{"id":11559,"date":"2025-05-04T22:58:53","date_gmt":"2025-05-04T20:58:53","guid":{"rendered":"https:\/\/geopard.tech\/?p=11559"},"modified":"2025-05-04T23:00:29","modified_gmt":"2025-05-04T21:00:29","slug":"odrakasvatus-saab-hoogu-kerge-yolov5-tuvastamisega","status":"publish","type":"post","link":"https:\/\/geopard.tech\/est\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/","title":{"rendered":"Odrakasvatus saab hoogu kerge YOLOv5 tuvastusega"},"content":{"rendered":"

M\u00e4gismaa oder, vastupidav teraviljakultuur, mida kasvatatakse Hiina Qinghai-Tiibeti platoo k\u00f5rgm\u00e4estikualadel, m\u00e4ngib olulist rolli kohaliku toiduga kindlustatuse ja majandusliku stabiilsuse tagamisel. Teaduslikult tuntud kui\u00a0Harilik harilik<\/em>\u00a0L., see p\u00f5llukultuur edeneb \u00e4\u00e4rmuslikes tingimustes \u2013 h\u00f5re \u00f5hk, madal hapnikusisaldus ja keskmine aastatemperatuur 6,3 \u00b0C \u2013, mist\u00f5ttu on see asendamatu kogukondadele karmides keskkondades.<\/p>\n

Hiinas, peamiselt Xizangi autonoomses piirkonnas, kasvatatakse m\u00e4gismaa otra \u00fcle 270 000 hektari, moodustades seel\u00e4bi enam kui poole piirkonna istutusalast ja \u00fcle 701 000 000 hektari teravilja kogutoodangust. Odra tiheduse \u2013 taimede v\u00f5i v\u00f5rsete arvu pindala\u00fchiku kohta \u2013 t\u00e4pne j\u00e4lgimine on oluline p\u00f5llumajandustavade, n\u00e4iteks niisutamise ja v\u00e4etamise, optimeerimiseks ning saagikuse prognoosimiseks.<\/p>\n

Traditsioonilised meetodid, nagu k\u00e4sitsi prooviv\u00f5tt v\u00f5i satelliitpildistamine, on osutunud ebaefektiivseteks, t\u00f6\u00f6mahukateks v\u00f5i ebapiisavalt detailseteks. Nende probleemide lahendamiseks t\u00f6\u00f6tasid Fujiani P\u00f5llumajandus- ja Metsandus\u00fclikooli ning Chengdu Tehnika\u00fclikooli teadlased v\u00e4lja uuendusliku tehisintellekti mudeli, mis p\u00f5hineb tipptasemel objektide tuvastamise algoritmil YOLOv5.<\/p>\n

Nende t\u00f6\u00f6, mis avaldati\u00a0Taimemeetodid<\/em>\u00a0(2025) saavutas t\u00e4helepanuv\u00e4\u00e4rseid tulemusi, sealhulgas keskmise t\u00e4psuse (mAP) 93,1% \u2013 m\u00f5\u00f5dik, mis m\u00f5\u00f5dab \u00fcldist tuvastust\u00e4psust \u2013 ja arvutuskulude v\u00e4henemise 75,6% v\u00f5rra, mis muutis selle sobivaks droonide reaalajas kasutuselev\u00f5tuks.<\/p>\n

P\u00f5llukultuuride seire v\u00e4ljakutsed ja uuendused<\/h2>\n

M\u00e4gismaa odra t\u00e4htsus ulatub kaugemale selle rollist toiduallikana. Ainu\u00fcksi 2022. aastal koristati Rikaze linnas, mis on suur odrakasvatuspiirkond, 60 000 hektaril 408 900 tonni otra, mis moodustas peaaegu poole Tiibeti kogu teraviljatoodangust.<\/p>\n

