刘立昕 . 成像声呐目标检测与跟踪技术研究 [D ] . 哈尔滨 : 哈尔滨工程大学 , 2015 .

LIU L X . Research on target detection and tracking technology using imaging sonar [D ] . Harb in:Harbin Engineering University, 2015 . (in Chinese)

卞红雨 , 陈奕名 , 张志刚 , 等 . 像素重要性测量特征下的侧扫声呐目标检测 [J ] . 声学学报 , 2019 , 44 ( 3 ): 353 - 359 .

BIAN H Y , CHEN Y M , ZHANG Z G , et al. Target detection algorithm in side-scan sonar image based on pixel importance measurement [J ] . Chinese Journal of Acoustics , 2019 , 44 ( 3 ): 353 - 359 . (in Chinese)

LIPTON A J , FUJIYOSHI H , PATIL R S . Moving target classification and tracking from real-time video [C ] ∥Proceedings of the 4th IEEE Workshop on Applications of Computer.Princeton,PA, US:IEEE , 1998 : 8 - 14 .

VALERA M , VELASTIN S A . Intelligent distributed surveillance systems: a review [J ] . IEEE Proceeding of Vision, Image and Signal Processing , 2005 , 152 ( 2 ): 192 - 204 .

甘明刚 , 陈杰 , 刘劲 , 等 . 一种基于三帧差分和边缘信息的运动目标检测方法 [J ] . 电子与信息学报 , 2010 , 32 ( 4 ): 894 - 897 .

GAN M G , CHEN J , LIU J , et al. Moving object detection algorithm based on three-frame-differencing and edge information [J ] . Journal of Electronics & Information Technology , 2010 , 32 ( 4 ): 894 - 897 . (in Chinese)

李毅 , 孙正兴 , 远博 . 一种改进的帧差和背景减相结合的运动检测方法 [J ] . 中国图象图形学报 , 2009 , 14 ( 6 ): 1162 - 1168 .

LI Y , SUN Z X , YUAN B . An improved method for motion detection by frame difference and background subtraction [J ] . Journal of Image and Graphics , 2009 , 14 ( 6 ): 1162 - 1168 . (in Chinese)

李玉钰 , 颜景龙 . 多特征联合匹配的目标图像稳定跟踪算法 [J ] . 兵工学报 , 2011 , 32 ( 5 ): 574 - 579 . 针对图像制导目标跟踪系统中应用单一特征跟踪算法，由于特征不稳定而造成的跟踪点漂移，甚至目标丢失等问题，提出多特征联合匹配的目标图像复合跟踪方法。分析了分别单独使用灰度特征或者点特征进行目标跟踪存在的问题；通过归纳常用的目标跟踪算法与特征类型的对应关系，依据经验给出了几种多特征组合方案；以灰度特征和点特征作为多特征联合匹配依据进行方法验证。算法利用两种特征分别获取跟踪点，依据跟踪点邻域与模板之间的相似性度量准则，确定两种方法获得的跟踪点与理想目标点的一致程度，并为其分配权值，联合确定最佳跟踪点，并作为模板更新依据。以某导弹导引头实际飞行视频数据，进行多特征联合匹配跟踪点仿真。通过对比单一方法，算法综合了多种特征的优势，且跟踪点漂移范围满足要求。对进一步改进跟踪轨迹平滑性，以及算法实时性实现进行了探讨。

LI Y Y , YAN J L . Stabilized target tracking algorithm using multi-feature joint matching [J ] . Acta Armamentarii , 2011 , 32 ( 5 ): 574 - 579 . (in Chinese)

孟琭 , 杨旭 . 目标跟踪算法综述 [J ] . 自动化学报 , 2019 , 45 ( 7 ): 1244 - 1260 .

