深度学习在视频目标跟踪中的应用进展与展望

视频目标跟踪是计算机视觉的重要研究课题, 在视频监控、机器人、人机交互等方面具有广泛应用. 大数据时代的到来及深度学习方法的出现, 为视频目标跟踪的研究提供了新的契机. 本文首先阐述了视频目标跟踪的基本研究框架. 对新时期视频目标跟踪研究的特点与趋势进行了分析, 介绍了国际上新兴的数据平台、评测方法. 重点介绍了目前发展迅猛的深度学习方法, 包括堆叠自编码器、卷积神经网络等在视频目标跟踪中的最新具体应用情况并进行了深入分析与总结. 最后对深度学习方法在视频目标跟踪中的未来应用与发展方向进行了展望.     

Deep Learning for Object Detection: A Survey

Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in people s life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class. With the rapid development of deep learning algorithms for detection tasks, the performance of object detectors has been greatly improved. In order to understand the main development status of target detection, a comprehensive literature review of target detection and an overall discussion of the works closely related to it are presented in this paper. This paper various object detection methods, including one-stage and two-stage detectors, are systematically summarized, and the datasets and evaluation criteria used in object detection are introduced. In addition, the development of object detection technology is reviewed. Finally, based on the understanding of the current development of target detection, we discuss the main research directions in the future.     

基于深度学习的多目标跟踪关联模型设计

近年来, 深度学习在计算机视觉领域的应用取得了突破性进展, 但基于深度学习的视频多目标跟踪(Multiple object tracking, MOT)研究却相对甚少, 而鲁棒的关联模型设计是基于检测的多目标跟踪方法的核心.本文提出一种基于深度神经网络和度量学习的关联模型:采用行人再识别(Person re-identification, Re-ID)领域中广泛使用的度量学习技术和卷积神经网络(Convolutional neural networks, CNNs)设计目标外观模型, 即利用三元组损失函数设计一个三通道卷积神经网络, 提取更具判别性的外观特征构建目标外观相似度; 再结合运动模型计算轨迹片间的关联概率.在关联策略上, 采用匈牙利算法, 首先以逐帧关联方式得到短小可靠的轨迹片集合, 再通过自适应时间滑动窗机制多级关联, 输出各目标最终轨迹.在2DMOT2015、MOT16公开数据集上的实验结果证明了所提方法的有效性, 与当前一些主流算法相比较, 本文方法取得了相当或者领先的跟踪效果.     

多尺度目标检测的深度学习研究综述

目标检测一直以来都是计算机视觉领域的研究热点之一,其任务是返回给定图像中的单个或多个特定目标的类别与矩形包围框坐标.随着神经网络研究的飞速进展,R-CNN检测器的诞生标志着目标检测正式进入深度学习时代,速度和精度相较于传统算法均有了极大的提升.但是,目标检测的尺度问题对于深度学习算法而言也始终是一个难题,即检测器对于尺...     

基于深度学习的目标视频跟踪算法综述

深度学习理论在计算机视觉中的应用日趋广泛,在目标分类、检测领域取得了令人瞩目的成果,但是深度学习理论在目标跟踪领域的早期应用中,由于存在跟踪时只有目标为正样本,缺乏数据支持,对位置信息依赖程度高等问题,因而应用效果并不理想,传统方法仍占据主流地位.近年来,随着技术的不断发展,深度学习在目标跟踪方向取得了长足的进步.本文首先介绍了目标跟踪技术的基本概念和主要方法,然后针对深度学习在目标跟踪领域的发展现状,从基于深度特征的目标跟踪和基于深度网络的目标跟踪两方面重点阐述了深度学习在该领域的应用方法,并对近期较为流行的基于孪生网络的目标跟踪进行了详细介绍.最后对近年来深度学习在目标跟踪领域取得的成果,以及未来的发展方向作了总结和展望.     

基于深度学习的单目标跟踪算法综述

单目标跟踪是计算机视觉领域中的研究热点.传统算法如相关滤波的跟踪速度较快,但由于提取到的颜色、灰度等手工特征较为粗糙,跟踪精度往往不高.近年来随着深度学习理论的发展,使用深度特征的跟踪方法能够在跟踪的精度和速度方面达到很好的平衡.本文首先介绍单目标跟踪的相关背景,接着从相关滤波单目标跟踪、深度学习单目标跟踪两个阶段对单...     

