# Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving

## TL;DR

This paper introduces Gaussian YOLOv3, a real-time object detection method that models bounding boxes with Gaussian parameters and predicts localization uncertainty, significantly improving accuracy and reducing false positives for autonomous driving.

## Contribution

The paper presents a novel Gaussian modeling of bounding boxes and a localization uncertainty prediction in YOLOv3, enhancing detection accuracy and reliability in autonomous driving.

## Key findings

- Improves mAP by 3.09 on KITTI and 3.5 on BDD datasets.
- Achieves real-time detection at over 42 fps.
- Reduces false positives and increases true positives.

## Abstract

The use of object detection algorithms is becoming increasingly important in autonomous vehicles, and object detection at high accuracy and a fast inference speed is essential for safe autonomous driving. A false positive (FP) from a false localization during autonomous driving can lead to fatal accidents and hinder safe and efficient driving. Therefore, a detection algorithm that can cope with mislocalizations is required in autonomous driving applications. This paper proposes a method for improving the detection accuracy while supporting a real-time operation by modeling the bounding box (bbox) of YOLOv3, which is the most representative of one-stage detectors, with a Gaussian parameter and redesigning the loss function. In addition, this paper proposes a method for predicting the localization uncertainty that indicates the reliability of bbox. By using the predicted localization uncertainty during the detection process, the proposed schemes can significantly reduce the FP and increase the true positive (TP), thereby improving the accuracy. Compared to a conventional YOLOv3, the proposed algorithm, Gaussian YOLOv3, improves the mean average precision (mAP) by 3.09 and 3.5 on the KITTI and Berkeley deep drive (BDD) datasets, respectively. Nevertheless, the proposed algorithm is capable of real-time detection at faster than 42 frames per second (fps) and shows a higher accuracy than previous approaches with a similar fps. Therefore, the proposed algorithm is the most suitable for autonomous driving applications.