High-resolution Sensor Research Articles

Gaussian processes based extended target tracking in polar coordinates with input uncertainty

Gaussian processes (GP) based extended target tracking (ETT) technique has attracted the attention of scientists since it can accurately estimate the kinematic states as well as the contour states of irregular-shape targets. Most traditional GP methods consider the ETT problem with a linear measurement model in Cartesian coordinates and ignore the input uncertainty of GP for simplicity. In many applications, however, measurements are generated with high-resolution sensors in polar coordinates. More importantly, the ignorance of input uncertainty in GP will exacerbate the tracking performance in these cases. In order to track an irregular-shape extended target in polar coordinates with input uncertainty, an improved GP-based probabilistic data association (IGP-PDA) algorithm is developed that includes the following enhancements: Firstly, a nonlinear measurement model is used and the unbiased converted measurement technique is invoked for the ETT problem. Secondly, the analytical form of statistical properties of the input uncertainty due to measurements noise and predicted error is derived. Thirdly, an IGP-PDA taking into account measurement origin uncertainty as well as input uncertainty is proposed, and three sub-optimal implementations are provided. Last, the posterior Cramer-Rao lower bound of ETT with input uncertainty is derived. Simulation results verify the effectiveness of the proposed method.

KmT, Kilometer-long mooring of high-resolution Temperature measurements results overview

The global oceans show extensive bottom topography above which intensive turbulent mixing is generated by breaking internal waves. Growing evidence suggests that the mixing is sufficient to maintain the ocean’s stable vertical density stratification, thereby preventing the deep-ocean from becoming a stagnant pool of cold water. Observational details of the extent of turbulent mixing away from topography are still scarce however. In this paper, results are presented from 760 high-resolution temperature sensors that were moored between 8 and 1146.5 m above a 2380-m deep sloping seafloor of Mount Josephine NE-Atlantic for 4 months. The local seafloor-slope is supercritical for semidiurnal internal tides under average stratification. The purpose of the > 1-km-long densely instrumented mooring is to provide insight in the variability of coherent scales, and in the connection between seamount-slope and mixing-effects up to 7-km horizontally into the ocean-interior. Largest four-month mean turbulence values are found near the seafloor, decreasing to half an order of magnitude lower values at 500 m above, and remaining steady-high further up. Local increases of mean turbulence values are observed in bands of 100–200 m thickness. Larger internal wave breaking occurs during baroclinic spring tide, which also affects internal waves and turbulent overturning in the interior. Spectrally, a turbulence inertial subrange dominates part of the internal wave band continuum near the seafloor. Coupling between interior- and near-seafloor-mixing is not only via previously suggested isopycnal transport of mixed waters, but also via strong internal wave interactions. Seamount-flow contributes to absolute vorticity so that blue-shifted near-inertial motions interact with internal tides.

Acid-Base Reaction-Assisted Quantum Dot Patterning via Ligand Engineering and Photolithography.

The integration of quantum dots (QDs) into device arrays for high-resolution display and imaging sensor systems remains a significant challenge in research and industry because of issues associated with the QD patterning process. It is difficult for conventional patterning processes such as stamping, inkjet printing, and photolithography to employ QDs and fabricate high-resolution patterns without degrading the properties of QDs. Here, we introduce a novel strategy for the QD patterning process by treating QDs with a bifunctional ligand for acid-base reaction-assisted photolithography. Bifunctional ligands, such as MPA (mercaptopropionic acid) or TGA (thioglycolic acid), have a carboxyl group on one side that allows the QDs to be etched along with the photoresist (PR) by the base developer, while on the opposite side the ligands have a thiol group that passivates the QD surface. Passivating MPA ligands on QDs facilitates patterning of QD films and makes them compatible with harsh photolithography processes. We successfully achieved the patterning of QDs down to 5 μm. We also fabricated high-resolution patterned QD light-emitting diodes (LEDs) and QD photodetector arrays. Our patterning process provides precise control for the fabrication of highly integrated QD-based optoelectronic devices.

High-Resolution, Transparent, and Flexible Printing of Polydimethylsiloxane via Electrohydrodynamic Jet Printing for Conductive Electronic Device Applications.

