I
Ian Reid
Researcher at University of Adelaide
Publications - 474
Citations - 47964
Ian Reid is an academic researcher from University of Adelaide. The author has contributed to research in topics: Deep learning & Segmentation. The author has an hindex of 88, co-authored 469 publications receiving 37035 citations. Previous affiliations of Ian Reid include Brunel University London & Queensland University of Technology.
Papers
More filters
Journal ArticleDOI
MonoSLAM: Real-Time Single Camera SLAM
TL;DR: The first successful application of the SLAM methodology from mobile robotics to the "pure vision" domain of a single uncontrolled camera, achieving real time but drift-free performance inaccessible to structure from motion approaches is presented.
Proceedings ArticleDOI
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
TL;DR: RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner.
Journal ArticleDOI
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age
Cesar Cadena,Luca Carlone,Henry Carrillo,Yasir Latif,Davide Scaramuzza,José Neira,Ian Reid,John J. Leonard +7 more
TL;DR: Simultaneous localization and mapping (SLAM) as mentioned in this paper consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it.
Journal ArticleDOI
Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
Cesar Cadena,Luca Carlone,Henry Carrillo,Yasir Latif,Davide Scaramuzza,José L. Neira,Ian Reid,John J. Leonard +7 more
TL;DR: What is now the de-facto standard formulation for SLAM is presented, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers.
Proceedings ArticleDOI
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
TL;DR: In this paper, a generalized IoU (GIoU) metric is proposed for non-overlapping bounding boxes, which can be directly used as a regression loss.