Final report on research project PS2010, proof of concept of automated mapping of weeds in arable fields

Many weeds occur in patches but farmers frequently spray whole fields to control the weeds in these patches. Given a geo-referenced weed map, technology exists to confine spraying to these patches. Adoption of patch spraying by arable farmers has, however, been negligible partly due to the difficulty of constructing weed maps. Building on previous DEFRA and HGCA projects, this proposal aims to develop and evaluate a machine vision system to automate the weed mapping process. The project thereby addresses the principal technical stumbling block to widespread adoption of site specific weed management (SSWM). The accuracy of weed identification by machine vision based on a single field survey may be inadequate to create herbicide application maps. We therefore propose to test the hypothesis that sufficiently accurate weed maps can be constructed by integrating information from geo-referenced images captured automatically at different times of the year during normal field activities. Accuracy of identification will also be increased by utilising a priori knowledge of weeds present in fields. To prove this concept, images will be captured from arable fields on two farms and processed offline to identify and map the weeds, focussing especially on black-grass, wild oats, barren brome, couch grass and cleavers. As advocated by Lutman et al. (2002), the approach uncouples the weed mapping and treatment processes and builds on the observation that patches of these weeds are quite stable in arable fields. There are three main aspects to the project. 1) Machine vision hardware. Hardware component parts of the system are one or more cameras connected to a single board computer (Concurrent Solutions LLC) and interfaced with an accurate Global Positioning System (GPS) supplied by Patchwork Technology. The camera(s) will take separate measurements for each of the three primary colours of visible light (red, green and blue) in each pixel. The basic proof of concept can be achieved in principle using a single camera system, but in practice systems with more than one camera may need to be installed so that larger fractions of each field can be photographed. Hardware will be reviewed regularly during the project in response to feedback from other work packages and updated as required. 2) Image capture and weed identification software. The machine vision system will be attached to toolbars of farm machinery so that images can be collected during different field operations. Images will be captured at different ground speeds, in different directions and at different crop growth stages as well as in different crop backgrounds. Having captured geo-referenced images in the field, image analysis software will be developed to identify weed species by Murray State and Reading Universities with advice from The Arable Group. A wide range of pattern recognition and in particular Bayesian Networks will be used to advance the state of the art in machine vision-based weed identification and mapping. Weed identification algorithms used by others are inadequate for this project as we intend to collect and correlate images collected at different growth stages. Plants grown for this purpose by Herbiseed will be used in the first instance. In addition, our image capture and analysis system will include plant characteristics such as leaf shape, size, vein structure, colour and textural pattern, some of which are not detectable by other machine vision systems or are omitted by their algorithms. Using such a list of features observable using our machine vision system, we will determine those that can be used to distinguish weed species of interest. 3) Weed mapping. Geo-referenced maps of weeds in arable fields (Reading University and Syngenta) will be produced with advice from The Arable Group and Patchwork Technology. Natural infestations will be mapped in the fields but we will also introduce specimen plants in pots to facilitate more rigorous system evaluation and testing. Manual weed maps of the same fields will be generated by Reading University, Syngenta and Peter Lutman so that the accuracy of automated mapping can be assessed. The principal hypothesis and concept to be tested is that by combining maps from several surveys, a weed map with acceptable accuracy for endusers can be produced. If the concept is proved and can be commercialised, systems could be retrofitted at low cost onto existing farm machinery. The outputs of the weed mapping software would then link with the precision farming options already built into many commercial sprayers, allowing their use for targeted, site-specific herbicide applications. Immediate economic benefits would, therefore, arise directly from reducing herbicide costs. SSWM will also reduce the overall pesticide load on the crop and so may reduce pesticide residues in food and drinking water, and reduce adverse impacts of pesticides on non-target species and beneficials. Farmers may even choose to leave unsprayed some non-injurious, environmentally-beneficial, low density weed infestations. These benefits fit very well with the anticipated legislation emerging in the new EU Thematic Strategy for Pesticides which will encourage more targeted use of pesticides and greater uptake of Integrated Crop (Pest) Management approaches, and also with the requirements of the Water Framework Directive to reduce levels of pesticides in water bodies. The greater precision of weed management offered by SSWM is therefore a key element in preparing arable farming systems for the future, where policy makers and consumers want to minimise pesticide use and the carbon footprint of farming while maintaining food production and security. The mapping technology could also be used on organic farms to identify areas of fields needing mechanical weed control thereby reducing both carbon footprints and also damage to crops by, for example, spring tines. Objective i. To develop a prototype machine vision system for automated image capture during agricultural field operations; ii. To prove the concept that images captured by the machine vision system over a series of field operations can be processed to identify and geo-reference specific weeds in the field; iii. To generate weed maps from the geo-referenced, weed plants/patches identified in objective (ii).

