High-Throughput, Resource-Efficient Multi-Dimensional Parallel Architecture for Space-Borne Sea-Land Segmentation

2020 ◽  
pp. 2150027
Author(s):  
Cunguang Zhang ◽  
Hongxun Jiang ◽  
Riwei Pan ◽  
Haiheng Cao ◽  
Mingliang Zhou
Keyword(s):  
Remote Sensing ◽  
High Throughput ◽  
Large Scale ◽  
Parallel Architecture ◽  
Remote Sensing Image ◽  
Satellite System ◽  
Peak Performance ◽  
Remote Sensing Images ◽  
Block Level ◽  
Remote Sensing Image Processing

Sea-land segmentation based on edge detection is commonly utilized in ship detection, coastline extraction, and satellite system applications due to its high accuracy and rapid speed. Pixel-level distribution statistics do not currently satisfy the requirements for high-resolution, large-scale remote sensing image processing. To address the above problem, in this paper, we propose a high-throughput hardware architecture for sea-land segmentation based on multi-dimensional parallel characteristics. The proposed architecture is well suited to wide remote sensing images. Efficient multi-dimensional block level statistics allow for relatively infrequent pixel-level memory access; a boundary block tracking process replaces the whole-image scanning process, markedly enhancing efficiency. The tracking efficiency is further improved by a convenient two-step scanning strategy that feeds back the path state in a timely manner for a large number of blocks in the same direction appearing in the algorithm. The proposed architecture was deployed on Xilinx Virtex k7-410t to find that its practical processing time for a [Formula: see text] remote sensing image is only about 0.4[Formula: see text]s. The peak performance is 1.625[Formula: see text]gbps, which is higher than other FPGA implementations of segmentation algorithms. The proposed structure is highly competitive in processing wide remote sensing images.

MILL: Channel Attention–based Deep Multiple Instance Learning for Landslide Recognition

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-11
Author(s):  
Xiaochuan Tang ◽  
Mingzhe Liu ◽  
Hao Zhong ◽  
Yuanzhen Ju ◽  
Weile Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Large Scale ◽  
Remote Sensing Image ◽  
Disaster Risk ◽  
Multiple Instance Learning ◽  
Remote Sensing Images ◽  
Loess Area ◽  
Remote Sensing Image Classification ◽  
Natural Disaster Risk

Landslide recognition is widely used in natural disaster risk management. Traditional landslide recognition is mainly conducted by geologists, which is accurate but inefficient. This article introduces multiple instance learning (MIL) to perform automatic landslide recognition. An end-to-end deep convolutional neural network is proposed, referred to as Multiple Instance Learning–based Landslide classification (MILL). First, MILL uses a large-scale remote sensing image classification dataset to build pre-train networks for landslide feature extraction. Second, MILL extracts instances and assign instance labels without pixel-level annotations. Third, MILL uses a new channel attention–based MIL pooling function to map instance-level labels to bag-level label. We apply MIL to detect landslides in a loess area. Experimental results demonstrate that MILL is effective in identifying landslides in remote sensing images.

scholarly journals Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3232 ◽  
Author(s):  
Yan Liu ◽  
Qirui Ren ◽  
Jiahui Geng ◽  
Meng Ding ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Training Data ◽  
Land Resources ◽  
Remote Sensing Images ◽  
Training Strategy ◽  
The Impact

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Rapid dehazing algorithm based on large-scale median filtering for high-resolution visible near-infrared remote sensing images

2014 ◽  
Vol 12 (05) ◽  
pp. 1461010 ◽  
Author(s):  
Changmiao Hu ◽  
Ping Tang
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Land Surface ◽  
Large Scale ◽  
Near Infrared ◽  
Low Frequency ◽  
Median Filtering ◽  
Remote Sensing Images ◽  
Infrared Band ◽  
Remote Sensing Image Processing

In recent years, China's demand for satellite remote sensing images increased. Thus, the country launched a series of satellites equipped with high-resolution sensors. The resolutions of these satellites range from 30 m to a few meters, and the spectral range covers the visible to the near-infrared band. These satellite images are mainly used for environmental monitoring, mapping, land surface classification and other fields. However, haze is an important factor that often affects image quality. Thus, dehazing technology is becoming a critical step in high-resolution remote sensing image processing. This paper presents a rapid algorithm for dehazing based on a semi-physical haze model. Large-scale median filtering technique is used to extract large areas of bright, low-frequency information from images to estimate the distribution and thickness of the haze. Four images from different satellites are used for experiment. Results show that the algorithm is valid, fast, and suitable for the rapid dehazing of numerous large-sized high-resolution remote sensing images in engineering applications.

scholarly journals Cohesion Intensive Deep Hashing for Remote Sensing Image Retrieval

2019 ◽  
Vol 12 (1) ◽  
pp. 101 ◽  
Author(s):  
Lirong Han ◽  
Peng Li ◽  
Xiao Bai ◽  
Christos Grecos ◽  
Xiaoyu Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Optimization Method ◽  
Remote Sensing Image ◽  
Model Parameters ◽  
Remote Sensing Images ◽  
Deep Hashing ◽  
Deep Model

Recently, the demand for remote sensing image retrieval is growing and attracting the interest of many researchers because of the increasing number of remote sensing images. Hashing, as a method of retrieving images, has been widely applied to remote sensing image retrieval. In order to improve hashing performance, we develop a cohesion intensive deep hashing model for remote sensing image retrieval. The underlying architecture of our deep model is motivated by the state-of-the-art residual net. Residual nets aim at avoiding gradient vanishing and gradient explosion when the net reaches a certain depth. However, different from the residual net which outputs multiple class-labels, we present a residual hash net that is terminated by a Heaviside-like function for binarizing remote sensing images. In this scenario, the representational power of the residual net architecture is exploited to establish an end-to-end deep hashing model. The residual hash net is trained subject to a weighted loss strategy that intensifies the cohesiveness of image hash codes within one class. This effectively addresses the data imbalance problem normally arising in remote sensing image retrieval tasks. Furthermore, we adopted a gradualness optimization method for obtaining optimal model parameters in order to favor accurate binary codes with little quantization error. We conduct comparative experiments on large-scale remote sensing data sets such as UCMerced and AID. The experimental results validate the hypothesis that our method improves the performance of current remote sensing image retrieval.

scholarly journals BUILDING SHADOW DETECTION FROM GHOST IMAGERY

2018 ◽  
Vol XLII-3 ◽  
pp. 2527-2530
Author(s):  
G. Zhou ◽  
J. Sha ◽  
T. Yue ◽  
Q. Wang ◽  
X. Liu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Zenith Angle ◽  
Large Scale ◽  
Region Growing ◽  
Remote Sensing Image ◽  
Difficult Problem ◽  
Shadow Detection ◽  
Ghost Image ◽  
Basic Features ◽  
Remote Sensing Image Processing

Shadow is one of the basic features of remote sensing image, it expresses a lot of information of the object which is loss or interference, and the removal of shadow is always a difficult problem to remote sensing image processing. In this paper, it is mainly analyzes the characteristics and properties of shadows from the ghost image (traditional orthorectification). The DBM and the interior and exterior orientation elements of the image are used to calculate the zenith angle of sun. Then this paper combines the scope of the architectural shadows which has be determined by the zenith angle of sun with the region growing method to make the detection of architectural shadow areas. This method lays a solid foundation for the shadow of the repair from the ghost image later. It will greatly improve the accuracy of shadow detection from buildings and make it more conducive to solve the problem of urban large-scale aerial imagines.

scholarly journals Batch Processing of Remote Sensing Image Mosaic based on Python

2018 ◽  
Vol 14 (09) ◽  
pp. 208
Author(s):  
Hongling Xiu ◽  
Fengyun Yang
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Image Analysis ◽  
Remote Sensing Image ◽  
Image Mosaic ◽  
Remote Sensing Images ◽  
Complicated Process ◽  
Processing Software ◽  
Image Processing Software ◽  
Remote Sensing Image Processing

In the process of remote sensing image processing, analysis and interpretation, it is usually necessary to combine several local images into a complete image. Aiming at the shortcoming of long and complicated process of conventional semi-automatic video stitching. In this paper, using the splicing method of pixels, based on the Python interface of ArcGIS 10.1 platform, the idea of programming language is introduced and batch mosaic of remote sensing images is realized. Through the comparison with the image processing software, it is found that this method can shorten the time of image mosaic and improve the efficiency of splicing, which is convenient for later image analysis and other work under the premise of ensuring the accuracy.

scholarly journals Single Remote Sensing Image Dehazing Using a Prior-Based Dense Attentive Network

2019 ◽  
Vol 11 (24) ◽  
pp. 3008 ◽  
Author(s):  
Ziqi Gu ◽  
Zongqian Zhan ◽  
Qiangqiang Yuan ◽  
Li Yan
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
State Of The Art ◽  
Remote Sensing Image ◽  
Remote Sensing Images ◽  
Image Dehazing ◽  
Complex Issue ◽  
Atmospheric Scattering ◽  
Decoder Architecture ◽  
Density Map

Remote sensing image dehazing is an extremely complex issue due to the irregular and non-uniform distribution of haze. In this paper, a prior-based dense attentive dehazing network (DADN) is proposed for single remote sensing image haze removal. The proposed network, which is constructed based on dense blocks and attention blocks, contains an encoder-decoder architecture, which enables it to directly learn the mapping between the input images and the corresponding haze-free image, without being dependent on the traditional atmospheric scattering model (ASM). To better handle non-uniform hazy remote sensing images, we propose to combine a haze density prior with deep learning, where an initial haze density map (HDM) is firstly extracted from the original hazy image, and is subsequently utilized as the input of the network, together with the original hazy image. Meanwhile, a large-scale hazy remote sensing dataset is created for training and testing of the proposed method, which contains both uniform and non-uniform, synthetic and real hazy remote sensing images. Experimental results on the created dataset illustrate that the developed dehazing method obtains significant progresses over the state-of-the-art methods.

scholarly journals EXTRACTION OF RIVERS AND LAKES ON TIBETAN PLATEAU BASED ON GOOGLE EARTH ENGINE

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1797-1801
Author(s):  
R. G. Xu ◽  
G. Qiao ◽  
Y. J. Wu ◽  
Y. J. Cao
Keyword(s):  
Remote Sensing ◽  
Image Processing ◽  
Remote Sensing Image ◽  
Google Earth ◽  
Remote Sensing Images ◽  
Yarlung Zangbo River ◽  
Rivers And Lakes ◽  
Google Earth Engine ◽  
Remote Sensing Image Processing ◽  
Hydrological Station

<p><strong>Abstract.</strong> Tibetan Plateau (TP) is the most abundant area of water resources and water energy resources in China. It is also the birthplace of the main rivers in Southeast Asia and plays an important strategic role. However, due to its remote location and complex topography, the observation of surface hydrometeorological elements is extremely scarce, which seriously restricts the understanding of the water cycle in this area. Using remote sensing images to extract rivers and lakes on TP can obtain a lot of valuable water resources information. However, the downloading and processing of remote sensing images is very time-consuming, especially the processing of remote sensing images with large-scale and long time series often involves hundreds of gigabytes of data, which requires a high level of personal computers and is inefficient. As a cloud platform dedicated to data processing and analysis of geoscience, Google Earth Engine(GEE) integrates many excellent remote sensing image processing algorithms. It does not need to download images and supports online remote sensing image processing, which greatly improves the output efficiency. Based on GEE, the monthly data of Yarlung Zangbo River at Nuxia Hydrological Station and the annual data of typical lakes were extracted and vectorized from the pre-processed Landsat series images. It was found that the area of Yarlung Zangbo River at Nuxia Hydrological Station varies periodically. The changing trend of typical lakes is also revealed.</p>

scholarly journals Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval

2020 ◽  
Vol 12 (1) ◽  
pp. 175 ◽  
Author(s):  
Lili Fan ◽  
Hongwei Zhao ◽  
Haoyu Zhao
Keyword(s):  
Remote Sensing ◽  
Image Retrieval ◽  
Large Scale ◽  
Metric Learning ◽  
Remote Sensing Image ◽  
Positive Sample ◽  
Fine Tuning ◽  
Remote Sensing Images ◽  
Hard Samples ◽  
Image Datasets

Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures the semantic similarity information between data points by learning embedding in vector space. However, due to the uneven distribution of sample data in remote sensing image datasets, the pair-based loss currently used in DML is not suitable. To improve this, we propose a novel distribution consistency loss to solve this problem. First, we define a new way to mine samples by selecting five in-class hard samples and five inter-class hard samples to form an informative set. This method can make the network extract more useful information in a short time. Secondly, in order to avoid inaccurate feature extraction due to sample imbalance, we assign dynamic weight to the positive samples according to the ratio of the number of hard samples and easy samples in the class, and name the loss caused by the positive sample as the sample balance loss. We combine the sample balance of the positive samples with the ranking consistency of the negative samples to form our distribution consistency loss. Finally, we built an end-to-end fine-tuning network suitable for remote sensing image retrieval. We display comprehensive experimental results drawing on three remote sensing image datasets that are publicly available and show that our method achieves the state-of-the-art performance.

Sign in / Sign up

Export Citation Format

Share Document