一种新的FAST-Snake目标跟踪方法

提出一种新的FAST-Snake目标跟踪方法,利用改进的FAST角点特征匹配来估计目标轮廓在帧间的全局仿射变换,将投影轮廓点作为Snake模型的初始化轮廓.为提高跟踪实时性,在Snake能量模型中定义了先验约束能,并用限定搜索方向的贪婪算法（Greedy algorithm）实现局部轮廓优化.实验包括三维目标数据库及真实场景视频,验证了提出方法的均方误差（Means quare error,MSE）及收敛速度评估均优于对比算法,并具备对复杂运动及局部遮挡的适应能力.     

Deep Human-Interaction and Association by Graph-Based Learning for Multiple Object Tracking in the Wild

International Journal of Computer Vision - Multiple Object Tracking (MOT) in the wild has a wide range of applications in surveillance retrieval and autonomous driving. Tracking-by-Detection has...     

基于深度学习的嵌入式目标追踪研究进展

作为计算机视觉领域的基本问题之一, 目标追踪具有广泛的应用场景. 随着硬件算力和深度学习方法的进步, 常规的深度学习目标追踪方法精度越来越高, 但其模型参数量庞大, 计算资源和能耗需求高. 近年来, 随着无人机和智能物联网应用的蓬勃发展, 如何在存储空间和算力有限、低功耗需求的嵌入式硬件环境中进行实时目标跟踪, 成为当前研究的热点. 本文对面向嵌入式应用的目标追踪方法进行了分析综述, 包括相关滤波结合深度学习的目标追踪方法、基于轻量神经网络的目标跟踪方法, 并总结了深度学习模型部署流程和无人机等领域的嵌入式目标追踪典型应用实例, 最后对未来研究重点进行了展望.     

Towards Collaborative Robotics in Top View Surveillance: A Framework for Multiple Object Tracking by Detection Using Deep Learning

Collaborative Robotics is one of the high-interest research topics in the area of academia and industry. It has been progressively utilized in numerous applications, particularly in intelligent surveillance systems. It allows the deployment of smart cameras or optical sensors with computer vision techniques, which may serve in several object detection and tracking tasks. These tasks have been considered challenging and high-level perceptual problems, frequently dominated by relative information about the environment, where main concerns such as occlusion, illumination, background, object deformation, and object class variations are commonplace. In order to show the importance of top view surveillance, a collaborative robotics framework has been presented. It can assist in the detection and tracking of multiple objects in top view surveillance. The framework consists of a smart robotic camera embedded with the visual processing unit. The existing pre-trained deep learning models named SSD and YOLO has been adopted for object detection and localization. The detection models are further combined with different tracking algorithms, including GOTURN, MEDIANFLOW, TLD, KCF, MIL, and BOOSTING. These algorithms, along with detection models, help to track and predict the trajectories of detected objects. The pre-trained models are employed; therefore, the generalization performance is also investigated through testing the models on various sequences of top view data set. The detection models achieved maximum True Detection Rate 93% to 90% with a maximum 0.6% False Detection Rate. The tracking results of different algorithms are nearly identical, with tracking accuracy ranging from 90% to 94%. Furthermore, a discussion has been carried out on output results along with future guidelines.      

基于深度学习的显著性目标检测综述

显著性目标检测通过模仿人的视觉感知系统,寻找最吸引视觉注意的目标,已被广泛应用于图像理解、语义分割、目标跟踪等计算机视觉任务中。随着深度学习技术的快速发展,显著性目标检测研究取得了巨大突破。本文总结了近5年相关工作,全面回顾了3类不同模态的显著性目标检测任务,包括基于RGB图像、基于RGB-D/T(Depth/Thermal)图像以及基于光场图像的显著性目标检测。首先分析了3类研究分支的任务特点,并概述了研究难点;然后就各分支的研究技术路线和优缺点进行阐述和分析,并简单介绍了3类研究分支常用的数据集和主流的评价指标。最后,对基于深度学习的显著性目标检测领域未来研究方向进行了探讨。     

抗遮挡目标跟踪的模型学习综述

视觉目标跟踪任务中的遮挡问题是最具挑战的场景属性之一,研究有效的抗遮挡模型学习方案,对构建适应复杂场景的长期鲁棒跟踪模型具有重要意义.剖析了遮挡影响跟踪性能的本质原因,以抗遮挡性能较好的先进跟踪算法为研究对象,系统分析了模型学习中有效抗遮挡机制,并对其改善长短期遮挡问题的有效性进行比较分析,包括以硬负样本挖掘、有效样本...     