Vaatamata odra kultuurilisele ja majanduslikule t\u00e4htsusele on selle saagikuse hindamine pikka aega olnud keeruline. Traditsioonilised meetodid, n\u00e4iteks k\u00e4sitsi loendamine v\u00f5i satelliidipildid, on kas liiga t\u00f6\u00f6mahukad v\u00f5i neil puudub vajalik eraldusv\u00f5ime \u00fcksikute odrav\u00f5rsete \u2013 taime tera kandvate osade, mis on sageli vaid 2\u20133 sentimeetrit laiad \u2013 tuvastamiseks.<\/p>\n

K\u00e4sitsi proovide v\u00f5tmine n\u00f5uab p\u00f5llumeestelt p\u00f5lluosade f\u00fc\u00fcsilist kontrollimist \u2013 see protsess on aeglane, subjektiivne ja suurte farmide jaoks ebapraktiline. Satelliidipildid, kuigi kasulikud laiaulatuslike vaatluste jaoks, on h\u00e4das madala eraldusv\u00f5imega (sageli 10\u201330 meetrit piksli kohta) ja sagedaste ilmastikuh\u00e4iretega, n\u00e4iteks pilvkattega m\u00e4gistes piirkondades nagu Tiibet.<\/p>\n

Nende piirangute \u00fcletamiseks p\u00f6\u00f6rdusid teadlased mehitamata \u00f5hus\u00f5idukite (UAV) ehk droonide poole, mis on varustatud 20-megapiksliste kaameratega. Need droonid j\u00e4\u00e4dvustasid Rikaze linna odrap\u00f5ldudest 501 k\u00f5rglahutusega pilti kahes kriitilises kasvufaasis: kasvufaasis 2022. aasta augustis, mida iseloomustavad rohelised arenevad v\u00f5rsed, ja k\u00fcpsemisfaasis 2023. aasta augustis, mida iseloomustavad kuldkollased koristusvalmis v\u00f5rsed.<\/p>\n

\"Droonip\u00f5hine<\/p>\n

Nende piltide anal\u00fc\u00fcsimine tekitas aga v\u00e4ljakutseid, sealhulgas droonide liikumisest tingitud h\u00e4gused servad, odrav\u00f5rsete v\u00e4iksus \u00f5hust vaadatuna ja kattuvad v\u00f5rsed tihedalt istutatud p\u00f5ldudel.<\/p>\n

Nende probleemide lahendamiseks eelt\u00f6\u00f6tlesid teadlased pilte, jagades iga k\u00f5rge eraldusv\u00f5imega pildi 35 v\u00e4iksemaks alampildiks ja filtreerides v\u00e4lja udused servad, mille tulemuseks oli 2970 kvaliteetset alampilti treenimiseks. See eelt\u00f6\u00f6tlusetapp tagas, et mudel keskendus selgetele ja praktilistele andmetele, v\u00e4ltides madala kvaliteediga piirkondade segavaid tegureid.<\/p>\n

Objektide tuvastamise tehnilised edusammud<\/h2>\n

Selle uuringu keskmes on YOLOv5 algoritm (You Only Look Once version 5), \u00fcheastmeline objektide tuvastamise mudel, mis on tuntud oma kiiruse ja modulaarse disaini poolest. Erinevalt vanematest kaheastmelistest mudelitest nagu Faster R-CNN, mis esmalt tuvastavad huvipakkuvad piirkonnad ja seej\u00e4rel klassifitseerivad objektid, teostab YOLOv5 tuvastamise \u00fche l\u00e4bimisega, muutes selle oluliselt kiiremaks.<\/p>\n

Baasmudel YOLOv5n, millel oli 1,76 miljonit parameetrit (tehisintellekti mudeli konfigureeritavad komponendid) ja 4,1 miljardit FLOP-i (ujukomatehted, arvutusliku keerukuse m\u00f5\u00f5t), oli juba efektiivne. Kuid pisikeste, kattuvate odrat\u00e4ppide tuvastamine vajas edasist optimeerimist.<\/p>\n

Uurimisr\u00fchm tutvustas mudelis kolme peamist t\u00e4iustust: s\u00fcgavuti eraldatav konvolutsioon (DSConv), varikujuline konvolutsioon (GhostConv) ja konvolutsiooniline plokkide t\u00e4helepanu moodul (CBAM).<\/p>\n

