arXiv subjects

Junfeng Gao

Publications and source records attributed to Junfeng Gao.

36 records · Page 2Linked to original sources

arXiv2023

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.

cs.RO↗

arXiv2022

Transferring learned patterns from ground-based field imagery to predict UAV-based imagery for crop and weed semantic segmentation in precision crop farming

Weed and crop segmentation is becoming an increasingly integral part of precision farming that leverages the current computer vision and deep learning technologies. Research has been extensively carried out based on images captured with a camera from various platforms. Unmanned aerial vehicles (UAVs) and ground-based vehicles including agricultural robots are the two popular platforms for data collection in fields. They all contribute to site-specific weed management (SSWM) to maintain crop yield. Currently, the data from these two platforms is processed separately, though sharing the same semantic objects (weed and crop). In our paper, we have developed a deep convolutional network that enables to predict both field and aerial images from UAVs for weed segmentation and mapping with only field images provided in the training phase. The network learning process is visualized by feature maps at shallow and deep layers. The results show that the mean intersection of union (IOU) values of the segmentation for the crop (maize), weeds, and soil background in the developed model for the field dataset are 0.744, 0.577, 0.979, respectively, and the performance of aerial images from an UAV with the same model, the IOU values of the segmentation for the crop (maize), weeds and soil background are 0.596, 0.407, and 0.875, respectively. To estimate the effect on the use of plant protection agents, we quantify the relationship between herbicide spraying saving rate and grid size (spraying resolution) based on the predicted weed map. The spraying saving rate is up to 90% when the spraying resolution is at 1.78 x 1.78 cm2. The study shows that the developed deep convolutional neural network could be used to classify weeds from both field and aerial images and delivers satisfactory results.

cs.CV↗

arXiv2022

Vision based Crop Row Navigation under Varying Field Conditions in Arable Fields

Accurate crop row detection is often challenged by the varying field conditions present in real-world arable fields. Traditional colour based segmentation is unable to cater for all such variations. The lack of comprehensive datasets in agricultural environments limits the researchers from developing robust segmentation models to detect crop rows. We present a dataset for crop row detection with 11 field variations from Sugar Beet and Maize crops. We also present a novel crop row detection algorithm for visual servoing in crop row fields. Our algorithm can detect crop rows against varying field conditions such as curved crop rows, weed presence, discontinuities, growth stages, tramlines, shadows and light levels. Our method only uses RGB images from a front-mounted camera on a Husky robot to predict crop rows. Our method outperformed the classic colour based crop row detection baseline. Dense weed presence within inter-row space and discontinuities in crop rows were the most challenging field conditions for our crop row detection algorithm. Our method can detect the end of the crop row and navigate the robot towards the headland area when it reaches the end of the crop row.

cs.CV↗

arXiv2022

Towards Infield Navigation: leveraging simulated data for crop row detection

Agricultural datasets for crop row detection are often bound by their limited number of images. This restricts the researchers from developing deep learning based models for precision agricultural tasks involving crop row detection. We suggest the utilization of small real-world datasets along with additional data generated by simulations to yield similar crop row detection performance as that of a model trained with a large real world dataset. Our method could reach the performance of a deep learning based crop row detection model trained with real-world data by using 60% less labelled real-world data. Our model performed well against field variations such as shadows, sunlight and grow stages. We introduce an automated pipeline to generate labelled images for crop row detection in simulation domain. An extensive comparison is done to analyze the contribution of simulated data towards reaching robust crop row detection in various real-world field scenarios.

cs.CV↗

arXiv2022

Eliminating edge electronic and phonon states of phosphorene nanoribbon by unique edge reconstruction

Edge termination plays a vital role in determining the properties of 2D materials. By performing compelling ab initio simulations, a lowest-energy U-edge [ZZ(U)] reconstruction is revealed in the bilayer phosphorene. Such reconstruction reduces 60% edge energy compared with the pristine one and occurs almost without energy barrier, implying it should be the dominating edge in reality. The electronic band structure of phosphorene nanoribbon with such reconstruction resembles that of intrinsic 2D layer, exhibiting nearly edgeless band characteristics. Although ZZ(U) changes the topology of phosphorene nanoribbon (PNR), simulated TEM, STEM and STM images indicates it is very hard to be identified. One possible identify method is IR/Raman analyses because ZZ(U) edge alters vibrational modes dramatically. Beyond, it also increases the thermal conductivity of PNR 1.4 and 2.3 times than the pristine and Klein edges.

