Reinforcement Learning Based Optimal Camera Placement for Depth Observation of Indoor Scenes

TL;DR

This paper introduces an online reinforcement learning approach for optimal camera placement to improve depth observation accuracy in indoor scenes, outperforming traditional offline methods in various scenarios.

Contribution

It presents a novel RL-based system for real-time camera placement optimization tailored for depth observation in indoor environments.

Findings

Outperforms 7 of 10 baseline scenes in depth accuracy

Achieves less than 90% of baseline total error across tests

Demonstrates effectiveness without prior scene knowledge

Abstract

Exploring the most task-friendly camera setting -- optimal camera placement (OCP) problem -- in tasks that use multiple cameras is of great importance. However, few existing OCP solutions specialize in depth observation of indoor scenes, and most versatile solutions work offline. To this problem, an OCP online solution to depth observation of indoor scenes based on reinforcement learning is proposed in this paper. The proposed solution comprises a simulation environment that implements scene observation and reward estimation using shadow maps and an agent network containing a soft actor-critic (SAC)-based reinforcement learning backbone and a feature extractor to extract features from the observed point cloud layer-by-layer. Comparative experiments with two state-of-the-art optimization-based offline methods are conducted. The experimental results indicate that the proposed system outperforms seven out of ten test scenes in obtaining lower depth observation error. The total error in all test scenes is also less than 90% of the baseline ones. Therefore, the proposed system is more competent for depth camera placement in scenarios where there is no prior knowledge of the scenes or where a lower depth observation error is the main objective.