Cristhian A. Aguilera

Multispectral Image Feature Points

This paper presents a novel feature point descriptor for the multispectral image case Far-Infrared and Visible Spectrum images. It allows matching interest points on images of the same scene but acquired in different spectral bands. Initially, points of interest are detected on both images through a SIFT-like based scale space representation. Then, these points are characterized using an Edge Oriented Histogram (EOH) descriptor. Finally, points of interest from multispectral images are matched by finding nearest couples using the information from the descriptor. The provided experimental results and comparisons with similar methods show both the validity of the proposed approach as well as the improvements it offers with respect to the current state-of-the-art.

Multispectral Stereo Odometry

In this paper, we investigate the problem of visual odometry for ground vehicles based on the simultaneous utilization of multispectral cameras. It encompasses a stereo rig composed of an optical (visible) and thermal sensors. The novelty resides in the localization of the cameras as a stereo setup rather than two monocular cameras of different spectrums. To the best of our knowledge, this is the first time such task is attempted. Log-Gabor wavelets at different orientations and scales are used to extract interest points from both images. These are then described using a combination of frequency and spatial information within the local neighborhood. Matches between the pairs of multimodal images are computed using the cosine similarity function based on the descriptors. Pyramidal Lucas-Kanade tracker is also introduced to tackle temporal feature matching within challenging sequences of the data sets. The vehicle egomotion is computed from the triangulated 3-D points corresponding to the matched features. A windowed version of bundle adjustment incorporating Gauss-Newton optimization is utilized for motion estimation. An outlier removal scheme is also included within the framework to deal with outliers. Multispectral data sets were generated and used as test bed. They correspond to real outdoor scenarios captured using our multimodal setup. Finally, detailed results validating the proposed strategy are illustrated.

Learning Cross-Spectral Similarity Measures with Deep Convolutional Neural Networks

The simultaneous use of images from different spectra can be helpful to improve the performance of many computer vision tasks. The core idea behind the usage of crossspectral approaches is to take advantage of the strengths of each spectral band providing a richer representation of a scene, which cannot be obtained with just images from one spectral band. In this work we tackle the cross-spectral image similarity problem by using Convolutional Neural Networks (CNNs). We explore three different CNN architectures to compare the similarity of cross-spectral image patches. Specifically, we train each network with images from the visible and the near-infrared spectrum, and then test the result with two public cross-spectral datasets. Experimental results show that CNN approaches outperform the current state-of-art on both cross-spectral datasets. Additionally, our experiments show that some CNN architectures are capable of generalizing between different crossspectral domains.

Wavelet-Based Visible and Infrared Image Fusion: A Comparative Study.

This paper evaluates different wavelet-based cross-spectral image fusion strategies adopted to merge visible and infrared images. The objective is to find the best setup independently of the evaluation metric used to measure the performance. Quantitative performance results are obtained with state of the art approaches together with adaptations proposed in the current work. The options evaluated in the current work result from the combination of different setups in the wavelet image decomposition stage together with different fusion strategies for the final merging stage that generates the resulting representation. Most of the approaches evaluate results according to the application for which they are intended for. Sometimes a human observer is selected to judge the quality of the obtained results. In the current work, quantitative values are considered in order to find correlations between setups and performance of obtained results; these correlations can be used to define a criteria for selecting the best fusion strategy for a given pair of cross-spectral images. The whole procedure is evaluated with a large set of correctly registered visible and infrared image pairs, including both Near InfraRed (NIR) and Long Wave InfraRed (LWIR).

LGHD: A feature descriptor for matching across non-linear intensity variations

This paper presents a new feature descriptor suitable to the task of matching features points between images with nonlinear intensity variations. This includes image pairs with significant illuminations changes, multi-modal image pairs and multi-spectral image pairs. The proposed method describes the neighbourhood of feature points combining frequency and spatial information using multi-scale and multi-oriented Log-Gabor filters. Experimental results show the validity of the proposed approach and also the improvements with respect to the state of the art.

Sim-LIT: A Simulation Framework for Image Quality Assessment in Wireless Visual Sensor Networks under Packet Loss Conditions

In this paper we present Sim-LIT, a framework for the simulation of packet loss effects on the quality of non-coded or coded still images transported over wireless sensor networks. The tool is focused on image quality assessment and it can be used to evaluate error resilience during image communications. In this first version the evaluation of block interleaving methods is provided. Sim-LIT is highly configurable, providing several options and additional tools. It may be useful to rapidly evaluate interleaving algorithms, or other techniques, or to perform extensive tests considering various image files and loss patterns. Through different simulations we demonstrate the potential of Sim-LIT as a tool for supporting research activities on the image processing and wireless sensor networks domains.

A Visible-Thermal Fusion Based Monocular Visual Odometry

The manuscript evaluates the performance of a monocular visual odometry approach when images from different spectra are considered, both independently and fused. The objective behind this evaluation is to analyze if classical approaches can be improved when the given images, which are from different spectra, are fused and represented in new domains. The images in these new domains should have some of the following properties: i) more robust to noisy data; ii) less sensitive to changes (e.g., lighting); iii) more rich in descriptive information, among other. In particular in the current work two different image fusion strategies are considered. Firstly, images from the visible and thermal spectrum are fused using a Discrete Wavelet Transform (DWT) approach. Secondly, a monochrome threshold strategy is considered. The obtained representations are evaluated under a visual odometry framework, highlighting their advantages and disadvantages, using different urban and semi-urban scenarios. Comparisons with both monocular-visible spectrum and monocular-infrared spectrum, are also provided showing the validity of the proposed approach.

Simulated Annealing: A Novel Application of Image Processing in the Wood Area

Material’s internal structure knowledge is highly relevant to improve quality indexes [1]. For example, the exact information of the internal structure of a wood log or lumber such as density and internal defects is an important economic advantage (see [2]). Internal characteristics of materials have been studied with different non-destructive techniques, including ultrasound [3], microwaves [4-7,8], gamma rays, X-rays, nuclear magnetic resonance and, lately, artificial vision techniques [9]. X-rays have been used to examine the internal characteristics of many materials [10-13].

VISUALIZACIÓN INTERNA DE NUDOS EN ROLLIZOS DE MADERA DE PINUS RADIATA D. DON UTILIZANDO RAYOS-X

Visualizar la estructura interna de las trozas, permite conocer la calidad y destino optimo de la materia prima, generando ganancias de hasta 10 veces, al identificar el destino de las trozas. Las diferencias de densidad en las estructuras que componen la madera hacen posible que en una Tomografia Computarizada (TC) estas estructuras sean reconocibles y claramente diferenciadas. La coleccion de imagenes de TC debe ser tratada para poder visualizar el interior de la troza y diferenciar los defectos en esta. El Rendering Volumetrico (RV) nos permite, por otro lado, a partir de una coleccion de imagenes 2D, generar una visualizacion del volumen en 3D. El objetivo de este articulo es presentar los avances en la visualizacion de nudos en trozos de Pinus radiata D. Don crecido en Chile. Para ello se utilizan imagenes tomadas con un tomografo de rayos-X. Se presenta aqui la metodologia desarrollada para obtener la visualizacion y los resultados preliminares de la visualizacion interna. Se realizo un ensayo destructivo en las trozas, obteniendose indices de exactitud que se contrastaron con la TC y con la reconstruccion hecha por RV. Los resultados indican que es posible disponer de una simulacion de la troza y en particular observar como se comporta el cilindro nudoso Palabras clave : Caracterizacion No destructiva; Pinus radiata ; Rayos-X; Visualizacion.

Cross-Spectral Local Descriptors via Quadruplet Network

This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.