GrowliFlower: An image time‐series dataset for GROWth analysis of cauLIFLOWER

Abstract

In this paper, we present GrowliFlower, a georeferenced, image-based unmanned aerial vehicle time-series dataset of two monitored cauliflower fields (0.39 and 0.60 ha) acquired in 2 years, 2020 and 2021. The proposed dataset contains RGB and multispectral orthophotos with coordinates of approximately 14,000 individual cauliflower plants. The coordinates enable the extraction of complete and incomplete time-series of image patches showing individual plants. The dataset contains the collected phenotypic traits of 740 plants, including the developmental stage and plant and cauliflower size. The harvestable product is completely covered by leaves, thus, plant IDs and coordinates are provided to extract image pairs of plants pre-and postdefoliation. In addition, to facilitate classification, detection, segmentation, instance segmentation, and other similar computer vision tasks, the proposed dataset contains pixel-accurate leaf and plant instance segmentations, as well as stem annotations. The proposed dataset was created to facilitate the development and evaluation of various machine-learning approaches. It focuses on the analysis of growth and development of cauliflower and the derivation of phenotypic traits to advance automation in agriculture.Two baseline results of instance segmentation tasks at the plant and leaf level based on labeled instance segmentation data are presented. The complete GrowliFlower dataset is publicly available (http://rs.ipb.uni-bonn.de/data/growliflower/).

MAgro dataset: A dataset for simultaneous localization and mapping in agricultural environments

“…On the other hand, there are several agricultural datasets unrelated to the task of odometry, mapping or navigation, such as pest detection (Wang et al, 2021), insect pest recognition (Wang et al, 2021), harvest estimation (Altaheri et al, 2019; Häni et al, 2020), or fruit and plant detection (Kierdorf et al, 2023; Perez-Borrero et al, 2020), among others. Lu and Young (2020) present a survey of public datasets for computer vision tasks in precision agriculture.…”

“…There are also works that, although not originally made for SLAM, are related to visual navigation, such as de Silva et al ( 2021), which creates a dataset of marked rows in a sugar beet field, Aghi et al (2021), which creates a semantically segmented dataset of vineyard rows, and Smitt et al (2021) which present an automated platform for surveying sweet pepper and tomato crops using a pipe-rail trolley with an array of RGB-D cameras and a tracking camera inside a greenhouse. On the other hand, there are several agricultural datasets unrelated to the task of odometry, mapping or navigation, such as pest detection (Wang et al, 2021), insect pest recognition (Wang et al, 2021), harvest estimation (Altaheri et al, 2019;Häni et al, 2020), or fruit and plant detection (Kierdorf et al, 2023;Perez-Borrero et al, 2020), among others. Lu and Young (2020) present a survey of public datasets for computer vision tasks in precision agriculture.…”

Leveraging I4.0 smart methodologies for developing solutions for harvesting produce

“…Monitoring individual crop characteristics throughout growth can support the subsequent planning of actions performed by autonomous robotic solutions (Kierdorf et al, 2023), including establishing harvest priorities. Real-time machine learning classification and growth prediction models are methods that provide robotic solutions with knowledge regarding the current and future state of a crop.…”

“…Several studies have utilized IoT devices to create time-series datasets that can be used as input to growth prediction models. For example, Kierdorf et al (2023) created a time series UAV-based image dataset of cauliflower growth characteristics including developmental stage and size. Weyler et al (2021) collected images of beet plants throughout a cultivation period via ground robot and monitored phenotypic traits for growth stage classification.…”

Drone-Based Harvest Data Prediction Can Reduce On-Farm Food Loss and Improve Farmer Income

“…To fulfill the more complex outdoor tasks, a large amount of training data need to be manually labeled. Although there is a public training dataset for cauliflower available [ 40 ], it cannot be used directly on the broccoli head or another crop. Besides, labeling 14,000 individual plants manually as in that dataset is not feasible for building a new dataset for different crop or farmland applications.…”