Artificial Dummies for Urban Dataset Augmentation

12/15/2020
by   Antonin Vobecky, et al.
0

Existing datasets for training pedestrian detectors in images suffer from limited appearance and pose variation. The most challenging scenarios are rarely included because they are too difficult to capture due to safety reasons, or they are very unlikely to happen. The strict safety requirements in assisted and autonomous driving applications call for an extra high detection accuracy also in these rare situations. Having the ability to generate people images in arbitrary poses, with arbitrary appearances and embedded in different background scenes with varying illumination and weather conditions, is a crucial component for the development and testing of such applications. The contributions of this paper are three-fold. First, we describe an augmentation method for controlled synthesis of urban scenes containing people, thus producing rare or never-seen situations. This is achieved with a data generator (called DummyNet) with disentangled control of the pose, the appearance, and the target background scene. Second, the proposed generator relies on novel network architecture and associated loss that takes into account the segmentation of the foreground person and its composition into the background scene. Finally, we demonstrate that the data generated by our DummyNet improve performance of several existing person detectors across various datasets as well as in challenging situations, such as night-time conditions, where only a limited amount of training data is available. In the setup with only day-time data available, we improve the night-time detector by 17% log-average miss rate over the detector trained with the day-time data only.

READ FULL TEXT

page 2

page 4

page 6

page 13

page 16

page 18

page 19

page 20

research
01/10/2022

Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing

In an autonomous driving system, perception - identification of features...
research
07/22/2017

Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset

Person detection from vehicles has made rapid progress recently with the...
research
06/23/2023

Improving Panoptic Segmentation for Nighttime or Low-Illumination Urban Driving Scenes

Autonomous vehicles and driving systems use scene parsing as an essentia...
research
03/18/2023

3D Data Augmentation for Driving Scenes on Camera

Driving scenes are extremely diverse and complicated that it is impossib...
research
02/22/2022

A-Eye: Driving with the Eyes of AI for Corner Case Generation

The overall goal of this work is to enrich training data for automated d...
research
03/18/2017

Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters

As autonomous vehicles become an every-day reality, high-accuracy pedest...

Please sign up or login with your details

Forgot password? Click here to reset