# LiDAR Sensor Parameter Augmentation and Data-Driven Influence Analysis on Deep-Learning-Based People Detection

## TL;DR

This paper explores how LiDAR sensor parameters affect people detection using deep learning, showing that lower quality data can still yield good results.

## Contribution

The paper introduces augmentation methods to analyze LiDAR sensor parameters' influence on deep learning-based people detection.

## Key findings

- Reduced LiDAR resolution by up to 32 factors caused less than 5% degradation in object detection.
- Both PV-RCNN and SECOND networks require unshaded head height of ~0.5 m for good detection performance.
- Shadowing information is used in a software program to optimize sensor placement and orientation.

## Abstract

Light detection and ranging (LiDAR) sensor technology for people detection offers a significant advantage in data protection. However, to design these systems cost- and energy-efficiently, the relationship between the measurement data and final object detection output with deep neural networks (DNNs) has to be elaborated. Therefore, this paper presents augmentation methods to analyze the influence of the distance, resolution, noise, and shading parameters of a LiDAR sensor in real point clouds for people detection. Furthermore, their influence on object detection using DNNs was investigated. A significant reduction in the quality requirements for the point clouds was possible for the measurement setup with only minor degradation on the object list level. The DNNs PointVoxel-Region-based Convolutional Neural Network (PV-RCNN) and Sparsely Embedded Convolutional Detection (SECOND) both only show a reduction in object detection of less than 5% with a reduced resolution of up to 32 factors, for an increase in distance of 4 factors, and with a Gaussian noise up to μ=0 and σ=0.07. In addition, both networks require an unshaded height of approx. 0.5 m from a detected person’s head downwards to ensure good people detection performance without special training for these cases. The results obtained, such as shadowing information, are transferred to a software program to determine the minimum number of sensors and their orientation based on the mounting height of the sensor, the sensor parameters, and the ground area under consideration, both for detection at the point cloud level and object detection level.