scholarly journals Comparing Interpretation of High-Resolution Aerial Imagery by Humans and Artificial Intelligence to Detect an Invasive Tree Species

2021 ◽  
Vol 13 (17) ◽  
pp. 3503
Author(s):  
Roberto Rodriguez ◽  
Ryan L. Perroy ◽  
James Leary ◽  
Daniel Jenkins ◽  
Max Panoff ◽  
...  
Keyword(s):  
Image Analysis ◽  
High Resolution ◽  
Large Scale ◽  
Invasive Plant ◽  
Image Interpretation ◽  
Cost Effective ◽  
Human Detection ◽  
Aerial Imagery ◽  
Miconia Calvescens ◽  
Significant Factors

Timely, accurate maps of invasive plant species are critical for making appropriate management decisions to eliminate emerging target populations or contain infestations. High-resolution aerial imagery is routinely used to map, monitor, and detect invasive plant populations. While conventional image interpretation involving human analysts is straightforward, it can require high demands for time and resources to produce useful intelligence. We compared the performance of human analysts with a custom Retinanet-based deep convolutional neural network (DNN) for detecting individual miconia (Miconia calvescens DC) plants, using high-resolution unmanned aerial system (UAS) imagery collected over lowland tropical forests in Hawai’i. Human analysts (n = 38) examined imagery at three linear scrolling speeds (100, 200 and 300 px/s), achieving miconia detection recalls of 74 ± 3%, 60 ± 3%, and 50 ± 3%, respectively. The DNN achieved 83 ± 3% recall and completed the image analysis in 1% of the time of the fastest scrolling speed tested. Human analysts could discriminate large miconia leaf clusters better than isolated individual leaves, while the DNN detection efficacy was independent of leaf cluster size. Optically, the contrast in the red and green color channels and all three (i.e., red, green, and blue) signal to clutter ratios (SCR) were significant factors for human detection, while only the red channel contrast, and the red and green SCRs were significant factors for the DNN. A linear cost analysis estimated the operational use of a DNN to be more cost effective than human photo interpretation when the cumulative search area exceeds a minimum area. For invasive species like miconia, which can stochastically spread propagules across thousands of ha, the DNN provides a more efficient option for detecting incipient, immature miconia across large expanses of forested canopy. Increasing operational capacity for large-scale surveillance with a DNN-based image analysis workflow can provide more rapid comprehension of invasive plant abundance and distribution in forested watersheds and may become strategically vital to containing these invasions.

scholarly journals Detection and spatiotemporal analysis of methane ebullition on thermokarst lake ice using high-resolution optical aerial imagery

2016 ◽  
Vol 13 (1) ◽  
pp. 27-44 ◽  
Author(s):  
P. R. Lindgren ◽  
G. Grosse ◽  
K. M. Walter Anthony ◽  
F. J. Meyer
Keyword(s):  
Image Analysis ◽  
High Resolution ◽  
Image Acquisition ◽  
Optical Image ◽  
Aerial Imagery ◽  
Accurate Estimation ◽  
Lake Ice ◽  
Thermokarst Lakes ◽  
Thermokarst Lake ◽  
Methane Ebullition

Abstract. Thermokarst lakes are important emitters of methane, a potent greenhouse gas. However, accurate estimation of methane flux from thermokarst lakes is difficult due to their remoteness and observational challenges associated with the heterogeneous nature of ebullition. We used high-resolution (9–11 cm) snow-free aerial images of an interior Alaskan thermokarst lake acquired 2 and 4 days following freeze-up in 2011 and 2012, respectively, to detect and characterize methane ebullition seeps and to estimate whole-lake ebullition. Bubbles impeded by the lake ice sheet form distinct white patches as a function of bubbling when lake ice grows downward and around them, trapping the gas in the ice. Our aerial imagery thus captured a snapshot of bubbles trapped in lake ice during the ebullition events that occurred before the image acquisition. Image analysis showed that low-flux A- and B-type seeps are associated with low brightness patches and are statistically distinct from high-flux C-type and hotspot seeps associated with high brightness patches. Mean whole-lake ebullition based on optical image analysis in combination with bubble-trap flux measurements was estimated to be 174 ± 28 and 216 ± 33 mL gas m−2 d−1 for the years 2011 and 2012, respectively. A large number of seeps demonstrated spatiotemporal stability over our 2-year study period. A strong inverse exponential relationship (R2 >  =  0.79) was found between the percent of the surface area of lake ice covered with bubble patches and distance from the active thermokarst lake margin. Even though the narrow timing of optical image acquisition is a critical factor, with respect to both atmospheric pressure changes and snow/no-snow conditions during early lake freeze-up, our study shows that optical remote sensing is a powerful tool to map ebullition seeps on lake ice, to identify their relative strength of ebullition, and to assess their spatiotemporal variability.

