DeepAI AI Chat
Log In Sign Up

Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation

by   Ahmad El Sallab, et al.
Cairo University

Data scarcity is a bottleneck to machine learning-based perception modules, usually tackled by augmenting real data with synthetic data from simulators. Realistic models of the vehicle perception sensors are hard to formulate in closed form, and at the same time, they require the existence of paired data to be learned. In this work, we propose two unsupervised neural sensor models based on unpaired domain translations with CycleGANs and Neural Style Transfer techniques. We employ CARLA as the simulation environment to obtain simulated LiDAR point clouds, together with their annotations for data augmentation, and we use KITTI dataset as the real LiDAR dataset from which we learn the realistic sensor model mapping. Moreover, we provide a framework for data augmentation and evaluation of the developed sensor models, through extrinsic object detection task evaluation using YOLO network adapted to provide oriented bounding boxes for LiDAR Bird-eye-View projected point clouds. Evaluation is performed on unseen real LiDAR frames from KITTI dataset, with different amounts of simulated data augmentation using the two proposed approaches, showing improvement of 6 augmenting LiDAR point clouds adapted with the proposed neural sensor models over the raw simulated LiDAR.


page 2

page 8


LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving

In the autonomous driving domain, data collection and annotation from re...

Learning to Simulate Realistic LiDARs

Simulating realistic sensors is a challenging part in data generation fo...

KITTI-CARLA: a KITTI-like dataset generated by CARLA Simulator

KITTI-CARLA is a dataset built from the CARLA v0.9.10 simulator using a ...

A Simulation-based End-to-End Learning Framework for Evidential Occupancy Grid Mapping

Evidential occupancy grid maps (OGMs) are a popular representation of th...

Instant Domain Augmentation for LiDAR Semantic Segmentation

Despite the increasing popularity of LiDAR sensors, perception algorithm...

Lifting 2D Object Locations to 3D by Discounting LiDAR Outliers across Objects and Views

We present a system for automatic converting of 2D mask object predictio...