Object Detection From a Few LIDAR Scanning Planes

Rózsa, Zoltán; Szirányi, Tamás

doi:10.1109/tiv.2019.2938109

Cited by 21 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [ 21 ] present a method for the detection of far objects from dense point clouds. In the far range, in a LiDAR point cloud, objects have few points.…”

Section: Related Workmentioning

confidence: 99%

Obstacle Detection Using a Facet-Based Representation from 3-D LiDAR Measurements

Dulău

Oniga

2021

Sensors

View full text Add to dashboard Cite

In this paper, we propose an obstacle detection approach that uses a facet-based obstacle representation. The approach has three main steps: ground point detection, clustering of obstacle points, and facet extraction. Measurements from a 64-layer LiDAR are used as input. First, ground points are detected and eliminated in order to select obstacle points and create object instances. To determine the objects, obstacle points are grouped using a channel-based clustering approach. For each object instance, its contour is extracted and, using an RANSAC-based approach, the obstacle facets are selected. For each processing stage, optimizations are proposed in order to obtain a better runtime. For the evaluation, we compare our proposed approach with an existing approach, using the KITTI benchmark dataset. The proposed approach has similar or better results for some obstacle categories but a lower computational complexity.

show abstract

“…The authors of [ 21 ] present a method for the detection of far objects from dense point clouds. In the far range, in a LiDAR point cloud, objects have few points.…”

Section: Related Workmentioning

confidence: 99%

Obstacle Detection Using a Facet-Based Representation from 3-D LiDAR Measurements

Dulău

Oniga

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Digital Object Identifier 10.1109/TITS.2022.3199046 dynamic object appears [3]. While other methods require a series of frames to establish a decision, our method can already give a reliable estimation of the object motion and shape from only two frames (so two times faster than estimating from three; also, calculation time is negligible), which can be critical in braking distance.…”

Section: Introductionmentioning

confidence: 96%

Immediate Vehicle Movement Estimation and 3D Reconstruction for Mono Cameras by Utilizing Epipolar Geometry and Direction Prior

Rózsa

Golarits

Szirányi

2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

Motion estimation of surrounding objects is indispensable to any mobile machinery. The paper proposes a method to solve the estimation and reconstruction problem of dynamic objects with a mono camera. Using the relative camera motion and detected rigidly moving objects on the image, we estimate their movement up to a scale factor. Utilization priors about their moving direction are used to estimate the transformation, which maps the 3D object from the previous frame to the actual one. Our two-frame method works twice the speed or more as other methods using three frames or more for the estimation, and we do this without any constraints. We evaluate our method on various traffic scenarios of different autonomous driving datasets.

show abstract

“…M ONOCULAR 3D object detection in autonomous driving scenarios, with the goal of estimating the 2D and 3D geometric properties of on-road objects in a monocular image, is a challenging yet promising research topic. The state-of-the-art 3D detection methods [5], [6], [7], [8], [9] generally resort to the power of Light Detection and Ranging (LiDAR) sensors. Despite of the high performance these LiDAR-based methods can achieve, the practical demand for low cost necessitates the research on 3D object detection with a single RGB image as input, which is the focus of this work.…”

Section: Introductionmentioning

confidence: 99%

Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation

Gao,

Pan,

Gao

2020

Preprint

View full text Add to dashboard Cite

Monocular 3D object detection is a promising research topic for the intelligent perception systems of autonomous driving. In this work, a single-stage keypoint-based network, named as FADNet, is presented to address the task of monocular 3D object detection. In contrast to previous keypoint-based methods which adopt identical layouts for output branches, we propose to divide the output modalities into different groups according to the estimating difficulty, whereby different groups are treated differently by sequential feature association. Another contribution of this work is the strategy of depth hint augmentation. To provide characterized depth patterns as hints for depth estimation, a dedicated depth hint module is designed to generate row-wise features named as depth hints, which are explicitly supervised in a bin-wise manner. In the training stage, the regression outputs are uniformly encoded to enable loss disentanglement. The 2D loss term is further adapted to be depth-aware for improving the detection accuracy of small objects. The contributions of this work are validated by conducting experiments and ablation study on the KITTI benchmark. Without utilizing depth priors, post optimization, or other refinement modules, our network performs competitively against state-of-the-art methods while maintaining a decent running speed.

show abstract

Object Detection From a Few LIDAR Scanning Planes

Cited by 21 publications

References 38 publications

Obstacle Detection Using a Facet-Based Representation from 3-D LiDAR Measurements

Obstacle Detection Using a Facet-Based Representation from 3-D LiDAR Measurements

Immediate Vehicle Movement Estimation and 3D Reconstruction for Mono Cameras by Utilizing Epipolar Geometry and Direction Prior

Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation

Contact Info

Product

Resources

About