Hiep Luong - Academia.edu (original) (raw)

Papers by Hiep Luong

Many inverse problems (e.g., demosaicking, deblurring, denoising, image fusion, HDR synthesis) sh... more Many inverse problems (e.g., demosaicking, deblurring, denoising, image fusion, HDR synthesis) share various similarities: degradation operators are often modeled by a specific data fitting function while image prior knowledge (e.g., sparsity) is incorporated by additional regularization terms. In this paper, we investigate automatic algorithmic techniques for evaluating proximal operators. These algorithmic techniques also enable efficient calculation of adjoints from linear operators in a general matrix-free setting. In particular, we study the simultaneous-direction method of multipliers (SDMM) and the parallel proximal algorithm (PPXA) solvers and show that the automatically derived implementations are well suited for both single-GPU and multi-GPU processing. We demonstrate this approach for an Electron Microscopy (EM) deconvolution problem. * Note that the presented framework is general enough to treat a much broader scope of problems, however this convex problem is of particular interest in image reconstruction/restoration.

Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2022

Monocular visual odometry is a core component of visual Simultaneous Localization and Mapping (SL... more Monocular visual odometry is a core component of visual Simultaneous Localization and Mapping (SLAM). Nowadays, headsets with a forward-pointing camera abound for a wide range of use cases such as extreme sports, firefighting or military interventions. Many of these headsets do not feature additional sensors such as a stereo camera or an IMU, thus evaluating the accuracy and robustness of monocular odometry remains critical. In this paper, we develop a novel framework for procedural synthetic dataset generation and a dedicated motion model for headset-mounted cameras. With our method, we study the performance of the leading classes of monocular visual odometry algorithms, namely feature-based, direct and deep learning-based methods. Our experiments lead to the following conclusions: i) the performance deterioration on headset-mounted camera images is mostly caused by head rotations and not by translations caused by human walking style, ii) featurebased methods are more robust to fast head rotations compared to direct and deep learning-based methods, and iii) it is crucial to develop uncertainty metrics for deep learning-based odometry algorithms.

Journal of Electronic Imaging, Feb 16, 2016

Abstract. Realistic visualization is crucial for a more intuitive representation of complex data,... more Abstract. Realistic visualization is crucial for a more intuitive representation of complex data, medical imaging, simulation, and entertainment systems. In this respect, multiview autostereoscopic displays are a great step toward achieving the complete immersive user experience, although providing high-quality content for these types of displays is still a great challenge. Due to the different characteristics/settings of the cameras in the multiview setup and varying photometric characteristics of the objects in the scene, the same object may have a different appearance in the sequences acquired by the different cameras. Images representing views recorded using different cameras, in practice, have different local noise, color, and sharpness characteristics. View synthesis algorithms introduce artifacts due to errors in disparity estimation/bad occlusion handling or due to an erroneous warping function estimation. If the input multiview images are not of sufficient quality and have mismatching color and sharpness characteristics, these artifacts may become even more disturbing. Accordingly, the main goal of our method is to simultaneously perform multiview image sequence denoising, color correction, and the improvement of sharpness in slightly defocused regions. Results show that the proposed method significantly reduces the amount of the artifacts in multiview video sequences, resulting in a better visual experience.

IEEE transactions on neural networks and learning systems, 2023

... Record Type, conference. Author, Patrick De Smet [801001015325] - Ghent University PatrickR.D... more ... Record Type, conference. Author, Patrick De Smet [801001015325] - Ghent University PatrickR.DeSmet@UGent.be; Johan De Bock [801001748380] - Ghent University Johan.DeBock@UGent.be; Quang Luong [801001749087] - Ghent University Hiep.Luong@UGent. ...

Although the use of SEM/EDX equipment for GunShot Residue (GSR) analysis was already introduced i... more Although the use of SEM/EDX equipment for GunShot Residue (GSR) analysis was already introduced in the 1980's and has since been used for decades in the search for microscopic primer particles, the technique has continuously evolved. Part of the drive for this ongoing development comes from the continuous changes in the composition of ammunition primers. Recently, munition manufacturers are progressing away from the 'classic' compositions, containing (heavy) metals, with the introduction of primers containing no metallic elements. Especially this recent innovation poses severe problems for modern analysis systems. The commercial GSR analysis software depends on the BackScattered Electron signal of the metal GSR particles to set them apart from the Environmental Particles (EP), which are present in abundance on any sampler. However, as the mean Z of these metal-free GSR particles will approach that of the EP, the standard procedures and the parameter settings of these search algorithms will probably fail. Although as a partial solution other signals could be used for the detection of the relevant particles, such as Secondary Electrons or Cathode Luminescence, a much larger number of potential GSR particles will have to be analysed because a number of EP will also be selected as potential GSR particles. Finally, the EDX classification algorithms may encounter problems in discerning GSR particles from EP because of their similar chemical composition. The use of Big Data Analysis (BDA) techniques is a novel approach in the GSR field, which may yield a solution for a number of the problems posed by these new primers. In order to implement these BDA techniques, a database of the GSR particles is compiled, together with databases of EP. Against these 'Ground Truth' databases, a test sample's particle populations can be compared as a group, which will potentially yield a shortlist of munition types which produce similar particle groups. In order to develop and test these techniques, databases were compiled using classic munition data which was readily available from case samples. In this presentation, the preliminary results of this study, which involves researchers from three Belgian universities, all working within the iMinds ICON BAHAMAS project (2015-2016), will be discussed.