S\u00fcgavuti eraldatav konvolutsioon (DSConv) v\u00e4hendab arvutuskulusid, jagades standardse konvolutsiooniprotsessi \u2013 matemaatilise operatsiooni, mis eraldab piltidelt tunnuseid \u2013 kaheks etapiks. Esiteks rakendab s\u00fcgavuskonvolutsioon filtreid \u00fcksikutele v\u00e4rvikanalitele (nt punane, roheline, sinine), anal\u00fc\u00fcsides iga kanalit eraldi.<\/p>\n

Sellele j\u00e4rgneb punktp\u00f5hine konvolutsioon, mis kombineerib tulemusi kanalite l\u00f5ikes 1\u00d71 tuumade abil. See l\u00e4henemisviis v\u00e4hendab parameetrite arvu kuni 75% v\u00f5rra.<\/p>\n

\"Parameetri<\/p>\n

N\u00e4iteks traditsiooniline 3\u00d73 konvolutsioon 64 sisend- ja 128 v\u00e4ljundkanaliga n\u00f5uab 73 728 parameetrit, samas kui DSConv v\u00e4hendab selle vaid 8768-ni \u2013 88% v\u00e4hendus. See efektiivsus on kriitilise t\u00e4htsusega mudelite juurutamiseks droonidele v\u00f5i piiratud t\u00f6\u00f6tlemisv\u00f5imsusega mobiilseadmetele.<\/p>\n

GhostConvolutsioon (GhostConv) lihtsustab mudelit veelgi, genereerides t\u00e4iendavaid tunnuskaarte \u2013 pildimustrite lihtsustatud esitusi \u2013 lihtsate lineaarsete toimingute, n\u00e4iteks p\u00f6\u00f6ramise v\u00f5i skaleerimise abil, ressursimahukate konvolutsioonide asemel.<\/p>\n

Traditsioonilised konvolutsioonikihid toodavad \u00fcleliigseid tunnuseid, raiskades arvutusressursse. GhostConv lahendab selle probleemi, luues olemasolevatest tunnustest "varjatud" tunnuseid, v\u00e4hendades teatud kihtide parameetreid sisuliselt poole v\u00f5rra.<\/p>\n

N\u00e4iteks 64 sisend- ja 128 v\u00e4ljundkanaliga kiht n\u00f5uaks traditsiooniliselt\u00a073 728 parameetrit<\/strong>, aga GhostConv v\u00e4hendab selle v\u00e4\u00e4rtuseks\u00a036,864<\/strong>\u00a0s\u00e4ilitades samal ajal t\u00e4psuse. See tehnika on eriti kasulik v\u00e4ikeste objektide, n\u00e4iteks odrap\u00f5ldude tuvastamiseks, kus arvutuslik efektiivsus on \u00fclioluline.<\/p>\n

Mudeli kriitiliste tunnuste esiletoomiseks isegi tihedas keskkonnas integreeriti konvolutsioonilise plokk-t\u00e4helepanu moodul (CBAM). Inimeste visuaalsetest s\u00fcsteemidest inspireeritud t\u00e4helepanumehhanismid v\u00f5imaldavad tehisintellekti mudelitel pildi olulisi osi t\u00e4htsuse j\u00e4rjekorda seada.<\/p>\n

CBAM kasutab kahte t\u00fc\u00fcpi t\u00e4helepanu: kanalite t\u00e4helepanu, mis tuvastab olulised v\u00e4rvikanalid (nt roheline kasvavate okaste jaoks) ja ruumiline t\u00e4helepanu, mis t\u00f5stab esile pildil olevad v\u00f5tmepiirkonnad (nt okaste klastrid). Asendades standardmoodulid DSConv ja GhostConv-iga ning kaasates CBAM-i, l\u00f5id teadlased lihtsustatud ja t\u00e4psema odra tuvastamiseks kohandatud mudeli.<\/p>\n

