Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends

Hoeser, Thorsten; Kuenzer, Claudia

doi:10.3390/rs12101667

Cited by 247 publications

(214 citation statements)

References 144 publications

Supporting

Mentioning

163

Contrasting

Unclassified

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

“…One of the most important characteristics of utilizing CNNs in object detection is that the CNN can obtain essential features by itself. Furthermore, it can build and use more abstract concepts [18].…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5

et al. 2021

View full text Add to dashboard Cite

The apple target recognition algorithm is one of the core technologies of the apple picking robot. However, most of the existing apple detection algorithms cannot distinguish between the apples that are occluded by tree branches and occluded by other apples. The apples, grasping end-effector and mechanical picking arm of the robot are very likely to be damaged if the algorithm is directly applied to the picking robot. Based on this practical problem, in order to automatically recognize the graspable and ungraspable apples in an apple tree image, a light-weight apple targets detection method was proposed for picking robot using improved YOLOv5s. Firstly, BottleneckCSP module was improved designed to BottleneckCSP-2 module which was used to replace the BottleneckCSP module in backbone architecture of original YOLOv5s network. Secondly, SE module, which belonged to the visual attention mechanism network, was inserted to the proposed improved backbone network. Thirdly, the bonding fusion mode of feature maps, which were inputs to the target detection layer of medium size in the original YOLOv5s network, were improved. Finally, the initial anchor box size of the original network was improved. The experimental results indicated that the graspable apples, which were unoccluded or only occluded by tree leaves, and the ungraspable apples, which were occluded by tree branches or occluded by other fruits, could be identified effectively using the proposed improved network model in this study. Specifically, the recognition recall, precision, mAP and F1 were 91.48%, 83.83%, 86.75% and 87.49%, respectively. The average recognition time was 0.015 s per image. Contrasted with original YOLOv5s, YOLOv3, YOLOv4 and EfficientDet-D0 model, the mAP of the proposed improved YOLOv5s model increased by 5.05%, 14.95%, 4.74% and 6.75% respectively, the size of the model compressed by 9.29%, 94.6%, 94.8% and 15.3% respectively. The average recognition speeds per image of the proposed improved YOLOv5s model were 2.53, 1.13 and 3.53 times of EfficientDet-D0, YOLOv4 and YOLOv3 and model, respectively. The proposed method can provide technical support for the real-time accurate detection of multiple fruit targets for the apple picking robot.

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 I: Evolution and Recent Trends

Cited by 247 publications

References 144 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

A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5

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

Contact Info

Product

Resources

About