Occupancy grids generation based on Geometric-Featured Voxel maps

Plaza-Leiva, Victoria; Gómez-Ruiz, José Antonio; Ababsa, Fakhreddine; Mandow, Anthony; Morales, José; García-Cerezo, Alfonso J.

doi:10.1109/med.2015.7158838

Cited by 5 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding grid distribution, the 2D grid space is more commonly used due to its simplicity, whereas the 3D grid space is rarely used due to its complexity. Plazaleiva et al [27] used 3D LiDAR to perform space construction in a voxel grid, but the 3D grid map was then transformed into 2D for further application. In the application of 2D grid space, uniform distribution is commonly used because it is simpler to realize sensor fusion on grid cells of equal size.…”

Section: Construction Of the Grid Spacementioning

confidence: 99%

Driving Space for Autonomous Vehicles

et al. 2019

View full text Add to dashboard Cite

Driving space for autonomous vehicles (AVs) is a simplified representation of real driving environments that helps facilitate driving decision processes. Existing literatures present numerous methods for constructing driving spaces, which is a fundamental step in AV development. This study reviews the existing researches to gain a more systematic understanding of driving space and focuses on two questions: how to reconstruct the driving environment, and how to make driving decisions within the constructed driving space. Furthermore, the advantages and disadvantages of different types of driving space are analyzed. The study provides further understanding of the relationship between perception and decision-making and gives insight into direction of future research on driving space of AVs.

show abstract

Section: Construction Of the Grid Spacementioning

confidence: 99%

Driving Space for Autonomous Vehicles

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In order to reduce the memory consumption, the voxel size is enlarged, which leads to a coarser representation of the environment. The octomap or octree approach is a hierarchical data structure in which each parent voxel has exactly eight children (Jessup et al, 2014; Zhang et al, 2018). Thus, the 3D environment is represented as a collection of voxels with varied sizes, and hence, some voxels are recursively subdivided into eight children until a desired resolution is achieved.…”

Section: Introductionmentioning

confidence: 99%

Multi‐slices navigation approach for unknown 3D environments using micro aerial vehicles

et al. 2020

View full text Add to dashboard Cite

Due to the small size of Micro Aerial Vehicles, they are well suited for various indoor applications, especially search/rescue operations. Most of these operations are performed in unknown 3D environments. Real‐time map construction and vehicle's localization are essential tasks. Various approaches provide solutions for 3D‐map representation. However, these approaches require expensive embedded systems to afford high‐processing memory/computational costs. Because of its exposure to risks, the MAV should be equipped with a low‐cost navigation system. The principal aim of map construction herein is to facilitate the navigation task. Thus, constructing a massive 3D map is not required. Consequently, this paper proposes an efficient real‐time 3D SLAM. The proposed method avoids the 3D‐map representation of each region of the trajectory. Alternatively, it divides the environment along the trajectory into several 2D maps with a single 2D map in every region at the height of the MAV, as well as a transient region between each of the two constructed maps to enable connecting neighboring maps.

show abstract

“…Our interest was to use this classification method for object segmentation [31] and construction of 2D occupancy grids for autonomous navigation [32]. In order to reduce the computational load of the NN classifier in [30], we implemented a computationally simple voxel-based neighborhood approach where all points in each non-overlapping voxel in a regular grid were assigned to the same class by considering features within a support region defined only by the voxel itself.…”

Section: Introductionmentioning

confidence: 99%

Voxel-Based Neighborhood for Spatial Shape Pattern Classification of Lidar Point Clouds with Supervised Learning

Plaza-Leiva

Gómez-Ruiz

Mandow

et al. 2017

Sensors

Self Cite

View full text Add to dashboard Cite

Improving the effectiveness of spatial shape features classification from 3D lidar data is very relevant because it is largely used as a fundamental step towards higher level scene understanding challenges of autonomous vehicles and terrestrial robots. In this sense, computing neighborhood for points in dense scans becomes a costly process for both training and classification. This paper proposes a new general framework for implementing and comparing different supervised learning classifiers with a simple voxel-based neighborhood computation where points in each non-overlapping voxel in a regular grid are assigned to the same class by considering features within a support region defined by the voxel itself. The contribution provides offline training and online classification procedures as well as five alternative feature vector definitions based on principal component analysis for scatter, tubular and planar shapes. Moreover, the feasibility of this approach is evaluated by implementing a neural network (NN) method previously proposed by the authors as well as three other supervised learning classifiers found in scene processing methods: support vector machines (SVM), Gaussian processes (GP), and Gaussian mixture models (GMM). A comparative performance analysis is presented using real point clouds from both natural and urban environments and two different 3D rangefinders (a tilting Hokuyo UTM-30LX and a Riegl). Classification performance metrics and processing time measurements confirm the benefits of the NN classifier and the feasibility of voxel-based neighborhood.

show abstract

Occupancy grids generation based on Geometric-Featured Voxel maps

Cited by 5 publications

References 18 publications

Driving Space for Autonomous Vehicles

Driving Space for Autonomous Vehicles

Multi‐slices navigation approach for unknown 3D environments using micro aerial vehicles

Voxel-Based Neighborhood for Spatial Shape Pattern Classification of Lidar Point Clouds with Supervised Learning

Contact Info

Product

Resources

About