Rakendamine ja tulemused<\/h2>\n

Mudeli treenimiseks sildistasid teadlased k\u00e4sitsi 135 originaalpilti, kasutades piiravaid kaste \u2013 ristk\u00fclikukujulisi raame, mis t\u00e4histavad odrav\u00f5rsete asukohta \u2013, liigitades v\u00f5rsed kasvu- ja k\u00fcpsemisfaasidesse. Andmete t\u00e4iendamise tehnikad \u2013 sealhulgas p\u00f6\u00f6ramine, m\u00fcras\u00fcst, oklusioon ja teravustamine \u2013 laiendasid andmestikku 2970 pildini, parandades mudeli \u00fcldistamisv\u00f5imet erinevates v\u00e4litingimustes.<\/p>\n

N\u00e4iteks piltide p\u00f6\u00f6ramine 90\u00b0, 180\u00b0 v\u00f5i 270\u00b0 v\u00f5rra aitas mudelil tuvastada erinevate nurkade alt tulevaid naelu, lisades samal ajal m\u00fcra, simuleerides reaalseid ebat\u00e4iusi, nagu tolm v\u00f5i varjud. Andmestik jagati treeningkomplektiks (80%) ja valideerimiskomplektiks (20%), tagades usaldusv\u00e4\u00e4rse hindamise.<\/p>\n

Treening toimus suure j\u00f5udlusega s\u00fcsteemis, millel oli AMD Ryzen 7 protsessor, NVIDIA RTX 4060 graafikakaart ja 64 GB muutm\u00e4lu, kasutades PyTorchi raamistikku \u2013 populaarset s\u00fcva\u00f5ppe t\u00f6\u00f6riista. Hoolikalt j\u00e4lgiti \u00fcle 300 treeningperioodi (andmestiku t\u00e4ielikud l\u00e4bimised), mudeli t\u00e4psust (\u00f5igete tuvastamiste t\u00e4psus), meeldej\u00e4\u00e4vust (v\u00f5ime leida k\u00f5ik olulised piigid) ja kadusid (veam\u00e4\u00e4r).<\/p>\n

Tulemused olid rabavad. T\u00e4iustatud YOLOv5 mudel saavutas t\u00e4psuse 92,2% (v\u00f5rreldes algtaseme 89,1%-ga) ja taasesitatavuse 86,2% (v\u00f5rreldes algtaseme 83,1%-ga), edestades algtaseme YOLOv5n-i m\u00f5lemas m\u00f5\u00f5dikus 3,1% v\u00f5rra. Selle keskmine t\u00e4psus (mAP) \u2013 terviklik m\u00f5\u00f5dik, mis keskmistab tuvastust\u00e4psuse k\u00f5igis kategooriates \u2013 ulatus 93,1%-ni, kusjuures individuaalsed skoorid olid kasvufaasi piikide puhul 92,7% ja k\u00fcpsusfaasi piikide puhul 93,5%.<\/p>\n

\"YOLOv5<\/p>\n

Sama muljetavaldav oli ka selle arvutuslik efektiivsus: mudeli parameetrid langesid 70,6% v\u00f5rra 1,2 miljonini ja FLOP-ide arv v\u00e4henes 75,6% v\u00f5rra 3,1 miljardini. V\u00f5rdlusanal\u00fc\u00fcsid juhtivate mudelitega nagu Faster R-CNN ja YOLOv8n t\u00f5id esile selle paremuse.<\/p>\n

Kuigi YOLOv8n saavutas veidi k\u00f5rgema mAP-i (93,8%), olid selle parameetrid (3,0 miljonit) ja FLOP-id (8,1 miljardit) vastavalt 2,5x ja 2,6x k\u00f5rgemad, muutes pakutud mudeli reaalajas rakenduste jaoks palju t\u00f5husamaks.<\/p>\n

Visuaalsed v\u00f5rdlused r\u00f5hutasid neid edusamme. Kasvufaasi piltidel tuvastas t\u00e4iustatud mudel 41 oga v\u00f5rreldes algtaseme 28-ga. K\u00fcpsemise ajal tuvastas see 3 oga v\u00f5rreldes algtaseme 2-ga, kusjuures v\u00e4hem oli m\u00f6\u00f6dalaskmisi (t\u00e4histatud oran\u017eide nooltega) ja valepositiivseid tulemusi (t\u00e4histatud lillade nooltega).<\/p>\n