cond-mat.mtrl-sci↗

arXiv2021

In-field early disease recognition of potato late blight based on deep learning and proximal hyperspectral imaging

Effective early detection of potato late blight (PLB) is an essential aspect of potato cultivation. However, it is a challenge to detect late blight at an early stage in fields with conventional imaging approaches because of the lack of visual cues displayed at the canopy level. Hyperspectral imaging can, capture spectral signals from a wide range of wavelengths also outside the visual wavelengths. In this context, we propose a deep learning classification architecture for hyperspectral images by combining 2D convolutional neural network (2D-CNN) and 3D-CNN with deep cooperative attention networks (PLB-2D-3D-A). First, 2D-CNN and 3D-CNN are used to extract rich spectral space features, and then the attention mechanism AttentionBlock and SE-ResNet are used to emphasize the salient features in the feature maps and increase the generalization ability of the model. The dataset is built with 15,360 images (64x64x204), cropped from 240 raw images captured in an experimental field with over 20 potato genotypes. The accuracy in the test dataset of 2000 images reached 0.739 in the full band and 0.790 in the specific bands (492nm, 519nm, 560nm, 592nm, 717nm and 765nm). This study shows an encouraging result for early detection of PLB with deep learning and proximal hyperspectral imaging.

cs.CV↗

arXiv2021

Tea Chrysanthemum Detection under Unstructured Environments Using the TC-YOLO Model

Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development. However, it is a challenge to detect flowering chrysanthemums under unstructured field environments given the variations on illumination, occlusion and object scale. In this context, we propose a highly fused and lightweight deep learning architecture based on YOLO for tea chrysanthemum detection (TC-YOLO). First, in the backbone component and neck component, the method uses the Cross-Stage Partially Dense Network (CSPDenseNet) as the main network, and embeds custom feature fusion modules to guide the gradient flow. In the final head component, the method combines the recursive feature pyramid (RFP) multiscale fusion reflow structure and the Atrous Spatial Pyramid Pool (ASPP) module with cavity convolution to achieve the detection task. The resulting model was tested on 300 field images, showing that under the NVIDIA Tesla P100 GPU environment, if the inference speed is 47.23 FPS for each image (416 * 416), TC-YOLO can achieve the average precision (AP) of 92.49% on our own tea chrysanthemum dataset. In addition, this method (13.6M) can be deployed on a single mobile GPU, and it could be further developed as a perception system for a selective chrysanthemum harvesting robot in the future.

cs.CV↗

arXiv2021

Towards practical object detection for weed spraying in precision agriculture

The evolution of smaller, faster processors and cheaper digital storage mechanisms across the last 4-5 decades has vastly increased the opportunity to integrate intelligent technologies in a wide range of practical environments to address a broad spectrum of tasks. One exciting application domain for such technologies is precision agriculture, where the ability to integrate on-board machine vision with data-driven actuation means that farmers can make decisions about crop care and harvesting at the level of the individual plant rather than the whole field. This makes sense both economically and environmentally. However, the key driver for this capability is fast and robust machine vision -- typically driven by machine learning (ML) solutions and dependent on accurate modelling. One critical challenge is that the bulk of ML-based vision research considers only metrics that evaluate the accuracy of object detection and do not assess practical factors. This paper introduces three metrics that highlight different aspects relevant for real-world deployment of precision weeding and demonstrates their utility through experimental results.

cs.CV↗

arXiv2021

Towards agricultural autonomy: crop row detection under varying field conditions using deep learning

This paper presents a novel metric to evaluate the robustness of deep learning based semantic segmentation approaches for crop row detection under different field conditions encountered by a field robot. A dataset with ten main categories encountered under various field conditions was used for testing. The effect on these conditions on the angular accuracy of crop row detection was compared. A deep convolutional encoder decoder network is implemented to predict crop row masks using RGB input images. The predicted mask is then sent to a post processing algorithm to extract the crop rows. The deep learning model was found to be robust against shadows and growth stages of the crop while the performance was reduced under direct sunlight, increasing weed density, tramlines and discontinuities in crop rows when evaluated with the novel metric.