In the field of soft electronics, high-resolution and transparent structures based on various flexible materials constructed via various printing techniques are gaining attention. With the support of electrical stress-induced conductive inks, the electrohydrodynamic (EHD) jet printing technique enables us to build high-resolution structures compared with conventional inkjet printing techniques. Here, EHD jet printing was used to fabricate a high-resolution, transparent, and flexible strain sensor using a polydimethylsiloxane (PDMS)/xylene elastomer, where repetitive and controllable high-resolution printed mesh structures were obtained. The parametric effects of voltage, flow rate, nozzle distance from the substrate, and speed were experimentally investigated to achieve a high-resolution (5 µm) printed mesh structure. Plasma treatment was performed to enhance the adhesion between the AgNWs and the elastomer structure. The plasma-treated functional structure exhibited stable and long strain-sensing cycles during stretching and bending. This simple printing technique resulted in high-resolution, transparent, flexible, and stable strain sensing. The gauge factor of the strain sensor was significantly increased, owing to the high resolution and sensitivity of the printed mesh structures, demonstrating that EHD technology can be applied to high-resolution microchannels, 3D printing, and electronic devices.

High Resolution and Stability Self-Reference Plasmonic Sensor With Metallic Grating on Multilayered Dielectric Cavity Substrate

In order to improve the sensing performance of surface plasmon resonance (SPR) refractive index (RI) sensor and avoid the negative effect of various environmental factors, a self-reference plasmonic sensor with high resolution and stability based on the combination of metallic grating and multilayered dielectric cavity is proposed in this article. The sensing mode, based on SPR in the metallic grating, is sensitive to the RI variations of the analyte. The guided mode resonances (GMRs), excited by the multilayered dielectric cavity, can be served as self-references due to the insensitivity to the analyte’s RI variations. It is verified that the sensitivity of 500 nm/RIU is achieved, and the smallest sensitivity of self-reference resonance is 0.83 nm/RIU; thus, the sensitivity ratio (stability) is up to 602. Also, a large figure of merit (FOM) of 238 RIU−1 in the sensor is realized and a high-quality factor of 4668 of self-reference mode with high resolution is achieved, which is much better than that of the previous works. The results provide a theoretical basis to design a highly sensitive self-reference plasmonic sensor and have a potential application in the industrial measuring instruments such as the sensor to measure water content in heavy oil.

Few-shot learning for modeling cyber physical systems in non-stationary environments

This paper proposes a modeling scheme for cyber physical systems operating in non-stationary, small data environments. Unlike the traditional modeling logic, we introduce the few-shot learning paradigm, the operation of which is based on quantifying both similarities and dissimilarities. As such, we designed a suitable change detection mechanism able to reveal previously unknown operational states, which are incorporated in the dictionary online. We elaborate on spectrograms extracted from high-resolution ultrasound depth sensor timeseries, while the backbone of the proposed method is a Siamese Neural Network. The experimental scenario considers data representing liquid containers for fuel/water when the following five operational states are present: normal, accident, breakdown, sabotage, and cyber-attack. Thorough experiments were carried out assessing every aspect of the present framework and demonstrating its efficacy even when very few samples per class are available. In addition, we propose a probabilistic data selection scheme facilitating one-shot learning. Last but not least, responding to the wide requirement for interpretable AI, we explain the obtained predictions by examining the layer-wise activation maps.

High-Speed and High-Resolution Optical Fiber Sensor Interrogation Based on Optical Injection in Semiconductor Laser and Microwave Filtering

Real-time and high-speed interrogation of optical fiber sensors normally requires sophisticated detection systems. Here a novel microwave photonic approach for interrogation of high-speed and high-resolution optical fiber sensors based on optical injection in a semiconductor laser and simple passive microwave frequency filtering is proposed and experimentally demonstrated. An intensity-modulated master laser is injected into a semiconductor laser to produce a wavelength scanning optical sideband. A fiber Bragg grating (FBG) sensor is embedded into a fiber ring laser. Beating of the scanning optical sideband and the fiber ring laser wavelength at a photodetector generates a linearly frequency-chirped microwave signal. The real-time wavelength shift of the FBG sensor is converted into the change of the microwave center frequency. After a simple passive microwave bandpass filter, two electrical pulses are obtained corresponding to positive and negative frequency sweeping. The FBG wavelength can be retrieved from the time interval of the two pulses. A proof-of-concept experiment to measure an FBG strain sensor has been carried out. A high interrogation speed of 1 MHz and measurement sensitivity of 17.3 ns/μϵ have been achieved.

