Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Driving

07/11/2021
by   Ferhat Ozgur Catak, et al.
13

Object detection in autonomous cars is commonly based on camera images and Lidar inputs, which are often used to train prediction models such as deep artificial neural networks for decision making for object recognition, adjusting speed, etc. A mistake in such decision making can be damaging; thus, it is vital to measure the reliability of decisions made by such prediction models via uncertainty measurement. Uncertainty, in deep learning models, is often measured for classification problems. However, deep learning models in autonomous driving are often multi-output regression models. Hence, we propose a novel method called PURE (Prediction sURface uncErtainty) for measuring prediction uncertainty of such regression models. We formulate the object recognition problem as a regression model with more than one outputs for finding object locations in a 2-dimensional camera view. For evaluation, we modified three widely-applied object recognition models (i.e., YoLo, SSD300 and SSD512) and used the KITTI, Stanford Cars, Berkeley DeepDrive, and NEXET datasets. Results showed the statistically significant negative correlation between prediction surface uncertainty and prediction accuracy suggesting that uncertainty significantly impacts the decisions made by autonomous driving.

READ FULL TEXT

page 1

page 4

page 5

page 6

research
01/11/2023

Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective

Motion prediction is essential for safe and efficient autonomous driving...
research
05/31/2023

Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization

The uncertainty quantification of prediction models (e.g., neural networ...
research
01/24/2020

Temporal Pulses Driven Spiking Neural Network for Fast Object Recognition in Autonomous Driving

Accurate real-time object recognition from sensory data has long been a ...
research
02/16/2022

Reducing Overconfidence Predictions for Autonomous Driving Perception

In state-of-the-art deep learning for object recognition, SoftMax and Si...
research
10/18/2022

Object Recognition in Different Lighting Conditions at Various Angles by Deep Learning Method

Existing computer vision and object detection methods strongly rely on n...
research
03/28/2022

Neurosymbolic hybrid approach to driver collision warning

There are two main algorithmic approaches to autonomous driving systems:...
research
10/29/2018

Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks

Neural networks has been successfully used in the processing of Lidar da...

Please sign up or login with your details

Forgot password? Click here to reset