arXiv subjects

Liangpei Zhang

Publications and source records attributed to Liangpei Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2019

Mapping PM2.5 concentration at sub-km level resolution: a dual-scale retrieval method

Satellite-based retrieval has become a popular PM2.5 monitoring method currently. To improve the retrieval performance, multiple variables are usually introduced as auxiliary variable in addition to aerosol optical depth (AOD). Different kinds of variables are usually at different resolutions varying from sub-kilometers to dozens of kilometers. Generally, when doing the retrieval, variables at different resolutions are resampled to the same resolution as the AOD product to keep the scale consistency. A deficiency of doing this is that the information contained in the scale difference is discarded. To fully utilize the information contained at different scales, a dual-scale retrieval method is proposed in this study. At the first stage, variables which influence PM2.5 concentration at large scale were used for PM2.5 retrieval at coarse resolution. Then at the second stage, variables which affect PM2.5 distribution in finer scale, were used for the further PM2.5 retrieval at high resolution (sub-km level resolution) with the retrieved PM2.5 at the first stage at coarser resolution also as input. In this study, four different retrieval models including multiple linear regression (MLR), geographically weighted regression (GWR), random forest (RF) and generalized regression neural network (GRNN) are adopted to test the performance of the dual-scale retrieval method. Compared with the traditional retrieval method, the proposed dual-scale retrieval method can achieve PM2.5 mapping at finer resolution and with higher accuracy. Dual-scale retrieval can fully utilize the information contained at different scales, thus achieving a higher resolution and accuracy. It can be used for the generation of quantitative remote sensing products in various fields, and promote the improvement of the quality of quantitative remote sensing products.

physics.ao-ph↗

arXiv2019

DOTA: A Large-scale Dataset for Object Detection in Aerial Images

Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in natural scenes, such successes have been slow to aerial imagery, not only because of the huge variation in the scale, orientation and shape of the object instances on the earth's surface, but also due to the scarcity of well-annotated datasets of objects in aerial scenes. To advance object detection research in Earth Vision, also known as Earth Observation and Remote Sensing, we introduce a large-scale Dataset for Object deTection in Aerial images (DOTA). To this end, we collect $2806$ aerial images from different sensors and platforms. Each image is of the size about 4000-by-4000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. These DOTA images are then annotated by experts in aerial image interpretation using $15$ common object categories. The fully annotated DOTA images contains $188,282$ instances, each of which is labeled by an arbitrary (8 d.o.f.) quadrilateral To build a baseline for object detection in Earth Vision, we evaluate state-of-the-art object detection algorithms on DOTA. Experiments demonstrate that DOTA well represents real Earth Vision applications and are quite challenging.

cs.CV↗

arXiv2019

Exploring Representativeness and Informativeness for Active Learning

How can we find a general way to choose the most suitable samples for training a classifier? Even with very limited prior information? Active learning, which can be regarded as an iterative optimization procedure, plays a key role to construct a refined training set to improve the classification performance in a variety of applications, such as text analysis, image recognition, social network modeling, etc. Although combining representativeness and informativeness of samples has been proven promising for active sampling, state-of-the-art methods perform well under certain data structures. Then can we find a way to fuse the two active sampling criteria without any assumption on data? This paper proposes a general active learning framework that effectively fuses the two criteria. Inspired by a two-sample discrepancy problem, triple measures are elaborately designed to guarantee that the query samples not only possess the representativeness of the unlabeled data but also reveal the diversity of the labeled data. Any appropriate similarity measure can be employed to construct the triple measures. Meanwhile, an uncertain measure is leveraged to generate the informativeness criterion, which can be carried out in different ways. Rooted in this framework, a practical active learning algorithm is proposed, which exploits a radial basis function together with the estimated probabilities to construct the triple measures and a modified Best-versus-Second-Best strategy to construct the uncertain measure, respectively. Experimental results on benchmark datasets demonstrate that our algorithm consistently achieves superior performance over the state-of-the-art active learning algorithms.

cs.LG↗

arXiv2019

Robust and Discriminative Labeling for Multi-label Active Learning Based on Maximum Correntropy Criterion

