Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection

2025-06-26

AI Summary

In safety-critical applications such as autonomous driving, conventional object detectors lack the ability to quantify whether “undetected regions” (i.e., free space) are truly obstacle-free—a critical gap in spatial safety reasoning. To address this, we propose the first object detection framework based on Conditional Marked Point Processes (CMPPs). Unlike standard approaches that only calibrate confidence scores for positive detections, our method models detection as a semantic-marked spatial point process, explicitly characterizing the drivability probability distribution over free space. Leveraging likelihood-driven training and uncertainty calibration, the framework yields physically interpretable and statistically verifiable probabilistic outputs. Empirically, it maintains competitive standard detection performance while significantly improving confidence calibration and reliability in free-space assessment—enabling principled, uncertainty-aware safety reasoning for autonomous systems.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Computer Vision: Object Detection & Categorization

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Deep neural networks have set the state-of-the-art in computer vision tasks such as bounding box detection and semantic segmentation. Object detectors and segmentation models assign confidence scores to predictions, reflecting the model's uncertainty in object detection or pixel-wise classification. However, these confidence estimates are often miscalibrated, as their architectures and loss functions are tailored to task performance rather than probabilistic foundation. Even with well calibrated predictions, object detectors fail to quantify uncertainty outside detected bounding boxes, i.e., the model does not make a probability assessment of whether an area without detected objects is truly free of obstacles. This poses a safety risk in applications such as automated driving, where uncertainty in empty areas remains unexplored. In this work, we propose an object detection model grounded in spatial statistics. Bounding box data matches realizations of a marked point process, commonly used to describe the probabilistic occurrence of spatial point events identified as bounding box centers, where marks are used to describe the spatial extension of bounding boxes and classes. Our statistical framework enables a likelihood-based training and provides well-defined confidence estimates for whether a region is drivable, i.e., free of objects. We demonstrate the effectiveness of our method through calibration assessments and evaluation of performance.

Problem

• Miscalibrated confidence estimates in object detection models
• Uncertainty quantification failure in empty areas without detected objects
• Safety risks in applications like automated driving due to unexplored uncertainty

Innovation

• Conditional marked point processes for detection
• Likelihood-based training for confidence estimates
• Spatial statistics framework for empty regions