Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
arXiv:1809.04730 · doi:10.1109/LRA.2019.2891027
Abstract
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete semantic understanding of the forward surroundings, we propose to stitch semantic images from multiple cameras with varying orientations. However, previously trained semantic segmentation models showed unacceptable performance after significant changes to the camera orientations and the lighting conditions. To avoid time-consuming hand labeling, we explore and evaluate the use of data augmentation techniques, specifically skew and gamma correction, from a practical real-world standpoint to extend the existing model and provide more robust performance. The presented experimental results have shown significant improvements with varying illumination and camera perspective changes.
arXiv commentSubmitted to IEEE Robotics and Automation Letters (RA-L) and 2019 IEEE International Conference on Robotics and Automation (ICRA)
References in corpus (10)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Fully Convolutional Networks for Semantic Segmentation
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- AutoAugment: Learning Augmentation Policies from Data
- Smart Augmentation - Learning an Optimal Data Augmentation Strategy
- Pyramid Scene Parsing Network
- Enabling Pedestrian Safety using Computer Vision Techniques: A Case Study of the 2018 Uber Inc. Self-driving Car Crash
- RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
- Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis