Abstract
Ship detection in high-resolution synthetic aperture radar (SAR) imagery is a challenging problem in the case of complex environments, especially inshore and offshore scenes. Nowadays, the existing methods of SAR ship detection mainly use low-resolution representations obtained by classification networks or recover high-resolution representations from low-resolution representations in SAR images. As the representation learning is characterized by low resolution and the huge loss of resolution makes it difficult to obtain accurate prediction results in spatial accuracy; therefore, these networks are not suitable to ship detection of region-level. In this paper, a novel ship detection method based on a high-resolution ship detection network (HR-SDNet) for high-resolution SAR imagery is proposed. The HR-SDNet adopts a novel high-resolution feature pyramid network (HRFPN) to take full advantage of the feature maps of high-resolution and low-resolution convolutions for SAR image ship detection. In this scheme, the HRFPN connects high-to-low resolution subnetworks in parallel and can maintain high resolution. Next, the Soft Non-Maximum Suppression (Soft-NMS) is used to improve the performance of the NMS, thereby improving the detection performance of the dense ships. Then, we introduce the Microsoft Common Objects in Context (COCO) evaluation metrics, which provides not only the higher quality evaluation metrics average precision (AP) for more accurate bounding box regression, but also the evaluation metrics for small, medium and large targets, so as to precisely evaluate the detection performance of our method. Finally, the experimental results on the SAR ship detection dataset (SSDD) and TerraSAR-X high-resolution images reveal that (1) our approach based on the HRFPN has superior detection performance for both inshore and offshore scenes of the high-resolution SAR imagery, which achieves nearly 4.3% performance gains compared to feature pyramid network (FPN) in inshore scenes, thus proving its effectiveness; (2) compared with the existing algorithms, our approach is more accurate and robust for ship detection of high-resolution SAR imagery, especially inshore and offshore scenes; (3) with the Soft-NMS algorithm, our network performs better, which achieves nearly 1% performance gains in terms of AP; (4) the COCO evaluation metrics are effective for SAR image ship detection; (5) the displayed thresholds within a certain range have a significant impact on the robustness of ship detectors.
Highlights
The high-resolution synthetic aperture radar (SAR) images are provided by the airborne and spaceborne SAR sensor with the capability of working in all-weather and all-day
Our results demonstrate that the proposed framework gains much better performance than the existing state-of-the-art single-model ship detectors on the SAR ship detection dataset (SSDD) dataset [35], especially using the higher quality evaluation metrics
The other multi-resolution representation information exchange in the high-resolution feature pyramid network (HRFPN) is similar to Figure 5
Summary
