LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
arXiv:2103.02263
Abstract
Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. An alignment strategy, which we call Temporal Memory Alignment, uses ego motion to temporally align the memory between consecutive frames in feature space. A Residual Network and ConvGRU are investigated for the memory update. We demonstrate the benefits of the presented approach on two large-scale datasets and compare it to several stateof-the-art methods. Our approach ranks first on the SemanticKITTI multiple scan benchmark and achieves state-of-the-art performance on the single scan benchmark. In addition, the evaluation shows that the exploitation of temporal information significantly improves segmentation results compared to a single frame approach.
References in corpus (8)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- YOLOv3: An Incremental Improvement
- Deep Residual Learning for Image Recognition
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Delving Deeper into Convolutional Networks for Learning Video Representations
- SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
- The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
- SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud