Context-sensitive similarity based supervised image change detection

Li, Chao; Leifu, Gao

doi:10.1109/fskd.2016.7603147

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure of PCANet1 is shown in Fig. 4 (5) where , ih y denotes mean-removed and vectorized , ih R . (7) where the  operator means 2-D convolution.…”

Section: Training Pcanet1mentioning

confidence: 99%

“…This strategy requires a significant number of ground reference data to train the algorithm, and the labelling process can be extremely labor-intensive and time-consuming [4]. In [5], a context-sensitive similarity measure is presented based on supervised classification to amplify the dissimilarity between changed and unchanged pixels. Unsupervised methods for change detection can be viewed as a clustering approach which divides the data into changed and unchanged classes [6][7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Two-Phase Object-Based Deep Learning for Multi-Temporal SAR Image Change Detection

Zhang

Atkinson

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Change detection is one of the fundamental applications of synthetic aperture radar (SAR) images. However, speckle noise presented in SAR images has a negative effect on change detection, leading to frequent false alarms in the mapping products. In this research, a novel two-phase objectbased deep learning approach is proposed for multi-temporal SAR image change detection. Compared with traditional methods, the proposed approach brings two main innovations. One is to classify all pixels into three categories rather than two categories: unchanged pixels, changed pixels caused by strong speckle (false changes), and changed pixels formed by real terrain variation (real changes). The other is to group neighboring pixels into segmented into superpixel objects (from pixels) such as to exploit local spatial context. Two phases are designed in the methodology: 1) Generate objects based on the simple linear iterative clustering (SLIC) algorithm, and discriminate these objects into changed and unchanged classes using fuzzy c-means (FCM) clustering and a deep PCANet. The prediction of this Phase is the set of changed and unchanged superpixels. 2) Deep learning on the pixel sets over the changed superpixels only, obtained in the first phase, to discriminate real changes from false changes. SLIC is employed again to achieve new superpixels in the second phase. Low rank and sparse decomposition are applied to these new superpixels to suppress speckle noise significantly. A further clustering step is applied to these new superpixels via FCM. A new PCANet is then trained to classify two kinds of changed superpixels to achieve the final change maps. Numerical experiments demonstrate that, compared with benchmark methods, the proposed approach can distinguish real changes from false changes effectively with significantly reduced false alarm rates, and achieve up to 99.71% change detection accuracy using multi-temporal SAR imagery.

show abstract

“…The structure of PCANet1 is shown in Fig. 4 (5) where , ih y denotes mean-removed and vectorized , ih R . (7) where the  operator means 2-D convolution.…”

Section: Training Pcanet1mentioning

confidence: 99%