This study outlines a new method of automatically estimating weed species and growth stages (from cotyledon until eight leaves are visible) of in situ images covering 18 weed species or families. Images of weeds growing within a variety of crops were gathered across variable environmental conditions with regards to soil types, resolution and light settings. Then, 9649 of these images were used for training the computer, which automatically divided the weeds into nine growth classes. The performance of this proposed convolutional neural network approach was evaluated on a further set of 2516 images, which also varied in term of crop, soil type, image resolution and light conditions. The overall performance of this approach achieved a maximum accuracy of 78% for identifying Polygonum spp. and a minimum accuracy of 46% for blackgrass. In addition, it achieved an average 70% accuracy rate in estimating the number of leaves and 96% accuracy when accepting a deviation of two leaves. These results show that this new method of using deep convolutional neural networks has a relatively high ability to estimate early growth stages across a wide variety of weed species.

In recent years, analyzing Synthetic Aperture Radar (SAR) data has turned into one of the challenging and interesting topics in remote sensing. Radar sensors are capable of imaging Earth’s surface independently of the weather conditions, local time of day, penetrating of waves through clouds, and containing spatial information on agricultural crop types. Based on these characteristics, the main goal sought in this research is to reveal the SAR imaging data capability in recognizing various agricultural crops in the main growth season in a more clarified and detailed way by using a deep-learning-based method. In the present research, the multi-temporal C-band Sentinel 1 images were used to classify 14 major classes of agricultural crops plus background in Denmark. By considering the capability of a deep learning method in analyzing satellite images, a novel, optimal, and lightweight network structure was developed and implemented based on a combination of a fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM) network. The average pixel-based accuracy and Intersection over Union obtained from the proposed network were 86% and 0.64, respectively. Winter rapeseed, winter barley, winter wheat, spring barley, and sugar beet had the highest pixel-based accuracies of 95%, 94%, 93%, 90%, and 90%; respectively. The pixel-based accuracies for eight crop types and the background class were more than 84%. The network prediction showed that in field borders the classification confidence was lower than the center regions of the fields. However, the proposed structure has been able to identify different crops in multi-temporal Sentinel 1 data of a large area of around 254 thousand hectares with high performance.

For decades, significant effort has been put into the development of plant detection and classification algorithms. However, it has been difficult to compare the performance of the different algorithms, due to the lack of a common testbed, such as a public available annotated reference dataset. In this paper, we present the Open Plant Phenotype Database (OPPD), a public dataset for plant detection and plant classification. The dataset contains 7590 RGB images of 47 plant species. Each species is cultivated under three different growth conditions, to provide a high degree of diversity in terms of visual appearance. The images are collected at the semifield area at Aarhus University, Research Centre Flakkebjerg, Denmark, using a customized data acquisition platform that provides well-illuminated images with a ground resolution of ∼6.6 px mm ${}^{-1}$ . All images are annotated with plant species using the EPPO encoding system, bounding box annotations for detection and extraction of individual plants, applied growth conditions and time passed since seeding. Additionally, the individual plants have been tracked temporally and given unique IDs. The dataset is accompanied by two experiments for: (1) plant instance detection and (2) plant species classification. The experiments introduce evaluation metrics and methods for the two tasks and provide baselines for future work on the data.