMP: "Learning Discriminative Model Prediction for Tracking"
6. : "Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking"
7. GradNet: "GradNet: Gradient-Guided Network for Visual Object Tracking"
8. : "Bridging the Gap Between Detection and Tracking: A Unified Approach"
9. : "Physical Adversarial Textures That Fool Visual Object Tracking"
10. CDTB : "CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark"

1. ARCF: “Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking”

[在线阅读]
在这里插入图片描述
Figure 1. Comparison between background-aware correlation filter (BACF) and the proposed ARCF tracker. The central figure is to demonstrate the differences between previous response map and current response map on group1 1 from UAV123@10fps. Sudden changes of response maps indicate aberrances. When aberrances take place, BACF is tend to lose track of the object while the proposed ARCF can repress aberrances so that this kind of drifting can be avoided.

在这里插入图片描述
Figure 2. Main work-flow of the proposed ARCF tracker. It learns both positive sample (green samples) of the object and negative samples (red samples) extracted from the background and the response map restriction is integrated in the learning process so that aberrances in response maps can be repressed. $\left[\psi_{p, q}\right]$ serves to shift the generated response map so that the peak position in the previous frame is the same as that of the current frame and thus the position of the detected object will not affect the restriction.

2. MLT: “Deep Meta Learning for Real-Time Target-Aware Visual Tracking”

[在线阅读]
在这里插入图片描述
Figure 1: Motivation of the proposed visual tracker. Our framework incorporates a meta-learner network along with a matching network. The meta-learner network receives meta information from the matching network and provides the matching network with the adaptive target-specific feature space needed for robust matching and tracking.

在这里插入图片描述
Figure 2: Overview of proposed visual tracking framework. The matching network provides the meta-learner network with meta-information in the form of loss gradients obtained using the training samples. Then the meta-learner network provides the matching network with target-specific information in the form of convolutional kernels and channel-wise attention.
在这里插入图片描述
Figure 3: Training scheme of meta-learner network. The meta-learner network uses loss gradients $δ$ in (2) as meta information, derived from the matching network, which explains its own status in the current feature space [35]. Then, the function $g$