G. Payen de La Garanderie
Eliminating the Dreaded Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
Payen de La Garanderie, G.; Atapour-Abarghouei, A.; Breckon, T.P.
Professor Toby Breckon firstname.lastname@example.org
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 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.
Payen de La Garanderie, G., Atapour-Abarghouei, A., & Breckon, T. (2018). Eliminating the Dreaded Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery.
|15th European Conference on Computer Vision (ECCV 2018)
|Sep 8, 2018
|Sep 14, 2018
|Jul 5, 2018
|Sep 1, 2018
|Sep 19, 2018
|Lecture Notes in Computer Science (LNCS)
You might also like
Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
U3DS3 : Unsupervised 3D Semantic Scene Segmentation
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation