CROP WILTING ANGLE MEASUREMENT USING OPENCV SONIA MARIA D’SOUZA1, S VINAY KUMAR REDDY2, S SAMUEL SUNDAR3, SIDDAMREDDY MOHITH REDDY4, RAVVA SAI CHARAN5

Abstract: Water stress is one of the largest causes of crop yield loss in rainfed farming systems across dryland in rural areas. The early detection of water stress before the visible of discoloration or leaf death occurs, and it allows farmers to respond with targeted irrigation and can prevent yield losses of 30-60%. Current methods for detecting water stress rely on expensive soil moisture sensors, laboratory-based leaf water potential measurements or satellite imagery, all of these are hard to reach the smallholder farmers. This research proposes a solution for measuring the sloping angle of crop leaves and stems directly from a photograph taken with any basic smartphone camera. We use OpenCV based image processing to extract the structure of the plant's main stem or primary leaf, this compute the angle between the erect reference axis and the actual observed axis, and classify the resulting angle into three water stress categories called No stress (0–15 degrees), Mild stress (16–35 degrees) and severe stress (above 35 degrees) using a k-Nearest Neighbours classifier trained on annotated field images. Experiments can be conducted on major crops like (tomato, paddy, maize, sunflower, cotton, chilli etc.) The proposed method requires no specialist equipment, only a smartphone camera and a python script making it the most accessible water stress detection tool which is proposed for Indian smallholder farmers.

Keywords: Wilting Angle, Water Stress, OpenCV, rainfed farming, image processing, leaf water potential.