Self-Supervised Velocity Estimation for Automotive Radar Object Detection Networks

Niederlohner, Daniel; Ulrich, Michael; Braun, Sascha; Köhler, Daniel; Faion, Florian; Gläser, Claudius; Treptow, André; Blume, Holger

doi:10.1109/iv51971.2022.9827295

Cited by 10 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of 3D object detection is to estimate rotated 3D bounding boxes of surrounding objects in a certain sensor field of view. Sensor modalities commonly used for this are cameras [11], [12], lidar [13], [2] and radar [14]. We focus on lidar input in this paper, although the transformer architecture is flexible to accommodate for different input modalities [15].…”

Section: A Anchor Based Object Detectionmentioning

confidence: 99%

Transformers for Multi-Object Tracking on Point Clouds

Felicia

Faion

Gläser

et al. 2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to point clouds that span a large area, e.g. those that are common in autonomous driving, with lidar or radar data. TransLPC is able to remedy these issues: The structure of the transformer model is modified to allow for larger input sequence lengths, which are sufficient for large point clouds. Besides this, we propose a novel query refinement technique to improve detection accuracy, while retaining a memory-friendly number of transformer decoder queries. The queries are repositioned between layers, moving them closer to the bounding box they are estimating, in an efficient manner. This simple technique has a significant effect on detection accuracy, which is evaluated on the challenging nuScenes dataset on real-world lidar data. Besides this, the proposed method is compatible with existing transformer-based solutions that require object detection, e.g. for joint multi-object tracking and detection, and enables them to be used in conjunction with large point clouds.• We present TransLPC, a novel transformer-based object detector that is applicable to large point clouds. • A novel query refinement method is presented, which

show abstract

Section: A Anchor Based Object Detectionmentioning

confidence: 99%

Transformers for Multi-Object Tracking on Point Clouds

Felicia

Faion

Gläser

et al. 2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…Only by correctly recognizing road objects and conditions can effective intelligent judgments be made. Existing autonomous driving object recognition can be divided into three categories: radar-based object recognition [3,4], camera-based object recognition, and fusion-based object recognition [5,6,7].…”

Section: Introductionmentioning

confidence: 99%

Review of Object Detection Challenges in Autonomous Driving

Cao

2023

ACE

View full text Add to dashboard Cite

This paper presents a comprehensive review of object detection in autonomous driving applications. The classical object detection network is presented, along with several well-known online resources and benchmark methods. A thorough review of the challenges in object detection for autonomous driving is provided, along with potential solutions to these challenges. By exploring the current state of object detection in autonomous vehicles, this paper aims to contribute to the ongoing efforts to improve the safety and efficiency of autonomous driving technology.

show abstract