Crop Agnostic Monitoring Driven by Deep Learning.

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 R 2 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.

Automating analysis of vegetation with computer vision: Cover estimates and classification.

This study develops an approach to automating the process of vegetation cover estimates using computer vision and pattern recognition algorithms. Visual cover estimation is a key tool for many ecological studies, yet quadrat-based analyses are known to suffer from issues of consistency between people as well as across sites (spatially) and time (temporally). Previous efforts to estimate cover from photograps require considerable manual work. We demonstrate that an automated system can be used to estimate vegetation cover and the type of vegetation cover present using top-down photographs of 1 m by 1 m quadrats. Vegetation cover is estimated by modelling the distribution of color using a multivariate Gaussian. The type of vegetation cover is then classified, using illumination robust local binary pattern features, into two broad groups: graminoids (grasses) and forbs. This system is evaluated on two datasets from the globally distributed experiment, the Nutrient Network (NutNet). These NutNet sites were selected for analyses because repeat photographs were taken over time and these sites are representative of very different grassland ecosystems-a low stature subalpine grassland in an alpine region of Australia and a higher stature and more productive lowland grassland in the Pacific Northwest of the USA. We find that estimates of treatment effects on grass and forb cover did not differ between field and automated estimates for eight of nine experimental treatments. Conclusions about total vegetation cover did not correspond quite as strongly, particularly at the more productive site. A limitation with this automated system is that the total vegetation cover is given as a percentage of pixels considered to contain vegetation, but ecologists can distinguish species with overlapping coverage and thus can estimate total coverage to exceed 100%. Automated approaches such as this offer techniques for estimating vegetation cover that are repeatable, cheaper to use, and likely more reliable for quantifying changes in vegetation over the long-term. These approaches would also enable ecologists to increase the spatial and temporal depth of their coverage estimates with methods that allow for vegetation sampling over large spatial scales quickly.

DeepFruits: A Fruit Detection System Using Deep Neural Networks.

This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0 . 807 to 0 . 838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.

A scalable formulation of probabilistic linear discriminant analysis: applied to face recognition.

In this paper, we present a scalable and exact solution for probabilistic linear discriminant analysis (PLDA). PLDA is a probabilistic model that has been shown to provide state-of-the-art performance for both face and speaker recognition. However, it has one major drawback: At training time estimating the latent variables requires the inversion and storage of a matrix whose size grows quadratically with the number of samples for the identity (class). To date, two approaches have been taken to deal with this problem, to 1) use an exact solution that calculates this large matrix and is obviously not scalable with the number of samples or 2) derive a variational approximation to the problem. We present a scalable derivation which is theoretically equivalent to the previous nonscalable solution and thus obviates the need for a variational approximation. Experimentally, we demonstrate the efficacy of our approach in two ways. First, on labeled faces in the wild, we illustrate the equivalence of our scalable implementation with previously published work. Second, on the large Multi-PIE database, we illustrate the gain in performance when using more training samples per identity (class), which is made possible by the proposed scalable formulation of PLDA.