Classification of objects in polarimetric radar images using CNNs at 77 GHz

Visentin, Tristan; Sagainov, Andrej; Hasch, Jürgen; Zwick, Thomas

doi:10.1109/apmc.2017.8251453

Cited by 12 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Lombacher et al employ Radar grid maps made by accumulating Radar data over several time-stamps [151] for static object classification [152] and semantic segmentation [153] in autonomous driving. Visentin et al show that CNNs can be employed for object classification in a post-processed range-velocity map [154]. Kim et al [155] use a series of Radar range-velocity images and convolutional recurrent neural networks for moving objects classification.…”

Section: ) Radar Signalsmentioning

confidence: 99%

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Feng

Haase-Schütz

Rosenbaum

et al. 2021

IEEE Trans. Intell. Transport. Syst.

897

338

View full text Add to dashboard Cite

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of "what to fuse", "when to fuse", and "how to fuse" remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/. 0.99 0.8 0.98 0.99 0.96 0.96 0.94 Vehicle Person Road sign Traffic light LiDAR Points Map Radar Points RGB Image

show abstract

Section: ) Radar Signalsmentioning

confidence: 99%

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Feng

Haase-Schütz

Rosenbaum

et al. 2021

IEEE Trans. Intell. Transport. Syst.

897

338

View full text Add to dashboard Cite

show abstract

“…Lombacher et al [8] accumulate the radar data over several timestamps to develop radar grid maps for static object classification. Visentin et al [9] present a postprocessed range-velocity map fed to the CNN model for object classification, and Kim et al [10] complete moving object classification by a series of radar range-velocity maps and CNN. However, those classification methods based on only radar sensors did not provide promising results.…”

Section: Related Workmentioning

confidence: 99%

“…The offset is added to cover the ROI shift between the previous frame, Img t−1 , and the current frame Img t . With the expanded ROI, the motion is calculated using Equation (9). The motion output that exceeds the range of [0, 255] is truncated and the first gradient of M t is calculated.…”

Section: ∀(X Y) Wherementioning

confidence: 99%

A Sensor Fused Rear Cross Traffic Detection System Using Transfer Learning

Park¹,

Yu²

2021

Sensors

View full text Add to dashboard Cite

Recent emerging automotive sensors and innovative technologies in Advanced Driver Assistance Systems (ADAS) increase the safety of driving a vehicle on the road. ADAS enhance road safety by providing early warning signals for drivers and controlling a vehicle accordingly to mitigate a collision. A Rear Cross Traffic (RCT) detection system is an important application of ADAS. Rear-end crashes are a frequently occurring type of collision, and approximately 29.7% of all crashes are rear-ended collisions. The RCT detection system detects obstacles at the rear while the car is backing up. In this paper, a robust sensor fused RCT detection system is proposed. By combining the information from two radars and a wide-angle camera, the locations of the target objects are identified using the proposed sensor fused algorithm. Then, the transferred Convolution Neural Network (CNN) model is used to classify the object type. The experiments show that the proposed sensor fused RCT detection system reduced the processing time 15.34 times faster than the camera-only system. The proposed system has achieved 96.42% accuracy. The experimental results demonstrate that the proposed sensor fused system has robust object detection accuracy and fast processing time, which is vital for deploying the ADAS system.

show abstract

“…Some of these methods process the points by discretizing the 3D space into 3D voxels [18], [19], while others process the point clouds in the continuous vector space without voxelization to obtain individual features for each point [7], [8]. For object detection and classification using radar data, [20] proposes radar grid maps by accumulating radar data over several time-stamps, while [21] uses CNNs on a post-processed range-velocity map. The radar data can also be processed as a 3D point cloud.…”

Section: A Single-modality Object Detectionmentioning

confidence: 99%

Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles

Nabati,

2020

Preprint

View full text Add to dashboard Cite

In this paper we present a novel radar-camera sensor fusion framework for accurate object detection and distance estimation in autonomous driving scenarios. The proposed architecture uses a middle-fusion approach to fuse the radar point clouds and RGB images. Our radar object proposal network uses radar point clouds to generate 3D proposals from a set of 3D prior boxes. These proposals are mapped to the image and fed into a Radar Proposal Refinement (RPR) network for objectness score prediction and box refinement. The RPR network utilizes both radar information and image feature maps to generate accurate object proposals and distance estimations.The radar-based proposals are combined with image-based proposals generated by a modified Region Proposal Network (RPN). The RPN has a distance regression layer for estimating distance for every generated proposal. The radar-based and image-based proposals are merged and used in the next stage for object classification. Experiments on the challenging nuScenes dataset show our method outperforms other existing radarcamera fusion methods in the 2D object detection task while at the same time accurately estimates objects' distances.

show abstract

Classification of objects in polarimetric radar images using CNNs at 77 GHz

Cited by 12 publications

References 5 publications

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

A Sensor Fused Rear Cross Traffic Detection System Using Transfer Learning

Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles

Contact Info

Product

Resources

About