Reducing the False Positive Rate Using Bayesian Inference in Autonomous Driving Perception

TL;DR

This paper proposes a Bayesian inference-based method to reduce false positive rates in autonomous vehicle perception systems by integrating multisensory data and validating on the KITTI dataset.

Contribution

It introduces a novel Bayesian inference approach utilizing Gaussian kernel density estimations and normalized histograms to lower false positives in object recognition.

Findings

Significant reduction in false positive rates demonstrated on KITTI dataset.

Effective integration of RGB and LiDAR modalities improves recognition accuracy.

Applicable to deep networks like DenseNet, NasNet, EfficientNet, and 3D point cloud networks.

Abstract

Object recognition is a crucial step in perception systems for autonomous and intelligent vehicles, as evidenced by the numerous research works in the topic. In this paper, object recognition is explored by using multisensory and multimodality approaches, with the intention of reducing the false positive rate (FPR). The reduction of the FPR becomes increasingly important in perception systems since the misclassification of an object can potentially cause accidents. In particular, this work presents a strategy through Bayesian inference to reduce the FPR considering the likelihood function as a cumulative distribution function from Gaussian kernel density estimations, and the prior probabilities as cumulative functions of normalized histograms. The validation of the proposed methodology is performed on the KITTI dataset using deep networks (DenseNet, NasNet, and EfficientNet), and recent 3D point cloud networks (PointNet, and PintNet++), by considering three object-categories (cars, cyclists, pedestrians) and the RGB and LiDAR sensor modalities.