In this model ,I have detected wheat heads from outdoor images of wheat plants, including wheat datasets from around the globe.Using worldwide data,I have focused on the generalized solution to estimate the number and sizes of wheat heads.To better guage the performance for the unseen genotypes, environments and observational conditions the training dataset covers multiple region.
- Performed careful analysis of wheat heads grown in different varieties, planting densities, patterns, and field conditions to estimate the density and size of wheat heads.
- Researchers can accurately estimate the density and size of the wheat heads in different varieties.
- With improved wheat head detection, farmers can better assess their crops.
- Developed a model using CNN which efficiently creates a bounding box around a wheat head given an image of a wheat field in any geographical conditions
- Tensorflow (An open source deep learning platform)
Python
- Convolutional Neural Network
- YOLO loss
You Only Look Once: Unified, Real-Time Object Detection.