Plausibility Verification For 3D Object Detectors Using Energy-Based Optimization

TL;DR

This paper introduces an energy-based plausibility verification framework for 3D object detectors, enhancing safety and reducing false positives by leveraging cross-sensor data and a novel optimization schema.

Contribution

It proposes a new plausibility verification method using energy functions and a two-step optimization process for 3D object proposals in autonomous perception systems.

Findings

Reduces false positives in 3D object detection

Improves verification accuracy with energy functions

Enhances safety in autonomous vehicle perception

Abstract

Environmental perception obtained via object detectors have no predictable safety layer encoded into their model schema, which creates the question of trustworthiness about the system's prediction. As can be seen from recent adversarial attacks, most of the current object detection networks are vulnerable to input tampering, which in the real world could compromise the safety of autonomous vehicles. The problem would be amplified even more when uncertainty errors could not propagate into the submodules, if these are not a part of the end-to-end system design. To address these concerns, a parallel module which verifies the predictions of the object proposals coming out of Deep Neural Networks are required. This work aims to verify 3D object proposals from MonoRUn model by proposing a plausibility framework that leverages cross sensor streams to reduce false positives. The verification metric being proposed uses prior knowledge in the form of four different energy functions, each utilizing a certain prior to output an energy value leading to a plausibility justification for the hypothesis under consideration. We also employ a novel two-step schema to improve the optimization of the composite energy function representing the energy model.