scholarly journals High-Resolution Melting Is a Sensitive, Cost-Effective, Time-Saving Technique for BRAF V600E Detection in Thyroid FNAB Washing Liquid: A Prospective Cohort Study

2015 ◽  
Vol 4 (2) ◽  
pp. 73-81 ◽  
Author(s):  
Marco Marino ◽  
Maria Laura Monzani ◽  
Giulia Brigante ◽  
Katia Cioni ◽  
Bruno Madeo ◽  
...  
Keyword(s):  
Cohort Study ◽  
High Resolution ◽  
Molecular Analysis ◽  
Prospective Cohort Study ◽  
Prospective Cohort ◽  
Large Scale ◽  
High Resolution Melting ◽  
Cost Effective ◽  
Braf V600e Mutation ◽  
Braf V600e

Objective: The diagnostic accuracy of thyroid fine needle aspiration biopsy (FNAB) can be improved by the combination of cytological and molecular analysis. In this study, washing liquids of FNAB (wFNAB) were tested for the BRAF V600E mutation, using the sensitive and cost-effective technique called high-resolution melting (HRM). The aim was to demonstrate the feasibility of BRAF analysis in wFNAB and its diagnostic utility, combined with cytology. Design: Prospective cohort study. Methods: 481 patients, corresponding to 648 FNAB samples, were subjected to both cytological (on cells smeared onto a glass slide) and molecular analysis (on fluids obtained washing the FNAB needle with 1 ml of saline) of the same aspiration. BRAF V600E analysis was performed by HRM after methodological validation for application to wFNAB (technique sensitivity: 5.4%). Results: The cytological results of the FNAB were: 136 (21%) nondiagnostic (THY1); 415 (64%) benign (THY2); 80 (12.4%) indeterminate (THY3); 9 (1.4%) suspicious for malignancy (THY4); 8 (1.2%) diagnostic of malignancy (THY5). The BRAF V600E mutation was found in 5 THY2, 2 THY3, 6 THY4 and 6 THY5 samples. Papillary carcinoma diagnosis was histologically confirmed in all BRAF+ thyroidectomized patients. BRAF combined with cytology improved the diagnostic value compared to cytology alone in a subgroup of 74 operated patients. Conclusions: HRM was demonstrated to be a feasible method for BRAF analysis in wFNAB. Thanks to its sensitivity and cost-effectiveness, it might be routinely used on a large scale in clinical practice. In perspective, standby wFNAB samples could be analyzed a posteriori in case of indeterminate cytology and/or suspicious findings on ultrasound.

scholarly journals High-resolution prestack seismic inversion using a hybrid FISTA least-squares strategy

Geophysics ◽  
2013 ◽  
Vol 78 (5) ◽  
pp. R185-R195 ◽  
Author(s):  
Daniel O. Pérez ◽  
Danilo R. Velis ◽  
Mauricio D. Sacchi
Keyword(s):  
High Resolution ◽  
Least Squares ◽  
Large Scale ◽  
Cost Effective ◽  
Seismic Inversion ◽  
Iterative Solvers ◽  
Gradient Algorithm ◽  
Inversion Method ◽  
Thresholding Algorithm ◽  
Sparse Solutions

A new inversion method to estimate high-resolution amplitude-versus-angle attributes (AVA) attributes such as intercept and gradient from prestack data is presented. The proposed technique promotes sparse-spike reflectivities that, when convolved with the source wavelet, fit the observed data. The inversion is carried out using a hybrid two-step strategy that combines fast iterative shrinkage-thresholding algorithm (FISTA) and a standard least-squares (LS) inversion. FISTA, which can be viewed as an extension of the classical gradient algorithm, provides sparse solutions by minimizing the misfit between the modeled and the observed data, and the [Formula: see text]-norm of the solution. FISTA is used to estimate the location in time of the main reflectors. Then, LS is used to retrieve the appropriate reflectivity amplitudes that honor the data. FISTA, like other iterative solvers for [Formula: see text]-norm regularization, does not require matrices in explicit form, making it easy to apply, economic in computational terms, and adequate for solving large-scale problems. As a consequence, the FISTA+LS strategy represents a simple and cost-effective new procedure to solve the AVA inversion problem. Results on synthetic and field data show that the proposed hybrid method can obtain high-resolution AVA attributes from noisy observations, making it an interesting alternative to conventional methods.

