scholarly journals Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery

2021 ◽  
Vol 13 (11) ◽  
pp. 5389-5401
Author(s):  
Hou Jiang ◽  
Ling Yao ◽  
Ning Lu ◽  
Jun Qin ◽  
Tang Liu ◽  
...  
Keyword(s):  
Rapid Development ◽  
Model Performance ◽  
Detection Algorithm ◽  
Fine Tuning ◽  
Aerial Images ◽  
Photovoltaic Panel ◽  
Fine Grained ◽  
Automatic Information ◽  
Deep Networks ◽  
Direct Cross

Abstract. In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of the energy sector. Automatic information extraction based on deep learning requires high-quality labeled samples that should be collected at multiple spatial resolutions and under different backgrounds due to the diversity and variable scale of PVs. We established a PV dataset using satellite and aerial images with spatial resolutions of 0.8, 0.3, and 0.1 m, which focus on concentrated PVs, distributed ground PVs, and fine-grained rooftop PVs, respectively. The dataset contains 3716 samples of PVs installed on shrub land, grassland, cropland, saline–alkali land, and water surfaces, as well as flat concrete, steel tile, and brick roofs. The dataset is used to examine the model performance of different deep networks on PV segmentation. On average, an intersection over union (IoU) greater than 85 % is achieved. In addition, our experiments show that direct cross application between samples with different resolutions is not feasible and that fine-tuning of the pre-trained deep networks using target samples is necessary. The dataset can support more work on PV technology for greater value, such as developing a PV detection algorithm, simulating PV conversion efficiency, and estimating regional PV potential. The dataset is available from Zenodo on the following website: https://doi.org/10.5281/zenodo.5171712 (Jiang et al., 2021).

scholarly journals Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery

2021 ◽  
Author(s):  
Hou Jiang ◽  
Ling Yao ◽  
Ning Lu ◽  
Jun Qin ◽  
Tang Liu ◽  
...  
Keyword(s):  
Rapid Development ◽  
Model Performance ◽  
Detection Algorithm ◽  
Fine Tuning ◽  
Aerial Images ◽  
Photovoltaic Panel ◽  
Fine Grained ◽  
Automatic Information ◽  
Deep Networks ◽  
Direct Cross

Abstract. In the context of global carbon emission reduction, solar photovoltaics (PV) is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of energy sector. Automatic information extraction based on deep learning requires high-quality labelled samples that should be collected at multiple spatial resolutions and under different backgrounds due to the diversity and variable scale of PV. We established a PV dataset using satellite and aerial images with spatial resolutions of 0.8 m, 0.3 m and 0.1 m, which focus on concentrated PV, distributed ground PV and fine-grained rooftop PV, respectively. The dataset contains 3716 samples of PVs installed on shrub land, grassland, cropland, saline-alkali, and water surface, as well as flat concrete, steel tile, and brick roofs. We used this dataset to examine the model performance of different deep networks on PV segmentation, and on average an intersection over union (IoU) greater than 85 % was achieved. In addition, our experiments show that direct cross application between samples with different resolutions is not feasible, and fine-tuning of the pre-trained deep networks using target samples is necessary. The dataset can support more works on PVs for greater value, such as, developing PV detection algorithm, simulating PV conversion efficiency, and estimating regional PV potential. The dataset is available from Zenodo on the following website: https://doi.org/10.5281/zenodo.5171712 (Jiang et al. 2021).

Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings

2021 ◽  
pp. 1-18
Author(s):  
Hui Liu ◽  
Boxia He ◽  
Yong He ◽  
Xiaotian Tao
Keyword(s):  
Feature Extraction ◽  
Defect Detection ◽  
Surface Defect ◽  
Surface Defects ◽  
Detection Algorithm ◽  
Seal Ring ◽  
Fine Grained ◽  
Aerospace Applications ◽  
Surface Defect Detection ◽  
The Mean

The existing seal ring surface defect detection methods for aerospace applications have the problems of low detection efficiency, strong specificity, large fine-grained classification errors, and unstable detection results. Considering these problems, a fine-grained seal ring surface defect detection algorithm for aerospace applications is proposed. Based on analysis of the stacking process of standard convolution, heat maps of original pixels in the receptive field participating in the convolution operation are quantified and generated. According to the generated heat map, the feature extraction optimization method of convolution combinations with different dilation rates is proposed, and an efficient convolution feature extraction network containing three kinds of dilated convolutions is designed. Combined with the O-ring surface defect features, a multiscale defect detection network is designed. Before the head of multiscale classification and position regression, feature fusion tree modules are added to ensure the reuse and compression of the responsive features of different receptive fields on the same scale feature maps. Experimental results show that on the O-rings-3000 testing dataset, the mean condition accuracy of the proposed algorithm reaches 95.10% for 5 types of surface defects of aerospace O-rings. Compared with RefineDet, the mean condition accuracy of the proposed algorithm is only reduced by 1.79%, while the parameters and FLOPs are reduced by 35.29% and 64.90%, respectively. Moreover, the proposed algorithm has good adaptability to image blur and light changes caused by the cutting of imaging hardware, thus saving the cost.

