DeepAI AI Chat
Log In Sign Up

DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scans

by   Ayush Dewan, et al.

Understanding the semantic characteristics of the environment is a key enabler for autonomous robot operation. In this paper, we propose a deep convolutional neural network (DCNN) for the semantic segmentation of a LiDAR scan into the classes car, pedestrian or bicyclist. This architecture is based on dense blocks and efficiently utilizes depth separable convolutions to limit the number of parameters while still maintaining state-of-the-art performance. To make the predictions from the DCNN temporally consistent, we propose a Bayes filter based method. This method uses the predictions from the neural network to recursively estimate the current semantic state of a point in a scan. This recursive estimation uses the knowledge gained from previous scans, thereby making the predictions temporally consistent and robust towards isolated erroneous predictions. We compare the performance of our proposed architecture with other state-of-the-art neural network architectures and report substantial improvement. For the proposed Bayes filter approach, we show results on various sequences in the KITTI tracking benchmark.


A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI

Panoptic segmentation is the recently introduced task that tackles seman...

PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data

Semantic understanding of the surrounding environment is essential for a...

KPRNet: Improving projection-based LiDAR semantic segmentation

Semantic segmentation is an important component in the perception system...

Deep Semantic Classification for 3D LiDAR Data

Robots are expected to operate autonomously in dynamic environments. Und...

Semi-Local Convolutions for LiDAR Scan Processing

A number of applications, such as mobile robots or automated vehicles, u...

4D Panoptic Segmentation as Invariant and Equivariant Field Prediction

In this paper, we develop rotation-equivariant neural networks for 4D pa...

Code Repositories