Active learning with point supervision for cost-effective panicle detection in cereal crops

Abstract

Background: Panicle density of cereal crops such as wheat and sorghum is one of the main components for plant breeders and agronomists in understanding the yield of their crops. To phenotype the panicle density effectively, researchers agree there is a significant need for computer vision-based object detection techniques. Especially in recent times, research in deep learning-based object detection shows promising results in various agricultural studies. However, training such systems usually requires a lot of bounding-box labeled data. Since crops vary by both environmental and genetic conditions, acquisition of huge amount of labeled image datasets for each crop is expensive and time-consuming. Thus, to catalyze the widespread usage of automatic object detection for crop phenotyping, a cost-effective method to develop such automated systems is essential.Results: We propose a weak supervision based active learning approach for panicle detection in cereal crops. In our approach, the model constantly interacts with a human annotator by iteratively querying the labels for only the most informative images, as opposed to all images in a dataset. Our query method is specifically designed for cereal crops which usually tend to have panicles with low variance in appearance. Our method reduces labeling costs by intelligently leveraging low-cost weak labels (object centers) for picking the most informative images for which strong labels (bounding boxes) are required. We show promising results on two publicly available cereal crop datasets -Sorghum and Wheat. On Sorghum, 6 variants of our proposed method outperform the best baseline method with more than 55% savings in labeling time. Similarly, on Wheat, 3 variants of our proposed methods outperform the best baseline method with more than 50% of savings in labeling time. Conclusion:We proposed a cost effective method to train reliable panicle detectors for cereal crops. A low cost panicle detection method for cereal crops is highly beneficial to both breeders and agronomists. Plant breeders can obtain quick crop yield estimates to make important crop management decisions. Similarly, obtaining real time visual crop analysis is valuable for researchers to analyze the crop's response to various experimental conditions.

Sorghum Panicle Detection and Counting Using Unmanned Aerial System Images and Deep Learning

“…Previous studies have also shown such challenges in machine learning and deep learning algorithms to directly process high-resolution images. It is common to crop or split the original large dimension images to smaller images for detecting and counting objects ( Aich et al., 2018 ; Wu et al., 2019 ; Chandra et al., 2020 ). This potentially leads to overestimation.…”

Field‐based individual plant phenotyping of herbaceous species by unmanned aerial vehicle

“…Therefore, researchers proposed several methods to distinguish weeds from the plant. For example, the use of a specific camera that can provide more spectral information; the use of complex algorithms such as machine learning with the manual selection of features and models, deep learning with the manual labeled training data (Chandra et al., 2020; Guo et al., 2018; Pérez‐Ortiz et al., 2015; Sa et al., 2017, 2018; Yu et al., 2019). Here, relying on the height of H. tuberosus , we propose the simple WEIPS method to segment plants from weeds.…”

Intact Detection of Highly Occluded Immature Tomatoes on Plants Using Deep Learning Techniques

“…This causes errors in tomato training and detection. Several efficient labelling methods have been developed [33][34][35]. Use of these methods not only saves time spent labelling but also uses less labour, making it possible to standardize the method of box placement.…”