Bird’s-eye view image acquisition from simulated scenes using geometric inverse perspective mapping

Justs, Daniels Jānis; Novickis, Rihards; Ozols, Kaspars; Greitāns, Modris

doi:10.1109/bec49624.2020.9277042

Cited by 5 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After receiving the segmented image from the previous layer, an inverse perspective transformation (IPT) was applied to achieve a top-down view (see Figure 3). IPT allows us to disregard the perspective phenomenon of the camera sensor and treat its pixel lattice as it would have been projected on a flat surface in front of the car [10].…”

Section: B Perspective Inversionmentioning

confidence: 99%

Autonomous Driving Using Fluid Flow Simulation

Sułkowski

Izydorczyk

Szelest³

2022

IEEE Access

View full text Add to dashboard Cite

This paper describes a fluid simulation application for the generation of driving trajectories in a simulated environment. The proposed method translates a segmented view from a front-facing camera into a top-down view of a road network, which is used as a river system where fluid flow is being simulated. Inspired by the natural phenomenon of water particles navigating complex riverbed obstacles, the driving trajectory is planned by tracing the simulated fluid flow. To demonstrate the feasibility of the proposed solution, the method was tested in several driving scenarios proposed in state-of-the-art papers, including navigating traffic and obstacles in city and highway environments. This solution shows that even very complex tasks can be solved using elegant nature-inspired approaches.INDEX TERMS Automotive applications, autonomous systems, vehicle driving, signal processing algorithms.

show abstract

Section: B Perspective Inversionmentioning

confidence: 99%

Autonomous Driving Using Fluid Flow Simulation

Sułkowski

Izydorczyk

Szelest³

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

Front-to-Bird’s-Eye-View Transformation for Autonomous Vehicles: A Class Imbalance-Based Approach

Martinez-Barba,

Valentin-Coronado,

Becerra

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A multi‐stage model for bird's eye view prediction based on stereo‐matching model and RGB‐D semantic segmentation

Rao

Cai

Wang

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Bird's‐Eye‐View (BEV) map is a powerful and detailed scene representation for intelligent vehicles that provides both the location and semantic information about nearby objects from a top‐down perspective. BEV map generation is a complex multi‐stage task, and the existing methods typically perform poorly for distant scenes. Thus, the authors introduce a novel multi‐stage model that infers to obtain more accurate BEV map. First, the authors propose the Adaptive Aggregation with Stereo Mixture Density (AA‐SMD) model, which is an improved stereo matching model that eliminates bleeding artefacts and provides more accurate depth estimation. Next, the authors employ the RGB‐Depth (RGB‐D) semantic segmentation model to improve the semantic segmentation performance and connectivity of their model. The depth map and semantic segmentation maps are then combined to create an incomplete BEV map. Finally, the authors propose a Multi Strip Pooling Unet (MSP‐Unet) model with a hierarchical multi‐scale (HMS) attention and strip pooling (SP) module to improve prediction with BEV generation. The authors evaluate their model with a Car Learn to Act (CARLA)‐generated synthetic dataset. The experiment results demonstrate that the authors’ model generates a highly accurate representation of the surrounding environment achieving a state‐of‐the‐art result of 61.50% Mean Intersection‐over‐Union (MIoU) across eight classes.

show abstract

Bird’s-eye view image acquisition from simulated scenes using geometric inverse perspective mapping

Cited by 5 publications

References 6 publications

Autonomous Driving Using Fluid Flow Simulation

Autonomous Driving Using Fluid Flow Simulation

Front-to-Bird’s-Eye-View Transformation for Autonomous Vehicles: A Class Imbalance-Based Approach

A multi‐stage model for bird's eye view prediction based on stereo‐matching model and RGB‐D semantic segmentation

Contact Info

Product

Resources

About