weedNet: Dense Semantic Weed Classification Using Multispectral Images and MAV for Smart Farming

By Inkyu Sa, Zetao Chen, Marija Popovic, Raghav Khanna, Frank Liebisch, Juan I. Nieto, Roland Yves Siegwart. IEEE Robotics and Automation Letters, 2017

309 citations recorded by the source corpus.

Selective weed treatment is a critical step in autonomous crop management as related to crop health and yield. However, a key challenge is reliable and accurate weed detection to minimize damage to surrounding plants. In this letter, we present an approach for dense semantic weed classification with multispectral images collected by a micro aerial vehicle (MAV). We use the recently developed encoder–decoder cascaded convolutional neural network, SegNet, that infers dense semantic classes while allowing any number of input image channels and class balancing with our sugar beet and weed datasets. To obtain training datasets, we established an experimental field with varying herbicide levels resulting in field plots containing only either crop or weed, enabling us to use the normalized difference vegetation index as a distinguishable feature for automatic ground truth generation. We train six models with different numbers of input channels and condition (fine tune) it to achieve $\sim$0.8 F1-score and 0.78 area under the curve classification metrics. For the model deployment, an embedded Graphics Processing Unit (GPU) system (Jetson TX2) is tested for MAV integration. Dataset used in this letter is released to support the community and future work.

Subfields: Ecology, Plant Science, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/b648d73edd1a533decd22eec2e7722b96746ceae

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Internet of Things (IoT) and Agricultural Unmanned Aerial Vehicles (UAVs) in smart farming: A comprehensive review (2020, background): “The field of sugar beet plants was selected by the researchers in [84,85] to address the problem of selective weed treatment in autonomous crop management.”
A Survey of Deep Learning Techniques for Weed Detection from Images (2021, methodology): “Image pre-processing techniques were also involved in (Sa et al., 2017) for having a bounding box around crop plants or weeds and removed the background.”
Internet-of-Things (IoT)-Based Smart Agriculture: Toward Making the Fields Talk (2019, unknown): “The idea is used in [256], where authors used the multispectral images to classify various weeds.”
From Industry 4.0 to Agriculture 4.0: Current Status, Enabling Technologies, and Research Challenges (2020, background): “However, the dynamic and complex farm environment makes it challenging to precisely classify plants because of the changing appearance, growthstage,weathercondition,objectoverlapping,orevenpar-tialocclusion[67],[68].”