Need t\u00e4iustused on \u00fcliolulised p\u00f5llumeestele, kes tuginevad t\u00e4psetele andmetele saagikuse ennustamiseks ja ressursside optimeerimiseks. N\u00e4iteks v\u00f5imaldab t\u00e4pne viljapeade loendamine paremini hinnata teraviljatoodangut, mis annab teavet otsuste langetamiseks koristusaja, ladustamise ja turuplaneerimise kohta.<\/p>\n

Tulevased suunad ja praktilised tagaj\u00e4rjed<\/h2>\n

Vaatamata edule tunnistas uuring ka selle piiranguid. J\u00f5udlus langes \u00e4\u00e4rmuslikes valgustingimustes, n\u00e4iteks karmi keskp\u00e4evase pimestamise v\u00f5i tugevate varjude korral, mis v\u00f5ivad varjata ogade detaile. Lisaks ei sobinud ristk\u00fclikukujulised piiravad kastid m\u00f5nikord ebakorrap\u00e4rase kujuga ogadele, mis tekitas v\u00e4iksemaid ebat\u00e4psusi.<\/p>\n

Mudel v\u00e4listas ka mehitamata \u00f5hus\u00f5idukite piltidelt udused servad, mis n\u00f5udis k\u00e4sitsi eelt\u00f6\u00f6tlust \u2013 etapp, mis lisab aega ja keerukust.<\/p>\n

Edasine t\u00f6\u00f6 eesm\u00e4rk on neid probleeme lahendada, laiendades andmestikku, et see h\u00f5lmaks koidikul, keskp\u00e4eval ja videvikus j\u00e4\u00e4dvustatud pilte, katsetades hulknurga kujuga m\u00e4rkustega (paindlikud kujundid, mis sobivad paremini ebakorrap\u00e4raste objektidega) ja t\u00f6\u00f6tades v\u00e4lja algoritme, mis aitaksid uduseid piirkondi paremini k\u00e4sitsi sekkumiseta k\u00e4sitleda.<\/p>\n

Sellel uuringul on s\u00fcgavad tagaj\u00e4rjed. Selliste piirkondade nagu Tiibet p\u00f5llumeestele pakub mudel reaalajas saagikuse hindamist, asendades t\u00f6\u00f6mahuka k\u00e4sitsi loendamise droonip\u00f5hise automatiseerimisega. Kasvufaaside eristamine v\u00f5imaldab t\u00e4pset saagikoristust planeerida, v\u00e4hendades enneaegsest v\u00f5i hilinenud koristamisest tulenevaid kahjusid.<\/p>\n

\u00dcksikasjalikud andmed v\u00f5rsete tiheduse kohta \u2013 n\u00e4iteks ala- v\u00f5i \u00fclerahvastatud alade tuvastamine \u2013 v\u00f5ivad anda teavet niisutus- ja v\u00e4etamisstrateegiate kohta, v\u00e4hendades vee- ja kemikaalij\u00e4\u00e4tmeid. Lisaks odrale on kergekaaluline arhitektuur paljulubav ka teiste p\u00f5llukultuuride, n\u00e4iteks nisu, riisi v\u00f5i puuviljade puhul, sillutades teed laiematele rakendustele t\u00e4ppisp\u00f5llumajanduses.<\/p>\n

Kokkuv\u00f5te<\/h2>\n

Kokkuv\u00f5tteks v\u00f5ib \u00f6elda, et see uuring n\u00e4itab tehisintellekti transformatiivset potentsiaali p\u00f5llumajanduslike v\u00e4ljakutsete lahendamisel. T\u00e4iustades YOLOv5 uuenduslike kergete tehnikatega, on teadlased loonud t\u00f6\u00f6riista, mis tasakaalustab t\u00e4psuse ja t\u00f5hususe \u2013 see on kriitilise t\u00e4htsusega reaalseks rakendamiseks ressursipiiranguga keskkondades.<\/p>\n

