PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving
This addresses the need for concise structural representations of objects in driving scenarios, though it appears incremental with its multi-task approach.
The paper tackles the problem of unified multi-category skeleton detection for autonomous driving by introducing PoseDriver, which models each category as a distinct task and achieves state-of-the-art performance on the OpenLane dataset for lane detection.
Object skeletons offer a concise representation of structural information, capturing essential aspects of posture and orientation that are crucial for autonomous driving applications. However, a unified architecture that simultaneously handles multiple instances and categories using only the input image remains elusive. In this paper, we introduce PoseDriver, a unified framework for bottom-up multi-category skeleton detection tailored to common objects in driving scenarios. We model each category as a distinct task to systematically address the challenges of multi-task learning. Specifically, we propose a novel approach for lane detection based on skeleton representations, achieving state-of-the-art performance on the OpenLane dataset. Moreover, we present a new dataset for bicycle skeleton detection and assess the transferability of our framework to novel categories. Experimental results validate the effectiveness of the proposed approach.