scholarly journals MXtrodes: MXene-infused bioelectronic interfaces for multiscale electrophysiology and stimulation

2021 ◽  
Author(s):  
Nicolette Driscoll ◽  
Brian Erickson ◽  
Brendan B. Murphy ◽  
Andrew G. Richardson ◽  
Gregory Robbins ◽  
...  
Keyword(s):  
High Resolution ◽  
Animal Models ◽  
Electrochemical Properties ◽  
Large Scale ◽  
Treatment Strategies ◽  
Small Animal ◽  
Cost Effective ◽  
Solution Processing ◽  
Small Animal Models ◽  
Paradigm Shifting

Soft bioelectronic interfaces for mapping and modulating excitable networks at high resolution and at large scale can enable paradigm-shifting diagnostics, monitoring, and treatment strategies. Yet, current technologies largely rely on materials and fabrication schemes that are expensive, do not scale, and critically limit the maximum attainable resolution and coverage. Solution processing is a cost-effective manufacturing alternative, but biocompatible conductive inks matching the performance of conventional metals are lacking. Here, we introduce MXtrodes, a novel class of soft, high-resolution, large-scale bioelectronic interfaces enabled by Ti3C2 MXene and scalable solution processing. We show that the electrochemical properties of MXtrodes exceed those of conventional materials, and do not require conductive gels when used in epidermal electronics. Furthermore, we validate MXtrodes in a number of applications ranging from mapping large scale neuromuscular networks in humans to delivering cortical microstimulation in small animal models. Finally, we demonstrate that MXtrodes are compatible with standard clinical neuroimaging modalities.

scholarly journals CHARACTERISTICS OF TEXTURE INDEX OF DAMAGED BUILDINGS USING TIME-SERIES HIGH-RESOLUTION OPTICAL SATELLITE IMAGES

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 1709-1714
Author(s):  
M. Sonobe
Keyword(s):  
Time Series ◽  
High Resolution ◽  
Texture Analysis ◽  
Large Scale ◽  
Satellite Images ◽  
Image Interpretation ◽  
High Resolution Satellite Images ◽  
Survey Results ◽  
Occurrence Matrix ◽  
Optical Satellite Images

Abstract. A large-scale disaster has occurred due to the earthquake. In particular, 20% of the world's earthquakes with a magnitude of 6 or more occur near Japan. Damage analysis of buildings by image analysis have been effectively carried out using optical high-resolution satellite images and aerial photograph with spatial resolution of about 2 m or less. In this study, the damaged buildings caused by large-scale and continuous earthquakes in Kumamoto, Japan that occurred in April 2016 was selected as a typical example of damaged buildings. For these earthquake event, the applicability of damage distribution of buildings and recovery/restoration status by texture analysis was examined. The applicability of the representative in the dissimilarity texture analysis methods Gray- Level Co-occurrence Matrix (GLCM) method by image interpretation in the case of a large number of collapsed and wrecked buildings in a wide area was assessed. These results suggest that dissimilarity was applicable to the extraction of damaged and removed buildings in the event of such an earthquake. In addition, the analysis results were appropriately evaluated by comparing the field survey results with the image interpretation results of the pan-sharpened image. From these results, we confirmed the effectiveness of texture analysis using time-series high-resolution satellite images in grasping the damaged buildings before and immediately after the disaster and in the restoration situation 1 year after the disaster.

scholarly journals OBJECTS GROUPING FOR SEGMENTATION OF ROADS NETWORK IN HIGH RESOLUTION IMAGES OF URBAN AREAS

2016 ◽  
Vol XLI-B7 ◽  
pp. 897-902 ◽  
Author(s):  
M. Maboudi ◽  
J. Amini ◽  
M. Hahn
Keyword(s):  
Image Analysis ◽  
High Resolution ◽  
Urban Areas ◽  
Traffic Management ◽  
Large Scale ◽  
Route Planning ◽  
Technological Advancement ◽  
Image Objects ◽  
High Resolution Images ◽  
Road Segments