cs.CV↗

arXiv2019

Design of Phosphorene for Hydrogen Evolution Performance Comparable to Platinum

Phosphorene, a monolayer of bulk black phosphorus, is promising for light harvest owing to its high charge mobility and tunable direct band gap covering a broad spectral range of light. Here, via atomic-scale first-principles simulations, we report a ultrahigh activity of hydrogen evolution reaction (HER) of phosphorene originated from defective activation. Quantitative evaluation of the Gibbs free energy of the ad desorption of hydrogen (H) to from phosphorene (delta_GH) reveals that atomic vacancies and edges play a dominant role in activating the reaction. We find that the defective states, empty and well-localized around the defect core, are compensated by H species. This induces a proper hydrogen interaction complying with the thermoneutral condition of the free energy (delta_GH=0) comparable to platinum. Our findings of the highly activating defective states suggest the design of non-metal HER catalysts with structural engineering of earth-abundant phosphorus structures.

cond-mat.mtrl-sci↗

arXiv2019

Evolution of Intrinsic Vacancies and Prolonged Lifetime of Vacancy Clusters in Black Phosphorene

Due to the relatively low formation energies and highly mobile characteristics of atomic vacancies in phosphorene, understanding their evolutions becomes crucial for its structural integrity, chemical activities and applications. Herein, by combining first-principles calculations and kinetic Monte Carlo simulation, we investigate the time evolution and formation of atomic vacancy clusters from isolated monovacancies (MVs), aiming to uncover the mechanisms of diffusion, annihilation, reaction of these atomic vacancies. We find that while isolated MVs possess a highly mobile character, they react and form MV pairs which possess much lower mobility and high stability under ambient condition. We also show that the disappearance of MVs at the edge is quite slow due to the relatively high energy barrier, and as a result, around 80% of MVs remains even after two years under ambient condition. Our findings on one hand provide useful information for the structural repairing of phosphorene through chemical functionalization of these vacancy clusters, and on the other hand, suggest that these rather stable vacancy clusters may be used as an activated catalyst.

cond-mat.mtrl-sci↗

arXiv2018

Unravelling the origin of piezo/ferro-electric properties of metal-organic frameworks (MOFs) nanocrystals

Metal-organic framework (MOF) UiO-66 nanocrystals were previously believed to be piezo/ferro-electrically inactive because of their centrosymmetric lattice symmetries (Fm-3m (225)) revealed by Powder X-ray diffraction. However, via delicate dual AC resonance tracking piezoresponse force microscopy and piezoresponse force spectroscopy characterizations, our nanoscale probing for the first time demonstrate that UiO-66 nanocrystals show piezo/ferro-electric response. Our compelling experimental and theoretically analyses disclose that the structure of UiO-66 should not be the highly centrosymmetric Fm-3m (225) but a reduced symmetry form instead. UiO-66(Hf)-type MOFs possess stronger piezoresponse and better ferroelectric switching behaviours than their counterparts UiO-66 (Zr)-type MOFs. Our study not only enriches the structural understanding of UiO-66 MOF, but also suggests possible modification of electronic property of the MOFs by judicious selection of metal ions and functional ligands.

cond-mat.mtrl-sci↗

arXiv2017

Magic Graphene Clusters Formation in the graphene CVD growth process on Ru and Rh

To improve atomically controlled chemical vapor deposition (CVD) growth of graphene, understanding the evolution from various carbon species to a graphene nuclei on various catalyst surfaces is essential. Experimentally, an ultra-stable carbon cluster on Ru(0001), Rh(111) surfaces was observed, while its structure and formation process were still under highly debate. Using ab initio calculations and kinetic analyses, we disclosed a specific type of carbon clusters, composed of a C21 core and a few dangling C atoms around, were exceptional stable in the size range from 21 to 27. The most stable one of them, an isomer of C24 characterized as three dangling C atoms attached to the C21 (denoted as C21-3C), is the most promising candidate for the experimental observation. The ultra-stability of C21-3C originates from both the stable core and the appropriate passivation of dangling carbon atoms by the catalyst surface.

cond-mat.mtrl-sci↗

arXiv2017

MoS2-graphene in-plane contact for high interfacial thermal conduction

Recent studies showed that the in-plane and inter-plane thermal conductivities of two-dimensional (2D) MoS2 are low, posing a significant challenge in heat management in MoS2-based electronic devices. To address this challenge, we design the interfaces between MoS2 and graphene by fully utilizing graphene, a 2D material with an ultra-high thermal conduction. We first perform ab initio atomistic simulations to understand the bonding nature and structure stability of the interfaces. Our results show that the designed interfaces, which are found to be connected together by strong covalent bonds between Mo and C atoms, are energetically stable. We then perform molecular dynamics simulations to investigate the interfacial thermal conductance. It is found surprisingly that the interface thermal conductance is high, comparable to that of graphene-metal covalent-bonded interfaces. Importantly, each interfacial Mo-C bond serves as an independent thermal channel, enabling the modulation of interfacial thermal conductance by controlling Mo vacancy concentration at the interface. The present work provides a viable route for heat management in MoS2 based electronic devices.