scholarly journals Janus Face of Inflation Targeting_Walter_PrePrint

2019 ◽  
Author(s):  
Timo Walter
Keyword(s):  
Monetary Policy ◽  
Inflation Targeting ◽  
Recent Trend ◽  
Central Banks ◽  
Fine Tuning ◽  
Fine Grained ◽  
Prototype Development ◽  
The Us ◽  
Fundamental Uncertainty ◽  
Overall Effectiveness

In the 1980s, central banks around the world stumbled upon a new method for conducting theirmonetary policy: instead of the heavy-handed, „hydraulic“ manipulation of monetary aggregates,they learned to „govern the future“ by managing the expectations of market actors directly.New and better indicators and forecasts would provide the basis for a new communicativecoordination of markets expectations, permitting a more fine-grained and effective implementationof monetary policy, particular in controlling inflation.Focusing on the US Federal Reserve’s prototype development of inflation-targeting, this paper putsthis storyline to the test. Against the recent trend in sociology to conceive of expectations andfuturity as modes of coordination that thrive under conditions of (fundamental) uncertainty that defyrational calculation, I argue that futurity and the formation expectations inextricably depend onprior processes of formalization.Examining the transition to modern ‘inflation targeting’ monetary policy, I show how theeffectiveness of coordination by expectation is achieved by extensive processes of proceduralizationand standardization. While increasing the technical efficiency of fine-tuning expectations, thesegains are only possible because of the procedural narrowing of the scope of communicativeinteraction, which may significantly affect the overall effectiveness of this mode of coordination.I conclude with a call to more closely examine how formal and informal modes of coordination aremutually interdependent – and how the nature of their entanglements affects their effectiveness.

scholarly journals A feature fusion deep-projection convolution neural network for vehicle detection in aerial images

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0250782
Author(s):  
Bin Wang ◽  
Bin Xu
Keyword(s):  
Neural Network ◽  
Feature Fusion ◽  
Rapid Development ◽  
Vehicle Detection ◽  
Convolution Neural Network ◽  
Aerial Images ◽  
Semantic Features ◽  
General Object ◽  
High Level ◽  
The Impact

With the rapid development of Unmanned Aerial Vehicles, vehicle detection in aerial images plays an important role in different applications. Comparing with general object detection problems, vehicle detection in aerial images is still a challenging research topic since it is plagued by various unique factors, e.g. different camera angle, small vehicle size and complex background. In this paper, a Feature Fusion Deep-Projection Convolution Neural Network is proposed to enhance the ability to detect small vehicles in aerial images. The backbone of the proposed framework utilizes a novel residual block named stepwise res-block to explore high-level semantic features as well as conserve low-level detail features at the same time. A specially designed feature fusion module is adopted in the proposed framework to further balance the features obtained from different levels of the backbone. A deep-projection deconvolution module is used to minimize the impact of the information contamination introduced by down-sampling/up-sampling processes. The proposed framework has been evaluated by UCAS-AOD, VEDAI, and DOTA datasets. According to the evaluation results, the proposed framework outperforms other state-of-the-art vehicle detection algorithms for aerial images.

scholarly journals USING SEMANTICALLY PAIRED IMAGES TO IMPROVE DOMAIN ADAPTATION FOR THE SEMANTIC SEGMENTATION OF AERIAL IMAGES

2020 ◽  
Vol V-2-2020 ◽  
pp. 483-492
Author(s):  
D. Gritzner ◽  
J. Ostermann
Keyword(s):  
Time Window ◽  
Domain Adaptation ◽  
Geographical Area ◽  
Model Performance ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Training Data ◽  
Aerial Images ◽  
Target Domain ◽  
Training Examples

Abstract. Modern machine learning, especially deep learning, which is used in a variety of applications, requires a lot of labelled data for model training. Having an insufficient amount of training examples leads to models which do not generalize well to new input instances. This is a particular significant problem for tasks involving aerial images: often training data is only available for a limited geographical area and a narrow time window, thus leading to models which perform poorly in different regions, at different times of day, or during different seasons. Domain adaptation can mitigate this issue by using labelled source domain training examples and unlabeled target domain images to train a model which performs well on both domains. Modern adversarial domain adaptation approaches use unpaired data. We propose using pairs of semantically similar images, i.e., whose segmentations are accurate predictions of each other, for improved model performance. In this paper we show that, as an upper limit based on ground truth, using semantically paired aerial images during training almost always increases model performance with an average improvement of 4.2% accuracy and .036 mean intersection-over-union (mIoU). Using a practical estimate of semantic similarity, we still achieve improvements in more than half of all cases, with average improvements of 2.5% accuracy and .017 mIoU in those cases.

