|
- 2017
TasselNet: counting maize tassels in the wild via local counts regression networkDOI: 10.1186/s13007-017-0224-0 Keywords: Maize tassels, Object counting, Computer vision, Deep learning, Convolutional neural networks Abstract: Intrinsic and extrinsic variations in the maize field. These variations pose significant challenges for in-field counting of maize tassels. a Shape and size vary significantly as plants grow over time. b Appearance variations due to different cultivars. c Illumination variations due to different weather conditions. d Pose variations due to wind, imaging and perspective distortions. e Occlusions between leaves and tassels or different tassels. f Cluttered background caused by wires, poles and weeds. g Image degradation due to dust or rain drops on the camera lens. h Texture variations due to different flowering statu
|