Search

Vehicle re-identification (V-ReID) is a critical task that aims to match the same vehicle across images from different camera viewpoints. The previous studies have leveraged attribute clues, such as color, model, and license plate, to enhance the V-ReID performance. However, these methods often lack effective interaction between the global–local features and the final V-ReID objective. Moreover, they do not address the challenging issues in real-world scenarios, such as high viewpoint variations, extreme illumination conditions, and car appearance changes (e.g., due to damage or wrong driving). We propose a novel framework to tackle these problems and advance the research in V-ReID, which can handle various types of car appearance changes and achieve robust V-ReID under varying lighting conditions. Our main contributions are as follows: (i) we propose a new Re-ID architecture named global–local self-attention network, which integrates local information into the feature learning process and enhances the feature representation for V-ReID and (ii) we introduce a novel damaged vehicle Re-ID dataset called VERI-D, which is the first publicly available dataset that focuses on this challenging yet practical scenario. The dataset contains both natural and synthetic images of damaged vehicles captured from multiple camera viewpoints and under different lighting conditions. (iii) We conduct extensive experiments on the VERI-D dataset and demonstrate the effectiveness of our approach in addressing the challenges associated with damaged vehicle re-identification. We also compare our method to several state-of-the-art V-ReID methods and show its superiority. [ABSTRACT FROM AUTHOR]

In this work, we describe a method of calculation of the 1-D circular quantum convolution of signals represented by 3-qubit superpositions in the computational basis states. The examples of the ideal low pass and high pass filters are described and quantum schemes for the 3-qubit circular convolution are presented. In the proposed method, the 3-qubit Fourier transformis used and one addition qubit, to prepare the quantum superposition for the inverse quantum Fourier transform. It is considered that the discrete Fourier transform of one of the signals is known and calculated in advance and only the quantum Fourier transform of another signal is calculated. The frequency characteristics of many linear time-invariant systems and filters are well known. Therefore, the described method of convolution can be used for these systems in quantum computation. [ABSTRACT FROM AUTHOR]

This paper presents a new concept of removing impulse noise through primary implicant elimination (PIE) applied to a logical system representation of the data. Applicable to binary and grayscale images, errors are corrected efficiently, in terms of the number of computations and memory requirements, while the fine details of the image are mostly preserved. Three filtering algorithms are presented: a general form in addition to iterative and switching variations. Experimental results on salt-and-pepper impulse noise, as well as on random-valued impulse noise, are compared against the performance of traditional median-based filters (both regular and switching) and are shown to be most successful in the often difficult case of when the original image contains many detailed patterns. Index Terms--Logical transform, median filter, random-valued impulse noise, salt-and-pepper impulse noise, switching filter.

Varying scene illumination poses many challenging problems for machine vision systems. One such issue is developing global enhancement methods that work effectively across the varying illumination. In this paper, we introduce two novel image enhancement algorithms: edge-preserving contrast enhancement, which is able to better preserve edge details while enhancing contrast in images with varying illumination, and a novel multi-histogram equalization method which utilizes the human visual system (HVS) to segment the image, allowing a fast and efficient correction of nonuniform illumination. We then extend this HVS-based multihistogram equalization approach to create a general enhancement method that can utilize any combination of enhancement algorithms for an improved performance. Additionally, we propose new quantitative measures of image enhancement, called the logarithmic Michelson contrast measure (AME) and the logarithmic AME by entropy. Many image enhancement methods require selection of operating parameters, which are typically chosen using subjective methods, but these new measures allow for automated selection. We present experimental results for these methods and make a comparison against other leading algorithms. Index Terms--Enhancement measure, human visual system (HVS), image enhancement, logarithmic image processing.

Three methods of image enhancement, based on the properties of the logarithmic transform domain histogram and histogram equalization are proposed. A human visual system-based quantitative measurement of image contrast improvement has helped in choosing the best parameters and transform for each enhancement.

A new concept is presented for calculating fast discrete orthogonal transforms that leads to a general split manageable algorithm for computing discrete unitary transforms. A fast Fourier transform (FFT) algorithm is developed with less arithmetical complexity by replacing some of the arithmetical operations by others, such as shifting operations.

In this paper, the method of splitting or parallelization of calculation of the $N$-point discrete Fourier transform (DFT) by the DFTs of smaller orders is described. For that the concept of partitions revealing the one-dimensional (1-D) DFT of order $q2^r,$ where $r > 1$ and $q > 1$ is a positive odd number, is described. Two different partitions are considered and the corresponding effective algorithms of calculation of the $q2^r$ -point 1-D DFT are described for the $q=3$ case. The calculation of the transform is based on the paired representations, when the signal is represented as a set of 1-D signals which define the 1-D DFT in disjoint subsets of frequency-points which cover the set of all frequencies. The splittings of the $q2^r$ -point 1-D DFT are performed by the 1-D discrete 2- and $q$ -paired transforms which allow for calculating with a minimum number of operations. The examples of the paired transforms and computational complexity of the proposed algorithms for the $N=6$ and 12 cases are given. [ABSTRACT FROM PUBLISHER]