Proceedings of SPIE, Mar 16, 2015

Realistic visualization is crucial for more intuitive representation of complex data, medical ima... more Realistic visualization is crucial for more intuitive representation of complex data, medical imaging, simulation and entertainment systems. Multiview autostereoscopic displays are great step towards achieving complete immersive user experience. However, providing high quality content for this type of displays is still a great challenge. Due to the different characteristics/settings of the cameras in the multivew setup and varying photometric characteristics of the objects in the scene, the same object may have different appearance in the sequences acquired by the different cameras. Images representing views recorded using different cameras in practice have different local noise, color and sharpness characteristics. View synthesis algorithms introduce artefacts due to errors in disparity estimation/bad occlusion handling or due to erroneous warping function estimation. If the input multivew images are not of sufficient quality and have mismatching color and sharpness characteristics, these artifacts may become even more disturbing. The main goal of our method is to simultaneously perform multiview image sequence denoising, color correction and the improvement of sharpness in slightly blurred regions. Results show that the proposed method significantly reduces the amount of the artefacts in multiview video sequences resulting in a better visual experience.

IEEE Transactions on Multimedia, 2022

Journal of Visual Communication and Image Representation, 2012

Proceedings of SPIE, Jul 1, 2005

In this paper we describe a novel approach to image interpolation while preserving sharp edge inf... more In this paper we describe a novel approach to image interpolation while preserving sharp edge information. Many interpolation methods already have been proposed in the literature, but suffer from one or more artifacts such as aliasing, blurring, ringing etc. Non-linear methods or edge-directed methods result in sharp interpolated images but often look segmented or have great visual degradation in fine structured textures. We concentrate in this paper on tackling blurred edges by mapping the image's level curves. Image's level curves or isophotes are spatial curves with a constant intensity level. The mapping of these intensity levels can be seen as a local contrast enhancement problem, therefore we can rely on some contrast enhancement techniques. A great advantage of this approach is that the shape of the level curves (and of the objects) are preserved and no explicit edge detection is needed here. Additional constraints in function of the image interpolation are defined in this flexible framework. Different strategies of extending greyscale interpolation to colour images are also discussed in this paper. The results show a large improvement in visual quality: the edges are sharper and ringing effects are removed.

In this paper we present a novel method for interpolating images and we introduce the concept of ... more In this paper we present a novel method for interpolating images and we introduce the concept of non-local interpolation. Unlike other conventional interpolation methods, the estimation of the unknown pixel values is not only based on its local surrounding neighbourhood, but on the whole image (nonlocally). In particularly, we exploit the repetitive character of the image. A great advantage of our proposed approach is that we have more information at our disposal, which leads to better estimates of the unknown pixel values. Results show the effectiveness of non-local interpolation and its superiority at very large magnifications to other interpolation methods.

arXiv (Cornell University), Mar 23, 2023

arXiv (Cornell University), May 6, 2023

Hyperspectral imaging (HI) has emerged as a powerful tool in diverse fields such as medical diagn... more Hyperspectral imaging (HI) has emerged as a powerful tool in diverse fields such as medical diagnosis, industrial inspection, and agriculture, owing to its ability to detect subtle differences in physical properties through high spectral resolution. However, hyperspectral images (HSIs) are often quite noisy because of narrow band spectral filtering. To reduce the noise in HSI data cubes, both model-driven and learning-based denoising algorithms have been proposed. However, model-based approaches rely on hand-crafted priors and hyperparameters, while learning-based methods are incapable of estimating the inherent degradation patterns and noise distributions in the imaging procedure, which could inform supervised learning. Secondly, learning-based algorithms predominantly rely on CNN and fail to capture long-range dependencies, resulting in limited interpretability. This paper proposes a Degradation-Noise-Aware Unfolding Network (DNA-Net) that addresses these issues. Firstly, DNA-Net models sparse noise, Gaussian noise, and explicitly represent image prior using transformer. Then the model is unfolded into an end-to-end network, the hyperparameters within the model are estimated from the noisy HSI and degradation model and utilizes them to control each iteration. Additionally, we introduce a novel U-Shaped Local-Non-local-Spectral Transformer (U-LNSA) that captures spectral correlation, local contents, and nonlocal dependencies simultaneously. By integrating U-LNSA into DNA-Net, we present the first Transformer-based deep unfolding HSI denoising method. Experimental results show that DNA-Net outperforms state-of-the-art methods, and the modeling of noise distributions helps in cases with heavy noise.