Multi-label learning draws great interests in many real world applications. It is a highly costly task to assign many labels by the oracle for one instance. Meanwhile, it is also hard to build a good model without diagnosing discriminative labels. Can we reduce the label costs and improve the ability to train a good model for multi-label learning simultaneously? Active learning addresses the less training samples problem by querying the most valuable samples to achieve a better performance with little costs. In multi-label active learning, some researches have been done for querying the relevant labels with less training samples or querying all labels without diagnosing the discriminative information. They all cannot effectively handle the outlier labels for the measurement of uncertainty. Since Maximum Correntropy Criterion (MCC) provides a robust analysis for outliers in many machine learning and data mining algorithms, in this paper, we derive a robust multi-label active learning algorithm based on MCC by merging uncertainty and representativeness, and propose an efficient alternating optimization method to solve it. With MCC, our method can eliminate the influence of outlier labels that are not discriminative to measure the uncertainty. To make further improvement on the ability of information measurement, we merge uncertainty and representativeness with the prediction labels of unknown data. It can not only enhance the uncertainty but also improve the similarity measurement of multi-label data with labels information. Experiments on benchmark multi-label data sets have shown a superior performance than the state-of-the-art methods.

cs.LG↗

arXiv2019

Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network

The existence of hybrid noise in hyperspectral images (HSIs) severely degrades the data quality, reduces the interpretation accuracy of HSIs, and restricts the subsequent HSIs applications. In this paper, the spatial-spectral gradient network (SSGN) is presented for mixed noise removal in HSIs. The proposed method employs a spatial-spectral gradient learning strategy, in consideration of the unique spatial structure directionality of sparse noise and spectral differences with additional complementary information for better extracting intrinsic and deep features of HSIs. Based on a fully cascaded multi-scale convolutional network, SSGN can simultaneously deal with the different types of noise in different HSIs or spectra by the use of the same model. The simulated and real-data experiments undertaken in this study confirmed that the proposed SSGN performs better at mixed noise removal than the other state-of-the-art HSI denoising algorithms, in evaluation indices, visual assessments, and time consumption.

cs.CV↗

arXiv2019

Learning Attraction Field Representation for Robust Line Segment Detection

This paper presents a region-partition based attraction field dual representation for line segment maps, and thus poses the problem of line segment detection (LSD) as the region coloring problem. The latter is then addressed by learning deep convolutional neural networks (ConvNets) for accuracy, robustness and efficiency. For a 2D line segment map, our dual representation consists of three components: (i) A region-partition map in which every pixel is assigned to one and only one line segment; (ii) An attraction field map in which every pixel in a partition region is encoded by its 2D projection vector w.r.t. the associated line segment; and (iii) A squeeze module which squashes the attraction field to a line segment map that almost perfectly recovers the input one. By leveraging the duality, we learn ConvNets to compute the attraction field maps for raw in-put images, followed by the squeeze module for LSD, in an end-to-end manner. Our method rigorously addresses several challenges in LSD such as local ambiguity and class imbalance. Our method also harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained. Especially, we advance the performance by 4.5 percents on the WireFrame dataset. Our method is also fast with 6.6~10.4 FPS, outperforming most of existing line segment detectors.

cs.CV↗

arXiv2018

Validation approaches for satellite-based PM2.5 estimation: Assessment and a new approach

Satellite-derived aerosol optical depth (AOD) has been increasingly employed for the estimation of ground-level PM2.5, which is often achieved by modeling the relationship between AOD and PM2.5. To evaluate the accuracy of PM2.5 estimation, the cross-validation (CV) technique has been widely used. There have been several CV-based validation approaches applied for the AOD-PM2.5 models. However, the applicable conditions of these validation approaches still remain unclear. Additionally, is there space to develop better validation approaches for the AOD-PM2.5 models? The contributions of this study can be summarized as two aspects. Firstly, we comprehensively analyze and assess the existing validation approaches, and give the suggestions for applicable conditions of them. Then, the existing validation approaches do not take the distance to monitoring station into consideration. A new validation approach considering the distance to monitoring station is proposed in this study. Among the existing validation approaches, the sample-based CV is used to reflect the overall prediction ability; the site-based CV and the region-based CV have the potentials to evaluate spatial prediction performance; the time-based CV and the historical validation are capable of evaluating temporal prediction accuracy. In addition, the validation results indicate that the proposed validation approach has shown great potentials to better evaluate the accuracy of PM2.5 estimation. This study provides application implications and new perspectives for the validation of AOD-PM2.5 models.