The high-resolution synthetic aperture radar (SAR) images are provided by the airborne and spaceborne SAR sensor with the capability of working in all-weather and all-day. SAR images have been diffusely applied in multiple fields, such as environmental management, land anSdArResoimuracgeessahdamveinbiseterantidoinff,unsaetluyraapl dpliiseadsteinr fmoruelwtipalren,fiaenlddsn, asuticohnaalsdeenfevnirsoen[m1,e2n].taIlnmpaanrtaicguemlare,nstu, ch fielladnsdasamnadritriemsoeutrrcaensspaodrmt sianfiesttryaatinodn,fisnhaetruyraelnfdoirscaesmteerntfo[3re–w5]atrenn,datnodmankaetiounsealofdtehfeenhsigeh[-1re,2s]o. LuIntion SApRaritmicauglaers, tsoucshhifpiedldesteacstimona,riwtimhiechtriasntshpeormt asainfettoypaincdinfitshhiesrpyaepnefro.rcement [3,4,5] tend to make use of tShheiphidgeht-ercetsioolnutiinoSnASRARimimagaegreysitsoaschoipmdpelitceacttieodnp, wrohbilcehmi,smthaeinmlyaicnotnotpaiicniinngthtwis opatapsekrs. One is SthhiepredceotegcntiiotinoninpSrAobRleimma, gwehryeries tahceodmeptelicctaotresdsperpoabrlaetme ,thmeasinhliypscofnrotamintinhge btwacoktgarsokusntdosbaend setsoalcvceudr.aOtensehiispthcelarsescolagbneitliso.nApnrootbhleemr i,swthheerleotchaetidoentepcrtoobrslesmep,aarsastiegtnhiensghpiprsecfrisoembtohuenbdaicnkggrboouxnedssfor daniffafadocnerctrdhuedsnereiatfsttfsmeeahlrcyaeicp,lnulstars.anhsHtdhiepiospstwhhsai.eeprvHecseloemraaw,sasdselylulvateesborhte,obilpsdet.suhAigeeannrctoeoootrhmeeteahdprse,lyieascxntothdobmeatpblchokeleecgxadirtgoeibnonuanosncrepkdegrds,orh,tobhiapuleennsmsddah,,riatepthshsdseeiaigffidrsneehcinndiupgsilesffitptarcsoerhuecdiliptisdssettoiifbanfdoirgceueuutnleidtdscihitftnfo,aigaccduscbeulosttrhxeaetocotstwelny, in dFiisgtuinrgeu1is. HT,haesresfhoorwe,nthinis Fpiagpuerre f1o.cTuhseesreofonrae,ntahciscupraapteeranfodcurosebsuostnsahnipadcceutercattieonanmd ertohboudstfosrhibpoth insdheoterectaionndmoefftshhoodrefosrcbeontehs ionfshhoigrhe -arnedsoolufftsihoonreSAscReniemsaogfehriyg.h-resolution SAR imagery. TrTadraidtiiotinoanlalshshipipddeetteeccttiioonn aapppprrooaacchheessaraeremmainailnylcyoncostnasnttafnatlsfealaslearmalarramtesra(CteFsA(RC)FbAaRse)dboansed onththeestsattaitsitsictiaclaldidsitsritbriubtuiotniosnosfotfhtehesesaeaclucltutetrte[r6–[68–] 8a]nadndthetheexetrxatcrtaecdtefdeafteuarteusreasrearbeasbeadseodnotnhethe mamcahcihnienelelaeranrnininggmmeetthhoodd [[99––1122]]..HHoowweveevre,rt,htehseesceoncovnenvteionntiaolnmael tmhoedths oadreshairgehlhyigdheplyenddeepnetnodnetnhteon thedidstirsitbruibtiuotnios nosf offeafetuartuesrepsrpedreedfienfiednebdybyhuhmuamnasn[s9,[193,–1135–]1,5d],edgreagdriandgintghethpeerpfeorrfmoramncaencoef oshf isphip dedteectteicotniofnorfonrewneSwARSAimRagimerayg[e9r,y15[]9.,1T5h].erTehfoerree,fothree,sethmeseethmodesthaorde sdiaffirecudltiftfoicupletrftoormpesrhfoiprmdestheciption accduerteactteiloynaancdcurroabteulsytlayn. DInestehcotrotr, t(hFeSStwDo) -[s3t0a]g,eRaeltginoariNthemt [s3h1a],veetch.igInhesrhaocrct,utrhaecytwthoa-nstathgee oanlgeo-srtiathgme, sbuhtave higtthhheeeNroSoNnaAwceoRc-wasutidraamaagdacyeaygsyie,sstrrh,fyearaessnfestieeeatrlahrdrcae.chnhoLedenirurmses-heohsttaraaevavglsee.eima,[a3lblrp2ruee]laetaaddttphyoypeitlnriionaetnridtnoreo.ds-sdputeuaccegctdeeradtilhstrehfeadessietddeeuepraeallpenabdlraensmaierndongrioenmngseiltmmahnopeddtl-hesfoeotodar stsfrheoaigrpimnsd.heenitpteacdttiieootnnecittnoion in rtehaelizSeAaRutiommaagteicrysefileecldti.ngLituheetcaanl.d[i3d2a]teapshpilpieldocsaptieocntraanl drecsoidnuvoallubtiaosneadl onneulraanldn-estewaosrekgsmtoensthaiption to dreisaclriizme ianuattoiomn.aKtiacnsgeleetcatiln. [g33th] edecsaingndeiddaatecosnhtiepxltoucaal trieognioann-dbacsoendvRo-lCuNtioNnwalitnhemurualltinlaeytwerofrukssiotnotsohip disimcrpimroivneattihoenp. eKrfaonrgmeatnacel. o[3f3d]edteecstiignngetdhea scmonaltlexshtuipasl.rKeganiogne-bt aasl.e[d34R]-pCrNopNosweditha mmuodltiifliaeydefrafsutesrion
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
