GPU Framework for Change Detection in Multitemporal Hyperspectral Images

Lopez-Fandino, Javier; Heras, Dora B.; Argüello, Francisco; Mura, Mauro Dalla

doi:10.1007/s10766-017-0547-5

Cited by 48 publications

(32 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CD is the process of identifying differences in the state of an object or phenomenon by observing it at different times (Hussain et al, 2013). The change detection is used in many applications that include: urban monitoring, land use/cover mapping, and damage assessment (Ghosh and Chakravortty, 2020;Liu et al, 2019;López-Fandiño et al, 2019;Pati et al, 2020;Zhan et al, 2020). Recently, due to the increasing availability of hyperspectral images the HCD convert to hot research topic area and many methods have been developed by researchers.…”

Section: Introductionmentioning

confidence: 99%

Binary Hyperspectral Change Detection Based on 3d Convolution Deep Learning

Seydi

Hasanlou

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Timely and accurate change detection of Earth’s surface features is extremely important for understanding relationships and interactions between human and natural phenomena to promote better decision making. The bi-temporal hyperspectral imagery has a high potential for the detection of surface changes. However, the extraction of changes from bi-temporal hyperspectral imagery due to special content of data, and environment conditions (atmospheric condition), change into challenging task. To this end, this research proposed a change detection framework based on deep learning using bi-temporal hyperspectral imagery. The proposed framework is applied in two main steps: (1) predict phase that the change areas highlighted from no-change areas using image differencing algorithm (ID), (2) decision phase that it decides for detecting change pixels based on 3D convolution neural network (CNN). The efficiency of the presented method is evaluated using Hyperion multi-temporal hyperspectral imagery. To evaluate the performance of the proposed method, two bi-temporal hyperspectral Hyperion with a variety of land cover classes were used. The results show that the proposed method has high accuracy and low false alarms rate: overall accuracy is more than 95%, and the kappa coefficient is greater than 0.9 and the miss-detection is lower than 10% and the false rate is lower than 4%.

show abstract

Section: Introductionmentioning

confidence: 99%

Binary Hyperspectral Change Detection Based on 3d Convolution Deep Learning

Seydi

Hasanlou

2020

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Among the most effective methods of spatial modeling for the analysis of HRRS images, the operators in MAPs can be efficiently implemented based on the multiscale representation of land covers via tree structures [22,23]. Compared with traditional feature extraction strategies based on the given filter windows, the MAPs can expand the analysis unit to all connected pixels with similar attribute, which is helpful to accurately extract the spatial structure information of the object that the pixel belongs to.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Remote-Sensing Image-Change Detection Based on Morphological Attribute Profiles and Decision Fusion

et al. 2020

View full text Add to dashboard Cite

Change detection (CD) is essential for accurate understanding of land surface changes with multitemporal Earth observation data. Due to the great advantages in spatial information modeling, Morphological Attribute Profiles (MAPs) are becoming increasingly popular for improving the recognition ability in CD applications. However, most of the MAPs-based CD methods are implemented by setting the scale parameters of Attribute Profiles (APs) manually and ignoring the uncertainty of change information from different sources. To address these issues, a novel method for CD in high-resolution remote sensing (HRRS) images based on morphological attribute profiles and decision fusion is proposed in this study. By establishing the objective function based on the minimum of average interscale correlation, a morphological attribute profile with adaptive scale parameters (ASP-MAPs) is presented to exploit the spatial structure information. On this basis, a multifeature decision fusion framework based on the Dempster–Shafer (D-S) theory is constructed for obtaining the CD map. Experiments of multitemporal HRRS images from different sensors have shown that the proposed method outperforms the other advanced comparison CD methods, and the overall accuracy (OA) can reach more than 83.9%.

show abstract

“…The efficiency gains that are made there allow the detection of contours in much larger images and the algorithms are applicable to various approaches to image segmentation. [12] starts from the fact that nowadays it is increasingly common to detect changes in land use and coverage using multispectral images and that a large part of the available change detection (CD) methods available focus on pixel-based operations. Since the use of spectral-spatial techniques helps to improve accuracy results, but also implies a significant increase in process time, [12] used a GPU framework to make object-based CD from multitemporal hyperspectral images and achieved real-time execution with accelerations of up to 46.5 times with respect to an open multiprocessing (OpenMP) implementation.…”

Section: Introductionmentioning

confidence: 99%

Inter-Pixel Filtrering of Digital Images with CUDA from NVIDIA

Medina¹

2020

Computer Science Research Notes

View full text Add to dashboard Cite

The process of filtering digital images represented by complex Cartesian allows to use the available onedimensional (1D) elements (interpixel); however, having those additional 1D elements increases both the volume of data and the time for processing them. The time reduction strategy based on a parallel computing scheme on the number of available central processing units (CPUs) does not consider additional computing resources such as those offered by general purpose graphics processing units (GPUs) of NVIDIA. Parallel computing possibilities provided by the NVIDIA GPUs were explored and, based on them, a computational scheme for the digital image Cartesian complexes filtering task was proposed using the application program interface Open Computing Language (OpenCL) provided for NVIDIA corporation GPUs. The results assessment was established by comparing the response times of the proposed solution compared to those obtained using only CPU resources. The obtained implementation is an alternative to parallelization of the filtering task, which provides response times up to 14 times faster than those obtained with the implementation that uses only the CPU resource. The NVIDIA multicore GPU significantly improves the parallelism, which can be used in conjunction with the available multicore CPU computing capacity, balancing the workload between these two computing powers using both simultaneously.

show abstract

GPU Framework for Change Detection in Multitemporal Hyperspectral Images

Cited by 48 publications

References 32 publications

Binary Hyperspectral Change Detection Based on 3d Convolution Deep Learning

Binary Hyperspectral Change Detection Based on 3d Convolution Deep Learning

High-Resolution Remote-Sensing Image-Change Detection Based on Morphological Attribute Profiles and Decision Fusion

Inter-Pixel Filtrering of Digital Images with CUDA from NVIDIA

Contact Info

Product

Resources

About