Sellised terminid nagu mAP, FLOP ja t\u00e4helepanumehhanismid v\u00f5ivad tunduda tehnilised, kuid nende m\u00f5ju on s\u00fcgavalt praktiline: need v\u00f5imaldavad p\u00f5llumeestel teha andmep\u00f5hiseid otsuseid, s\u00e4\u00e4sta ressursse ja maksimeerida saagikust. Kuna kliimamuutused ja rahvastiku kasv suurendavad survet \u00fclemaailmsetele toidus\u00fcsteemidele, on sellised edusammud h\u00e4davajalikud.<\/p>\n

Tiibeti ja kaugemate piirkondade p\u00f5llumeeste jaoks ei t\u00e4henda see tehnoloogia mitte ainult p\u00f5llumajandusliku efektiivsuse h\u00fcpet, vaid ka lootusekiirt j\u00e4tkusuutliku toiduga kindlustatuse saavutamiseks ebakindlas tulevikus.<\/p>\n

Viide: <\/strong>Cai, M., Deng, H., Cai, J. jt. T\u00e4iustatud YOLOv5-l p\u00f5hinev kerge m\u00e4gismaa odra tuvastamine. Plant Methods 21, 42 (2025). https:\/\/doi.org\/10.1186\/s13007-025-01353-0<\/a><\/p>","protected":false},"excerpt":{"rendered":"

