IROAM: Improving Roadside Monocular 3D Object Detection Learning from Autonomous Vehicle Data Domain
This addresses a domain-specific problem for autonomous driving systems by improving roadside perception, but it appears incremental as it builds on existing methods to handle domain gaps.
The paper tackled the problem of viewpoint domain gaps in monocular 3D object detection between vehicle and roadside cameras in autonomous driving, proposing IROAM to improve roadside detection performance, though no concrete numbers were provided in the abstract.
In autonomous driving, The perception capabilities of the ego-vehicle can be improved with roadside sensors, which can provide a holistic view of the environment. However, existing monocular detection methods designed for vehicle cameras are not suitable for roadside cameras due to viewpoint domain gaps. To bridge this gap and Improve ROAdside Monocular 3D object detection, we propose IROAM, a semantic-geometry decoupled contrastive learning framework, which takes vehicle-side and roadside data as input simultaneously. IROAM has two significant modules. In-Domain Query Interaction module utilizes a transformer to learn content and depth information for each domain and outputs object queries. Cross-Domain Query Enhancement To learn better feature representations from two domains, Cross-Domain Query Enhancement decouples queries into semantic and geometry parts and only the former is used for contrastive learning. Experiments demonstrate the effectiveness of IROAM in improving roadside detector's performance. The results validate that IROAM has the capabilities to learn cross-domain information.