• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Robust structured tracking.
【24h】

Robust structured tracking.

机译：强大的结构化跟踪。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Model-free visual tracking is an important problem in computer vision. The abundance of applications make the problem attractive, and, as a result, significant progress was made, especially in the recent years. A number of reasons make tracking a hard problem: change of lighting conditions throughout the video, change of scale and rotation of the object, as well as frequent occlusions. In this dissertation, we build upon a tracker known as Struck, which is based on a structured support vector machine.;To make the structured tracker robust, we improve it in a number of ways. To make the structured tracker robust to short-time occlusions and false-positive detections, we propose to use the Robust Kalman filter. Here, we develop a strategy that allows us to detect, and recover from, short-time occlusions and/or incorrect detections. By treating inconsistent detections, which are labeled by the filter as outliers, we show that our new method, called RobStruck, improves the tracking accuracy as measured by standard tracking-accuracy metrics.;To guide the tracker into locations that are more likely to contain an object, we propose to use saliency measures. Saliency measures, also known as objectness, estimate how likely a given location in the image to contain an object of any type. The objectness measures we consider here - straddling and edge density - are based on semantic object segmentation and edge detection. These measures are unsupervised, and are fast to compute - an ideal fit for tracking, where real-time performance is often desired. We build a object-aware tracker, which we call ObjStruck and show that objectness measures improve tracking.;To find a better feature representation, we incorporate deep features from pre-learned deep-convolutional network in a computationally-efficient manner. Using a M-Best diverse-sampling approach, we can sample a small and diverse set of bounding boxes that are likely to contain the target. These bounding boxes are then used to perform detection using deep features. The resulting tracker, which we call M-BestStruck, uses high-quality feature representation while remaining computationally efficient.;We systematically evaluate each of our contributions on four different visual-tracking benchmarks and compare them to the state-of-the-art.
机译：无模型视觉跟踪是计算机视觉中的重要问题。大量的应用使该问题变得引人注目，因此，取得了重大进展，尤其是在最近几年。造成跟踪困难的原因有很多：整个视频中的照明条件发生变化，对象的比例和旋转发生变化以及频繁发生遮挡。在本文中，我们基于结构化支持向量机，建立了称为Struck的跟踪器。为了使结构化跟踪器更健壮，我们通过多种方式对其进行了改进。为了使结构化跟踪器对短时遮挡和假阳性检测具有鲁棒性，我们建议使用鲁棒卡尔曼滤波器。在这里，我们制定了一种策略，使我们能够检测到短时的咬合和/或错误的检测并从中恢复。通过将不一致的检测（由过滤器标记为离群值）进行处理，我们证明了称为RobStruck的新方法可以提高通过标准跟踪准确性指标衡量的跟踪准确性。要引导跟踪器进入更可能包含的位置一个对象，我们建议使用显着性度量。显着性度量（也称为对象性）估计图像中给定位置包含任何类型的对象的可能性。我们在这里考虑的客观性度量-跨度和边缘密度-基于语义对象分割和边缘检测。这些度量是无监督的，并且计算速度快-非常适合跟踪，通常需要实时性能。我们构建了一个对象感知跟踪器，我们将其称为ObjStruck并显示出客观性指标可以改善跟踪。使用M-Best多样化采样方法，我们可以对可能包含目标的一小套多样化的边界框进行采样。这些边界框然后用于使用深度特征执行检测。最终的跟踪器（我们称为M-BestStruck）在保持计算效率的同时使用了高质量的特征表示。我们在四种不同的视觉跟踪基准上系统地评估了我们的每项贡献，并将它们与最新技术进行了比较。

著录项

  • 作者

    Bogun, Ivan.;

  • 作者单位

    Florida Institute of Technology.;

  • 授予单位 Florida Institute of Technology.;
  • 学科 Computer science.
  • 学位 Ph.D.
  • 年度 2016
  • 页码 122 p.
  • 总页数 122
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 农学（农艺学）;
  • 关键词

  • 入库时间 2022-08-17 11:39:44

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号