Colorisation of archival aerial imagery using deep learning

2021 ◽  
Author(s):  
Ryusei Ishii ◽  
Patrice Carbonneau ◽  
Hitoshi Miyamoto
Keyword(s):  
Deep Learning ◽  
Urban Expansion ◽  
Research Work ◽  
Fine Tuning ◽  
Aerial Images ◽  
Model Parameters ◽  
Style Transfer ◽  
Freeze Layer ◽  
Rgb Images ◽  
Japanese Rivers

<p>Archival imagery dating back to the mid-twentieth century holds information that pre-dates urban expansion and the worst impacts of climate change.  In this research, we examine deep learning colorisation methods applied to historical aerial images in Japan.  Specifically, we attempt to colorize monochrome images of river basins by applying the method of Neural Style Transfer (NST).    First, we created RGB orthomosaics (1m) for reaches of 3 Japanese rivers, the Kurobe, Ishikari, and Kinu rivers.  From the orthomosaics, we extract 60 thousand image tiles of `100 x100` pixels in order to train the CNN used in NST.  The Image tiles were classified into 6 classes: urban, river, forest, tree, grass, and paddy field.  Second, we use the VGG16 model pre-trained on ImageNet data in a transfer learning approach where we freeze a variable number of layers.  We fine-tuned the training epochs, learning rate, and frozen layers in VGG16 in order to derive the optimal CNN used in NST.  The fine tuning resulted in the F-measure accuracy of 0.961, 0.947, and 0.917 for the freeze layer in 7,11,15, respectively.  Third, we colorize monochrome aerial images by the NST with the retrained model weights.  Here used RGB images for 7 Japanese rivers and the corresponding grayscale versions to evaluate the present NST colorization performance.  The RMSE between the RGB and resultant colorized images showed the best performance with the model parameters of lower content layer (6), shallower freeze layer (7), and larger style/content weighting ratio (1.0 x10⁵).  The NST hyperparameter analysis indicated that the colorized images became rougher when the content layer selected deeper in the VGG model.  This is because the deeper the layer, the more features were extracted from the original image.  It was also confirmed that the Kurobe and Ishikari rivers indicated higher accuracy in colorisation.  It might come from the fact that the training dataset of the fine tuning was extracted from these river images.  Finally, we colorized historical monochrome images of Kurobe river with the best NST parameters, resulting in quality high enough compared with the RGB images.  The result indicated that the fine tuning of the NST model could achieve high performance to proceed further land cover classification in future research work.</p>

Using bootstrap procedures for testing the modular partition inferred via leading eigenvector community detection algorithm

2021 ◽  
Author(s):  
Oksana Vertsimakha ◽  
Igor Dzeverin
Keyword(s):  
Community Detection ◽  
Detection Algorithm ◽  
Fine Tuning ◽  
Modular Structure ◽  
Biological Organization ◽  
Detection Algorithms ◽  
Community Detection Algorithm ◽  
Numeric Data ◽  
Bootstrap Algorithm ◽  
Modular Structures

AbstractModularity and modular structures can be recognized at various levels of biological organization and in various domains of studies. Recently, algorithms based on network analysis came into focus. And while such a framework is a powerful tool in studying modular structure, those methods usually pose a problem of assessing statistical support for the obtained modular structures. One of the widely applied methods is the leading eigenvector, or Newman’s spectral community detection algorithm. We conduct a brief overview of the method, including a comparison with some other community detection algorithms and explore a possible fine-tuning procedure. Finally, we propose an adapted bootstrap-based procedure based on Shimodaira’s multiscale bootstrap algorithm to derive approximately unbiased p-values for the module partitions of observations datasets. The proposed procedure also gives a lot of freedom to the researcher in constructing the network construction from the raw numeric data, and can be applied to various types of data and used in diverse problems concerning modular structure. We provide an R language code for all the calculations and the visualization of the obtained results for the researchers interested in using the procedure.

scholarly journals Mask R-CNN Refitting Strategy for Plant Counting and Sizing in UAV Imagery