Resource allocation analysis of the stochastic diffusion search

The Stochastic Diffusion Search (SDS) was developed as a solution to the best-fit search problem. Thus, as a special case it is capable of solving the transform invariant pattern recognition problem. SDS is efficient and, although inherently probabilistic, produces very reliable solutions in widely ranging search conditions. However, to date a systematic formal investigation of its properties has not been carried out. This thesis addresses this problem. The thesis reports results pertaining to the global convergence of SDS as well as characterising its time complexity. However, the main emphasis of the work, reports on the resource allocation aspect of the Stochastic Diffusion Search operations. The thesis introduces a novel model of the algorithm, generalising an Ehrenfest Urn Model from statistical physics. This approach makes it possible to obtain a thorough characterisation of the response of the algorithm in terms of the parameters describing the search conditions in case of a unique best-fit pattern in the search space. This model is further generalised in order to account for different search conditions: two solutions in the search space and search for a unique solution in a noisy search space. Also an approximate solution in the case of two alternative solutions is proposed and compared with predictions of the extended Ehrenfest Urn model. The analysis performed enabled a quantitative characterisation of the Stochastic Diffusion Search in terms of exploration and exploitation of the search space. It appeared that SDS is biased towards the latter mode of operation. This novel perspective on the Stochastic Diffusion Search lead to an investigation of extensions of the standard SDS, which would strike a different balance between these two modes of search space processing. Thus, two novel algorithms were derived from the standard Stochastic Diffusion Search, ‘context-free’ and ‘context-sensitive’ SDS, and their properties were analysed with respect to resource allocation. It appeared that they shared some of the desired features of their predecessor but also possessed some properties not present in the classic SDS. The theory developed in the thesis was illustrated throughout with carefully chosen simulations of a best-fit search for a string pattern, a simple but representative domain, enabling careful control of search conditions.

Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

Auto-associative memory using n-tuple techniques

The use of n-tuple or weightless neural networks as pattern recognition devices has been well documented. They have a significant advantages over more common networks paradigms, such as the multilayer perceptron in that they can be easily implemented in digital hardware using standard random access memories. To date, n-tuple networks have predominantly been used as fast pattern classification devices. The paper describes how n-tuple techniques can be used in the hardware implementation of a general auto-associative network.

On-line handwritten segmentation in linear drawings

This paper addresses the problem of tracking line segments corresponding to on-line handwritten obtained through a digitizer tablet. The approach is based on Kalman filtering to model linear portions of on-line handwritten, particularly, handwritten numerals, and to detect abrupt changes in handwritten direction underlying a model change. This approach uses a Kalman filter framework constrained by a normalized line equation, where quadratic terms are linearized through a first-order Taylor expansion. The modeling is then carried out under the assumption that the state is deterministic and time-invariant, while the detection relies on double thresholding mechanism which tests for a violation of this assumption. The first threshold is based on an approach of layout kinetics. The second one takes into account the jump in angle between the past observed direction of layout and its current direction. The method proposed enables real-time processing. To illustrate the methodology proposed, some results obtained from handwritten numerals are presented.

Application of a hybrid tracking algorithm to motion analysis

An algorithm for tracking multiple feature positions in a dynamic image sequence is presented. This is achieved using a combination of two trajectory-based methods, with the resulting hybrid algorithm exhibiting the advantages of both. An optimizing exchange algorithm is described which enables short feature paths to be tracked without prior knowledge of the motion being studied. The resulting partial trajectories are then used to initialize a fast predictor algorithm which is capable of rapidly tracking multiple feature paths. As this predictor algorithm becomes tuned to the feature positions being tracked, it is shown how the location of occluded or poorly detected features can be predicted. The results of applying this tracking algorithm to data obtained from real-world scenes are then presented.

Brain computer interface control via functional connectivity dynamics

The dynamics of inter-regional communication within the brain during cognitive processing – referred to as functional connectivity – are investigated as a control feature for a brain computer interface. EMDPL is used to map phase synchronization levels between all channel pair combinations in the EEG. This results in complex networks of channel connectivity at all time–frequency locations. The mean clustering coefficient is then used as a descriptive feature encapsulating information about inter-channel connectivity. Hidden Markov models are applied to characterize and classify dynamics of the resulting complex networks. Highly accurate levels of classification are achieved when this technique is applied to classify EEG recorded during real and imagined single finger taps. These results are compared to traditional features used in the classification of a finger tap BCI demonstrating that functional connectivity dynamics provide additional information and improved BCI control accuracies.

Time complexity analysis of the stochastic diffusion search

The Stochastic Diffusion Search algorithm -an integral part of Stochastic Search Networks is investigated. Stochastic Diffusion Search is an alternative solution for invariant pattern recognition and focus of attention. It has been shown that the algorithm can be modelled as an ergodic, finite state Markov Chain under some non-restrictive assumptions. Sub-linear time complexity for some settings of parameters has been formulated and proved. Some properties of the algorithm are then characterised and numerical examples illustrating some features of the algorithm are presented.

