Authors: Yongjiang He, Peng Cao, Zhongling Su, Xiaobo Liu

Published on: July 25, 2024

Impact Score: 6.8

Arxiv code: Arxiv:2407.17942

Summary

• What is new: The introduction of a new LiDAR perception entropy metric based on the probability of vehicle grid occupancy and an optimization model that improves LiDAR deployment using a differential evolution-based particle swarm optimization algorithm.
• Why this is important: Lack of evaluation metrics that are both fast and accurate for measuring LiDAR perception based on object detection or point cloud data.
• What the research proposes: A novel LiDAR perception entropy metric and a deployment optimization model that is solved using a differential evolution-based particle swarm optimization algorithm.
• Results: The proposed metric has a correlation of over 0.98 with vehicle detection ground truth and improves detection Recall by 25% for RS-32 LiDAR.

Technical Details

Technological frameworks used: nan

Models used: Differential evolution-based particle swarm optimization algorithm

Data used: Vehicle grid occupancy probability, point cloud data from LiDARs (RS-16, RS-32, RS-80)

Potential Impact

Autonomous vehicles, LiDAR manufacturers, and companies involved in advanced driver assistance systems (ADAS) and smart city infrastructure.

Want to implement this idea in a business?

We have generated a startup concept here: LiDARSense OptiMetrics.