physics.ao-ph↗

arXiv2018

Geographically and temporally weighted neural networks for satellite-based mapping of ground-level PM2.5

The integration of satellite-derived aerosol optical depth (AOD) and station-measured PM2.5 provides a promising approach for obtaining spatial PM2.5 data. Several spatiotemporal models, which considered spatial and temporal heterogeneities of AOD-PM2.5 relationship, have been widely adopted for PM2.5 estimation. However, they generally described the complex AOD-PM2.5 relationship based on a linear hypothesis. Previous machine learning models yielded great superiorities for fitting the nonlinear AOD-PM2.5 relationship, but seldom allowed for its spatiotemporal variations. To simultaneously consider the nonlinearity and spatiotemporal heterogeneities of AOD-PM2.5 relationship, geographically and temporally weighted neural networks (GTWNNs) were developed for satellite-based estimation of ground-level PM2.5 in this study. Using satellite AOD products, NDVI data, and meteorological factors over China as input, GTWNNs were set up with station PM2.5 measurements. Then the spatial PM2.5 data of those locations with no ground stations could be obtained. The proposed GTWNNs have achieved a better performance compared with previous spatiotemporal models, i.e., daily geographically weighted regression and geographically and temporally weighted regression. The sample-based and site-based cross-validation R2 values of GTWNNs are 0.80 and 0.79, respectively. On this basis, the spatial PM2.5 data with a resolution of 0.1 degree were generated in China. This study implemented the combination of geographical law and neural networks, and improved the accuracy of satellite-based PM2.5 estimation.

physics.ao-ph↗

arXiv2018

Oblique Stripe Removal in Remote Sensing Images via Oriented Variation

Destriping is a classical problem in remote sensing image processing. Although considerable effort has been made to remove stripes, few of the existing methods can eliminate stripe noise with arbitrary orientations. This situation makes the removal of oblique stripes in the higher-level remote sensing products become an unfinished and urgent issue. To overcome the challenging problem, we propose a novel destriping model which is self-adjusted to different orientations of stripe noise. First of all, the oriented variation model is designed to accomplish the stripe orientation approximation. In this model, the stripe direction is automatically estimated and then imbedded into the constraint term to depict the along-stripe smoothness of the stripe component. Mainly based on the oriented variation model, a whole destriping framework is proposed by jointly employing an L1-norm constraint and a TV regularization to separately capture the global distribution property of stripe component and the piecewise smoothness of the clean image. The qualitative and quantitative experimental results of both orientation and destriping aspects confirm the effectiveness and stability of the proposed method.

cs.CV↗

arXiv2018

Evaluation and comparison of MODIS Collection 6.1 aerosol optical depth against AERONET over regions in China with multifarious underlying surfaces

In this study, we evaluated the performance of the MODIS C6.1 AOD products and compared them with the C6 products over regions in China with multifarious underlying surfaces during 2001 to 2016. The AOD retrievals were validated against 20 AERONET sites, and the results show that the R for DT retrievals in C6.1 is 0.946, while the fraction within the EE can be considered relatively low at only 54.03%. DB retrievals in C6.1 have a slightly lower R value, but the other criteria are superior to DT. Comparing the results over urban and vegetation areas in C6.1, the overall quality of the DB retrievals is better than the DT retrievals in urban areas. The performance of DT is significantly superior to DB in the LEV areas. For the HEV areas, DB performs synthetically better than DT. In the spatial distribution aspect in C6.1, most of the DB AOD values are less than those of DT, and the relationship between DT and DB varies with the different land cover types. For the AOD coverage in C6.1, DT retrievals with high coverage mainly distribute in east-central China. However, the effects of high surface reflectance lead to low AOD coverage in the southwest. In contrast, the AOD coverage of DB tends to be high in areas where the main land cover type is bare soil and tends to be low in areas affected by snow. In terms of the comparison between C6.1 and C6, the overestimation of DT over urban areas in C6 is effectively mitigated in C6.1. However, a nearly systematic decline in DT is discovered in C6.1 as well. With respect to DB, consistent AOD coverage distribution is observed, with only subtle distinction. The AOD coverage of DB in C6.1 appears higher than that in C6 in the middle, south, and northeast of China. The quality of the DB retrievals in C6.1 increases slightly compared to C6, and the most remarkable improvement is observed for the coarse aerosol particles.

