A new land-cover match-based change detection for hyperspectral imagery

Seydi, Seyd Teymoor; Hasanlou, Mahdi

doi:10.1080/22797254.2017.1367963

Cited by 44 publications

(27 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, image differencing was used as the change detection algorithm. Image differencing is a simple and popular change detection algorithm [6]. This algorithm is based on the band-to-band pixel subtraction of datasets from the first-and second-time datasets (Equation (2)):…”

Section: Change Detectionmentioning

confidence: 99%

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform

Seydi

Akhoondzadeh

Amani³

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Wildfires are major natural disasters negatively affecting human safety, natural ecosystems, and wildlife. Timely and accurate estimation of wildfire burn areas is particularly important for post-fire management and decision making. In this regard, Remote Sensing (RS) images are great resources due to their wide coverage, high spatial and temporal resolution, and low cost. In this study, Australian areas affected by wildfire were estimated using Sentinel-2 imagery and Moderate Resolution Imaging Spectroradiometer (MODIS) products within the Google Earth Engine (GEE) cloud computing platform. To this end, a framework based on change analysis was implemented in two main phases: (1) producing the binary map of burned areas (i.e., burned vs. unburned); (2) estimating burned areas of different Land Use/Land Cover (LULC) types. The first phase was implemented in five main steps: (i) preprocessing, (ii) spectral and spatial feature extraction for pre-fire and post-fire analyses; (iii) prediction of burned areas based on a change detection by differencing the pre-fire and post-fire datasets; (iv) feature selection; and (v) binary mapping of burned areas based on the selected features by the classifiers. The second phase was defining the types of LULC classes over the burned areas using the global MODIS land cover product (MCD12Q1). Based on the test datasets, the proposed framework showed high potential in detecting burned areas with an overall accuracy (OA) and kappa coefficient (KC) of 91.02% and 0.82, respectively. It was also observed that the greatest burned area among different LULC classes was related to evergreen needle leaf forests with burning rate of over 25 (%). Finally, the results of this study were in good agreement with the Landsat burned products.

show abstract

Section: Change Detectionmentioning

confidence: 99%

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform

Seydi

Akhoondzadeh

Amani³

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the algebra-based change detection category, the ID algorithm is on the most common change detection methods (Seydi and Hasanlou, 2017). Due to simple interpretation and mathematical of this method, is used widely.…”

Section: Id Algorithmmentioning

confidence: 99%

“…Finally, endmember grouping is applied and the multiple change map is obtained by labeling on an abundance map. Seydi et al (2017) proposed match based HCD based on combining distance/similarity spectral measure metrics. The mentioned method is applied to two main phases: (1) predict change area by match based method, and (2) deciding on change/no-change pixels by the threshold selection method.…”

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.

Self Cite

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

“…Each pixel of a hyperspectral image has many dimensions pertaining to the absorption characteristics of a material at specific wavelengths in the visible, near infrared, and short-wave infrared (SWIR). As such, the data have been used for a variety of remote-sensing tasks, such as mapping/classification of surface materials [1][2][3], target detection [4,5] and change detection [6]. Because of the information content of each pixel in a hyperspectral image, the advantage of using hyperspectral imagery over conventional RGB and multispectral cameras is that many of the aforementioned tasks can be done at the pixel level.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Feature-Learning for Hyperspectral Data with Autoencoders

Windrim

Ramakrishnan²,

Melkumyan

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

This paper proposes novel autoencoders for unsupervised feature-learning from hyperspectral data. Hyperspectral data typically have many dimensions and a significant amount of variability such that many data points are required to represent the distribution of the data. This poses challenges for higher-level algorithms which use the hyperspectral data (e.g., those that map the environment). Feature-learning mitigates this by projecting the data into a lower-dimensional space where the important information is either preserved or enhanced. In many applications, the amount of labelled hyperspectral data that can be acquired is limited. Hence, there is a need for feature-learning algorithms to be unsupervised. This work proposes unsupervised techniques that incorporate spectral measures from the remote-sensing literature into the objective functions of autoencoder feature learners. The proposed techniques are evaluated on the separability of their feature spaces as well as on their application as features for a clustering task, where they are compared against other unsupervised feature-learning approaches on several different datasets. The results show that autoencoders using spectral measures outperform those using the standard squared-error objective function for unsupervised hyperspectral feature-learning.

show abstract

A new land-cover match-based change detection for hyperspectral imagery

Cited by 44 publications

References 64 publications

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform

Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform

Binary Hyperspectral Change Detection Based on 3d Convolution Deep Learning

Unsupervised Feature-Learning for Hyperspectral Data with Autoencoders

Contact Info

Product

Resources

About