Road Scene Understanding by Occupancy Grid Learning from Sparse Radar Clusters using Semantic Segmentation

Sless, Liat; Shlomo, Bat El; Cohen, Guy; Oron, Shaul

doi:10.1109/iccvw.2019.00115

Cited by 56 publications

(41 citation statements)

References 26 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even though CNNs function extraordinarily well on images, they can also be tried and applied to other sensors that can yield image-like data [ 108 ]. The two-dimensional radar grid representations accumulated according to different occupancy grid map algorithms have already been exploited in deep learning domains for various autonomous system tasks, such as static object classification [ 109 , 110 , 111 , 112 , 113 , 114 ] and dynamic object classification [ 115 , 116 , 117 ]. In this case, the objects denote any road user within an autonomous system environment, like the pedestrian, vehicles, motorcyclists, etc.…”

Section: Detection and Classification Of Radar Signals Using Deep mentioning

confidence: 99%

Application of Deep Learning on Millimeter-Wave Radar Signals: A Review

Abdu

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

The progress brought by the deep learning technology over the last decade has inspired many research domains, such as radar signal processing, speech and audio recognition, etc., to apply it to their respective problems. Most of the prominent deep learning models exploit data representations acquired with either Lidar or camera sensors, leaving automotive radars rarely used. This is despite the vital potential of radars in adverse weather conditions, as well as their ability to simultaneously measure an object’s range and radial velocity seamlessly. As radar signals have not been exploited very much so far, there is a lack of available benchmark data. However, recently, there has been a lot of interest in applying radar data as input to various deep learning algorithms, as more datasets are being provided. To this end, this paper presents a survey of various deep learning approaches processing radar signals to accomplish some significant tasks in an autonomous driving application, such as detection and classification. We have itemized the review based on different radar signal representations, as it is one of the critical aspects while using radar data with deep learning models. Furthermore, we give an extensive review of the recent deep learning-based multi-sensor fusion models exploiting radar signals and camera images for object detection tasks. We then provide a summary of the available datasets containing radar data. Finally, we discuss the gaps and important innovations in the reviewed papers and highlight some possible future research prospects.

show abstract

Section: Detection and Classification Of Radar Signals Using Deep mentioning

confidence: 99%

Application of Deep Learning on Millimeter-Wave Radar Signals: A Review

Abdu

Zhang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…One is the occupancy-based grid-mapping, and the other is the amplitude-based grid-mapping [ 13 ]. Traditionally, the most widely used method to perform grid-mapping is using an inverse sensor model (ISM) and Bayesian filtering techniques [ 14 ].…”

Section: Data Models and Representations From Mmw Radarmentioning

confidence: 99%

“…Besides the methods of building grid maps listed above, new studies try to use deep learning to solve the same problem. They use ground truth from LIDAR and supervised learning to realize occupancy grid-mapping for static obstacles, from radar data on nuScenes [ 14 ].…”

Section: Data Models and Representations From Mmw Radarmentioning

confidence: 99%

“…In these applications, raw point cloud data of single snapshot is used to obtan object dimension [ 7 , 8 ], orientation, motion estimation [ 9 , 10 ], and object category [ 11 , 12 ]. Then, raw radar data accumulated from multiple snapshots is used to build grid maps [ 13 , 14 ]. These representations are used to express dynamic and static environment elements and applied to many applications such as object detection and tracking [ 8 , 15 , 16 ], environment mapping, and vehicle localization [ 17 , 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Driving scene understanding is a crucial task for autonomous cars, and it has taken a big leap with recent advances in artificial intelligence [1]. Collision-free space (or simply freespace) detection is a fundamental component of driving scene understanding [27]. Freespace detection approaches generally classify each pixel in an RGB or depth/disparity image as drivable or undrivable.…”

Section: Introductionmentioning

confidence: 99%

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection

Fan¹,

Wang²,

Cai³

et al. 2020

Preprint

View full text Add to dashboard Cite

Freespace detection is an essential component of visual perception for self-driving cars. The recent efforts made in data-fusion convolutional neural networks (CNNs) have significantly improved semantic driving scene segmentation. Freespace can be hypothesized as a ground plane, on which the points have similar surface normals. Hence, in this paper, we first introduce a novel module, named surface normal estimator (SNE), which can infer surface normal information from dense depth/disparity images with high accuracy and efficiency. Furthermore, we propose a data-fusion CNN architecture, referred to as RoadSeg, which can extract and fuse features from both RGB images and the inferred surface normal information for accurate freespace detection. For research purposes, we publish a large-scale synthetic freespace detection dataset, named Ready-to-Drive (R2D) road dataset, collected under different illumination and weather conditions. The experimental results demonstrate that our proposed SNE module can benefit all the state-of-the-art CNNs for freespace detection, and our SNE-RoadSeg achieves the best overall performance among different datasets.

show abstract

Road Scene Understanding by Occupancy Grid Learning from Sparse Radar Clusters using Semantic Segmentation

Cited by 56 publications

References 26 publications

Application of Deep Learning on Millimeter-Wave Radar Signals: A Review

Application of Deep Learning on Millimeter-Wave Radar Signals: A Review

MMW Radar-Based Technologies in Autonomous Driving: A Review

SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection

Contact Info

Product

Resources

About