Photothermal regulated multi-perceptive poly(ionic liquids) hydrogel sensor for bioelectronics

Hydrogels with excellent flexibility, water retention, and biocompatibility are natural carriers for drug delivery. However, the poor drug compatibility seriously limits the practical application of traditional PNIPAM-based hydrogel. Herein, a photothermal regulated smart hydrogel was synthesized by introducing poly(ionic liquids) chain into the binary polymer chain. The temperature-induced hydrophilic-hydrophobic switchable poly(ionic liquids) chain endows the smart hydrogel with editable transparency, enabling intuitive visualization of drug loading and releasing capacity. The smart hydrogel could be used as NIR/temperature-controlled drug carrier to achieve efficient and visualized release (40.8 % drug release rate in 30 min). Besides, the smart hydrogel sensor showed excellent strain sensing sensitivity (gauge factor = 3.73), short response time (116 ms), high durability (1800 s at 20 % strain), and impressive temperature sensing sensitivity (TCR = -1.252 %/°C). Based on the excellent sensing performance and editable drug-delivery ability, the smart hydrogel was assembled into a dynamic wound management system to realize personalized wound treatment and wireless state diagnosis. The wireless sensor early warning system could realize wireless monitoring and state warning of joints (fingers, ankles, and elbows), exhibiting guiding significance for rehabilitation treatment. Moreover, the high-resolution sensor array composed of 5 × 5 smart hydrogels could accurately identify the strain, temperature and NIR light in three-dimensional space and direction. In short, the smart hydrogel provides an innovative solution to personalized wound diagnosis and assisted rehabilitation.

Yearly weather variation and surface temperature drives the spatiotemporal dynamics of a threatened butterfly and its host plant

It remains unclear to what extent yearly weather variation and spatial variation in microclimate influences the outcome of interacting plant-animal species and whether responses differ between life stages. We collected data over several years on 46 ha on File Hajdar, Gotland, Sweden, and executed a complete mapping of larva nests (n= 776) and imago (n= 5,952) of the marsh fritillary butterflyEuphydryas auriniaand its host plantSuccisa pratensis. The phenology of the butterflies and the major nectar plants visited varied among years. The duration of the adult flight period decreased with increasing ambient air temperatures. The density of butterflies, host plants, and host plant leaf size increased between years with increasing precipitation in the preceding year, and decreased with increasing average ambient air temperature in the preceding year. In 2021–2022 we deployed a unmanned aerial vehicle (UAV) with a high-resolution thermal sensor to measure spatial variation in surface temperatures in the study area. We found that survival from the egg to the larva stage increased with increasing surface temperature and host plant density. Host plants and larva nests generally occupied warmer microhabitats compared to imago butterflies. The results further suggested that the relationships linking surface temperature to the densities of imago, larva, host plants, and leaf size differed qualitatively between years. In 2017, larva nests and host plant density increased with increasing surface temperatures, and butterflies showed a non-linear response with a density peak at intermediate temperatures. As a result of the extreme drought in 2018 there was a reduction in maximum leaf size, and in the densities of plants, larvae, and butterflies. Moreover, the slopes of the relationships linking the density of larvae, butterflies, and plants to temperature shifted from linear positive to negative or curvilinear. Our findings demonstrate how yearly weather variation and heterogeneous surface temperatures can drive the spatiotemporal distribution and dynamics of butterflies and their host plants. The context specificity of the responses indicated by our results makes it challenging to project how climate change will affect the dynamics of ecological communities.

Tactile Gym 2.0: Sim-to-Real Deep Reinforcement Learning for Comparing Low-Cost High-Resolution Robot Touch

High-resolution optical tactile sensors are increasingly used in robotic learning environments due to their ability to capture large amounts of data directly relating to agent-environment interaction. However, there is a high barrier of entry to research in this area due to the high cost of tactile robot platforms, specialised simulation software, and sim-to-real methods that lack generality across different sensors. In this letter we extend the Tactile Gym simulator to include three new optical tactile sensors (TacTip, DIGIT and DigiTac) of the two most popular types, Gelsight-style (image-shading based) and TacTip-style (marker based). We demonstrate that a single sim-to-real approach can be used with these three different sensors to achieve strong real-world performance despite the significant differences between real tactile images. Additionally, we lower the barrier of entry to the proposed tasks by adapting them to an inexpensive 4-DoF robot arm, further enabling the dissemination of this benchmark. We validate the extended environment on three physically-interactive tasks requiring a sense of touch: object pushing, edge following and surface following. The results of our experimental validation highlight some differences between these sensors, which may help future researchers select and customize the physical characteristics of tactile sensors for different manipulations scenarios.