2020 ◽  
Vol 12 (18) ◽  
pp. 3015 ◽  
Author(s):  
Mélissande Machefer ◽  
François Lemarchand ◽  
Virginie Bonnefond ◽  
Alasdair Hitchins ◽  
Panagiotis Sidiropoulos
Keyword(s):  
Deep Learning ◽  
Fine Tuning ◽  
Aerial Images ◽  
Individual Plant ◽  
Low Density ◽  
Tracking Accuracy ◽  
Potato Plants ◽  
The Individual ◽  
Segmentation Task ◽  
Vision Algorithm

This work introduces a method that combines remote sensing and deep learning into a framework that is tailored for accurate, reliable and efficient counting and sizing of plants in aerial images. The investigated task focuses on two low-density crops, potato and lettuce. This double objective of counting and sizing is achieved through the detection and segmentation of individual plants by fine-tuning an existing deep learning architecture called Mask R-CNN. This paper includes a thorough discussion on the optimal parametrisation to adapt the Mask R-CNN architecture to this novel task. As we examine the correlation of the Mask R-CNN performance to the annotation volume and granularity (coarse or refined) of remotely sensed images of plants, we conclude that transfer learning can be effectively used to reduce the required amount of labelled data. Indeed, a previously trained Mask R-CNN on a low-density crop can improve performances after training on new crops. Once trained for a given crop, the Mask R-CNN solution is shown to outperform a manually-tuned computer vision algorithm. Model performances are assessed using intuitive metrics such as Mean Average Precision (mAP) from Intersection over Union (IoU) of the masks for individual plant segmentation and Multiple Object Tracking Accuracy (MOTA) for detection. The presented model reaches an mAP of 0.418 for potato plants and 0.660 for lettuces for the individual plant segmentation task. In detection, we obtain a MOTA of 0.781 for potato plants and 0.918 for lettuces.

scholarly journals Research on Fine-Grained Classification of Rumors in Public Crisis ——Take the COVID-19 incident as an example

2020 ◽  
Vol 179 ◽  
pp. 02027
Author(s):  
Shuaipu Chen
Keyword(s):  
Reference Value ◽  
Training Model ◽  
Fine Tuning ◽  
The Public ◽  
Fine Grained ◽  
Model Method ◽  
Public Crisis ◽  
Sentence Level ◽  
Good Classification

[Purpose / Meaning] Rumors are frequent in the COVID-19 epidemic crisis. In order to unite the power of dispelling rumors of various media platforms to help to break the rumors in a timely and professional manner, this article has designed a new fine-grained classification of rumors about COVID-19 based on the BERT model. [Method / Process] Based on the rumor data of several mainstream rumor refuting platforms, the pre-training model of BERT was used to fine-tuning in the context of COVID-19 events to obtain the feature vector representation of the rumor sentence level to achieve fine-grained classification, and a comparative experiment was conducted with the TextCNN and TextRNN models. [Result / Conclusion] The results show that the classificationF1 value of the model designed in this paper reaches 98.34%, which is higher than the TextCNN and TextRNN models by 2%, indicating that the model in this paper has a good classification judgment ability for COVID-19 rumors, and provides certain reference value for promoting the coordinated refuting of rumors during the public crisis.

scholarly journals RF-SML: A SAR-Based Multi-Granular and Real-Time Localization Method for RFID Tags

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1447
Author(s):  
Yue Jiang ◽  
Yongtao Ma ◽  
Hankai Liu ◽  
Yunlei Zhang
Keyword(s):  
Rapid Development ◽  
Target Position ◽  
Coarse Grained ◽  
Uhf Rfid ◽  
Localization Accuracy ◽  
Fine Grained ◽  
Antenna Phase ◽  
Phase Calibration ◽  
Commercial Off The Shelf ◽  
Antenna Phase Center

With the rapid development of the Internet of Things (IoT) technology, location based service in context awareness has received increasing attention. As one of the main localization technologies, UHF RFID technology has been widely used in many fields of life and industry due to its advantages. In this article, we introduce a RFID-based system RF-SML, which is a method for quickly and accurately locating static objects via the tag and mobile reader. Specifically, the method utilizes the idea of multi-granularity in order to find the high-probability region of the target position by reconstructing the reflection coefficient of the scene in the coarse-grained localization stage. Subsequently, in the fine-grained localization stage, the grid is traversed in this area to calculate the corresponding evaluation factor to determine the final position result, thereby reducing the time-consuming of localization calculation. At the same time, it uses phase calibration to remove the phase offsets that are caused by the hardware device and the antenna phase center, thereby obtaining higher localization accuracy. We conduct experiments to verify the performance of RF-SML with commercial-off-the-shelf (COTS) RFID equipment. The results show that the proposed method can efficiently achieve the centimeter-level positioning of objects.

Sign in / Sign up

Export Citation Format

Share Document