Weed Density and Distribution Estimation for Precision Agriculture Using Semi-Supervised Learning

Abstract

Uncontrolled growth of weeds can severely affect the crop yield and quality. Unrestricted use of herbicide for weed removal alters biodiversity and cause environmental pollution. Instead, identifying weed-infested regions can aid selective chemical treatment of these regions. Advances in analyzing farm images have resulted in solutions to identify weed plants. However, a majority of these approaches are based on supervised learning methods which requires huge amount of manually annotated images. As a result, these supervised approaches are economically infeasible for the individual farmer because of the wide variety of plant species being cultivated. In this paper, we propose a deep learning-based semi-supervised approach for robust estimation of weed density and distribution across farmlands using only limited color images acquired from autonomous robots. This weed density and distribution can be useful in a site-specific weed management system for selective treatment of infected areas using autonomous robots. In this work, the foreground vegetation pixels containing crops and weeds are first identified using a Convolutional Neural Network (CNN) based unsupervised segmentation. Subsequently, the weed infected regions are identified using a fine-tuned CNN, eliminating the need for designing hand-crafted features. The approach is validated on two datasets of different crop/weed species (1) Crop Weed Field Image Dataset (CWFID), which consists of carrot plant images and the (2) Sugar Beets dataset. The proposed method is able to localize weed-infested regions a maximum recall of 0.99 and estimate weed density with a maximum accuracy of 82.13%. Hence, the proposed approach is shown to generalize to different plant species without the need for extensive labeled data.

Review of Current Robotic Approaches for Precision Weed Management

“…A selfsupervised method was proposed in [100] to automatically generate training data using a row detection and extraction method. Shorewala et al [101] classified pixels on unlabelled images that are similar to each other, according to a show that even when the data used for retraining is imperfectly annotated, the classification performance is within 2% of that of networks trained with laboriously annotated pixel-precision data.…”

Self-Supervised Overlapped Multiple Weed and Crop Species Leaf Segmentation under Complex Light Condition

“…After that, each tile's transformation function is calculated. The pixels in the tile center are a good fit for the transformation functions [25]. All other pixels are given interpolated values and up to four transformation functions based on the center pixels of the tiles that are closest to them.…”

A Deep Learning-Based Novel Approach for Weed Growth Estimation

“…The implementation of CNN-based unsupervised segmentation on weed density distribution is performed using two datasets, the first is weed field image dataset (CWFID) and the second is sugar beet dataset. This work also uses a site-specific weed management system for weed density distribution with penetrates area of your weed leaf where recall value is 99% and accuracy is 82.13% [12]. This work has covered two effective powerful CNN architectures that are Inception V4 and Efficient Net B7 for plant growth estimation across different weed plants in rabi crop.…”