Simulation study on inclined orbit constellation of high-resolution electrooptical sensors for enhanced imaging efficiency in region of interest

Traditionally, high-resolution electrooptical (EO) sensors are placed in Sun-synchronous orbits (SSO) as they enable consistent solar illumination during imaging and near-global coverage for various remote sensing applications. However, these sensors inherently offer limited swath coverage resulting in poorer imaging efficiency and often require a large number of satellites in constellation for improving revisit time over region of interest (RoI). Compared with constellation of satellites in SSO, a smaller number of satellites in lower inclination orbits can provide significant advantage in terms of imaging efficiency in the tropical and near-tropical RoIs, which is desirable for many civilian and strategic applications. In this work, detailed analytical simulations have been performed for inclined orbit constellation of high-resolution EO sensors, and higher imaging efficiency has been demonstrated against SSO constellation. Rigorous mathematical models are developed to enable optimization of constellation design with proper fine-tuning of orbital parameters to maximize imaging efficiency in the RoI, and the model output is validated through STK simulation. For quantitative evaluation of imaging efficiency, two figures of merits, namely, average number of access per day and number of days with no access, have been estimated for various design cases. This study shows significant improvements in imaging efficiency parameters up to a factor of 3 in RoI as compared with traditional SSO constellation. This study is generic in nature and is applicable for any inclination angles and latitudes in the tropical and near tropical RoIs. This study can significantly aid in design of satellite constellations for future remote sensing missions.

HUMAN ACTIVITY DETECTION SYSTEM

The purpose of this project is to develop a model that would take the image input from different sources and detect actions that are being performed in them by the people also commonly referred to as Human actions recognition. The project starts by analyzing the procedures and models that already exist to perform this activity along with the assessment of their advantages and disadvantages respectively. There were many approaches to build this project that mainly used sensors and various modelling procedures such as Convolutional Neural Networks (CNN), Recurrent Neural Networks(RNN), Deep Neural Networks(DNN) and few Image Processing techniques. The goal is to come up with a model that is able to detect a selection of activities on which the model was trained during the development phase. The designed model helps to overcome the disadvantage of the previously built models that relied on the use of sensors. With the elimination of sensors, we eliminate the cost associated with respect to the sensors and the errors that can be caused due to the use of sensors. The vision-based HAR(human activity recognition) has produced fruitful findings with the advantage of high optical sensor resolution and the rapidly evolving computer vision techniques.

Instantaneous Frequency Measurement with Reasonable Resolution and Simple Structure

Microwave signals carry important intelligence information in electronic warfare. Hence, the measurement of microwave signals plays a very important role. Traditional electronic microwave measurement systems are not appropriate for the instantaneous frequency measurement (IFM) of high-speed signals. A simple and low-cost photonic approach to the IFM based on frequency-to-power mapping is proposed and demonstrated with a reasonable resolution. The measurement is performed on account of a double Mach–Zehnder modulator (MZM), single-mode fiber (SMF), photodetector (PD), and signal processing. The scheme using four wavelengths achieves resolutions of ±0.1 and ±0.09 GHz respectively for the 15.8–18.4 and 18.4−21.2 GHz frequency measurement ranges. Therefore, the scheme is a broad prospects method for high-resolution IFM. Moreover, it is of great importance for applications in electronic warfare and high-resolution sensor systems.

A high-resolution MEMS magnetoresistive sensor utilizing magnetic tunnel junction motion modulation driven by the piezoelectric resonator

High-sensitivity MEMS magnetoresistive (MR) sensors have attracted ever-increasing attention due to their ability to detect weak magnetic fields, but the resolution is severely limited by the 1/f noise. This paper reports a MEMS MR sensor that can effectively suppress the 1/f noise by modulating the magnetic field signal to the higher frequency region utilizing magnetic tunnel junction vertical motion modulation based on the MEMS piezoelectric cantilever resonator. The magnetic sensitivity can be increased to 2283.3%/mT with a high magnetic gain of 39.3 by integrating the structure-optimized fixed magnetic flux concentrators. The signal-to-noise ratio of the MEMS MR sensor can be improved by three orders of magnitude and the 160 pT/√Hz resolution can be reached. These results make the MEMS MR sensor based on the MTJ motion modulation a competitive candidate in the pico-Tesla magnetic detection.

