arXiv subjects

Aggelos Katsaggelos

Publications and source records attributed to Aggelos Katsaggelos.

26 records · Page 2Linked to original sources

arXiv2022

Denoising Fast X-Ray Fluorescence Raster Scans of Paintings

Macro x-ray fluorescence (XRF) imaging of cultural heritage objects, while a popular non-invasive technique for providing elemental distribution maps, is a slow acquisition process in acquiring high signal-to-noise ratio XRF volumes. Typically on the order of tenths of a second per pixel, a raster scanning probe counts the number of photons at different energies emitted by the object under x-ray illumination. In an effort to reduce the scan times without sacrificing elemental map and XRF volume quality, we propose using dictionary learning with a Poisson noise model as well as a color image-based prior to restore noisy, rapidly acquired XRF data.

eess.IV↗

arXiv2021

A Joint Intensity-Neuromorphic Event Imaging System for Resource Constrained Devices

We present a novel adaptive multi-modal intensity-event algorithm to optimize an overall objective of object tracking under bit rate constraints for a host-chip architecture. The chip is a computationally resource constrained device acquiring high resolution intensity frames and events, while the host is capable of performing computationally expensive tasks. We develop a joint intensity-neuromorphic event rate-distortion compression framework with a quadtree (QT) based compression of intensity and events scheme. The data acquisition on the chip is driven by the presence of objects of interest in the scene as detected by an object detector. The most informative intensity and event data are communicated to the host under rate constraints, so that the best possible tracking performance is obtained. The detection and tracking of objects in the scene are done on the distorted data at the host. Intensity and events are jointly used in a fusion framework to enhance the quality of the distorted images, so as to improve the object detection and tracking performance. The performance assessment of the overall system is done in terms of the multiple object tracking accuracy (MOTA) score. Compared to using intensity modality only, there is an improvement in MOTA using both these modalities in different scenarios.

eess.IV↗

arXiv2020

Lossy Event Compression based on Image-derived Quad Trees and Poisson Disk Sampling

With several advantages over conventional RGB cameras, event cameras have provided new opportunities for tackling visual tasks under challenging scenarios with fast motion, high dynamic range, and/or power constraint. Yet unlike image/video compression, the performance of event compression algorithm is far from satisfying and practical. The main challenge for compressing events is the unique event data form, i.e., a stream of asynchronously fired event tuples each encoding the 2D spatial location, timestamp, and polarity (denoting an increase or decrease in brightness). Since events only encode temporal variations, they lack spatial structure which is crucial for compression. To address this problem, we propose a novel event compression algorithm based on a quad tree (QT) segmentation map derived from the adjacent intensity images. The QT informs 2D spatial priority within the 3D space-time volume. In the event encoding step, events are first aggregated over time to form polarity-based event histograms. The histograms are then variably sampled via Poisson Disk Sampling prioritized by the QT based segmentation map. Next, differential encoding and run length encoding are employed for encoding the spatial and polarity information of the sampled events, respectively, followed by Huffman encoding to produce the final encoded events. Our Poisson Disk Sampling based Lossy Event Compression (PDS-LEC) algorithm performs rate-distortion based optimal allocation. On average, our algorithm achieves greater than 6x compression compared to the state of the art.

cs.CV↗

arXiv2019

Event-driven Video Frame Synthesis

Temporal Video Frame Synthesis (TVFS) aims at synthesizing novel frames at timestamps different from existing frames, which has wide applications in video codec, editing and analysis. In this paper, we propose a high framerate TVFS framework which takes hybrid input data from a low-speed frame-based sensor and a high-speed event-based sensor. Compared to frame-based sensors, event-based sensors report brightness changes at very high speed, which may well provide useful spatio-temoral information for high framerate TVFS. In our framework, we first introduce a differentiable forward model to approximate the physical sensing process, fusing the two different modes of data as well as unifying a variety of TVFS tasks, i.e., interpolation, prediction and motion deblur. We leverage autodifferentiation which propagates the gradients of a loss defined on the measured data back to the latent high framerate video. We show results with better performance compared to state-of-the-art. Second, we develop a deep learning-based strategy to enhance the results from the first step, which we refer as a residual "denoising" process. Our trained "denoiser" is beyond Gaussian denoising and shows properties such as contrast enhancement and motion awareness. We show that our framework is capable of handling challenging scenes including both fast motion and strong occlusions.