cond-mat.mtrl-sci↗

arXiv2017

Phosphorene Edge Reconstruction by Self-Rolling

Edge atomic configuration often plays an important role in dictating the properties of finite-sized two-dimensional (2D) materials. By performing ab initio calculations, we identify a highly stable zigzag edge of phosphorene, which is the most stable one among all the considered edges. Surprisingly, this highly stable edge exhibits a novel nanotube-like structure, which is topologically distinctively different from any previously reported edge reconstruction. We further show that this new edge type can form easily, with an energy barrier of only 0.234 eV. It may be the dominant edge type at room temperature in vacuum condition or even under low hydrogen gas pressure. The calculated band structure reveals that the reconstructed edge possesses a bandgap of 1.23 eV. It is expected that this newly found edge structure may stimulate more studies in uncovering other novel edge types and further exploring their practical applications.

cond-mat.mtrl-sci↗

arXiv2016

The Critical Role of Substrate in Stabilizing Phosphorene Nanoflake: A Theoretical Exploration

Phosphorene, a new two-dimensional (2D) semiconductor, has received much interest due to its robust direct band gap and high charge mobility. Currently, however, phosphorene can only be produced by mechanical or liquid exfoliation, and it is still a significant challenge to directly epitaxially grow phosphorene, which greatly hinders its mass production and, thus, applications. In epitaxial growth, the stability of nanoscale cluster or flake on a substrate is crucial. Here, we perform ab initio energy optimizations and molecular dynamics simulations to explore the critical role of substrate on the stability of a representative phosphorene flake. Our calculations show that the stability of the phosphorene nanoflake is strongly dependent on the interaction strength between the nanoflake and substrate. Specifically, the strong interaction (0.75 eV/P atom) with Cu(111) substrate breaks up the phosphorene nanoflake, while the weak interaction (0.063 eV/P atom) with h-BN substrate fails to stabilize its 2D structure. Remarkably, we find that a substrate with a moderate interaction (about 0.35 eV/P atom) is able to stabilize the 2D characteristics of the nanoflake on a realistic time scale. Our findings here provide useful guidelines for searching suitable substrates for the directly epitaxial growth of phosphorene.

cond-mat.mtrl-sci↗

arXiv2015

Wafer-scale CVD Growth of Monolayer Hexagonal Boron Nitride with Large Domain Size by Cu Foil Enclosure Approach

Chemical vapor deposition synthesis of large domain hexagonal boron nitride (h-BN) with uniform thickness on Cu foils is of great challenge, originating from the extremely high nucleation densities and the reverse hydrogen etching competition reaction. We report herein the successful growth of wafer-scale high-quality h-BN monolayer film with the largest single crystalline domain sizes up to 72 micrometer in edge length using a folded Cu enclosure approach. The highly-confined growth space with this facile and unique approach enables the drastic decrease of nucleation centers together with the effective suppression of hydrogen etching reaction. It is revealed, for the first time, that the orientations of as-grown h-BN monolayers are strongly correlated with the crystalline facets of growth substrates, with the Cu (111) being the best substrate for growing high-quality single crystalline h-BN monolayer, consistent with the density functional theory calculations. The present study offers a practical pathway for growing high-quality h-BN films and deepens the fundamental understanding of h-BN growth process.

cond-mat.mtrl-sci↗

arXiv2011

Graphene Nucleation on Transition Metal Surface: Structure Transformation and Role of the Metal Step Edge

The nucleation of graphene on a transition metal (TM) surface, either on a terrace or near a step edge, is systematically explored using density functional theory (DFT) calculations and applying the two-dimensional (2D) crystal nucleation theory. Careful optimization of the supported carbon clusters, CN (with size N ranging from 1 to 24), on the Ni(111) surface indicates a ground state structure transformation from a one-dimensional (1D) C chain to a two-dimensional (2D) sp2 C network at N ~ 10-12. Furthermore, the crucial parameters controlling graphene growth on the metal surface, nucleation barrier, nucleus size, and the nucleation rate on a terrace or near a step edge, are calculated. In agreement with numerous experimental observations, our analysis shows that graphene nucleation near a metal step edge is superior to that on a terrace. Based on our analysis, we propose the use of seeded graphene to synthesize high-quality graphene in large area.

cond-mat.mtrl-sci↗