Semantic Segmentation on Automotive Radar Maps

Prophet, Robert; Li, Gang; Sturm, Christian; Vossiek, Martin

doi:10.1109/ivs.2019.8813808

Cited by 30 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides classification of specific targets, deep learning can provide better scene understanding by semantic segmentation [127]. For radar, the surroundings of vehicles have been successfully assigned to different categories based on grid maps [128], point clouds [129], and utilizing both [130]. In [131], region of interest-based segmentation is applied to range-velocity spectra.…”

Section: E Machine Learning and Automotive Radarmentioning

confidence: 99%

Automotive Radar — From First Efforts to Future Systems

2021

View full text Add to dashboard Cite

Section: E Machine Learning and Automotive Radarmentioning

confidence: 99%

Automotive Radar — From First Efforts to Future Systems

2021

View full text Add to dashboard Cite

“…In recent years, more and more studies employ diversiform methods to enhance the results of object detection and classification based on MMW radar data [ 23 , 24 , 42 ]. Researchers chose to process radar data with neural networks or grid-mapping to obtain rich target perception information.…”

Section: Mmw Radar Perception Approachesmentioning

confidence: 99%

“…As gridmaps are not quite sparse, they can improve this problem to a certain degree. Then use segmentation networks to process radar-based gridmaps like processing images [ 15 , 42 , 43 ]. Connected area analysis and convolutional neural network are used in [ 15 ].…”

Section: Mmw Radar Perception Approachesmentioning

confidence: 99%

MMW Radar-Based Technologies in Autonomous Driving: A Review

Zhou

Yang

Jiang

et al. 2020

Sensors

View full text Add to dashboard Cite

With the rapid development of automated vehicles (AVs), more and more demands are proposed towards environmental perception. Among the commonly used sensors, MMW radar plays an important role due to its low cost, adaptability In different weather, and motion detection capability. Radar can provide different data types to satisfy requirements for various levels of autonomous driving. The objective of this study is to present an overview of the state-of-the-art radar-based technologies applied In AVs. Although several published research papers focus on MMW Radars for intelligent vehicles, no general survey on deep learning applied In radar data for autonomous vehicles exists. Therefore, we try to provide related survey In this paper. First, we introduce models and representations from millimeter-wave (MMW) radar data. Secondly, we present radar-based applications used on AVs. For low-level automated driving, radar data have been widely used In advanced driving-assistance systems (ADAS). For high-level automated driving, radar data is used In object detection, object tracking, motion prediction, and self-localization. Finally, we discuss the remaining challenges and future development direction of related studies.

show abstract

“…This requires so-called unpooling operations and/or transposed convolutions. In [8], we used multiple CNNs -originally designed to segment camera images -for this purpose. The best results were achieved with SegNet-1 [23].…”

Section: Network Architecturementioning

confidence: 99%

“…On the other hand, [7] uses convolutional neural networks (CNN) to investigate the image details. Finally, [4] and [8] achieved good results with complete pixel-wise classifications using extensive CNNs, thus avoiding the error-prone clustering step. All existing publications have in common that classification is based on 2D grids.…”

Section: Introductionmentioning

confidence: 98%

Semantic Segmentation on 3D Occupancy Grids for Automotive Radar

et al. 2020

Self Cite

View full text Add to dashboard Cite

Radar sensors have great advantages over other sensors in estimating the motion states of moving objects, because they detect velocity components within one measurement cycle. Moreover, numerous successes have already been achieved regarding the classification of such objects. However, the advantage of instantaneous velocity measurement is lost when detecting static objects, so that their classification is much more demanding. In this paper, we use semantic segmentation networks to distinguish between frequently occurring infrastructure objects. The resulting semantic grids provide a location-based classification of the vehicle environment. Since even modern radars have a significantly poorer angular resolution than lidars, the relatively thin radar point cloud is accumulated in advance and transformed into 2D or 3D grids that act as network inputs. Occupancy grids are particularly advantageous here, since they calculate not only the obstacles but also the free spaces. With suitable parameter selection, which is very challenging due to the complexity of radar measurement, the resulting grids allow for good association with camera images. Finally, in order to evaluate possible advantages of 3D grids as network input with respect to the segmentation result, we created and evaluated a simulation dataset and two different real-world datasets in car parks and on motorways. As a result, Jaccard coefficients between 81% and 88% were achieved, depending on the dataset. It was also found that 3D input images lead to improvements in the car park dataset.

show abstract

Semantic Segmentation on Automotive Radar Maps

Cited by 30 publications

References 14 publications

Automotive Radar — From First Efforts to Future Systems

Automotive Radar — From First Efforts to Future Systems

MMW Radar-Based Technologies in Autonomous Driving: A Review

Semantic Segmentation on 3D Occupancy Grids for Automotive Radar

Contact Info

Product

Resources

About