人脸检测跟踪的TLD方法

需积分: 10 168 浏览量更新于2024-09-11 收藏 1.96MB PDF 举报

"这篇论文介绍了将Tracking-Learning-Detection (TLD)方法应用到人脸识别中的新系统——FACE-TLD。该系统通过结合一个通用检测器和验证器，增强了TLD在无约束视频中长期追踪人脸的能力，特别针对遮挡和外观变化的情况。离线训练的检测器定位正面人脸，而在线训练的验证器则负责判断哪些人脸与被追踪的主题相对应。论文评估了多种构建验证器的策略，并在实际场景视频（23分钟）和监控视频（8分钟）上验证了系统的性能，系统能够自动从单个正面例子和未标记的视频中学习多视图模型进行检测和追踪。关键词包括：长期人脸识别、学习、检测、验证、实时处理。" 详细说明： 1. **Tracking-Learning-Detection (TLD)**：TLD是一种计算机视觉技术，它结合了目标检测、跟踪和学习三个核心元素。在TLD框架下，系统首先检测目标，然后持续跟踪目标，同时不断学习和更新目标的特征，以适应目标外观的变化。 2. **FACE-TLD**：这是TLD方法的一个特化版本，专用于人脸识别。它设计了一个专门的通用检测器来定位视频中的正面人脸，并且引入了一个验证器来处理遮挡和外观变化带来的挑战，确保对正确人脸的跟踪。 3. **通用检测器**：这是一个预先训练的模型，能够在不同背景下寻找并定位人脸，尤其关注正面人脸。它的作用是提供初始的目标位置信息。 4. **验证器**：这是一个在线训练的组件，它的主要任务是在跟踪过程中判断当前检测到的人脸是否属于正在追踪的目标个体。这有助于减少误识别和丢失目标的风险。 5. **长期人脸识别**：系统旨在在长时间的视频序列中持续追踪同一人脸，即使面临遮挡、光照变化、表情变化等复杂情况。 6. **学习策略**：论文探讨了在跟踪过程中构建验证器的不同策略，并通过定量评估来确定最佳方法。这可能包括利用已有的正面人脸样本和未标记的视频数据来不断优化模型。 7. **实时性能**：系统设计考虑了实时性，这意味着它能在处理视频流的同时进行人脸检测、跟踪和学习，而不造成明显的延迟。 8. **视频验证**：系统在两个不同类型的视频（一个持续23分钟，另一个8分钟）上进行了测试，证明了其在实际场景中检测和追踪人脸的能力，以及从单一正面示例和未标记视频自动学习多视图模型的效能。 FACE-TLD系统代表了一种高效的人脸识别和追踪解决方案，特别是在无约束的视频环境中，它能适应各种复杂的视觉挑战。

FACE-TLD: TRACKING-LEARNING-DETECTION APPLIED TO FACES

Zdenek Kalal

†

, Krystian Mikolajczyk

†

, Jiri Matas

‡

†

Centre for Vision, Speech and Signal Processing, University of Surrey, UK

‡

Center for Machine Perception, Czech Technical University, Czech Republic

ABSTRACT

A novel system for long-term tracking of a human face in

unconstrained videos is built on Tracking-Learning-Detection

(TLD) approach. The system extends TLD with the concept

of a generic detector and a validator which is designed for

real-time face tracking resistent to occlusions and appearance

changes. The off-line trained detector localizes frontal faces

and the online trained validator decides which faces corre-

spond to the tracked subject. Several strategies for build-

ing the validator during tracking are quantitatively evaluated.

The system is validated on a sitcom episode (23 min.) and a

surveillance (8 min.) video. In both cases the system detects-

tracks the face and automatically learns a multi-view model

from a single frontal example and an unlabeled video.

Index Terms— long-term face tracking, learning, detec-

tion, veriﬁcation, real-time

1. INTRODUCTION

Long-term real-time tracking of human faces in uncon-

strained environments is a challenging problem: given a

single example of a speciﬁc face, track the face in a video

that may include frame cuts, sudden appearance changes,

long-lasting occlusions etc. In such environments, the frame-

by-frame tracking meets face detection and veriﬁcation at

one point with a common goal to determine the location of

the speciﬁc face. This paper proposes a novel solution that is

suitable in such situations.

Two approaches are used for modeling an object ap-

pearance in tracking: static and adaptive. Static models [1]

assume that the object appearance change is limited and

known. Unexpected changes of the object appearance can not

be tracked. This drawback is addressed by adaptive meth-

ods [2] which update the object model during tracking. The

underlying assumption is that every update is correct. Every

incorrect update brings error to the model that accumulates

over time and causes drift. In the context of faces, the drift

problem has been addressed by introduction of so called

visual constraints [3]. Even though this approach demon-

strated increased robustness and accuracy, its performance

was tested only on videos where the face was in the ﬁeld

of view. In scenarios where a face moves in and out of the

Fig. 1. Our system tracks, learns and detects a speciﬁc face in

real-time in unconstrained videos.

frame, face re-detection is essential. Face detection have been

extensively studied [4] and a range of ready-to-use face de-

tectors are available [5] which enable tracking-by-detection.

Apart from expensive ofﬂine training, the disadvantage of

tracking-by-detection is that all faces have the same model

and therefore the identities can not be distinguished. To

elevate this problem, Li et al. [6] proposed a face tracking

algorithm that splits the face model into three parts with dif-

ferent lifespan. This makes the tracker suitable for low-frame

rate videos but the longest period the face can disappear from

the camera view is limited. Another class of approaches for

face tracking was developed as part of automatic character

annotation in video [7]. These systems can handle the sce-

nario considered in this paper, but they have been designed

for ofﬂine processing and adaptation for real-time tracking is

not straightforward.

In this work, we build on an approach called Tracking-

Learning-Detection (TLD) [8], whose learning part was ana-

lyzed in [9]. The TLD method was designed for long-term

tracking of arbitrary objects in unconstrained environments.

The object was tracked and simultaneously learned in order

to build a detector that supports the tracker once it fails. The

detector was build upon the information from the ﬁrst frame

as well as the information provided by the tracker. This paper

has three contributions w.r.t. TLD: (i) Additional source of

information (ofﬂine detector) is embedded to the TLD frame-

work which simpliﬁes the learning task in cases when the ob-

下载后可阅读完整内容，剩余3页未读，立即下载

Ruby_Rose

粉丝: 0
资源: 1

人脸检测跟踪的TLD方法

8.1蓝牙+PWM+Tacking调速小车

opject-tacking-opencv.rar_代码opject

Probabilistic tacking of the soccer ball.pdf

使用git pull命令：there is no tacking information for the current branch. Please specify which branch you want to merge with. See git-pull(1) for details . git pull <remote> <branch>

技术资料分享nRF24L01P(新版无线模块控制IC)很好的技术资料.zip

C++ 课程设计项目，基于 Qt 制作的经典小游戏愤怒的小鸟 FlappyBird源代码

控件以及双指放大缩小图片、单指拖动图片.zip

【路径规划】基于matlab FMM快速行进法船舶路径规划【Matlab仿真 2291期】.md

Python基于 YOLOv8 的甲骨文原始拓片图像单字分割识别模型源代码+使用说明

几种常见简单滤波器用于二维图像降噪，包括均值、中值、高斯、低通、双边滤波器，语言是python

最新资源