Video-Based Prediction for Header-Height Control of a Combine Harvester

Many automation applications in the agriculture industry focus on navigation or steering control. But there are few studies on functional controls such as header automation. This paper introduces a video-based prediction system for header-height control of a combine harvester. To achieve this goal, we propose a lighting-invariant spatial segmentation method to locate the field region. Crop presence detection is performed by training a classifier on texture features and the percentage of crops in the field can be estimated. Then the time to lift the header is predicted based on observing the trend of crop presence. The framework is tested on both bean and wheat harvesting video sequences and the decreasing crop percentage can be successfully estimated.