physics.ao-ph↗

arXiv2018

Spatial-Spectral Fusion by Combining Deep Learning and Variation Model

In the field of spatial-spectral fusion, the model-based method and the deep learning (DL)-based method are state-of-the-art. This paper presents a fusion method that incorporates the deep neural network into the model-based method for the most common case in the spatial-spectral fusion: PAN/multispectral (MS) fusion. Specifically, we first map the gradient of the high spatial resolution panchromatic image (HR-PAN) and the low spatial resolution multispectral image (LR-MS) to the gradient of the high spatial resolution multispectral image (HR-MS) via a deep residual convolutional neural network (CNN). Then we construct a fusion framework by the LR-MS image, the gradient prior learned from the gradient network, and the ideal fused image. Finally, an iterative optimization algorithm is used to solve the fusion model. Both quantitative and visual assessments on high-quality images from various sources demonstrate that the proposed fusion method is superior to all the mainstream algorithms included in the comparison in terms of overall fusion accuracy.

cs.CV↗

arXiv2018

The relationships between PM2.5 and AOD in China: About and behind spatiotemporal variations

Satellite aerosol products have been widely used to retrieve ground PM2.5 concentration because of its wide coverage and continuously spatial distribution. While more and more studies focus on the retrieval algorithm, we find that the relationship between PM2.5 concentration and satellite AOD has not been fully discussed in China. Is satellite AOD always a good indicator for PM2.5 in different regions and can AOD still be employed to retrieve PM2.5 with pollution conditions changing in these years remain unclear. In this study, the relationships between PM2.5 and AOD were investigated in 368 cities in China for a continuous period from February 2013 to December 2017, at different time and regional scales. Pearson correlation coefficients and PM2.5/AOD ratio were used as the indicator. Firstly, we concluded the relationship of PM2.5 and AOD in terms of spatiotemporal variations. Then the impact of meteorological factors, aerosol size and topography were discussed. Finally, a GWR retrieval experiment was conducted to find out how was the retrieval accuracy changing with the varying of PM2.5-AOD relationship. We found that spatially the correlation is higher in Beijing-Tianjin-Hebei and Chengyu region and weaker in coastal areas such as Yangtze River Delta and Pearl River Delta. The PM2.5/AOD ratio has obvious North-South difference with a high ratio in north China and a lower ratio in south China. Temporally, PM2.5/AOD ratio is higher in winter and lower in summer, the correlation coefficient tends to be higher in May and September. As for interannual variations from 2013 to 2017, we detected a declining tendency on PM2.5/AOD ratio. The accuracy of GWR retrievals were decreasing too, which may imply that AOD may not be a good indicator for PM2.5 in the future.

physics.geo-ph↗

arXiv2018

Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.

cs.CV↗

arXiv2018

Accurate Building Detection in VHR Remote Sensing Images using Geometric Saliency

This paper aims to address the problem of detecting buildings from remote sensing images with very high resolution (VHR). Inspired by the observation that buildings are always more distinguishable in geometries than in texture or spectral, we propose a new geometric building index (GBI) for accurate building detection, which relies on the geometric saliency of building structures. The geometric saliency of buildings is derived from a mid-level geometric representations based on meaningful junctions that can locally describe anisotropic geometrical structures of images. The resulting GBI is measured by integrating the derived geometric saliency of buildings. Experiments on three public datasets demonstrate that the proposed GBI achieves very promising performance, and meanwhile shows impressive generalization capability.