Proceedings of the ... International Conference on Document Analysis and Recognition, Sep 1, 2007

Abstract In this paper we present a novel method for reconstructing low-resolution text images. U... more Abstract In this paper we present a novel method for reconstructing low-resolution text images. Unlike other conventional interpolation methods, the unknown pixel value is not estimated based on its local surrounding neighbourhood, but on the whole text image. In ...

Nowadays remotely operated vehicles (ROV) have become a popular tool among biologists and geologi... more Nowadays remotely operated vehicles (ROV) have become a popular tool among biologists and geologists to examine and map the seafloor. For analytical purposes, mosaics have to be created from a large amount of recorded video sequences. Existing mosaicing techniques fail in case of non-uniform illuminated environments, due to the presence of a spotlight mounted on the ROV. Also traditional image blending techniques suffer from ghosting artifacts in the presence of moving objects. We propose a general observation model and a robust mosaicing algorithm which tackles these major problems. Results show an improvement in visual quality: noise and ghosting artifacts are removed.

Journal of Computer Science and Cybernetics, Jun 12, 2017

Table plane detection in the scene is a prerequisite step in developing object-findingaided syste... more Table plane detection in the scene is a prerequisite step in developing object-findingaided systems for visually impaired people. In order to determine the table plane in the scene, we have to detect planes in the scene first and then define the table from these detected planes based on the specific characteristics. Although a number of approaches have been proposed for plane segmentation, it still lacks proper table plane detection. In this paper, the authors propose a table plane detection method using information coming from a Microsoft Kinect sensor. The contribution of the paper is threefold. First, for plane detection step, the dedicated down-sampling algorithms to original point cloud thereby representing it as the organized point cloud structure in are applied to get real-time computation. Second, the acceleration information provided by the Kinect sensor is employed to detect the table plane among all detected planes. Finally, three different measures for the evaluation of the table plane detector are defined. The proposed method has been evaluated using a dataset of 10 scenes and published RGB-D dataset which are common contexts in daily activities of visually impaired people. The proposed method outperforms the state-of-the-art method based on PROSAC and obtains a comparable result as a method based on organized point cloud where the frame rate is six times higher.

Multispectral imaging technology analyzes for each pixel a wide spectrum of light and provides mo... more Multispectral imaging technology analyzes for each pixel a wide spectrum of light and provides more spectral information compared to traditional RGB images. Most current Unmanned Aerial Vehicles (UAV) camera systems are limited by the number of spectral bands (≤10 bands) and are usually not fully integrated with the ground controller to provide a live view of the spectral data. We have developed a compact multispectral camera system which has two CMV2K 4x4 snapshot mosaic sensors internally, providing 31 bands in total covering the visible and near-infrared spectral range (460-860nm). It is compatible with (but not limited to) the DJI M600 and can be easily mounted to the drone. Our system is fully integrated with the drone, providing stable and consistent communication between the flight controller, the drone/UAV, and our camera payload. With our camera control application on an Android tablet connected to the flight controller, users can easily control the camera system with a live view of the data and many useful information including histogram, sensor temperature, etc. The system acquires images at a maximum framerate of 2x20 fps and saves them on an internal storage of 1T Byte. The GPS data from the drone is logged with our system automatically. After the flight, data can be easily transferred to an external hard disk. Then the data can be visualized and processed using our software into single multispectral cubes and one stitched multispectral cube with a data quality report and a stitching report.

Sid's Digest Of Technical Papers, Sep 1, 2015

Highly realistic visualization becomes crucial in numerous applications such as: medical imaging,... more Highly realistic visualization becomes crucial in numerous applications such as: medical imaging, simulation and entertainment systems. In this article, we describe the image/video capture system aimed for autostereoscopic multiview displays, as well as view interpolation and image restoration algorithms used to enhance the image quality. We evaluate the proposed algorithms on a head tracking based stereoscopic multiview display.

Abstract The huge amount of incoming synthetic aperture radar (SAR) data nowadays demands the nee... more Abstract The huge amount of incoming synthetic aperture radar (SAR) data nowadays demands the need for automatic image registration. Due the presence of speckle noise and the huge size of SAR images, registering SAR images is more difficult than traditional ...