Scale Space Generation Research Articles

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

The 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 image resolution is achieved which is favorably faster in comparison with other work.

A novel SIFT architecture and ASIC implementation for real time SOC application

Local feature detection and description algorithms such as scale invariant feature transform (SIFT) algorithm are among the most commonly used techniques in computer vision. They are used mainly to detect and extract high-level information from low-level (pixel) information in images. These algorithms are computationally intensive and its pure software implementations are far from reaching real-time performance especially on embedded systems with limited computational power. In this paper, an Application-Specific Integrated Circuit (ASIC) implementation of the SIFT algorithm is proposed that is suitable for real-time image processing. In the Gaussian scale space generation step, several techniques were used to substantially reduce the hardware complexity: the multiplierless multiple constant multiplication, the symmetrical property of Gaussian mask in addition to the common sub expression elimination algorithm. Through the re-arrangement of SIFT’s 128 values in a specific approach, a new multi-ported memory is implemented to reduce the memory size. Furthermore, a novel mechanism is applied to continuously monitor the active window in the input and the intermediate results. The proposed technique does not only improve the performance of the SIFT implementation, but it also keeps the features extraction accuracy exactly the same as the software implementation. In this work, for an image size of $$256 \times 256$$ a frame rate of 56 fps was achieved. Additionally, the results confirm that the proposed architecture has lower hardware and memory costs compared to other works in the literature (FPGA based implementations). Lastly this architecture was implemented using Standard Cell Library Based ASIC flow using 65 nm low power GF library, it occupied an area of 1.4 $${{{\mathrm{mm}}}^2}$$ and consumed a total power of 30.4604 mW which makes it very suitable for integrated System on Chips (SoC) applications.

Morphological scale-space in image processing

The purpose of this paper is twofold. First, we provide an extensive review of the state-of-the-art in scale-space generation techniques for image processing, including linear methods, diffusion-based methods, and emphasizing morphological methods. Then, we introduce a new morphological approach to scale-space, called the lomo scale-space. The technique introduces a novel two-dimensional generalization of the concept of locally monotonic (lomo) signals. The lomo scale-space is a sequence of locally monotonic image representations where the scale is specified by the spatial extent or degree of local monotonicity. The morphological process used to generate the lomo scale-space retains many desirable properties of other morphological methods, such as edge localization and smoothing of extrema. In contrast to previous morphological scale-space methods, the filters employed here are self-dual, and thus do not induce a gray-level bias into the scaled signal representations. The scale-space methods reviewed and introduced in this paper are applicable to several multiscale image processing tasks such as segmentation, object-based image compression, content-based retrieval, and video tracking.

On the representation of image structures via scale space entropy conditions

This paper deals with a novel way for representing and computing image features encapsulated within different regions of scale-space. Employing a thermodynamical model for scale-space generation, the method derives features as those corresponding to "entropy rich" image regions where, within a given range of spatial scales, the entropy gradient remains constant. Different types of image features, defining regions of different information content, are accordingly encoded by such regions within different bands of spatial scale.