Deep Learning for Precision Agriculture: Post-Spraying Evaluation and Deposition Estimation

Precision spraying evaluation requires automation primarily in post-spraying imagery. In this paper we propose an eXplainable Artificial Intelligence (XAI) computer vision pipeline to evaluate a precision spraying system post-spraying without the need for traditional agricultural methods. The developed system can semantically segment potential targets such as lettuce, chickweed, and meadowgrass and correctly identify if targets have been sprayed. Furthermore, this pipeline evaluates using a domain-specific Weakly Supervised Deposition Estimation task, allowing for class-specific quantification of spray deposit weights in {\mu}L. Estimation of coverage rates of spray deposition in a class-wise manner allows for further understanding of effectiveness of precision spraying systems. Our study evaluates different Class Activation Mapping techniques, namely AblationCAM and ScoreCAM, to determine which is more effective and interpretable for these tasks. In the pipeline, inference-only feature fusion is used to allow for further interpretability and to enable the automation of precision spraying evaluation post-spray. Our findings indicate that a Fully Convolutional Network with an EfficientNet-B0 backbone and inference-only feature fusion achieves an average absolute difference in deposition values of 156.8 {\mu}L across three classes in our test set. The dataset curated in this paper is publicly available at https://github.com/Harry-Rogers/PSIE

Optimising robotic operation speed with edge computing over 5G networks: Insights from selective harvesting robots

Selective harvesting by autonomous robots will be a critical enabling technology for future farming. Increases in inflation and shortages of skilled labour are driving factors that can help encourage user acceptability of robotic harvesting. For example, robotic strawberry harvesting requires real-time high-precision fruit localisation, 3D mapping and path planning for 3-D cluster manipulation. Whilst industry and academia have developed multiple strawberry harvesting robots, none have yet achieved human-cost parity. Achieving this goal requires increased picking speed (perception, control and movement), accuracy and the development of low-cost robotic system designs. We propose the edge-server over 5G for Selective Harvesting (E5SH) system, which is an integration of high bandwidth and low latency Fifth Generation (5G) mobile network into a crop harvesting robotic platform, which we view as an enabler for future robotic harvesting systems. We also consider processing scale and speed in conjunction with system environmental and energy costs. A system architecture is presented and evaluated with support from quantitative results from a series of experiments that compare the performance of the system in response to different architecture choices, including image segmentation models, network infrastructure (5G vs WiFi) and messaging protocols such as Message Queuing Telemetry Transport (MQTT) and Transport Control Protocol Robot Operating System (TCPROS). Our results demonstrate that the E5SH system delivers step-change peak processing performance speedup of above 18-fold than a stand-alone embedded computing Nvidia Jetson Xavier NX (NJXN) system.

Dual-band feature selection for maturity classification of specialty crops by hyperspectral imaging

The maturity classification of specialty crops such as strawberries and tomatoes is an essential agricultural downstream activity for selective harvesting and quality control (QC) at production and packaging sites. Recent advancements in Deep Learning (DL) have produced encouraging results in color images for maturity classification applications. However, hyperspectral imaging (HSI) outperforms methods based on color vision. Multivariate analysis methods and Convolutional Neural Networks (CNN) deliver promising results; however, a large amount of input data and the associated preprocessing requirements cause hindrances in practical application. Conventionally, the reflectance intensity in a given electromagnetic spectrum is employed in estimating fruit maturity. We present a feature extraction method to empirically demonstrate that the peak reflectance in subbands such as 500-670 nm (pigment band) and the wavelength of the peak position, and contrarily, the trough reflectance and its corresponding wavelength within 671-790 nm (chlorophyll band) are convenient to compute yet distinctive features for the maturity classification. The proposed feature selection method is beneficial because preprocessing, such as dimensionality reduction, is avoided before every prediction. The feature set is designed to capture these traits. The best SOTA methods, among 3D-CNN, 1D-CNN, and SVM, achieve at most 90.0 % accuracy for strawberries and 92.0 % for tomatoes on our dataset. Results show that the proposed method outperforms the SOTA as it yields an accuracy above 98.0 % in strawberry and 96.0 % in tomato classification. A comparative analysis of the time efficiency of these methods is also conducted, which shows the proposed method performs prediction at 13 Frames Per Second (FPS) compared to the maximum 1.16 FPS attained by the full-spectrum SVM classifier.

Lincoln's Annotated Spatio-Temporal Strawberry Dataset (LAST-Straw)

Automated phenotyping of plants for breeding and plant studies promises to provide quantitative metrics on plant traits at a previously unattainable observation frequency. Developers of tools for performing high-throughput phenotyping are, however, constrained by the availability of relevant datasets on which to perform validation. To this end, we present a spatio-temporal dataset of 3D point clouds of strawberry plants for two varieties, totalling 84 individual point clouds. We focus on the end use of such tools - the extraction of biologically relevant phenotypes - and demonstrate a phenotyping pipeline on the dataset. This comprises of the steps, including; segmentation, skeletonisation and tracking, and we detail how each stage facilitates the extraction of different phenotypes or provision of data insights. We particularly note that assessment is focused on the validation of phenotypes, extracted from the representations acquired at each step of the pipeline, rather than singularly focusing on assessing the representation itself. Therefore, where possible, we provide \textit{in silico} ground truth baselines for the phenotypes extracted at each step and introduce methodology for the quantitative assessment of skeletonisation and the length trait extracted thereof. This dataset contributes to the corpus of freely available agricultural/horticultural spatio-temporal data for the development of next-generation phenotyping tools, increasing the number of plant varieties available for research in this field and providing a basis for genuine comparison of new phenotyping methodology.

Key Point-based Orientation Estimation of Strawberries for Robotic Fruit Picking

Selective robotic harvesting is a promising technological solution to address labour shortages which are affecting modern agriculture in many parts of the world. For an accurate and efficient picking process, a robotic harvester requires the precise location and orientation of the fruit to effectively plan the trajectory of the end effector. The current methods for estimating fruit orientation employ either complete 3D information which typically requires registration from multiple views or rely on fully-supervised learning techniques, which require difficult-to-obtain manual annotation of the reference orientation. In this paper, we introduce a novel key-point-based fruit orientation estimation method allowing for the prediction of 3D orientation from 2D images directly. The proposed technique can work without full 3D orientation annotations but can also exploit such information for improved accuracy. We evaluate our work on two separate datasets of strawberry images obtained from real-world data collection scenarios. Our proposed method achieves state-of-the-art performance with an average error as low as $8^{\circ}$, improving predictions by $\sim30\%$ compared to previous work presented in~\cite{wagner2021efficient}. Furthermore, our method is suited for real-time robotic applications with fast inference times of $\sim30$ms.

Crop Row Switching for Vision-Based Navigation: A Comprehensive Approach for Efficient Crop Field Navigation

Vision-based mobile robot navigation systems in arable fields are mostly limited to in-row navigation. The process of switching from one crop row to the next in such systems is often aided by GNSS sensors or multiple camera setups. This paper presents a novel vision-based crop row-switching algorithm that enables a mobile robot to navigate an entire field of arable crops using a single front-mounted camera. The proposed row-switching manoeuvre uses deep learning-based RGB image segmentation and depth data to detect the end of the crop row, and re-entry point to the next crop row which would be used in a multi-state row switching pipeline. Each state of this pipeline use visual feedback or wheel odometry of the robot to successfully navigate towards the next crop row. The proposed crop row navigation pipeline was tested in a real sugar beet field containing crop rows with discontinuities, varying light levels, shadows and irregular headland surfaces. The robot could successfully exit from one crop row and re-enter the next crop row using the proposed pipeline with absolute median errors averaging at 19.25 cm and 6.77{\deg} for linear and rotational steps of the proposed manoeuvre.

Leaving the Lines Behind: Vision-Based Crop Row Exit for Agricultural Robot Navigation

Usage of purely vision based solutions for row switching is not well explored in existing vision based crop row navigation frameworks. This method only uses RGB images for local feature matching based visual feedback to exit crop row. Depth images were used at crop row end to estimate the navigation distance within headland. The algorithm was tested on diverse headland areas with soil and vegetation. The proposed method could reach the end of the crop row and then navigate into the headland completely leaving behind the crop row with an error margin of 50 cm.

End-to-end Unsupervised Learning of Long-Term 3D Stable objects

3D point cloud semantic classification is an important task in robotics as it enables a better understanding of the mapped environment. This work proposes to learn the long-term stability of the 3D objects using a neural network based on PointNet++, where the long-term stable object refers to a static object that cannot move on its own (e.g. tree, pole, building). The training data is generated in an unsupervised manner by assigning a continuous label to individual points by exploiting multiple time slices of the same environment. Instead of using discrete labels, i.e. static/dynamic, we propose to use a continuous label value indicating point temporal stability to train a regression PointNet++ network. We evaluated our approach on point cloud data of two parking lots from the NCLT dataset. The experiments' performance reveals that static vs dynamic object classification is best performed by training a regression model, followed by thresholding, compared to directly training a classification model.

Collection and Evaluation of a Long-Term 4D Agri-Robotic Dataset

Long-term autonomy is one of the most demanded capabilities looked into a robot. The possibility to perform the same task over and over on a long temporal horizon, offering a high standard of reproducibility and robustness, is appealing. Long-term autonomy can play a crucial role in the adoption of robotics systems for precision agriculture, for example in assisting humans in monitoring and harvesting crops in a large orchard. With this scope in mind, we report an ongoing effort in the long-term deployment of an autonomous mobile robot in a vineyard for data collection across multiple months. The main aim is to collect data from the same area at different points in time so to be able to analyse the impact of the environmental changes in the mapping and localisation tasks. In this work, we present a map-based localisation study taking 4 data sessions. We identify expected failures when the pre-built map visually differs from the environment's current appearance and we anticipate LTS-Net, a solution pointed at extracting stable temporal features for improving long-term 4D localisation results.

Cloud Hopping; Navigating in 3D Uneven Environments via Supervoxels and Control Lyapunov Function

This paper presents a novel feedback motion planning method for mobile robot navigation in 3D uneven terrains. We take advantage of the \textit{supervoxel} representation of point clouds, which enables a compact connectivity graph of traversable regions on the point cloud maps. Given this graph of traversable areas, our approach navigates the robot to any reachable goal pose using a control Lyapunov function (cLf) and a navigation function. The cLf ensures the kinodynamic feasibility and target convergence of the generated motion plans, while the navigation function optimizes the resulting feedback motion plans. We carried out navigation experiments in real and simulated 3D uneven terrains. In all circumstances, the experimental findings show that our approach performs superior to the baselines, proving the approach's efficiency and adaptability to navigate a robot in challenging uneven 3D terrains. The proposed method can also navigate a robot with a particular objective, e.g., shortest-distance or least-inclined plan. We compared our approach to well-established sampling-based motion planners in which our method outperformed all other planners in terms of execution time and resulting path length. Finally, we provide an open-source implementation of the proposed method to benefit the robotics community.