Farmers require diverse and complex information to make agronomical decisions about crop management including intervention tasks. Generally, this information is gathered by farmers traversing their fields or glasshouses which is often a time consuming and potentially expensive process. In recent years, robotic platforms have gained significant traction due to advances in artificial intelligence. However, these platforms are usually tied to one setting (such as arable farmland), or algorithms are designed for a single platform. This creates a significant gap between available technology and farmer requirements. We propose a novel field agnostic monitoring technique that is able to operate on two different robots, in arable farmland or a glasshouse (horticultural setting). Instance segmentation forms the backbone of this approach from which object location and class, object area, and yield information can be obtained. In arable farmland, our segmentation network is able to estimate crop and weed at a species level and in a glasshouse we are able to estimate the sweet pepper and their ripeness. For yield information, we introduce a novel matching criterion that removes the pixel-wise constraints of previous versions. This approach is able to accurately estimate the number of fruit (sweet pepper) in a glasshouse with a normalized absolute error of 4.7% and an R2 of 0.901 with the visual ground truth. When applied to cluttered arable farmland scenes it improves on the prior approach by 50%. Finally, a qualitative analysis shows the validity of this agnostic monitoring algorithm by supplying decision enabling information to the farmer such as the impact of a low level weeding intervention scheme.

No abstract

No abstract

In agriculture, the majority of vision systems perform still image classification. Yet, recent work has highlighted the potential of spatial and temporal cues as a rich source of information to improve the classification performance. In this paper, we propose novel approaches to explicitly capture both spatial and temporal information to improve the classification of deep convolutional neural networks. We leverage available RGB-D images and robot odometry to perform inter-frame feature map spatial registration. This information is then fused within recurrent deep learnt models, to improve their accuracy and robustness. We demonstrate that this can considerably improve the classification performance with our best performing spatial-temporal model (ST-Atte) achieving absolute performance improvements for intersection-over-union (IoU[%]) of 4.7 for crop-weed segmentation and 2.6 for fruit (sweet pepper) segmentation. Furthermore, we show that these approaches are robust to variable framerates and odometry errors, which are frequently observed in real-world applications.

We present PATHoBot an autonomous crop surveying and intervention robot for glasshouse environments. The aim of this platform is to autonomously gather high quality data and also estimate key phenotypic parameters. To achieve this we retro-fit an off-the-shelf pipe-rail trolley with an array of multi-modal cameras, navigation sensors and a robotic arm for close surveying tasks and intervention. In this paper we describe PATHoBot design choices made to ensure proper operation in a commercial glasshouse environment. As a surveying platform we collect a number of datasets which include both sweet pepper and tomatoes. We show how PATHoBot enables novel surveillance approaches by first improving our previous work on fruit counting by incorporating wheel odometry and depth information. We find that by introducing re-projection and depth information we are able to achieve an absolute improvement of 20 points over the baseline technique in an "in the wild" situation. Finally, we present a 3D mapping case study, further showcasing PATHoBot's crop surveying capabilities.