Fast Explicit Diffusion for Accelerated Features in Nonlinear Scale Spaces

Recently, deep learning-based image deblurring and deraining have been well developed. However, most of these methods fail to distill the useful features. What is more, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from a high computational burden. We propose a lightweight fusion distillation network (LFDN) for image deblurring and deraining to solve the above problems. The proposed LFDN is designed as an encoder–decoder architecture. In the encoding stage, the image feature is reduced to various small-scale spaces for multi-scale information extraction and fusion without much information loss. Then, a feature distillation normalization block is designed at the beginning of the decoding stage, which enables the network to distill and screen valuable channel information of feature maps continuously. Besides, an information fusion strategy between distillation modules and feature channels is also carried out by the attention mechanism. By fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring and deraining results with a smaller number of parameters and outperform the existing methods in model complexity.

Download Full-text

Real-time FPGA-based implementation of the AKAZE algorithm with nonlinear scale space generation using image partitioning

Journal of Real-Time Image Processing ◽

10.1007/s11554-021-01089-9 ◽

2021 ◽

Author(s):

Parastoo Soleimani ◽

David W. Capson ◽

Kin Fun Li

Keyword(s):

Real Time ◽

Memory Management ◽

Scale Space ◽

Image Resolution ◽

Hardware Architecture ◽

Frame Rate ◽

Time Sharing ◽

Scale Invariant ◽

Nonlinear Scale Space ◽

Nonlinear Scale

AbstractThe first step in a scale invariant image matching system is scale space generation. Nonlinear scale space generation algorithms such as AKAZE, reduce noise and distortion in different scales while retaining the borders and key-points of the image. An FPGA-based hardware architecture for AKAZE nonlinear scale space generation is proposed to speed up this algorithm for real-time applications. The three contributions of this work are (1) mapping the two passes of the AKAZE algorithm onto a hardware architecture that realizes parallel processing of multiple sections, (2) multi-scale line buffers which can be used for different scales, and (3) a time-sharing mechanism in the memory management unit to process multiple sections of the image in parallel. We propose a time-sharing mechanism for memory management to prevent artifacts as a result of separating the process of image partitioning. We also use approximations in the algorithm to make hardware implementation more efficient while maintaining the repeatability of the detection. A frame rate of 304 frames per second for a $$1280 \times 768$$ 1280 × 768 image resolution is achieved which is favorably faster in comparison with other work.

Download Full-text

Infrared and visible image fusion via octave Gaussian pyramid framework

Scientific Reports ◽

10.1038/s41598-020-80189-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Lei Yan ◽

Qun Hao ◽

Jie Cao ◽

Rizvi Saad ◽

Kun Li ◽

...

Keyword(s):

Image Fusion ◽

Low Frequency ◽

Objective Evaluation ◽

Visible Image ◽

Composite Image ◽

Multiscale Decomposition ◽

Gaussian Pyramid ◽

Fusion Methods ◽

Scale Spaces ◽

Fusion Framework

AbstractImage fusion integrates information from multiple images (of the same scene) to generate a (more informative) composite image suitable for human and computer vision perception. The method based on multiscale decomposition is one of the commonly fusion methods. In this study, a new fusion framework based on the octave Gaussian pyramid principle is proposed. In comparison with conventional multiscale decomposition, the proposed octave Gaussian pyramid framework retrieves more information by decomposing an image into two scale spaces (octave and interval spaces). Different from traditional multiscale decomposition with one set of detail and base layers, the proposed method decomposes an image into multiple sets of detail and base layers, and it efficiently retains high- and low-frequency information from the original image. The qualitative and quantitative comparison with five existing methods (on publicly available image databases) demonstrate that the proposed method has better visual effects and scores the highest in objective evaluation.

Download Full-text

Boundary Morphology for Hierarchical Simplification of Archaeological Fragments

Mathematical Morphology - Theory and Applications ◽

10.1515/mathm-2020-0101 ◽

2020 ◽

Vol 4 (1) ◽

pp. 46-63

Author(s):

Hanan ElNaghy ◽

Leo Dorst

Keyword(s):

Mathematical Morphology ◽

Masking Effect ◽

Morphological Operations ◽

Fracture Surfaces ◽

Morphological Approach ◽

Archaeological Artifacts ◽

Scale Spaces ◽

Extrusion Method

AbstractWhen fitting archaeological artifacts, one would like to have a representation that simplifies fragments while preserving their complementarity. In this paper, we propose to employ the scale-spaces of mathematical morphology to hierarchically simplify potentially fitting fracture surfaces. We study the masking effect when morphological operations are applied to selected subsets of objects. Since fitting locally depends on the complementarity of fractures only, we introduce ‘Boundary Morphology’ on surfaces rather than volumes. Moreover, demonstrating the Lipschitz nature of the terracotta fractures informs our novel extrusion method to compute both closing and opening operations simultaneously. We also show that in this proposed representation the effects of abrasion and uncertainty are naturally bounded, justifying the morphological approach. This work is an extension of our contribution earlier published in the proceedings of ISMM2019 [10].

Download Full-text