SWIR Camera-Based Localization and Mapping in Challenging Environments

Abstract : This paper assesses a monocular localization system for complex scenes. The system is carried by a moving agent in a complex environment (smoke, darkness, indoor-outdoor transitions). We show how using a short-wave infrared camera (SWIR) with a potential lighting source is a good compromise that allows to make just a slight adaptation of classical simultaneous localization and mapping (SLAM) techniques. This choice made it possible to obtain relevant features from SWIR images and also to limit tracking failures due to the lack of key points in such challenging environments. In addition, we propose a tracking failure recovery strategy in order to allow tracking re-initialization with or without the use of other sensors. Our localization system is validated using real datasets generated from a moving SWIR-camera in indoor environment. Obtained results are promising, and lead us to consider the integration of our mono-SLAM in a complete localization chain including a data fusion process from several sensors.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

Contributor : Frédéric Davesne <>
Submitted on : Wednesday, August 28, 2019 - 1:43:43 PM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM


Files produced by the author(s)



Viachaslau Kachurka, David Roussel, Hicham Hadj-Abdelkader, Fabien Bonardi, Jean-Yves Didier, et al.. SWIR Camera-Based Localization and Mapping in Challenging Environments. 20th International Conference on IMAGE ANALYSIS AND PROCESSING (ICIAP 2019), Sep 2019, Trento, Italy. pp.446--456, ⟨10.1007/978-3-030-30645-8_41⟩. ⟨hal-02271971⟩



Record views


Files downloads