Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

Hoeser, Thorsten; Bachofer, Felix; Kuenzer, Claudia

doi:10.3390/rs12183053

Cited by 129 publications

(132 citation statements)

References 387 publications

(611 reference statements)

Supporting

Mentioning

130

Contrasting

Order By: Relevance

“…The question is, can remote sensing-based damage assessment contribute to economic loss estimation on larger scale? Usage of VHR resolution imagery and machine learning approaches [ 146 , 147 , 148 , 149 ] to investigate the benefit in early locust damage and locust band detection. The question is, can dense locust bands be identified in VHR imagery?…”

Section: Discussionmentioning

confidence: 99%

Application of Remote Sensing Data for Locust Research and Management—A Review

Klein

Oppelt

Kuenzer

2021

Insects

Self Cite

View full text Add to dashboard Cite

Recently, locust outbreaks around the world have destroyed agricultural and natural vegetation and caused massive damage endangering food security. Unusual heavy rainfalls in habitats of the desert locust (Schistocerca gregaria) and lack of monitoring due to political conflicts or inaccessibility of those habitats lead to massive desert locust outbreaks and swarms migrating over the Arabian Peninsula, East Africa, India and Pakistan. At the same time, swarms of the Moroccan locust (Dociostaurus maroccanus) in some Central Asian countries and swarms of the Italian locust (Calliptamus italicus) in Russia and China destroyed crops despite developed and ongoing monitoring and control measurements. These recent events underline that the risk and damage caused by locust pests is as present as ever and affects 100 million of human lives despite technical progress in locust monitoring, prediction and control approaches. Remote sensing has become one of the most important data sources in locust management. Since the 1980s, remote sensing data and applications have accompanied many locust management activities and contributed to an improved and more effective control of locust outbreaks and plagues. Recently, open-access remote sensing data archives as well as progress in cloud computing provide unprecedented opportunity for remote sensing-based locust management and research. Additionally, unmanned aerial vehicle (UAV) systems bring up new prospects for a more effective and faster locust control. Nevertheless, the full capacity of available remote sensing applications and possibilities have not been exploited yet. This review paper provides a comprehensive and quantitative overview of international research articles focusing on remote sensing application for locust management and research. We reviewed 110 articles published over the last four decades, and categorized them into different aspects and main research topics to summarize achievements and gaps for further research and application development. The results reveal a strong focus on three species—the desert locust, the migratory locust (Locusta migratoria), and the Australian plague locust (Chortoicetes terminifera)—and corresponding regions of interest. There is still a lack of international studies for other pest species such as the Italian locust, the Moroccan locust, the Central American locust (Schistocerca piceifrons), the South American locust (Schistocerca cancellata), the brown locust (Locustana pardalina) and the red locust (Nomadacris septemfasciata). In terms of applied sensors, most studies utilized Advanced Very-High-Resolution Radiometer (AVHRR), Satellite Pour l’Observation de la Terre VEGETATION (SPOT-VGT), Moderate-Resolution Imaging Spectroradiometer (MODIS) as well as Landsat data focusing mainly on vegetation monitoring or land cover mapping. Application of geomorphological metrics as well as radar-based soil moisture data is comparably rare despite previous acknowledgement of their importance for locust outbreaks. Despite great advance and usage of available remote sensing resources, we identify several gaps and potential for future research to further improve the understanding and capacities of the use of remote sensing in supporting locust outbreak- research and management.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Remote Sensing Data for Locust Research and Management—A Review

Klein

Oppelt

Kuenzer

2021

Insects

Self Cite

View full text Add to dashboard Cite

show abstract

“…These regions then become the unit for subsequent analysis and classification [48,50,51]. CNN-based DL for semantic segmentation further expands the incorporation of spatial context information, and offers a natural extension of prior methods [52][53][54][55].…”

Section: Deep Learning Semantic Segmentationmentioning

confidence: 99%

“…By applying a bias and a non-linear activation function while iteratively adjusting the weights through multiple passes, or epochs, on the training data while monitoring a loss metric, patterns in the data can be learned to make new predictions [46,56,57]. DL expands upon this ML framework to include many hidden layers and associated nodes (i.e., tens or hundreds), which can allow for the modeling of more complex patterns and a greater abstraction of the input data [52][53][54][55].…”

