Monocular 3D Object Detection via Geometric Reasoning on Keypoints

Barabanau, Ivan; Artemov, Alexey; Burnaev, Evgeny; Murashkin, Vyacheslav

doi:10.5220/0009102506520659

Cited by 30 publications

(22 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depth estimation networks give the advantage of closing the gap of missing depth in a direct way. Yet, errors and noise occur during depth estimation, which may lead to biased overall results and contributes to a limited upperbound of performance (Brazil and Liu, 2019;Barabanau et al, 2020). Hence, various methods try to skip the naturally illposed depth estimation and tackle monocular 3DOD as a geometrical problem of mapping 2D into 3D space.…”

Section: Informed Monocular Approachesmentioning

confidence: 99%

Survey and Systematization of 3D Object Detection Models and Methods

Moritz¹,

Friederich²,

Egger³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper offers a comprehensive survey of recent developments in 3D object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection modules. We include basic concepts, focus our survey on a broad spectrum of different approaches arising in the last ten years and propose a systematization which offers a practical framework to compare those approaches on the methods level.

show abstract

Section: Informed Monocular Approachesmentioning

confidence: 99%

Survey and Systematization of 3D Object Detection Models and Methods

Moritz¹,

Friederich²,

Egger³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…They did not use any prior 3D CAD models. Barabanau et al improved the previous approach by using a 3D CAD model to infer the depth to the detected cars [13]. Wu et al [8] extended Mask R-CNN by adding customized heads, i.e., additional output layers, for predicting the vehicle's finer class, rotation, and translation.…”

Section: Image Based 3d Object Detection Using 3d Cad Modelsmentioning

confidence: 99%

“…The second group computes the discrepancy as the difference between some key points (such as window points, wheels, etc.) in the virtual and actual image [6,[11][12][13][14]. It was found that this approach led to more accurate results than the contour approach [9].…”

Section: Introductionmentioning

confidence: 95%

See 1 more Smart Citation

Towards Semantic SLAM: 3D Position and Velocity Estimation by Fusing Image Semantic Information with Camera Motion Parameters for Traffic Scene Analysis

et al. 2021

View full text Add to dashboard Cite

In this paper, an EKF (Extended Kalman Filter)-based algorithm is proposed to estimate 3D position and velocity components of different cars in a scene by fusing the semantic information and car model, extracted from successive frames with camera motion parameters. First, a 2D virtual image of the scene is made using a prior knowledge of the 3D Computer Aided Design (CAD) models of the detected cars and their predicted positions. Then, a discrepancy, i.e., distance, between the actual image and the virtual image is calculated. The 3D position and the velocity components are recursively estimated by minimizing the discrepancy using EKF. The experiments on the KiTTi dataset show a good performance of the proposed algorithm with a position estimation error up to 3–5% at 30 m and velocity estimation error up to 1 m/s.

show abstract

“…With the guidance of an appropriately designed directional field, both topological (e.g., placement of singularity points) and geometric (e.g., smoothness) properties of the underlying geometric structure may be efficiently derived. Other applications which could benefit from learnable directional fields include remote sensing [11,3,14,9], RGBD data processing [19] and related applications [1,5], shape retrieval [13]. However, obtaining a robust approximation of a directional field from raw input data is a challenging problem in many instances.…”

Section: Introductionmentioning

confidence: 99%

Learning to Approximate Directional Fields Defined Over 2D Planes

Taktasheva

Matveev

Artemov

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizable, require a considerable computational effort, and do not transfer across applications. In this work, we propose a deep learning-based approach and study the expressive power and generalization ability.

show abstract

Monocular 3D Object Detection via Geometric Reasoning on Keypoints

Cited by 30 publications

References 0 publications

Survey and Systematization of 3D Object Detection Models and Methods

Survey and Systematization of 3D Object Detection Models and Methods

Towards Semantic SLAM: 3D Position and Velocity Estimation by Fusing Image Semantic Information with Camera Motion Parameters for Traffic Scene Analysis

Learning to Approximate Directional Fields Defined Over 2D Planes

Contact Info

Product

Resources

About