Updated road databases are required for many purposes such as urban planning, disaster management, car navigation, route planning, traffic management and emergency handling. In the last decade, the improvement in spatial resolution of VHR civilian satellite sensors – as the main source of large scale mapping applications – was so considerable that GSD has become finer than size of common urban objects of interest such as building, trees and road parts. This technological advancement pushed the development of “Object-based Image Analysis (OBIA)” as an alternative to pixel-based image analysis methods. <br><br> Segmentation as one of the main stages of OBIA provides the image objects on which most of the following processes will be applied. Therefore, the success of an OBIA approach is strongly affected by the segmentation quality. In this paper, we propose a purpose-dependent refinement strategy in order to group road segments in urban areas using maximal similarity based region merging. For investigations with the proposed method, we use high resolution images of some urban sites. The promising results suggest that the proposed approach is applicable in grouping of road segments in urban areas.

scholarly journals OBJECTS GROUPING FOR SEGMENTATION OF ROADS NETWORK IN HIGH RESOLUTION IMAGES OF URBAN AREAS

2016 ◽  
Vol XLI-B7 ◽  
pp. 897-902 ◽  
Author(s):  
M. Maboudi ◽  
J. Amini ◽  
M. Hahn
Keyword(s):  
Image Analysis ◽  
High Resolution ◽  
Urban Areas ◽  
Traffic Management ◽  
Large Scale ◽  
Route Planning ◽  
Technological Advancement ◽  
Image Objects ◽  
High Resolution Images ◽  
Road Segments

Updated road databases are required for many purposes such as urban planning, disaster management, car navigation, route planning, traffic management and emergency handling. In the last decade, the improvement in spatial resolution of VHR civilian satellite sensors – as the main source of large scale mapping applications – was so considerable that GSD has become finer than size of common urban objects of interest such as building, trees and road parts. This technological advancement pushed the development of “Object-based Image Analysis (OBIA)” as an alternative to pixel-based image analysis methods. <br><br> Segmentation as one of the main stages of OBIA provides the image objects on which most of the following processes will be applied. Therefore, the success of an OBIA approach is strongly affected by the segmentation quality. In this paper, we propose a purpose-dependent refinement strategy in order to group road segments in urban areas using maximal similarity based region merging. For investigations with the proposed method, we use high resolution images of some urban sites. The promising results suggest that the proposed approach is applicable in grouping of road segments in urban areas.

scholarly journals A modified protocol of Capture-C allows affordable and flexible high-resolution promoter interactome analysis

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Arkadiy K. Golov ◽  
Dmitrii A. Abashkin ◽  
Nikolay V. Kondratyev ◽  
Sergey V. Razin ◽  
Alexey A. Gavrilov ◽  
...  
Keyword(s):  
High Resolution ◽  
Large Scale ◽  
Cost Effective ◽  
Probe Design ◽  
Functional Link ◽  
Chromosome Conformation ◽  
Transcription Start Sites ◽  
Relative Closeness ◽  
Cost Effective Alternative ◽  
Regulatory Sites

Abstract Large-scale epigenomic projects have mapped hundreds of thousands of potential regulatory sites in the human genome, but only a small proportion of these elements are proximal to transcription start sites. It is believed that the majority of these sequences are remote promoter-activating genomic sites scattered within several hundreds of kilobases from their cognate promoters and referred to as enhancers. It is still unclear what principles, aside from relative closeness in the linear genome, determine which promoter(s) is controlled by a given enhancer; however, this understanding is of great fundamental and clinical relevance. In recent years, C-methods (chromosome conformation capture-based methods) have become a powerful tool for the identification of enhancer–promoter spatial contacts that, in most cases, reflect their functional link. Here, we describe a new hybridisation-based promoter Capture-C protocol that makes use of biotinylated dsDNA probes generated by PCR from a custom pool of long oligonucleotides. The described protocol allows high-resolution promoter interactome description, providing a flexible and cost-effective alternative to the existing promoter Capture-C modifications. Based on the obtained data, we propose several tips on probe design that could potentially improve the results of future experiments.

Sign in / Sign up

Export Citation Format

Share Document