MENG L , YANG X . A survey of object tracking algorithms [J ] . IEEE/CAA Journal of Automatica Sinica , 2019 , 45 ( 7 ): 1244 - 1260 . (in Chinese)

LI C M , XU C Y , GUI C F , et al. Distance regularized level set evolution and its application to image segmentation [J ] . IEEE Transactions on Image Processing , 2010 , 19 ( 12 ): 3243 - 3253 . DOI: 10.1109/TIP.2010.2069690 http://doi.org/10.1109/TIP.2010.2069690 Level set methods have been widely used in image processing and computer vision. In conventional level set formulations, the level set function typically develops irregularities during its evolution, which may cause numerical errors and eventually destroy the stability of the evolution. Therefore, a numerical remedy, called reinitialization, is typically applied to periodically replace the degraded level set function with a signed distance function. However, the practice of reinitialization not only raises serious problems as when and how it should be performed, but also affects numerical accuracy in an undesirable way. This paper proposes a new variational level set formulation in which the regularity of the level set function is intrinsically maintained during the level set evolution. The level set evolution is derived as the gradient flow that minimizes an energy functional with a distance regularization term and an external energy that drives the motion of the zero level set toward desired locations. The distance regularization term is defined with a potential function such that the derived level set evolution has a unique forward-and-backward (FAB) diffusion effect, which is able to maintain a desired shape of the level set function, particularly a signed distance profile near the zero level set. This yields a new type of level set evolution called distance regularized level set evolution (DRLSE). The distance regularization effect eliminates the need for reinitialization and thereby avoids its induced numerical errors. In contrast to complicated implementations of conventional level set formulations, a simpler and more efficient finite difference scheme can be used to implement the DRLSE formulation. DRLSE also allows the use of more general and efficient initialization of the level set function. In its numerical implementation, relatively large time steps can be used in the finite difference scheme to reduce the number of iterations, while ensuring sufficient numerical accuracy. To demonstrate the effectiveness of the DRLSE formulation, we apply it to an edge-based active contour model for image segmentation, and provide a simple narrowband implementation to greatly reduce computational cost.

ARNOLD E , AL-JARRAH O Y , DIANATI M , et al. A survey on 3D object detection methods for autonomous driving applications [J ] . IEEE Transactions on Intelligent Transportation Systems , 2019 , 20 ( 10 ): 3782 - 3795 . DOI: 10.1109/TITS.6979 http://doi.org/10.1109/TITS.6979 https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979 https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

王朋 . 基于稀疏布阵的三维成像声呐信号处理算法研究 [D ] . 北京 : 中国科学院大学 , 2015 .

WANG P . Research on signal processing algorithm of three-dimensional acoustical imaging sonar based on sparse planar array [D ] . Beijing : University of Chinese Academy of Sciences , 2015 . (in Chinese)

曾腾 . 三维成像声呐图像重建与显示技术研究 [D ] . 北京 : 中国科学院大学 , 2020 .

ZENG T . Research on image reconstruction and display technology of 3-D imaging sonar system [D ] . Beijing : University of Chinese Academy of Sciences , 2020 . (in Chinese)

MURINO V . Three-dimensional image generation and processing in underwater acoustic vision [J ] . Proceeding of the IEEE , 2000 , 88 ( 12 ): 1903 - 1948 . DOI: 10.1109/5.899059 http://doi.org/10.1109/5.899059 http://ieeexplore.ieee.org/document/899059/ http://ieeexplore.ieee.org/document/899059/

HOUSTON K M . Three-dimensional acoustical imaging using micromechanical hydrophones [C ] ∥Proceedings of Oceans MTS/IEEE.San Diego, CA, US:IEEE , 1995 : 1174 - 1182 .

董静 . 基于图像声呐的动目标检测技术研究 [D ] . 哈尔滨 : 哈尔滨工程大学 , 2014 .

DONG J . Research on moving targets detection based on image sonar [D ] . Harb in:Harbin Engineering University, 2014 . (in Chinese)

阮秋琦 . 数字图像处理 [M ] . 第3版 . 北京 : 电子工业出版社 , 2011 : 560 - 564 .

RUAN Q Q . Digital image processing, third edition [M ] . 3rd Edition . Beijing : Publishing House of Electronics Industry , 2011 : 560 - 564 . (in Chinese)

付萍 , 薛定宇 , 林明秀 , 等 . 基于单目视觉的多车辆跟踪方法研究 [J ] . 兵工学报 , 2007 , 28 ( 8 ): 988 - 992 . 针对车载单目摄像机的汽车辅助驾驶系统，提出了一种多模式多线索的车辆跟踪算法。首先利用运动估计预测目标在下一帧的感兴趣区域，也就是跟踪窗。然后多目标遮挡推理机制确定目标是处于遮挡模式还是正常模式。在正常模式下，在跟踪窗内联合使用车辆的先验知识、评估环节、分块模板等线索对车辆目标定位；遮挡模式下，利用遮挡推理机制给出的遮挡区域，在跟踪窗内调用切割分块模板匹配进行遮挡处理。这种多模式多线索的车辆跟踪方法实现了对后方多车辆的稳定跟踪，同时也适合前视车辆。实验结果表明该算法是鲁棒的和准确的。