Section: Deep Learning Semantic Segmentationmentioning

confidence: 99%

“…Initially, CNNs were applied to scene labelling problems where an entire image is categorized. Advancements in CNNs have allowed for semantic segmentation, where each pixel is classified, similar to traditional remote sensing classification methods, or instance segmentation, where individual instances of a class are differentiated [52][53][54][55]. We make use of semantic segmentation in this study.…”

Section: Deep Learning Semantic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Segmentation Deep Learning for Extracting Surface Mine Extents from Historic Topographic Maps

et al. 2020

View full text Add to dashboard Cite

Historic topographic maps, which are georeferenced and made publicly available by the United States Geological Survey (USGS) and the National Map’s Historical Topographic Map Collection (HTMC), are a valuable source of historic land cover and land use (LCLU) information that could be used to expand the historic record when combined with data from moderate spatial resolution Earth observation missions. This is especially true for landscape disturbances that have a long and complex historic record, such as surface coal mining in the Appalachian region of the eastern United States. In this study, we investigate this specific mapping problem using modified UNet semantic segmentation deep learning (DL), which is based on convolutional neural networks (CNNs), and a large example dataset of historic surface mine disturbance extents from the USGS Geology, Geophysics, and Geochemistry Science Center (GGGSC). The primary objectives of this study are to (1) evaluate model generalization to new geographic extents and topographic maps and (2) to assess the impact of training sample size, or the number of manually interpreted topographic maps, on model performance. Using data from the state of Kentucky, our findings suggest that DL semantic segmentation can detect surface mine disturbance features from topographic maps with a high level of accuracy (Dice coefficient = 0.902) and relatively balanced omission and commission error rates (Precision = 0.891, Recall = 0.917). When the model is applied to new topographic maps in Ohio and Virginia to assess generalization, model performance decreases; however, performance is still strong (Ohio Dice coefficient = 0.837 and Virginia Dice coefficient = 0.763). Further, when reducing the number of topographic maps used to derive training image chips from 84 to 15, model performance was only slightly reduced, suggesting that models that generalize well to new data and geographic extents may not require a large training set. We suggest the incorporation of DL semantic segmentation methods into applied workflows to decrease manual digitizing labor requirements and call for additional research associated with applying semantic segmentation methods to alternative cartographic representations to supplement research focused on multispectral image analysis and classification.

show abstract

“…CNNs have been increasingly established as adaptive methods for new challenges in the field of earth observation (EO). Hoeser et al provided a comprehensive overview of the impact of CNNs on EO applications [25,26].…”

Section: Introductionmentioning

confidence: 99%

Techniques for the Automatic Detection and Hiding of Sensitive Targets in Emergency Mapping Based on Remote Sensing Data

Qiu

Liang

et al. 2021

IJGI

View full text Add to dashboard Cite

Emergency remote sensing mapping can provide support for decision making in disaster assessment or disaster relief, and therefore plays an important role in disaster response. Traditional emergency remote sensing mapping methods use decryption algorithms based on manual retrieval and image editing tools when processing sensitive targets. Although these traditional methods can achieve target recognition, they are inefficient and cannot meet the high time efficiency requirements of disaster relief. In this paper, we combined an object detection model with a generative adversarial network model to build a two-stage deep learning model for sensitive target detection and hiding in remote sensing images, and we verified the model performance on the aircraft object processing problem in remote sensing mapping. To improve the experimental protocol, we introduced a modification to the reconstruction loss function, candidate frame optimization in the region proposal network, the PointRend algorithm, and a modified attention mechanism based on the characteristics of aircraft objects. Experiments revealed that our method is more efficient than traditional manual processing; the precision is 94.87%, the recall is 84.75% higher than that of the original mask R-CNN model, and the F1-score is 44% higher than that of the original model. In addition, our method can quickly and intelligently detect and hide sensitive targets in remote sensing images, thereby shortening the time needed for emergency mapping.

show abstract

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

Cited by 129 publications

References 387 publications

Application of Remote Sensing Data for Locust Research and Management—A Review

Application of Remote Sensing Data for Locust Research and Management—A Review

Semantic Segmentation Deep Learning for Extracting Surface Mine Extents from Historic Topographic Maps

Techniques for the Automatic Detection and Hiding of Sensitive Targets in Emergency Mapping Based on Remote Sensing Data

Contact Info

Product

Resources

About