Scientific Programming / 2020 / Article / Tab 5

Research Article

Detecting Citrus in Orchard Environment by Using Improved YOLOv4

Table 5

Identification parameters of four methods for different occlusion degrees.

Occlusion conditionModelCitrus countCorrectly identifiedFalsely identifiedMissed
AmountRate (%)AmountRate (%)AmountRate (%)

Less than 50%Faster-RCNN20016281.24199.713115.44
YOLOv320015678.222311.523818.96
YOLOv420017386.38147.102211.21
Improved YOLOv420018793.58125.98168.15

More than 50%Faster-RCNN20015678.242612.813919.34
YOLOv320014874.223517.524622.96
YOLOv420016683.182010.052613.07
Improved YOLOv420018290.82147.182110.36