• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5481-5495
• /
• 2018

Single pixel imaging technology has developed for years, however the video acquisition on the single pixel camera is not a well-studied problem in computer vision. This work proposes a new scheme for single pixel camera to acquire video data and a new regularization for robust signal recovery algorithm. The method establishes a single pixel video compressive sensing scheme to reconstruct the video clips in spatial domain by recovering the difference of the consecutive frames. Different from traditional data acquisition method works in transform domain, the proposed scheme reconstructs the video frames directly in spatial domain. At the same time, a new regularization called spatial cluster is introduced to improve the performance of signal reconstruction. The regularization derives from the observation that the nonzero coefficients often tend to be clustered in the difference of the consecutive video frames. We implement an experiment platform to illustrate the effectiveness of the proposed algorithm. Numerous experiments show the well performance of video acquisition and frame reconstruction on single pixel camera.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.588-591
• /
• 2009

This paper proposes a reversible information hiding method for binary images. A half of pixels in noisy blocks on cover images is candidate for embeddable pixels. Among the candidate pixels, we select compressive pixels by bit patterns of its neighborhood to compress the pixels effectively. Thus, embeddable pixels in the proposed method are compressive pixels in noisy blocks. We provide experimental results using several binary images binarized by the different methods.

• Journal of the Optical Society of Korea
• /
• v.18 no.2
• /
• pp.146-150
• /
• 2014

We propose an experimental holographic imaging scheme combining compressive sensing (CS) theory with digital holography in phase-shifting conditions. We use the Mach-Zehnder interferometer for hologram formation, and apply the compressive sensing (CS) approach to the holography acquisition process. Through projecting the hologram pattern into a digital micro-mirror device (DMD), finally we will acquire the compressive sensing measurements using a photodiode. After receiving the data of two holograms via conventional communication channel, we reconstruct the original object using certain signal recovery algorithms of CS theory and hologram reconstruction techniques, which demonstrated the feasibility of the proposed method.

• Proceedings of the IEEK Conference
• /
• 2000.06b
• /
• pp.242-245
• /
• 2000

In this paper we present new idea to highly compress the images. The previous image is transformed with wavelet and the transformed data are transmitted. The previous image is subtracted from the next image. Then difference values per pixel are scanned to search motion areas and boundaries. In the motion boundaries, motion vectors and error values are transformed with wavelet and transmitted. We also include camera motion estimation and compensation. In this method this system has advantages of more compressive data, better quality of picture and shorter processing time compared to MPEG2, MPEG4.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.246-254
• /
• 2020

In this paper, we propose a learning based compressive sensing algorithm for the purpose of side scan sonar image denoising. The proposed method is based on Iterative Shrinkage and Thresholding Algorithm (ISTA) framework and incorporates a powerful strategy that reinforces the non-linearity of deep learning network for improved performance. The proposed method consists of three essential modules. The first module consists of a non-linear transform for input and initialization while the second module contains the ISTA block that maps the input features to sparse space and performs inverse transform. The third module is to transform from non-linear feature space to pixel space. Superiority in noise removal and memory efficiency of the proposed method is verified through various experiments.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.197-207
• /
• 2023

Concrete is a widely used material due to its excellent compressive strength and durability. However, depending on the surrounding environment and the characteristics of the materials used in the construction, various defects may occur, such as cracks on the surface and subsidence of the structure. The detects on the surface of the concrete structure occur after completion or over time. Neglecting these cracks may lead to severe structural damage, necessitating regular safety inspections. Traditional visual inspections of concrete walls are labor-intensive and expensive. This research presents a deep learning-based semantic segmentation model designed to detect cracks in concrete walls. The model addresses surface defects that arise from aging, and an image augmentation technique is employed to enhance feature extraction and generalization performance. A dataset for semantic segmentation was created by combining publicly available and self-generated datasets, and notable semantic segmentation models were evaluated and tested. The model, specifically trained for concrete wall fracture detection, achieved an extraction performance of 81.4%. Moreover, a 3% performance improvement was observed when applying the developed augmentation technique.