cs.CV↗

arXiv2018

Recent advances and opportunities in scene classification of aerial images with deep models

Scene classification is a fundamental task in interpretation of remote sensing images, and has become an active research topic in remote sensing community due to its important role in a wide range of applications. Over the past years, tremendous efforts have been made for developing powerful approaches for scene classification of remote sensing images, evolving from the traditional bag-of-visual-words model to the new generation deep convolutional neural networks (CNNs). The deep CNN based methods have exhibited remarkable breakthrough on performance, dramatically outperforming previous methods which strongly rely on hand-crafted features. However, performance with deep CNNs has gradually plateaued on existing public scene datasets, due to the notable drawbacks of these datasets, such as the small scale and low-diversity of training samples. Therefore, to promote the development of new methods and move the scene classification task a step further, we deeply discuss the existing problems in scene classification task, and accordingly present three open directions. We believe these potential directions will be instructive for the researchers in this field.

cs.CV↗

arXiv2018

Large-scale Land Cover Classification in GaoFen-2 Satellite Imagery

Many significant applications need land cover information of remote sensing images that are acquired from different areas and times, such as change detection and disaster monitoring. However, it is difficult to find a generic land cover classification scheme for different remote sensing images due to the spectral shift caused by diverse acquisition condition. In this paper, we develop a novel land cover classification method that can deal with large-scale data captured from widely distributed areas and different times. Additionally, we establish a large-scale land cover classification dataset consisting of 150 Gaofen-2 imageries as data support for model training and performance evaluation. Our experiments achieve outstanding classification accuracy compared with traditional methods.

cs.CV↗

arXiv2018

AID++: An Updated Version of AID on Scene Classification

Aerial image scene classification is a fundamental problem for understanding high-resolution remote sensing images and has become an active research task in the field of remote sensing due to its important role in a wide range of applications. However, the limitations of existing datasets for scene classification, such as the small scale and low-diversity, severely hamper the potential usage of the new generation deep convolutional neural networks (CNNs). Although huge efforts have been made in building large-scale datasets very recently, e.g., the Aerial Image Dataset (AID) which contains 10,000 image samples, they are still far from sufficient to fully train a high-capacity deep CNN model. To this end, we present a larger-scale dataset in this paper, named as AID++, for aerial scene classification based on the AID dataset. The proposed AID++ consists of more than 400,000 image samples that are semi-automatically annotated by using the existing the geographical data. We evaluate several prevalent CNN models on the proposed dataset, and the results show that our dataset can be used as a promising benchmark for scene classification.

cs.CV↗

arXiv2018

Real-time and Seamless Monitoring of Ground-level PM2.5 Using Satellite Remote Sensing

Satellite remote sensing has been reported to be a promising approach for the monitoring of atmospheric PM2.5. However, the satellite-based monitoring of ground-level PM2.5 is still challenging. First, the previously used polar-orbiting satellite observations, which can be usually acquired only once per day, are hard to monitor PM2.5 in real time. Second, many data gaps exist in satellite-derived PM2.5 due to the cloud contamination. In this paper, the hourly geostationary satellite (i.e., Himawari-8) observations were adopted for the real-time monitoring of PM2.5 in a deep learning architecture. On this basis, the satellite-derived PM2.5 in conjunction with ground PM2.5 measurements are incorporated into a spatio-temporal fusion model to fill the data gaps. Using Wuhan Urban Agglomeration as an example, we have successfully derived the real-time and seamless PM2.5 distributions. The results demonstrate that Himawari-8 satellite-based deep learning model achieves a satisfactory performance (out-of-sample cross-validation R2=0.80, RMSE=17.49 ug/m3) for the estimation of PM2.5. The missing data in satellite-derive PM2.5 are accurately recovered, with R2 between recoveries and ground measurements of 0.75. Overall, this study has inherently provided an effective strategy for the real-time and seamless monitoring of ground-level PM2.5.

physics.ao-ph↗