基于改進RT-DETR的小目標(biāo)檢測算法
打開文本圖片集
SmallobjectdetectionalgorithmbasedonimprovedRT-DETR
WANGKang1，WANGXiaolin2，LIUXinzhi2，DENGJianzhi1 （1.UniversityofTechnology，Guilin541o4，China; 2.GuangxiDatengxiaWaterControlProjectDevelopmentCo.，Ltd.，Nanning53oo21，China）
Abstract：Smallobjectdetectionoften faceschallengessuchasmisseddetectionsandfalsepositivesduetothesmal proportionoftheobjecttotheimageandthelimitedsemanticinformation.Inviewof this，animprovedRT-DETRbasedsmall objectdetectionmodelisproposedtoenhancedetectionperformancewhileensuringreal-timeperformance.Thebackbone networkof theRT-DETRmodelismodifiedbydesigningapartiallre-parameterizedconvolutionmoduletoimprovefeature extractioneficiencyAniientmulti-scaleattention （EMA）mchanismisitroducedtoagggatespatialandcrossspatial information.TheHiLoatentionmechanismisemployedintheAIFIencodertoreducethecomputationalcostsandenhancethe robustnessofthedetectionalgorithm.ExperimentswereconductedontheFloW-Imgdatasetofthesmallobjectsonwater.The resultsshowthatboththemisseddetectionrateandthefalsepositiverateof themodelbasedontheimprovedRT-DETRare reduced in comparison with the baseline model RT-DETR.On the test set， the mAP@0.5 of the proposed algorithm achieves 0.841and itsmAP@0.5：0.95is0.394，representingimprovementsof5.5%and3.7%，respectivelyoverthebaselinemodelRDETR.The detection performance surpasses thoseof both the baseline model and the object detection models of YOLO series.
Keywords：small object detection; RT-DETR model; PCov; Transformer; EMA; HiLo attention mechanism
0 引言
目標(biāo)檢測作為計算機視覺領(lǐng)域中的重要問題，其主要任務(wù)包括識別圖像中的目標(biāo)類別和確定目標(biāo)位置。（剩余9816字）