cs.CV↗

arXiv2018

Separation of time scales and direct computation of weights in deep neural networks

Artificial intelligence is revolutionizing our lives at an ever increasing pace. At the heart of this revolution is the recent advancements in deep neural networks (DNN), learning to perform sophisticated, high-level tasks. However, training DNNs requires massive amounts of data and is very computationally intensive. Gaining analytical understanding of the solutions found by DNNs can help us devise more efficient training algorithms, replacing the commonly used mthod of stochastic gradient descent (SGD). We analyze the dynamics of SGD and show that, indeed, direct computation of the solutions is possible in many cases. We show that a high performing setup used in DNNs introduces a separation of time-scales in the training dynamics, allowing SGD to train layers from the lowest (closest to input) to the highest. We then show that for each layer, the distribution of solutions found by SGD can be estimated using a class-based principal component analysis (PCA) of the layer's input. This finding allows us to forgo SGD entirely and directly derive the DNN parameters using this class-based PCA, which can be well estimated using significantly less data than SGD. We implement these results on image datasets MNIST, CIFAR10 and CIFAR100 and find that, in fact, layers derived using our class-based PCA perform comparable or superior to neural networks of the same size and architecture trained using SGD. We also confirm that the class-based PCA often converges using a fraction of the data required for SGD. Thus, using our method training time can be reduced both by requiring less training data than SGD, and by eliminating layers in the costly backpropagation step of the training.

cs.LG↗

arXiv2018

Particle Tracking and Extended Object Imaging by Interferometric Super Resolution Microscopy

An interferometric fluorescent microscope and a novel theoretic image reconstruction approach were developed and used to obtain super-resolution images of live biological samples and to enable dynamic real time tracking. The tracking utilizes the information stored in the interference pattern of both the illuminating incoherent light and the emitted light. By periodically shifting the interferometer phase and a phase retrieval algorithm we obtain information that allow localization with sub-2 nm axial resolution at 5 Hz.

physics.optics↗

arXiv2017

Global hard thresholding algorithms for joint sparse image representation and denoising

Sparse coding of images is traditionally done by cutting them into small patches and representing each patch individually over some dictionary given a pre-determined number of nonzero coefficients to use for each patch. In lack of a way to effectively distribute a total number (or global budget) of nonzero coefficients across all patches, current sparse recovery algorithms distribute the global budget equally across all patches despite the wide range of differences in structural complexity among them. In this work we propose a new framework for joint sparse representation and recovery of all image patches simultaneously. We also present two novel global hard thresholding algorithms, based on the notion of variable splitting, for solving the joint sparse model. Experimentation using both synthetic and real data shows effectiveness of the proposed framework for sparse image representation and denoising tasks. Additionally, time complexity analysis of the proposed algorithms indicate high scalability of both algorithms, making them favorable to use on large megapixel images.

cs.CV↗

arXiv2016

Fast and Effective Algorithms for Symmetric Nonnegative Matrix Factorization

Symmetric Nonnegative Matrix Factorization (SNMF) models arise naturally as simple reformulations of many standard clustering algorithms including the popular spectral clustering method. Recent work has demonstrated that an elementary instance of SNMF provides superior clustering quality compared to many classic clustering algorithms on a variety of synthetic and real world data sets. In this work, we present novel reformulations of this instance of SNMF based on the notion of variable splitting and produce two fast and effective algorithms for its optimization using i) the provably convergent Accelerated Proximal Gradient (APG) procedure and ii) a heuristic version of the Alternating Direction Method of Multipliers (ADMM) framework. Our two algorithms present an interesting tradeoff between computational speed and mathematical convergence guarantee: while the former method is provably convergent it is considerably slower than the latter approach, for which we also provide significant but less stringent mathematical proof regarding its convergence. Through extensive experiments we show not only that the efficacy of these approaches is equal to that of the state of the art SNMF algorithm, but also that the latter of our algorithms is extremely fast being one to two orders of magnitude faster in terms of total computation time than the state of the art approach, outperforming even spectral clustering in terms of computation time on large data sets.

cs.CV↗