DPGP: A Hybrid 2D-3D Dual Path Potential Ghost Probe Zone Prediction Framework for Safe Autonomous Driving

2025-04-23

AI Summary

In dense urban traffic, “ghost detection”—i.e., sudden emergence of pedestrians or objects into the vehicle’s path from non-line-of-sight (NLOS) regions—poses critical safety risks. Method: This paper proposes a lightweight 2D–3D fusion prediction framework leveraging only a monocular camera. It extends ghost detection region prediction to non-vehicular dynamic objects for the first time and introduces an unsupervised multi-representation feature fusion mechanism grounded in depth discontinuity priors—requiring no V2X communication, specialized hardware, or manual depth annotations. Contribution/Results: Evaluated on a newly curated dataset of 12K annotated images, our model outperforms state-of-the-art methods with <1.2M parameters and real-time inference speed exceeding 30 FPS, demonstrating readiness for onboard deployment. Both code and dataset will be publicly released.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Modern robots must coexist with humans in dense urban environments. A key challenge is the ghost probe problem, where pedestrians or objects unexpectedly rush into traffic paths. This issue affects both autonomous vehicles and human drivers. Existing works propose vehicle-to-everything (V2X) strategies and non-line-of-sight (NLOS) imaging for ghost probe zone detection. However, most require high computational power or specialized hardware, limiting real-world feasibility. Additionally, many methods do not explicitly address this issue. To tackle this, we propose DPGP, a hybrid 2D-3D fusion framework for ghost probe zone prediction using only a monocular camera during training and inference. With unsupervised depth prediction, we observe ghost probe zones align with depth discontinuities, but different depth representations offer varying robustness. To exploit this, we fuse multiple feature embeddings to improve prediction. To validate our approach, we created a 12K-image dataset annotated with ghost probe zones, carefully sourced and cross-checked for accuracy. Experimental results show our framework outperforms existing methods while remaining cost-effective. To our knowledge, this is the first work extending ghost probe zone prediction beyond vehicles, addressing diverse non-vehicle objects. We will open-source our code and dataset for community benefit.

Problem

• Predict ghost probe zones for safe autonomous driving
• Address ghost probe problem with hybrid 2D-3D fusion
• Detect unexpected pedestrian or object intrusions in traffic

Innovation

• Hybrid 2D-3D fusion for ghost probe prediction
• Unsupervised depth prediction with monocular camera
• Multi-feature fusion enhances prediction robustness