Navegando por Autor "Teichrieb, Veronica"

Agora exibindo 1 - 2 de 2

Artigo
Low-Cost 3D Reconstruction of Caves
(2023) Teixeira, Joao Marcelo; Pimentel, Narjara; Barbier, Eder; Bernard, Enrico; Teichrieb, Veronica; Chaves, Gimena
Caves are spatially complex environments, frequently formed by different shapes and structures. Capturing cave’s spatial complexity is often necessary for different purposes – from geological to biological aspects – but difficult due to the challenging logistics, frequent absence of light, and because the necessary equipment is prohibitively expensive. Efficient and low-cost mapping systems could produce direct and indirect benefits for cave users and policy-makers, enabling from non-invasive research of fragile structures (like speleothems) to new forms of interactive experiences in tourism, for example. Here we present a low-cost solution that combines hardware and software to allow capturing cave spatial information through RGB-D sensors and the later interpretation of the processed data. Our solution allows the navigation in a 3D reconstructed cave, and may be used to estimate volume and area information, frequently necessary for conservation or environmental licensing. We validated the proposed solution by partially reconstructing one cave in Northeastern Brazil. Although some challenges have to be overcome, our approach showed that it was possible to retrieve relevant information despite using low-cost RGB-D sensors.
Trabalhos publicados em eventos
Multi-Objective Tracking Applied to Bat Populations(Rastreamento Multi-Objetivo Aplicado a Populações de Morcegos)
(2016) Rodrigues, Eduardo; Teixeira, João Marcelo; Teichrieb, Veronica; Bernard, Enrico
Multiple target tracking is one of the greatchallenges faced by the computer vision community in lastyears. This paper presents a solution developed in order totrack bats in a clutter environment to account the populationof their colony. The algorithm is able to start detections,treat wrong or lost detections and process the detections inprogress. Tracked targets have their next state estimated byKalman Filter usage. As new measurements are performed,the algorithm can identify which of them are considerednoise, which are new targets and which are new statesof a previously detected target. A 3D viewer was alsoimplemented in order to help the analysis of the trackedflights by researchers in areas like biodiversity and biology.The aim of this paper is to present the operation of thedeveloped system, collaborate with other researchers workingwith tracking of multiple objects and make society aware ofthe importance of preserving the environment, exposing someof the consequences of changing its natural characteristics.The proposed algorithm showed amazing results in the teststages, reaching to overcome the current state of the art.