Dennis G. Romero

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).

Fine-Tuning Based Deep Convolutional Networks for Lepidopterous Genus Recognition.

This paper describes an image classification approach oriented to identify specimens of lepidopterous insects at Ecuadorian ecological reserves. This work seeks to contribute to studies in the area of biology about genus of butterflies and also to facilitate the registration of unrecognized specimens. The proposed approach is based on the fine-tuning of three widely used pre-trained Convolutional Neural Networks (CNNs). This strategy is intended to overcome the reduced number of labeled images. Experimental results with a dataset labeled by expert biologists is presented, reaching a recognition accuracy above 92%.

Hyperspectral imaging system for disease scanning on banana plants

Black Sigatoka (BS) is a banana plant disease caused by the fungus Mycosphaerella fijiensis. BS symptoms can be observed at late infection stages. By that time, BS has probably spread to other plants. In this paper, we present our current work on building an hyper-spectral (HS) imaging system aimed at in-vivo detection of BS pre-symptomatic responses in banana leaves. The proposed imaging system comprises a motorized stage, a high-sensitivity VIS-NIR camera and an optical spectrograph. To capture images of the banana leaf, the stages speed and cameras frame rate must be computed to reduce motion blur and to obtain the same resolution along both spatial dimensions of the resulting HS cube. Our continuous leaf scanning approach allows imaging leaves of arbitrary length with minimum frame loss. Once the images are captured, a denoising step is performed to improve HS image quality and spectral profile extraction.

A Dijkstra-Based Algorithm for Selecting the Shortest-Safe Evacuation Routes in Dynamic Environments (SSER)

In this work is proposed an approach for addressing the problem to find the shortest-safe routes in buildings with many evacuation doors and where the accessibility of internal areas could be changed by different kind of sensors. We present two advantages over the common use of Dijkstra’s algorithm, related to the problem of obtaining evacuation routes: (1) Fast search of the shortest-safe evacuation route to multiple exits with a backward approach and (2) Support to dynamic environments (graph with variable vertex availability). Four Dijkstra-based algorithms were considered in order to evaluate the performance of the proposed approach, achieving short times in evacuation to multiple exits.

Monocular visual odometry

This manuscript evaluates the usage of fused cross-spectral images in a monocular visual odometry approach. Fused images are obtained through a Discrete Wavelet Transform (DWT) scheme, where the best setup is empirically obtained by means of a mutual information based evaluation metric. The objective is to have a flexible scheme where fusion parameters are adapted according to the characteristics of the given images. Visual odometry is computed from the fused monocular images using an off the shelf approach. Experimental results using data sets obtained with two different platforms are presented. Additionally, comparison with a previous approach as well as with monocular-visible/infrared spectra are also provided showing the advantages of the proposed scheme. Monocular visual odometry based on a fused image approach.DWT image fusion parameters selected according to a quantitative evaluation metric.Experimental results with two public data sets illustrate its validity.Comparisons with other approaches are provided.

A Predictive Model for Human Activity Recognition by Observing Actions and Context

This paper presents a novel model to estimate human activities -- a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks RNN and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.