Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation

The automotive mmWave radar plays a key role in advanced driver assistance systems (ADAS) and autonomous driving. Deep learning-based instance segmentation enables real-time object identification from the radar detection points. In the conventional training process, accurate annotation is the key. However, high-quality annotations of radar detection points are challenging to achieve due to their ambiguity and sparsity. To address this issue, we propose a contrastive learning approach for implementing radar detection points-based instance segmentation. We define the positive and negative samples according to the ground-truth label, apply the contrastive loss to train the model first, and then perform fine-tuning for the following downstream task. In addition, these two steps can be merged into one, and pseudo labels can be generated for the unlabeled data to improve the performance further. Thus, there are four different training settings for our method. Experiments show that when the ground-truth information is only available for a small proportion of the training data, our method still achieves a comparable performance to the approach trained in a supervised manner with 100% ground-truth information.

[1]  Wanli Ouyang,et al.  Deep Instance Segmentation With Automotive Radar Detection Points , 2021, IEEE Transactions on Intelligent Vehicles.

[2]  Yi Zhou,et al.  Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges , 2022, Sensors.

[3]  Weiping Wang,et al.  Dense Semantic Contrast for Self-Supervised Visual Representation Learning , 2021, ACM Multimedia.

[4]  Quoc V. Le,et al.  Pay Attention to MLPs , 2021, NeurIPS.

[5]  Jenq-Neng Hwang,et al.  Rethinking of Radar’s Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Jürgen Dickmann,et al.  RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications , 2021, 2021 IEEE 24th International Conference on Information Fusion (FUSION).

[7]  L. Gool,et al.  Exploring Cross-Image Pixel Contrast for Semantic Segmentation , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[8]  Jenq-Neng Hwang,et al.  RODNet: Radar Object Detection using Cross-Modal Supervision , 2021, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[9]  Ying Wu,et al.  Contrastive Learning for Label Efficient Semantic Segmentation , 2020, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[10]  Federico Tombari,et al.  Panoster: End-to-End Panoptic Segmentation of LiDAR Point Clouds , 2020, IEEE Robotics and Automation Letters.

[11]  F. Tupin,et al.  CARRADA Dataset: Camera and Automotive Radar with Range- Angle- Doppler Annotations , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[12]  Cyrill Stachniss,et al.  A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI , 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Yuxuan Xia,et al.  Deep Instance Segmentation with High-Resolution Automotive Radar , 2021, ArXiv.

[14]  Bowen Gong,et al.  Slice-Based Instance and Semantic Segmentation for Low-Channel Roadside LiDAR Data , 2020, Remote. Sens..

[15]  Christian Wöhler,et al.  Scene Understanding With Automotive Radar , 2020, IEEE Transactions on Intelligent Vehicles.

[16]  Bowen Gong,et al.  Background Point Filtering of Low-Channel Infrastructure-Based LiDAR Data Using a Slice-Based Projection Filtering Algorithm , 2020, Sensors.

[17]  Ruigang Yang,et al.  Instance Segmentation of LiDAR Point Clouds , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[19]  Xuetao Hao,et al.  Adaptive Attention Model for Lidar Instance Segmentation , 2019, ISVC.

[20]  Wayne Stark,et al.  Interference in Automotive Radar Systems: Characteristics, mitigation techniques, and current and future research , 2019, IEEE Signal Processing Magazine.

[21]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[22]  Jürgen Dickmann,et al.  Supervised Clustering for Radar Applications: On the Way to Radar Instance Segmentation , 2018, 2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM).

[23]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[24]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.