Architecture and implementation of Shape Adaptive Discrete Wavelet Transform for remote sensing image onboard compression

The characteristics of a wide variety of scales about objects and complex texture features of high-resolution remote sensing images make deep learning-based change detection methods the mainstream method. However, existing deep learning methods have problems with spatial information loss and insufficient feature representation, resulting in unsatisfactory effects of small objects detection and boundary positioning in high-resolution remote sensing images change detection. To address the problems, a network architecture based on 2-dimensional discrete wavelet transform and adaptive feature weighted fusion is proposed. The proposed network takes Siamese network and Nested U-Net as the backbone; 2-dimensional discrete wavelet transform is used to replace the pooling layer; and the inverse transform is used to replace the upsampling to realize image reconstruction, reduce the loss of spatial information, and fully retain the original image information. In this way, the proposed network can accurately detect changed objects of different scales and reconstruct change maps with clear boundaries. Furthermore, different feature fusion methods of different stages are proposed to fully integrate multi-scale and multi-level features and improve the comprehensive representation ability of features, so as to achieve a more refined change detection effect while reducing pseudo-changes. To verify the effectiveness and advancement of the proposed method, it is compared with seven state-of-the-art methods on two datasets of Lebedev and SenseTime from the three aspects of quantitative analysis, qualitative analysis, and efficiency analysis, and the effectiveness of proposed modules is validated by an ablation study. The results of quantitative analysis and efficiency analysis show that, under the premise of taking into account the operation efficiency, our method can improve the recall while ensuring the detection precision, and realize the improvement of the overall detection performance. Specifically, it shows an average improvement of 37.9% and 12.35% on recall, and 34.76% and 11.88% on F1 with the Lebedev and SenseTime datasets, respectively, compared to other methods. The qualitative analysis shows that our method has better performance on small objects detection and boundary positioning than other methods, and a more refined change map can be obtained.

Download Full-text

Performance of Spatial Frequency Discrete Wavelet Transform Based Remote Sensing Image Fusion Algorithm

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c6402.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 7968-7978

Keyword(s):

Remote Sensing ◽

Wavelet Transform ◽

Spatial Frequency ◽

Image Fusion ◽

Discrete Wavelet Transform ◽

Discrete Wavelet ◽

Fusion Algorithm ◽

Fusion Technique ◽

Image Fusion Technique ◽

Better Than

The high sensor cost for producing images with superior spectral and spatial qualities in remote sensing application have led to the development of image fusion algorithms. Image fusion technique combines a Panchromatic image and a Multispectral image with an aim to produce images with excellent spatial and spectral qualities. One of the major factors that affect the performance of any image fusion algorithm is the capability of the algorithm in extracting the spatial and spectral data from the respective images and how effective the so extracted information is blended together. One of the recently developed spectral domain algorithm to perform image fusion in remote sensing applications is Spatial Frequency Discrete Wavelet Transform abbreviated as SFDWT. The excellence of SFDWT image fusion algorithm is already proven better than the prevailing algorithms based on Discrete Wavelet Transform. This paper is coined with an eye to realize the performance of SFDWT based image fusion algorithm with respect to IHS-DWT, which being an enhanced form of a typical DWT based image fusion algorithm. The performance of SFDWT and IHS-DWT based image fusion algorithms will be evaluated by applying both techniques in the fusion of urban images received from Pléiades sensors with 1:4 resolution ratio using qualitative and quantitative image quality assessment methods. The consequence of varying the decomposition level on the quality of the images produced using SFDWT image fusion technique and three variants of IHS-DWT techniques based on substitution, averaging and maximum selection will be also evaluated. From the experimental analysis done using MATLAB simulation, it will be vivid that images obtained using image fusion algorithm based on SFDWT are much better than that obtained using IHS-DWT technique with excellent spatial and spectral qualities

Download Full-text