PoseDriver: A Unified Approach to Multi-Category Skeleton Detection for Autonomous Driving

TL;DR

PoseDriver introduces a unified multi-category skeleton detection framework for autonomous driving, effectively handling multiple object types and demonstrating state-of-the-art results in lane detection and new bicycle skeleton datasets.

Contribution

It presents a novel unified architecture for multi-category skeleton detection, modeling each category as a separate task, and extends to new object categories like bicycles.

Findings

Achieves state-of-the-art lane detection performance

Introduces a new bicycle skeleton dataset

Validates transferability to new categories

Abstract

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.