期刊文献+

基于深度学习的目标跟踪方法研究现状与展望 被引量:100

Status and prospect of target tracking based on deep learning
下载PDF
导出
摘要 目标跟踪是计算机视觉领域的重要研究方向之一,在精确制导、智能视频监控、人机交互、机器人导航、公共安全等领域有着重要的作用。目标跟踪的基本问题是在一个视频或图像序列中选择感兴趣的目标,在接下来的连续帧中,找到该目标的准确位置并形成其运动轨迹。目标跟踪是一个颇具挑战性的问题,目标的非刚性变化往往改变了目标的表观模型,同时复杂的光照变化、目标与场景间的遮挡、背景中相似物体的干扰和摄像机的抖动等使目标跟踪任务变得更加困难。近年来,随着深度学习在目标检测和识别等领域中取得巨大的突破,许多学者开始将深度学习模型引入到目标跟踪中,并在一系列数据评测集上取得了优于传统方法的性能,逐渐开启了目标跟踪领域的新篇章。文中将首先阐述目标跟踪问题的难点和基本解决思路;然后根据利用深度学习算法解决目标跟踪问题的不同思路,对当前出现的此类主流算法进行分析,介绍这些算法各自的优缺点及未来的工作方向。 The inverse synthetic aperture lidar (ISAL) have attracted increasing attention for its merits including small visual tracking which is considered as one of the important research topics in the field of computer vision due to its key role in versatile applications, such as precision guidance, intelligent video surveillance, human-computer interaction, robot navigation and public safety. The basic idea for implementing visual tracking is composed of finding the target object in a video or sequence of images, then determining its exact position in the next successive frames and finally generating the corresponding trajectory of this object. Visual tracking, however, is still a challenging problem in practice while taking into account the abrupt appearance changes of the target objects induced by their non-rigid transformation, the sophisticated lighting variation, the obstruction by the block or similar objects in the background and the camera jitter. Motivated by the successful applications in target detection and recognition in recent years, plenty of deep learning models have been integrated in the visual tracking and better performance over traditional methods was achieved in a series of data evaluations, which opens a new door in the field of visual tracking. In this paper, the overview and progress on visual tracking were summarized. The current challenges and corresponding solving approaches in this field are introduced firsfly and in particular, several novel and mainstream visual tracking algorithms based on the deep learning are specially described and analyzed in details, including their basic ideas, advantages and disadvantages and future prospect.
出处 《红外与激光工程》 EI CSCD 北大核心 2017年第5期6-12,共7页 Infrared and Laser Engineering
基金 总装预研项目(51301030108)
关键词 目标跟踪 深度学习 计算机视觉 精确制导 target tracking deep learning computer vision precision guidance
  • 相关文献

参考文献1

二级参考文献10

  • 1王俊卿,黄莎白,史泽林,于海斌.基于小波变换的图像边缘检测[J].系统工程与电子技术,2004,26(7):887-888. 被引量:18
  • 2章玉晋.图像处理和分析[M].北京:清华大学出版社,1999..
  • 3Clark E OLSON, Daniel P. HUTTENLOCHER. Recognition by matching dense, oriented edge pixels[A]. IEEE, Proceedings of the International Symposium on Computer Vision [C]. Coral Gables, Florida, USA, 1995.91-96.
  • 4MEIER T, NGAN K.N. Automatic segmentation of moving objects for video object plane generation [J].IEEE Trans. on Circuits and Systems for Video Technology, 1998, 8(5): 525-538.
  • 5Benedicte BASCLE,Patrick BOUTHEMY,Rachid DERICHE,et a1.Tracking complex primitives in all image sequence[A].Proe.12^th Int.Conf.Pattern Recognition[C].Jerusalem,Israel,1994.426—431.
  • 6Douglas DE CARLO,Dimitris METAXAS.The integration of optical flow and deformable models:application to human face shape and motion estimation[A].Proc.IEEE Computer Vision and Pattern Recognition[C].San Francisco,California,USA,1996.23l-238.
  • 7Dofin COMANICIU,Peter MEER.Mean Shift:A robust approach toward feature space analysis[J].IEEE Trans.0n PAMI,2002,24(5):603—619.
  • 8Stuart GEMAN, Donald GEMAN. Stochastic relaxation, Gibbs distribution and the Bayesian restoration of images [J]. IEEE Trans. on PAMI, 1984, 6(6): 721-741.
  • 9Yu ZHONG, Anil K. JAIN, M.-P. DUBUISSON-JOLLY. Object tracking using deformable templates [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence, 2000, 22(5): 544-549.
  • 10Dong-Gyu SIM, Rae-Hong PARK. Two-dimensional object alignment based on the robust oriented Hausdorff similarity measure [J].IEEE Trans. on Image Processing, 2001, 10(3): 475-483.

共引文献3

同被引文献577

引证文献100

二级引证文献762

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部