摘 要：目前，尽管采用无人机巡检，航电枢纽库区非法捕捞现象依然严重。库区管理人员无法对非法捕捞人员取证。为了解决这一问题，本文提出将视频图像目标检测技术应用到无人机库区巡检中，对无人机采集的图像进行处理，获得证据。首先，估计初始化背景图像；其次，采用色度相似性估计的方法将图像背景与前景运动目标更清晰分割；最后，为了抑制背景噪声，采用双阈值法判别前景和背景，从而提取运动目标，锁定证据。通过在两个无人机库区巡检采集的视频中试验，该算法能够实现目标分割。目标检测技术可以很好地应用在无人机库区巡检中，配合管理人员取证。
关键词：信息技术；非法捕捞取证；目标检测；视频图像；巡检
作者介绍：
王俊文（1990－），男，河南方城人，。研究方向：港口、航电枢纽工程中的图像检测与识别。
中图分类号：TP391.41；U268.6 文献标识码：A 文章编号：2096-4706（2018）01-0000-03
TheApplication of Video Image Target Detection Technology in the Inspection of theReservoir Area
WANGJunwen，AN Xiaogang，CHENG Weiping
（China Waterborne Transport Research Institute，Beijing 100088，China）
Abstract：Atpresent, despite the use of unmanned aerial vehicle inspection，navigation and hydropower reservoir area illegal fishing phenomenonis still serious. The manager of the reservoir area was unable to obtainevidence of illegal fishing personnel. In order to solve this problem，the video image target detection technology is applied to the UAVreservoir area inspection，and the images collected fromUAV are processed to get evidence. First，estimate toinitialize the background image； secondly，using the colorimetric method of the similarity estimation of targetimage background and foreground segmentation more clearly； finally，in order to suppress the backgroundnoise，distinguishing foreground and background by usingthe dual threshold method to extract the moving target locking evidence. Thealgorithm can achieve target segmentation by testing the video captured in twounmanned aerial vehicles （UAV）area. The target detection technology can be well applied to the inspection ofthe UAV reservoir area，and can be used with themanagers to obtain evidence.
Keywords：informationtechnology；illegal fishing evidence；target detection；video image； inspection.
参考文献：
[1] 程为平，安小刚，王俊文.基于大顶子山库区无人机库区巡航应用方案研究 [J].科技资讯，2017，15（1）：11-11.
[2] Felzenszwalb P F，GirshickR B，Mcallester D，et al. Objectdetection with discriminatively trained part-based models.[J].Computer，2014，47（2）：6-7.
[3] Girshick R，DonahueJ，Darrell T，et al. Rich FeatureHierarchies for Accurate Object Detection and Semantic Segmentation[J]. 2013：580-587.
[4] Huang H，Li S，Tang K，et al. Accurate segmentation ofmoving objects and their shadows via brightness ratios and movement patterns [C]//Intelligent Vehicles Symposium Proceedings. IEEE，2014：820-826.
[5] Cucchiara R，GranaC，Piccardi M，et al. Detectingobjects，shadows and ghosts in video streams byexploiting color and motion information[C]// International Conference on ImageAnalysis and Processing，2001. Proceedings. IEEE，2001：360-365.
[6] Kyungnam Kim，ThanaratH. Chalidabhongse，David Harwood. Real-timeforeground–background segmentation using codebook model [J].Real-Time Imaging，2005，11（3）：172-185.