M\u00e4gismaa oder, vastupidav teraviljakultuur, mida kasvatatakse Hiina Qinghai-Tiibeti platoo k\u00f5rgm\u00e4estikualadel, m\u00e4ngib olulist rolli kohalikus toiduga kindlustatuses ja majanduslikus\u2026<\/p>","protected":false},"author":210157960,"featured_media":11562,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","_eb_attr":"","content-type":"","_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_wpcom_ai_launchpad_first_post":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"{title}\n\n{excerpt}\n\n{url}","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_wpas_customize_per_network":false,"jetpack_post_was_ever_published":false},"categories":[1657,1660,1377],"tags":[],"class_list":["post-11559","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-precision-farming","category-agriculture-mapping","category-crop-monitoring"],"acf":[],"yoast_head":"\nBarley Farming Gets a Boost With Lightweight YOLOv5 Detection - GeoPard Agriculture<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/geopard.tech\/est\/blogi\/odrakasvatus-saab-hoogu-kerge-yolov5-tuvastamisega\/\" \/>\n<meta property=\"og:locale\" content=\"et_EE\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection - GeoPard Agriculture\" \/>\n<meta property=\"og:description\" content=\"Highland barley, a resilient cereal crop grown in the high-altitude regions of China\u2019s Qinghai-Tibet Plateau, plays a critical role in local food security and economic...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/geopard.tech\/est\/blogi\/odrakasvatus-saab-hoogu-kerge-yolov5-tuvastamisega\/\" \/>\n<meta property=\"og:site_name\" content=\"GeoPard - Precision agriculture Mapping software\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/geopardAgriculture\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-04T20:58:53+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-04T21:00:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection-1024x576.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"576\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"dementievgeopard\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@geopardagri\" \/>\n<meta name=\"twitter:site\" content=\"@geopardagri\" \/>\n<meta name=\"twitter:label1\" content=\"Kirjutanud\" \/>\n\t<meta name=\"twitter:data1\" content=\"dementievgeopard\" \/>\n\t<meta name=\"twitter:label2\" content=\"Eeldatav lugemisaeg\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutit\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/\"},\"author\":{\"name\":\"dementievgeopard\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/#\\\/schema\\\/person\\\/dd217733c742620adc57befbbcd84a8a\"},\"headline\":\"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection\",\"datePublished\":\"2025-05-04T20:58:53+00:00\",\"dateModified\":\"2025-05-04T21:00:29+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/\"},\"wordCount\":1570,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1\",\"articleSection\":[\"Precision Farming\",\"Agriculture Mapping\",\"Crop monitoring\"],\"inLanguage\":\"et\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/\",\"url\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/\",\"name\":\"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection - GeoPard Agriculture\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1\",\"datePublished\":\"2025-05-04T20:58:53+00:00\",\"dateModified\":\"2025-05-04T21:00:29+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#breadcrumb\"},\"inLanguage\":\"et\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"et\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#primaryimage\",\"url\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1\",\"contentUrl\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1\",\"width\":3120,\"height\":1755,\"caption\":\"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/blog\\\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/geopard.tech\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/#website\",\"url\":\"https:\\\/\\\/geopard.tech\\\/\",\"name\":\"GeoPard - Precision agriculture software\",\"description\":\"Precision agriculture Mapping software\",\"publisher\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/#organization\"},\"alternateName\":\"GeoPard\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/geopard.tech\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"et\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/#organization\",\"name\":\"GeoPard Agriculture\",\"alternateName\":\"GeoPard\",\"url\":\"https:\\\/\\\/geopard.tech\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"et\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/geopard_logo_transparentbackground.png?fit=512%2C68&ssl=1\",\"contentUrl\":\"https:\\\/\\\/i0.wp.com\\\/geopard.tech\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/geopard_logo_transparentbackground.png?fit=512%2C68&ssl=1\",\"width\":512,\"height\":68,\"caption\":\"GeoPard Agriculture\"},\"image\":{\"@id\":\"https:\\\/\\\/geopard.tech\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/geopardAgriculture\\\/\",\"https:\\\/\\\/x.com\\\/geopardagri\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/geopard-agriculture\\\/\",\"https:\\\/\\\/www.instagram.com\\\/geopardagriculture\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCiaPGLAhRPNh-s85dXdC-Sw\",\"https:\\\/\\\/www.g2.com\\\/products\\\/geopard-agriculture-precision-farming-software\\\/reviews\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/geopard.tech\\\/#\\\/schema\\\/person\\\/dd217733c742620adc57befbbcd84a8a\",\"name\":\"dementievgeopard\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"et\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g\",\"caption\":\"dementievgeopard\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Odrakasvatus saab hoogu kerge YOLOv5 tuvastamisega - GeoPard Agriculture","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/geopard.tech\/est\/blogi\/odrakasvatus-saab-hoogu-kerge-yolov5-tuvastamisega\/","og_locale":"et_EE","og_type":"article","og_title":"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection - GeoPard Agriculture","og_description":"Highland barley, a resilient cereal crop grown in the high-altitude regions of China\u2019s Qinghai-Tibet Plateau, plays a critical role in local food security and economic...","og_url":"https:\/\/geopard.tech\/est\/blogi\/odrakasvatus-saab-hoogu-kerge-yolov5-tuvastamisega\/","og_site_name":"GeoPard - Precision agriculture Mapping software","article_publisher":"https:\/\/www.facebook.com\/geopardAgriculture\/","article_published_time":"2025-05-04T20:58:53+00:00","article_modified_time":"2025-05-04T21:00:29+00:00","og_image":[{"width":1024,"height":576,"url":"https:\/\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection-1024x576.png","type":"image\/png"}],"author":"dementievgeopard","twitter_card":"summary_large_image","twitter_creator":"@geopardagri","twitter_site":"@geopardagri","twitter_misc":{"Kirjutanud":"dementievgeopard","Eeldatav lugemisaeg":"8 minutit"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#article","isPartOf":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/"},"author":{"name":"dementievgeopard","@id":"https:\/\/geopard.tech\/#\/schema\/person\/dd217733c742620adc57befbbcd84a8a"},"headline":"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection","datePublished":"2025-05-04T20:58:53+00:00","dateModified":"2025-05-04T21:00:29+00:00","mainEntityOfPage":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/"},"wordCount":1570,"commentCount":0,"publisher":{"@id":"https:\/\/geopard.tech\/#organization"},"image":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#primaryimage"},"thumbnailUrl":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1","articleSection":["Precision Farming","Agriculture Mapping","Crop monitoring"],"inLanguage":"et","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/","url":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/","name":"Odrakasvatus saab hoogu kerge YOLOv5 tuvastamisega - GeoPard Agriculture","isPartOf":{"@id":"https:\/\/geopard.tech\/#website"},"primaryImageOfPage":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#primaryimage"},"image":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#primaryimage"},"thumbnailUrl":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1","datePublished":"2025-05-04T20:58:53+00:00","dateModified":"2025-05-04T21:00:29+00:00","breadcrumb":{"@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#breadcrumb"},"inLanguage":"et","potentialAction":[{"@type":"ReadAction","target":["https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/"]}]},{"@type":"ImageObject","inLanguage":"et","@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#primaryimage","url":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1","contentUrl":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1","width":3120,"height":1755,"caption":"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection"},{"@type":"BreadcrumbList","@id":"https:\/\/geopard.tech\/blog\/barley-farming-gets-a-boost-with-lightweight-yolov5-detection\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/geopard.tech\/"},{"@type":"ListItem","position":2,"name":"Barley Farming Gets a Boost With Lightweight YOLOv5 Detection"}]},{"@type":"WebSite","@id":"https:\/\/geopard.tech\/#website","url":"https:\/\/geopard.tech\/","name":"GeoPard - T\u00e4ppismajanduse tarkvara","description":"T\u00e4ppisp\u00f5llumajanduse kaardistamise tarkvara","publisher":{"@id":"https:\/\/geopard.tech\/#organization"},"alternateName":"GeoPard","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/geopard.tech\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"et"},{"@type":"Organization","@id":"https:\/\/geopard.tech\/#organization","name":"GeoPard P\u00f5llumajandus","alternateName":"GeoPard","url":"https:\/\/geopard.tech\/","logo":{"@type":"ImageObject","inLanguage":"et","@id":"https:\/\/geopard.tech\/#\/schema\/logo\/image\/","url":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2026\/07\/geopard_logo_transparentbackground.png?fit=512%2C68&ssl=1","contentUrl":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2026\/07\/geopard_logo_transparentbackground.png?fit=512%2C68&ssl=1","width":512,"height":68,"caption":"GeoPard Agriculture"},"image":{"@id":"https:\/\/geopard.tech\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/geopardAgriculture\/","https:\/\/x.com\/geopardagri","https:\/\/www.linkedin.com\/company\/geopard-agriculture\/","https:\/\/www.instagram.com\/geopardagriculture\/","https:\/\/www.youtube.com\/channel\/UCiaPGLAhRPNh-s85dXdC-Sw","https:\/\/www.g2.com\/products\/geopard-agriculture-precision-farming-software\/reviews"]},{"@type":"Person","@id":"https:\/\/geopard.tech\/#\/schema\/person\/dd217733c742620adc57befbbcd84a8a","name":"dementsusgeopard","image":{"@type":"ImageObject","inLanguage":"et","@id":"https:\/\/secure.gravatar.com\/avatar\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/7c09adac9c20b00454199df5a41ea67c812a6c97e948bf109899836ddde31354?s=96&d=identicon&r=g","caption":"dementievgeopard"}}]}},"jetpack_publicize_connections":[],"jetpack_likes_enabled":true,"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/pdiCPa-30r","jetpack_featured_media_url":"https:\/\/i0.wp.com\/geopard.tech\/wp-content\/uploads\/2025\/05\/Barley-Farming-Gets-a-Boost-With-Lightweight-YOLOv5-Detection.png?fit=3120%2C1755&ssl=1","_links":{"self":[{"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/posts\/11559","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/users\/210157960"}],"replies":[{"embeddable":true,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/comments?post=11559"}],"version-history":[{"count":0,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/posts\/11559\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/media\/11562"}],"wp:attachment":[{"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/media?parent=11559"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/categories?post=11559"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/geopard.tech\/est\/wp-json\/wp\/v2\/tags?post=11559"}],"curies":[{"name":"t\u00f6\u00f6leht","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}