A statistical approach to the problem of restoring damaged and contaminated images

We address the problem of automatically identifying and restoring damaged and contaminated images. We suggest a novel approach based on a semi-parametric model. This has two components, a parametric component describing known physical characteristics and a more flexible non-parametric component. The latter avoids the need for a detailed model for the sensor, which is often costly to produce and lacking in robustness. We assess our approach using an analysis of electroencephalographic images contaminated by eye-blink artefacts and highly damaged photographs contaminated by non-uniform lighting. These experiments show that our approach provides an effective solution to problems of this type.

PMCRI: a parallel modular classification rule induction framework

In a world where massive amounts of data are recorded on a large scale we need data mining technologies to gain knowledge from the data in a reasonable time. The Top Down Induction of Decision Trees (TDIDT) algorithm is a very widely used technology to predict the classification of newly recorded data. However alternative technologies have been derived that often produce better rules but do not scale well on large datasets. Such an alternative to TDIDT is the PrismTCS algorithm. PrismTCS performs particularly well on noisy data but does not scale well on large datasets. In this paper we introduce Prism and investigate its scaling behaviour. We describe how we improved the scalability of the serial version of Prism and investigate its limitations. We then describe our work to overcome these limitations by developing a framework to parallelise algorithms of the Prism family and similar algorithms. We also present the scale up results of a first prototype implementation.

An overview of the use of neural networks for data mining tasks

In the recent years, the area of data mining has been experiencing considerable demand for technologies that extract knowledge from large and complex data sources. There has been substantial commercial interest as well as active research in the area that aim to develop new and improved approaches for extracting information, relationships, and patterns from large datasets. Artificial neural networks (NNs) are popular biologically-inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas, including science, engineering, medicine, business, banking, telecommunication, and many other fields. This paper highlights from a data mining perspective the implementation of NN, using supervised and unsupervised learning, for pattern recognition, classification, prediction, and cluster analysis, and focuses the discussion on their usage in bioinformatics and financial data analysis tasks. © 2012 Wiley Periodicals, Inc.

In vitro fermentation of potential prebiotic flours from natural sources: impact on the human colonic microbiota and metabolome

Scope: Fibers and prebiotics represent a useful dietary approach for modulating the human gut microbiome. Therefore, aim of the present study was to investigate the impact of four flours (wholegrain rye, wholegrain wheat, chickpeas and lentils 50:50, and barley milled grains), characterized by a naturally high content in dietary fibers, on the intestinal microbiota composition and metabolomic output. Methods and results: A validated three-stage continuous fermentative system simulating the human colon was used to resemble the complexity and diversity of the intestinal microbiota. Fluorescence in situ hybridization was used to evaluate the impact of the flours on the composition of the microbiota, while small-molecule metabolome was assessed by NMR analysis followed by multivariate pattern recognition techniques. HT29 cell-growth curve assay was used to evaluate the modulatory properties of the bacterial metabolites on the growth of intestinal epithelial cells. All the four flours showed positive modulations of the microbiota composition and metabolic activity. Furthermore, none of the flours influenced the growth-modulatory potential of the metabolites toward HT29 cells. Conclusion: Our findings support the utilization of the tested ingredients in the development of a variety of potentially prebiotic food products aimed at improving gastrointestinal health.

Robust abandoned object detection integrating wide area visual surveillance and social context

This paper presents a video surveillance framework that robustly and efficiently detects abandoned objects in surveillance scenes. The framework is based on a novel threat assessment algorithm which combines the concept of ownership with automatic understanding of social relations in order to infer abandonment of objects. Implementation is achieved through development of a logic-based inference engine based on Prolog. Threat detection performance is conducted by testing against a range of datasets describing realistic situations and demonstrates a reduction in the number of false alarms generated. The proposed system represents the approach employed in the EU SUBITO project (Surveillance of Unattended Baggage and the Identification and Tracking of the Owner).

A survey of human motion analysis using depth imagery

Analysis of human behaviour through visual information has been a highly active research topic in the computer vision community. This was previously achieved via images from a conventional camera, but recently depth sensors have made a new type of data available. This survey starts by explaining the advantages of depth imagery, then describes the new sensors that are available to obtain it. In particular, the Microsoft Kinect has made high-resolution real-time depth cheaply available. The main published research on the use of depth imagery for analysing human activity is reviewed. Much of the existing work focuses on body part detection and pose estimation. A growing research area addresses the recognition of human actions. The publicly available datasets that include depth imagery are listed, as are the software libraries that can acquire it from a sensor. This survey concludes by summarising the current state of work on this topic, and pointing out promising future research directions.

Performance evaluation of crowd image analysis using the PETS2009 dataset

This paper presents the PETS2009 outdoor crowd image analysis surveillance dataset and the performance evaluation of people counting, detection and tracking results using the dataset submitted to five IEEE Performance Evaluation of Tracking and Surveillance (PETS) workshops. The evaluation was carried out using well established metrics developed in the Video Analysis and Content Extraction (VACE) programme and the CLassification of Events, Activities, and Relationships (CLEAR) consortium. The comparative evaluation highlights the detection and tracking performance of the authors’ systems in areas such as precision, accuracy and robustness and provides a brief analysis of the metrics themselves to provide further insights into the performance of the authors’ systems.