从驾驶者视角出发，提升复杂路况下关键物体识别精度。
A Two-Stage Framework for Ego-Centric Key Object Identification via Object State Prediction
- 构建虚拟驾驶者表征与模块化状态预测器，捕捉物体相对车辆行为
- 结合时空推理，依据物体状态与空间关系优先级排序
- 在真实驾驶数据集上验证，显著提升关键物体识别能力
本文提出一种新型框架，用于提升自动驾驶中关键物体的识别性能。现有方法多聚焦于独立检测物体或利用视觉关系，但未显式考虑驾驶者自身视角对物体重要性的判断。为弥补这一空白，我们设计了一种结构化方法，融合虚拟驾驶者表征与模块化物体状态预测器，实现对物体相对于自车行为的更准确估计。随后，通过时空推理机制，基于物体状态及其相对空间信息进行关键物体识别，而非仅依赖视觉关系。在真实驾驶数据集上的实验结果表明，该方法在复杂交通环境中能有效识别出关键物体，显著提升识别准确性。
原文摘要 · Abstract (English)
This paper presents a novel framework designed to enhance key object identification in autonomous driving. Existing methods primarily focus on either detecting objects independently or leveraging visual relationships, but they do not explicitly consider the ego vehicle's perspective in determining object importance. To address this gap, we propose a structured approach that integrates a virtual ego-vehicle representation and a modular object state predictor, enabling a more accurate estimation of object behaviors relative to the ego-vehicle. Subsequently, our framework employs spatial-temporal reasoning to refine key object identification, prioritizing objects based on their states and relative spatial information rather than relying solely on visual relationships. Experimental results on real-world driving datasets demonstrate the effectiveness of our approach in accurately detecting critical objects in complex traffic environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。