Feature-based Classification for Image Segmentation in Automotive Radar Based on Statistical Distribution Analysis

Xiao, Yang; Daniel, Liam; Gashinova, Marina

doi:10.1109/radarconf2043947.2020.9266596

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the azimuth direction, the number of cells corresponding to one raxel is, round [31]. In order to simplify the process of cell extraction, we disregard this difference and take the larger 3×2 cells for each raxel whatever the range to the raxel.…”

Section: A Methods To Extract Distribution Featuresmentioning

confidence: 99%

“…The radar system is an experimental high-resolution 79 GHz FMCW real aperture radar, designed by the University of Birmingham and ELVA-1 [31] with parameters presented in Table I.…”

Section: A Radar System Image Formation and Datasetmentioning

confidence: 99%

“…6. A full description of the transformation may be found in [31], it is very specific to the real aperture radar coordinate map and its representation and is summarised in Section III, A. The labelled image of the radar frame in Fig.…”

Section: Image Format and Data Labellingmentioning

confidence: 99%

See 2 more Smart Citations

Image Segmentation and Region Classification in Automotive High-Resolution Radar Imagery

2021

Self Cite

View full text Add to dashboard Cite

Image segmentation and classification of surfaces and obstacles in automotive radar imagery are the key technologies to provide valuable information for path planning in autonomous driving. As opposed to traditional radar processing, where clutter is considered as an unwanted return and should be effectively removed, autonomous driving requires full scene characterization. Hence, clutter carries necessary information for situational awareness of the autonomous platform and needs to be fully assessed to find the passable areas. In this paper, we proposed a method of automatic segmentation of automotive radar images based on two main steps: unsupervised image pre-segmentation using marker-based watershed transformation, followed by the supervised segmentation and classification of regions containing objects and surfaces based on the use of statistical distribution parameters. Several distributions were considered to characterize returns from specific region types of interest within the scene (denoted as classes) in calibrated radar imagery-the extracted distribution parameters were assessed for their ability to distinguish each class. These parameters were then used as features in a multivariate Gaussian distribution model classifier. Both the performances of the proposed supervised classification algorithm and the automatically segmented results were investigated using F1-score and Jaccard similarity coefficients, respectively.

show abstract

Section: A Methods To Extract Distribution Featuresmentioning

confidence: 99%

“…The radar system is an experimental high-resolution 79 GHz FMCW real aperture radar, designed by the University of Birmingham and ELVA-1 [31] with parameters presented in Table I.…”

Section: A Radar System Image Formation and Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Image Segmentation and Region Classification in Automotive High-Resolution Radar Imagery

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The ability of FMCW radar systems to segment scenes has recently begun to be investigated with approaches using data from the range-angle heatmap 12,19,20 and others using range-doppler data. 21 A unique approach uses ground penetrating radar (GPR), instead of the traditional automotive radars, to segment the road.…”

Section: Road Segmentationmentioning

confidence: 99%

“…FMCW radar is robust in the face of inclement weather and unaffected by illumination conditions, 10 but suffers from lower resolution compared to camera and Lidar sensors. 11 Imaging radars using several coupled radar chips offer fairly high azimuth resolution of less than 2 degrees and have been used to segment road surfaces 12 while single chip radar systems typically only provide 15 degree azimuthal resolution. Single chip radar is common in the automotive industry with radar placed around the body of vehicles used for ADAS functions like adaptive cruise control, lane change assist, cross traffic warning, and blind spot detection.…”

Section: Introductionmentioning

confidence: 99%

Millimeter wave radar-based road segmentation

Southcott

Zhang

Liu

2023

Radar Sensor Technology XXVII

View full text Add to dashboard Cite

Research into autonomous vehicles has focused on purpose-built vehicles with Lidar, camera, and radar systems. Many vehicles on the road today have sensors built into them to provide advanced driver assistance systems. In this paper we assess the ability of low-end automotive radar coupled with lightweight algorithms to perform scene segmentation. Results from a variety of scenes demonstrate the viability of this approach that complement existing autonomous driving systems.

show abstract