✳flâneur — a map of the web's best reading

Frontiers | Leaf Counting: Fusing Network Components for Improved Accuracy

frontiersin.org · 1,104 words · saved by 1 readers

Leaf counting in potted plants is an important building block for estimating their health status and growth rate and has obtained increasing attention from the visual phenotyping community in recent years. Two novel deep learning approaches for visual leaf counting tasks are proposed, evaluated, and compared in this study. The first method performs counting via direct regression but using multiple image representation resolutions to attend leaves of multiple scales. The leaf count from multiple resolutions is fused using a novel technique to get the final count. The second method is detection with a regression model that counts the leaves after locating leaf center points and aggregating them. The algorithms are evaluated on the Leaf Counting Challenge (LCC) dataset of the Computer Vision Problems in Plant Phenotyping (CVPPP) conference 2017, and a new larger dataset of banana leaves. Experimental results show that both methods outperform previous CVPPP LCC challenge winners, based on

;import{g as i,s as o,r as s,e as a,a as u,h as l,b as c,i as h,t as f,c as d,d as p,f as m,j as g,k as y,l as b,K as v,_ as w,S as E,m as _,o as C,w as M,n as S,p as O,q as B,u as D,v as I,x as T,y as x,z as R,A as N,G as k,J as F,B as L,C as P,X as U,D as j,E as q,F as z,H as $,I as V,L as H,M as W,N as G,O as K,P as Z,Q as Y,R as J,T as X,U as Q,V as AA,W as eA,Y as tA,Z as rA,$ as nA,a0 as iA,a1 as oA,a2 as sA,a3 as aA,a4 as uA,a5 as lA,a6 as cA,a7 as hA,a8 as fA,a9 as dA,aa as pA,ab as mA,ac as gA,ad as yA,ae as bA,af as vA,ag as wA,ah as EA,ai as _A,aj as CA,ak as MA,al as SA,am as OA}fr

Explore this link on the map →

saved by

related reading