First-principles investigation of ferroelectric and piezoelectric properties in one-dimensional transition metal oxytetrahalides

We perform first-principles density functional theory calculations to systematically investigate electronic structures of a quasi-one-dimensional $M\mathrm{O}{X}_{4}$ ($M=\mathrm{Cr},\mathrm{Mo},\mathrm{W}$, and $X=\mathrm{F},\mathrm{Cl},\mathrm{Br}$) materials consisting of weakly coupled one-dimensional chains. The compositional dependence on the ferroelectric and piezoelectric properties such as switching polarization, energy barriers, Born effective charges, and piezoelectric coefficients are investigated. We find that the majority of the $M\mathrm{O}{X}_{4}$ systems exhibit sizable polarization and large piezoelectric coefficients comparable to conventional ferroelectrics. More importantly, we find that the energy cost of forming a ${180}^{\ensuremath{\circ}}$ domain walls is negligibly small due to the weak interchain coupling, having an atomically thin domain wall with almost no reduction in the local polarization. The robust ferroelectric switching, atomically thin ferroelectric domain wall, and large piezoelectric coefficients make the $M\mathrm{O}{X}_{4}$ family of materials potential candidates for applications for efficient electronic devices such as high-density ferroelectric memories and high-resolution pressure sensors.

Watching the Saltmarsh Grow: A High-Resolution Remote Sensing Approach to Quantify the Effects of Wetland Restoration

Coastal wetlands are restored to regenerate lost ecosystem services. Accurate and frequent representations of the distribution and area of coastal wetland communities are critical for evaluating restoration success. Typically, such data are acquired through laborious, intensive and expensive field surveys or traditional remote sensing methods that can be erroneous. Recent advances in remote sensing techniques such as high-resolution sensors (<2 m resolution), object-based image analysis and shallow learning classifiers provide promising alternatives but have rarely been applied in a restoration context. We measured the changes to wetland communities at a 200 ha restoring coastal wetland in eastern Australia, using remotely sensed Worldview-2 imagery, object-based image analysis and random forest classification. Our approach used structural rasters (digital elevation and canopy height models) and a multi-temporal technique to distinguish between spectrally similar land cover. The accuracy of our land cover maps was high, with overall accuracies ranging between 91 and 95%, and this supported early detection of increases in the area of key ecosystems, including mixed she-oak and paperbark (10 ha), mangroves (0.91 ha) and saltmarsh (4.31 ha), over a 5-year monitoring period. Our approach provides coastal managers with an accurate and frequent method for quantifying early responses of coastal wetlands to restoration, which is essential for informing adaptive management in the regeneration of ecosystem services.

Compliant gripper with force estimation for physical human–robot interaction

Despite the major interest in the field of Human–Robot Interaction (HRI) in recent years, not much work has been presented on physical HRI (pHRI), especially for robot-initiated contact. Although pHRI is a key skill in areas like assistive or rescue robots, advances are limited by hard constraints in safety and compliance that require specific hardware features and force estimation capabilities. This work presents a new compliant gripper with four underactuated fingers and force-sensing capabilities designed to manipulate a human forearm. Fingers are based on the rigid-link approach, where one of the links has been replaced by a compression spring. High-resolution angular sensors at the passive joints allow computing the spring compression and the actuator torque. Then grasping forces are estimated through the kinetostatic model of the fingers. The gripper has been built and tested. Compliance and grasping force estimation and control have been successfully evaluated. Results prove that the proposed finger arrangement offers good performance, making our design suitable for pHRI applications.

Analysis of a novel hydrophobic acrylic enhanced monofocal intraocular lens compared to its standard monofocal type on the optical bench

