Semi-Supervised Object Detection for Sorghum Panicles in UAV Imagery

Abstract

The sorghum panicle is an important trait related to grain yield and plant development. Detecting and counting sorghum panicles can provide significant information for plant phenotyping. Current deep-learning-based object detection methods for panicles require a large amount of training data. The data labeling is time-consuming and not feasible for real application. In this paper, we present an approach to reduce the amount of training data for sorghum panicle detection via semi-supervised learning. Results show we can achieve similar performance as supervised methods for sorghum panicle detection by only using 10\% of original training data.

Code and data availability

The paper describes a semi-supervised sorghum panicle detection method using UAV imagery, but no public dataset, code, model, or supplement with an authors' URL or deposit is mentioned. The imagery was provided by Purdue's DPRG with no availability statement, and no code release is described.

No evidence-backed public reproduction asset is currently recorded.