A multithreaded algorithm of UAV visual localization based on a 3D model of environment: implementation with CUDA technology and CNN filtering of minor importance objects

Buyval, Alexander; Gavrilenkov, Mikhail; Magid, Evgeni

doi:10.5954/icarob.2017.gs2-3

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic systems with non-linear dependencies can be estimated On the other hand, machine learning methods build a multi-layer network that allows extracting special features from a data stream. One of the most used architectures are convolutional (CNN) [9] and recurrent neural networks (RNN). For example, in [10] the authors propose a CNN-based approach, which combines data from a camera and a laser scanner to improve the object detection algorithm performance.…”

Section: Sensor Fusionmentioning

confidence: 99%

Modern Methods of Map Construction Using Optical Sensors Fusion

Safin

Tsoy

Lavrenov

et al. 2023

Proceedings of International Conference on Artificial Life and Robotics

View full text Add to dashboard Cite

Map construction, or mapping, plays an important role in robotic applications. Mapping relies on inherently noisy sensor measurements to construct an accurate representation of a surrounding environment. Generally, individual sensors suffer from performance degradation issues under certain conditions in the environment. Sensor fusion allows to obtain statistically more accurate perception and to cope with performance degradation issues by combining data from multiple sensors of different modalities. This article reviews modern sensor fusion methods for map construction applications based on optical sensors, such as cameras and laser range finders. State-of-the-art mapping solutions built upon different mathematical theories and concepts, such as machine learning, are considered.

show abstract

Section: Sensor Fusionmentioning

confidence: 99%