IntroductionThe aim of this laboratory study is to objectively analyze the new hydrophobic, acrylic, enhanced monofocal intraocular lens Acunex Quantum (AN6Q) and compare it with the monofocal platform Acunex AN6. MethodsTwo IOL models were analyzed (Acunex Quantum AN6Q and Acunex AN6, Teleon Surgical, Spankeren, Netherlands), each having the same refractive power of + 22.0 D, on the optical bench with the OptiSpheric IOL PRO 2. The measurements followed the guidelines of the International Standard Organization with following parameters: ISO 2 cornea (+ 0,28 µ), ISO 11979/2, lens placement in situ in NaCl with 35° temperature, 546 nm and selection of different aperture sizes (3.0 mm vs 4.5 mm). The aberrations of each IOL were evaluated by the WaveMaster IOL 2, a high-resolution Shack-Hartmann sensor in reverse projection setup. An in-situ model eye was used according to ISO 11979 in NaCl (n = 1.337) with 546 nm, mask width 4.51. Zernike polynomials up to 10th order were determined by means of the measured wavefront that describe the optical properties of the IOL.ResultsThrough frequency modulation transfer function (mean) at 50 lp/mm (AN6Q/AN6 centered) was 0.687/0.731 (3.0 mm aperture) and 0.400/0.509 (4.5 mm aperture). The SR (mean) was 0.592/0.809 (3.0 mm) and 0.332/0.372 (4.5 mm). The MTF (mean) at 50 lp/mm (AN6Q/AN6 decentered by 1 mm) was 0.413/0.478 (3.0 mm) and 0.257/0.229 (4.5 mm). The SR (mean) was 0.393/0.404 (3.0 mm) and 0.183/0.212 (4.5 mm). The MTF (mean) at 50 lp/mm (AN6Q/AN6 tilted by 5°) was 0.508/0.710 (3.0 mm) and 0.337/0.513 (4.5 mm). The SR (mean) was 0.508/0.760 (3.0 mm) and 0.235/0.2372 (4.5 mm). AN6Q showed MTF peak of 0.55 with an enlarged depth of power of about 2.5 D and two cusps in the MTF curve. The spherical aberration Z 4–0 was about -0.21 µm and the secondary spherical aberration Z 6–0 was about 0.16 µm. No other relevant aberration showed up.ConclusionThe new, enhanced monofocal AN6Q provides an extended range of focus with only slight decrease in contrast quality. Both types of the hydrophobic, acrylic Acunex IOL platform have its particular advantages in clinical settings and therefore its importance, respectively.

8um 피치 SXGA급 비냉각 적외선 검출기 개발 및 환경성 평가

In the case of a thermal imaging system to which a uncooled infrared detector is applied, the application range is expanding in various ways in the field of military and civilian use. In particular, in the case of a military thermal system, it is required to develop a high-resolution infrared sensor to upgrade the system, and in the case of a civil thermal system, it is required to miniaturize and lighten the thermal detector to apply to various applications. By reducing the pixel pitch of infrared sensors from 17um pitch to 8um pitch size, it is easy to develop miniaturized and high-resolution sensors, but overcoming the problem of decreasing infrared sensor performance is the key to technology development. The structural separation of an area absorbing incident infrared rays and an area for thermal isolation is required to maximize the performance of an infrared sensor with a reduced pixel pitch, and to implement this, it is required to develop a multi-layered microbolometer. In this paper, we develop an SXGA-class (1280*1024) uncooled infrared detector with an 8um pixel pitch and fabricate using multilayered FPA(focal plane array) design techniques and 0.18um 3D MEMS technology design techniques to improve absorption area and thermal isolation reduction as the pitch decreases. For miniaturization and weight reduction of infrared detectors, ceramic packages were applied to manufacture uncooled infrared detectors of NETD 50 mK or less. In addition, environmental and reliability test evaluation of uncooled infrared detectors was performed to verify system applicability and practicality.

Detection of White Leaf Disease in Sugarcane Using Machine Learning Techniques over UAV Multispectral Images

Sugarcane white leaf phytoplasma (white leaf disease) in sugarcane crops is caused by a phytoplasma transmitted by leafhopper vectors. White leaf disease (WLD) occurs predominantly in some Asian countries and is a devastating global threat to sugarcane industries, especially Sri Lanka. Therefore, a feasible and an effective approach to precisely monitoring WLD infection is important, especially at the early pre-visual stage. This work presents the first approach on the preliminary detection of sugarcane WLD by using high-resolution multispectral sensors mounted on small unmanned aerial vehicles (UAVs) and supervised machine learning classifiers. The detection pipeline discussed in this paper was validated in a sugarcane field located in Gal-Oya Plantation, Hingurana, Sri Lanka. The pixelwise segmented samples were classified as ground, shadow, healthy plant, early symptom, and severe symptom. Four ML algorithms, namely XGBoost (XGB), random forest (RF), decision tree (DT), and K-nearest neighbors (KNN), were implemented along with different python libraries, vegetation indices (VIs), and five spectral bands to detect the WLD in the sugarcane field. The accuracy rate of 94% was attained in the XGB, RF, and KNN to detect WLD in the field. The top three vegetation indices (VIs) for separating healthy and infected sugarcane crops are modified soil-adjusted vegetation index (MSAVI), normalized difference vegetation index (NDVI), and excess green (ExG) in XGB, RF, and DT, while the best spectral band is red in XGB and RF and green in DT. The results revealed that this technology provides a dependable, more direct, cost-effective, and quick method for detecting WLD.