A survey of deep learning techniques for weed detection from images

Learning from a few samples to automatically recognize the plant leaf diseases is an attractive and promising study to protect the agricultural yield and quality. The existing few-shot classification studies in agriculture are mainly based on supervised learning schemes, ignoring unlabeled data's helpful information. In this paper, we proposed a semi-supervised few-shot learning approach to solve the plant leaf diseases recognition. Specifically, the public PlantVillage dataset is used and split into the source domain and target domain. Extensive comparison experiments considering the domain split and few-shot parameters (N-way, k-shot) were carried out to validate the correctness and generalization of proposed semi-supervised few-shot methods. In terms of selecting pseudo-labeled samples in the semi-supervised process, we adopted the confidence interval to determine the number of unlabeled samples for pseudo-labelling adaptively. The average improvement by the single semi-supervised method is 2.8%, and that by the iterative semi-supervised method is 4.6%. The proposed methods can outperform other related works with fewer labeled training data.

/pdf/semi-supervised-few-shot-learning-approach-for-plant-32o95uxq4d.pdf

Semi-supervised few-shot learning approach for plant diseases recognition.

With the rapid development of genetic analysis techniques and crop population size, phenotyping has become the bottleneck restricting crop breeding. Breaking through this bottleneck will require phenomics, defined as the accurate, high-throughput acquisition and analysis of multi-dimensional phenotypes during crop growth at organism-wide levels, ranging from cells to organs, individual plants, plots, and fields. Here we offer an overview of crop phenomics research from technological and platform viewpoints at various scales, including microscopic, ground-based, and aerial phenotyping and phenotypic data analysis. We describe recent applications of high-throughput phenotyping platforms for abiotic/biotic stress and yield assessment. Finally, we discuss current challenges and offer perspectives on future phenomics research.

High-throughput phenotyping: Breaking through the bottleneck in future crop breeding

Performance of deep learning models for classifying and detecting common weeds in corn and soybean production systems

Accelerating hybrid rice development

Identification and characterization of new traits with sound physiological foundation is essential for crop breeding and production management. Deep learning has been widely used in image data analysis to explore spatial and temporal information on crop growth and development, thus strengthening the power of identification of physiological traits. Taking the advantage of deep learning, this study aims to develop a novel trait of canopy structure that integrate source and sink in japonica rice. We applied a deep learning approach to accurately segment leaf and panicle, and subsequently developed the procedure of GvCrop to calculate the leaf to panicle ratio (LPR) of rice canopy during grain filling stage. Images of training dataset were captured in the field experiments, with large variations in camera shooting angle, the elevation and the azimuth angles of the sun, rice genotype, and plant phenological stages. Accurately labeled by manually annotating the panicle and leaf regions, the resulting dataset were used to train FPN-Mask (Feature Pyramid Network Mask) models, consisting of a backbone network and a task-specific sub-network. The model with the highest accuracy was then selected to check the variations in LPR among 192 rice germplasms and among agronomical practices. Despite the challenging field conditions, FPN-Mask models achieved a high detection accuracy, with Pixel Accuracy being 0.99 for panicles and 0.98 for leaves. The calculated LPR displayed large spatial and temporal variations as well as genotypic differences. In addition, it was responsive to agronomical practices such as nitrogen fertilization and spraying of plant growth regulators. Deep learning technique can achieve high accuracy in simultaneous detection of panicle and leaf data from complex rice field images. The proposed FPN-Mask model is applicable to detect and quantify crop performance under field conditions. The newly identified trait of LPR should provide a high throughput protocol for breeders to select superior rice cultivars as well as for agronomists to precisely manage field crops that have a good balance of source and sink.

/pdf/leaf-to-panicle-ratio-lpr-a-new-physiological-trait-5gkuwjrg35.pdf

Yangfeng Ding

Papers

Leaf to panicle ratio (LPR): a new physiological trait indicative of source and sink relation in japonica rice based on deep learning