Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery

Abstract

Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360° panoramic cameras. We present an approach to adapt contemporary deep network architectures developed on conventional rectilinear imagery to work on equirectangular 360° panoramic imagery. To address the lack of annotated panoramic automotive datasets availability, we adapt a contemporary automotive dataset, via style and projection transformations, to facilitate the cross-domain retraining of contemporary algorithms for panoramic imagery. Following this approach we retrain and adapt existing architectures to recover scene depth and 3D pose of vehicles from monocular panoramic imagery without any panoramic training labels or calibration parameters. Our approach is evaluated qualitatively on crowd-sourced panoramic images and quantitatively using an automotive environment simulator to provide the first benchmark for such techniques within panoramic imagery.

This work is accepted in ECCV 2018

References in corpus (10)

• Learning Transferable Features with Deep Adaptation Networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• A Learned Representation For Artistic Style
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Adversarial Discriminative Domain Adaptation
• CARLA: An Open Urban Driving Simulator
• Learning Spherical Convolution for Fast Features from 360° Imagery
• Semi-Supervised Deep Learning for Monocular Depth Map Prediction
• Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
• Accurate Single Stage Detector Using Recurrent Rolling Convolution