Change detection using deep learning approach with object-based image analysis

Liu, Tao; Yang, Hsiuhan Lexie; Lunga, Dalton

doi:10.1016/j.rse.2021.112308

Cited by 79 publications

(24 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that sensitivity and accuracy are appropriate for the classification of one class. A problem arises when they are used in assessing the classification of multiple classes, especially if the average value of the accuracy [34] or global precision [35] is reported as OA, creating an illusion of higher accuracy [36].…”

Section: Introductionmentioning

confidence: 99%

Reliable Crops Classification Using Limited Number of Sentinel-2 and Sentinel-1 Images

et al. 2021

View full text Add to dashboard Cite

The study presents the analysis of the possible use of limited number of the Sentinel-2 and Sentinel-1 to check if crop declarations that the EU farmers submit to receive subsidies are true. The declarations used in the research were randomly divided into two independent sets (training and test). Based on the training set, supervised classification of both single images and their combinations was performed using random forest algorithm in SNAP (ESA) and our own Python scripts. A comparative accuracy analysis was performed on the basis of two forms of confusion matrix (full confusion matrix commonly used in remote sensing and binary confusion matrix used in machine learning) and various accuracy metrics (overall accuracy, accuracy, specificity, sensitivity, etc.). The highest overall accuracy (81%) was obtained in the simultaneous classification of multitemporal images (three Sentinel-2 and one Sentinel-1). An unexpectedly high accuracy (79%) was achieved in the classification of one Sentinel-2 image at the end of May 2018. Noteworthy is the fact that the accuracy of the random forest method trained on the entire training set is equal 80% while using the sampling method ca. 50%. Based on the analysis of various accuracy metrics, it can be concluded that the metrics used in machine learning, for example: specificity and accuracy, are always higher then the overall accuracy. These metrics should be used with caution, because unlike the overall accuracy, to calculate these metrics, not only true positives but also false positives are used as positive results, giving the impression of higher accuracy. Correct calculation of overall accuracy values is essential for comparative analyzes. Reporting the mean accuracy value for the classes as overall accuracy gives a false impression of high accuracy. In our case, the difference was 10–16% for the validation data, and 25–45% for the test data.

show abstract

Section: Introductionmentioning

confidence: 99%

Reliable Crops Classification Using Limited Number of Sentinel-2 and Sentinel-1 Images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…PIFs, the core data for performing RRN, should be extracted from the invariant areas with similar radiometric characteristics [38,64]. Typically, most CPs based on the featurebased matching method are extracted from regions having invariant characteristics between images [36,50,65], thus satisfying the criteria of PIFs selection. However, some CPs are extracted from vegetation areas where the radiometric characteristics sensitively change according to the season and environment.…”

Section: Extraction Of Initial Pifs From Cps On Non-vegetation Areasmentioning

confidence: 99%

Integrated Preprocessing of Multitemporal Very-High-Resolution Satellite Images via Conjugate Points-Based Pseudo-Invariant Feature Extraction

Kim

Han

2021

Remote Sensing

View full text Add to dashboard Cite

Multitemporal very-high-resolution (VHR) satellite images are used as core data in the field of remote sensing because they express the topography and features of the region of interest in detail. However, geometric misalignment and radiometric dissimilarity occur when acquiring multitemporal VHR satellite images owing to external environmental factors, and these errors cause various inaccuracies, thereby hindering the effective use of multitemporal VHR satellite images. Such errors can be minimized by applying preprocessing methods such as image registration and relative radiometric normalization (RRN). However, as the data used in image registration and RRN differ, data consistency and computational efficiency are impaired, particularly when processing large amounts of data, such as a large volume of multitemporal VHR satellite images. To resolve these issues, we proposed an integrated preprocessing method by extracting pseudo-invariant features (PIFs), used for RRN, based on the conjugate points (CPs) extracted for image registration. To this end, the image registration was performed using CPs extracted using the speeded-up robust feature algorithm. Then, PIFs were extracted based on the CPs by removing vegetation areas followed by application of the region growing algorithm. Experiments were conducted on two sites constructed under different acquisition conditions to confirm the robustness of the proposed method. Various analyses based on visual and quantitative evaluation of the experimental results were performed from geometric and radiometric perspectives. The results evidence the successful integration of the image registration and RRN preprocessing steps by achieving a reasonable and stable performance.

show abstract

“…An operational limitation is generally due to the need for large annotated ground truth to be used for training purposes. Examples of state-of-the-art solutions based on CNNs are [62][63][64][65].…”

Section: Previous Work On Land Cover Change Detectionmentioning

confidence: 99%

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

et al. 2021

View full text Add to dashboard Cite

The aim of this paper is to address the monitoring of the recovery phase in the aftermath of Hurricane Matthew (28 September–10 October 2016) in the town of Jérémie, southwestern Haiti. This is accomplished via a novel change detection method that has been formulated, in a data fusion perspective, in terms of multitemporal supervised classification. The availability of very high resolution images provided by last-generation satellite synthetic aperture radar (SAR) and optical sensors makes this analysis promising from an application perspective and simultaneously challenging from a processing viewpoint. Indeed, pursuing such a goal requires the development of novel methodologies able to exploit the large amount of detailed information provided by this type of data. To take advantage of the temporal and spatial information associated with such images, the proposed method integrates multisensor, multisource, and contextual information. Markov random field modeling is adopted here to integrate the spatial context and the temporal correlation associated with images acquired at different dates. Moreover, the adoption of a region-based approach allows for the characterization of the geometrical structures in the images through multiple segmentation maps at different scales and times. The performances of the proposed approach are evaluated on multisensor pairs of COSMO-SkyMed SAR and Pléiades optical images acquired over Jérémie, in the aftermath of and during the three years after Hurricane Matthew. The effectiveness of the change detection results is analyzed both quantitatively, through the computation of accuracy measures on a test set, and qualitatively, by visual inspection of the classification maps. The robustness of the proposed method with respect to different algorithmic choices is also assessed, and the detected changes are discussed in relation to the recovery endeavors in the area and ground-truth data collected in the field in April 2019.

show abstract

Change detection using deep learning approach with object-based image analysis

Cited by 79 publications

References 44 publications

Reliable Crops Classification Using Limited Number of Sentinel-2 and Sentinel-1 Images

Reliable Crops Classification Using Limited Number of Sentinel-2 and Sentinel-1 Images

Integrated Preprocessing of Multitemporal Very-High-Resolution Satellite Images via Conjugate Points-Based Pseudo-Invariant Feature Extraction

Monitoring the Recovery after 2016 Hurricane Matthew in Haiti via Markovian Multitemporal Region-Based Modeling

Contact Info

Product

Resources

About