FU P , XUE D Y , LIN M X , et al. Research on tracking method of multiple vehicles based on monocular camera [J ] . Acta Armamentarii , 2007 , 28 ( 8 ): 988 - 992 . (in Chinese) The multi-mode and multi-clue vehicle tracking algorithm in image sequences was proposed for automobile assistance driving system with monocular camera. The regions of interest which contain the target in the next frame, namely tracking windows, are predicted by motion estimator. Either the occlusive mode or common mode of the target is determined by the multi-target occlusion reasoning mechanism. In the common mode, multiple clues, such as prior knowledge of vehicle, assessment component, division block template etc, are integrated to locate the vehicle target in the tracking win?dow; in the occlusive mode, partial division block template matcnmg is used to handle with occlusion.The vehicle observed in rear view can be tracked stably by the multi-mode and multi-clue vehicle track?ing algorithm. The approach is suitable for tracking vehicles observed in frontal view. Experiment re?sults illustrate the robust and accurate performance of the tracKing algorithm.

曾腾 , 张春华 , 王朋 . 基于局部异常因子算法的三维声呐单帧重建研究 [J ] . 兵工学报 , 2020 , 41 ( 3 ): 552 - 558 . DOI: 10.3969/j.issn.1000-1093.2020.03.016 http://doi.org/10.3969/j.issn.1000-1093.2020.03.016 海洋环境的复杂性会使三维声纳获取到的点云中存在异常点，从而影响点云的后期处理和可视化。将获取到的声纳数据依次进行三维波束成像、最大值滤波和坐标系转换，进而得到原始点云。提出将局部异常因子(LOF)算法应用到点云去噪、剔除干扰的异常点，并用一种改进三角网生长方法进行单帧重建。改进三角网生长法简化了三角网生成中关键的“第三点”搜寻过程，通过实际数据处理分析得知：相比于传统阈值去噪方式，基于LOF算法的去噪方式能够在保持目标真实轮廓的前提下有效剔除非目标点；经过所提去噪方式的声纳数据能够得到更贴合实际目标轮廓的三维重建结果。

ZENG T , ZHANG C H , WANG P . Research on the 3D sonar single-frame reconstruction based on local outlier factor algorithm [J ] . Acta Armamentarii , 2020 , 41 ( 3 ): 552 - 558 . (in Chinese) DOI: 10.3969/j.issn.1000-1093.2020.03.016 http://doi.org/10.3969/j.issn.1000-1093.2020.03.016 3D sonar always acquires the data point with outliers in the complex marine environment, which affects the post processing and visualization of point cloud. 3D beamforming imaging, maximum filtering and coordinate transformation are made for the sonar data to obtain the original point cloud. The local outlier factor (LOF) algorithm is used to eliminate the abnormal points, and a modified triangulation growing method is used for single-frame reconstruction. In the modified triangulation growing method, the crucial process of ‘the third point’ finding in triangular mesh generation is simplified. A denoising method based on LOF algorithm can be used to eliminate the points not belonging to the target under the premise in keeping the real contour of target compared with the traditional threshold denoising method. And the 3D reconstruction result of more realistic target contour can be achieved from the sonar data obtained by the proposed denoising method. Key

姚玉荣 , 章毓晋 . 利用小波和矩进行基于形状的图象检索 [J ] . 中国图象图形学报 , 2000 , 5 ( 3 ): 206 - 210 .

YAO Y R , ZHANG Y J . Shape-based image retrieval using wavelet and moment [J ] . Journal of Image and Graphics , 2000 , 5 ( 3 ): 206 - 210 . (in Chinese)

孙彦景 , 王赛楠 , 石韫开 , 等 . 基于全局背景与特征降维的视觉跟踪算法 [J ] . 电子与信息学报 , 2018 , 40 ( 9 ): 2135 - 2142 .

SUN Y J , WANG S N , SHI Y K , et al. Visual tracking algorithm based on global context and feature dimensionality reduction [J ] . Journal of Electronics & Information Technology , 2018 , 40 ( 9 ): 2135 - 2142 . (in Chinese)