Visual Tracking via Subspace Learning: A Discriminative Approach

Good tracking performance is in general attributed to accurate representation over previously obtained targets and/or reliable discrimination between the target and the surrounding background. In this work, a robust tracker is proposed by integrating the advantages of both approaches. A subspace is constructed to represent the target and the neighboring background, and their class labels are propagated simultaneously via the learned subspace. In addition, a novel criterion is proposed, by taking account of both the reliability of discrimination and the accuracy of representation, to identify the target from numerous target candidates in each frame. Thus, the ambiguity in the class labels of neighboring background samples, which influences the reliability of the discriminative tracking model, is effectively alleviated, while the training set still remains small. Extensive experiments demonstrate that the proposed approach outperforms most state-of-the-art trackers.     

Multiple Object Tracking through Background Learning

This paper discusses about the new approach of multiple object tracking relative to background information. The concept of multiple object tracking through background learning is based upon the theory of relativity, that involves a frame of reference in spatial domain to localize and/or track any object. The field of multiple object tracking has seen a lot of research, but researchers have considered the background as redundant. However, in object tracking, the background plays a vital role and leads to definite improvement in the overall process of tracking. In the present work an algorithm is proposed for the multiple object tracking through background learning. The learning framework is based on graph embedding approach for localizing multiple objects. The graph utilizes the inherent capabilities of depth modelling that assist in prior to track occlusion avoidance among multiple objects. The proposed algorithm has been compared with the recent work available in literature on numerous performance evaluation measures. It is observed that our proposed algorithm gives better performance.     

运动目标特征抽取方法探讨

此文介绍几种运动目标特征抽取方法,重点介绍了抽取运动目标的形状特征、运动特征和频率反射特征的物理意义及其数学模型.本文还给出了基于红外图象形状特征和运动特征的运动目标跟踪实验结果,实验结果表明此文所述特征抽取方法的抗噪声能力强,具有较好的识别跟踪效果.     

结合粒子滤波与Mean shift的高速运动目标跟踪

Mean shift跟踪算法能够有效跟踪视频序列中的各种运动目标,但是该算法无法准确地跟踪视频中高速运动目标.通过分析mean shift算法的原理,指出mean shift对高速运动目标跟踪失效的原因,提出一种基于mean shift的粒子滤波跟踪的新算法.通过实验比较,该算法能改善了Mean shift算法对高速运动目标的效果,并且在存在干扰目标的情况下具备良好的跟踪效果.     

深度学习目标检测方法综述

随着深度学习在目标检测领域的大规模应用,目标检测技术的精度和速度得到迅速提高,已被广泛应用于行人检测、人脸检测、文字检测、交通标志及信号灯检测和遥感图像检测等领域.本文在基于调研国内外相关文献的基础上对目标检测方法进行了综述.首先介绍了目标检测领域的研究现状以及对目标检测算法进行检验的数据集和性能指标.对两类不同架构的...     

面向嵌入式设备的深度学习物体检测优化算法

随着深度神经网络研究地不断深入,物体检测的精度和速率都在不断提升,但是随着网络层的加深,模型体积不断增大,计算代价也越来越高,无法满足神经网络直接在嵌入式设备上实现快速前向推理的需求.为了解决这个问题,本文针对嵌入式设备进行深度学习物体检测优化算法研究.首先,选择合适的物体检测算法框架和神经网络架构;然后在此基础上针对特定检测场景下采集的图片进行训练和模型剪枝;最后,对移植到嵌入式设备上的模型剪枝后的物体检测模型进行汇编指令优化.综合优化后,与原有网络模型相比,模型体积减小9.96%,速度加快8.82倍.     

深度学习的典型目标检测算法研究综述

目标检测是计算机视觉的一个重要研究方向,其目的是精确识别给定图像中特定目标物体的类别和位置.近年来,深度卷积神经网络(Deep Convolutional Neural Networks,DCNN)所具有的特征学习和迁移学习能力,在目标检测算法特征提取、图像表达、分类与识别等方面取得了显著进展.介绍了基于深度学习目标检...     

A Deep Learning Based Approach for Context-Aware Multi-Criteria Recommender Systems

Recommender systems are similar to an information filtering system that helps identify items that best satisfy the users’ demands based on their preference profiles. Context-aware recommender systems (CARSs) and multi-criteria recommender systems (MCRSs) are extensions of traditional recommender systems. CARSs have integrated additional contextual information such as time, place, and so on for providing better recommendations. However, the majority of CARSs use ratings as a unique criterion for building communities. Meanwhile, MCRSs utilize user preferences in multiple criteria to better generate recommendations. Up to now, how to exploit context in MCRSs is still an open issue. This paper proposes a novel approach, which relies on deep learning for context-aware multi-criteria recommender systems. We apply deep neural network (DNN) models to predict the context-aware multi-criteria ratings and learn the aggregation function. We conduct experiments to evaluate the effect of this approach on the real-world dataset. A significant result is that our method outperforms other state-of-the-art methods for recommendation effectiveness.