PDF 摘要：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。

The next-generation high-resolution automotive radar (4D radar) can provide addi tional elevation measurement and denser point clouds, which has great potential for 3D sensing in autonomous driving . In this paper, we introduce a dataset named TJ4DRadSet with 4D radar points for autonomous driving research. The dataset was collected in various driving scenarios, with a total of 7757 synchronized frames in 44 consecutive sequen ces, which are well annotated with 3D bounding boxes and tr ack ids. We provide a 4D radar-based 3D object detection baseline for our dataset to demonstrate the effectiveness o f deep learning methods for 4D radar point clouds. The dataset c an be accessed via the following link: https://github.com/TJRadarLab/TJ4DRadSet. I. I NTRODUCTION Autonomous driving technol ogy [1] has recently received much attention. The high-level autonomous driving system mainly consists of modules such as environment perception, road planning, and decision execution [2]. A highly reliable, low-cost, high-resolution perception module is necessary for self-driving vehicles. At the current stage, the perception module mainly uses sensors such as cameras, lidars, and automotive radars to obtain environmental information of different modes [3]. Undeni ably, the camera and lidar are vulnerable to harsh conditions such as rain, fog, and intense light, whose performance will decline significantly with the increase of adversity. In contrast, the automotive radar is essential because of its strong robustness [4] and cost-effectiveness. Due to l ow azimuthal resolution, conventional automotive radar is only used for blind-spot detection, collision warning, and other driving assistance applications. The emergence o f new-generation 4D radar [5] makes up for the low definition of conventional automotive radar and provides elevation measurement, which is well suited for applications in high-level autonomous driving. The four dimensions of 4D radar are range, azimuth, elevation, and Doppler velocity. It also provides some other low-level features such as radar-cross-s ection (RCS) or signal-to-noise ratio (SNR). 3D object detection and tracking are essential to environment perception. With the development of deep learning and artificial intelligence, an enormous amount of *This research was supported by the National Key R&D Program of China under grant number 2021YFB2501201. 1Lianqing Zheng, Zhixiong Ma, Xichan Zhu, Bin Tan, Sen Li, Kai Long, Weiqi Sun, Sihan Chen, Lu Zhang, Mengyue Wan are from the School of Automotive Studies, Tongji University, Shanghai, China. {zhenglianqing, mzx1978, zhuxichan, tanbin, lisen, 2011442, weiqisun, sihan.chen, 2131517, 2033606}@tongji.edu.cn 2Libo Huang, Jie Bai are from the School of Information and Electricity, Zhejiang University City Colleg e, Hangzhou, Zhejiang, China. huangl@zucc.edu.cn, baij@zucc.edu.cn Corresponding author: Zhixiong Ma, Jie Bai. neural networks have been applied to 3D perception [6]. Training a 3D object detection network requires large-scale data, which should cover many diverse and complex conditions. What’s more, the ground truth of data needs to be accurate for supervised learning to ensure the trained network is valid. Compared with camera and lidar, few autonomous driving datasets contain 4D radar, which limits the research and application of deep learning in the 4D radar point cloud. To fill this gap, we proposed a 4D radar dataset for autonomous driving called TJ4DRadSet. The data collection platform contains multi-sensors, including 4D radar, camera, lidar, and Global Navigation Satellite System (GNSS), as shown in Figure 1. We hope the dataset will facilitate the research of 4D radar-based perception algorithms. Our contributions are listed as follows:  We present a dataset named TJ4DRadSet, an autonomous driving dataset containing 4D radar point clouds in continuous sequences with 3D annotations, which also provides multi-modal complete information on lidar, camera and GNSS.  TJ4DRadSet contains 40K frames of synchronized data, where 7757 frames, 44 sequences with high-quality annotated 3D bounding boxes and track ids. The 3D annotation system uses joint multi-sensor annotation and multi-round manual checks.  TJ4DRadSet covers various road conditions, such as elevated roads, complex intersections, one-way roads, and urban roads. It also includes bad lighting conditions such as intense light and darkness. The dataset is suitable for developing 3D perception algorithms based on the 4D radar to facilitate its application in high-level autonomous driving. TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving Lianqing Zheng1, Zhixiong Ma1,*, Xichan Zhu 1,B i nT a n1,S e nL i1,K a iL o n g1,W e i q iS u n1,S i h a n Chen1,L uZ h a n g1, Mengyue Wan 1,L i b oH u a n g2,J i eB a i2,* 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) October 8-12, 2022, Macau, China 978-1-6654-6880-0/22/$31.00 ©2022 IEEE 493 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) | 978-1-6654-6880-0/22/$31.00 ©2022 IEEE | DOI: 10.1109/ITSC55140.2022.9922539 Authorized licensed use limited to: Guangdong Univ

全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。

To fill this gap, we proposed a 4D radar dataset for autonomous driving called TJ4DRadSet.

全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。

To fill this gap, we proposed a 4D radar dataset for autonomous driving called TJ4DRadSet.

全文第 1 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。

To fill this gap, we proposed a 4D radar dataset for autonomous driving called TJ4DRadSet.

全文第 6 页依据：中文翻译尚未生成，请点击“显示原文依据”查看英文内容。

We provide a detailed description of the dataset and conduct baseline experiments.