原文传递
Active Sensing Representations for Navigation and Visual Scene Analysis.
| 题名： | Active Sensing Representations for Navigation and Visual Scene Analysis. |
| 作者： | Soatto, S. |
| 关键词： | Image statistical deep, Artificial neural networks, Point clouds, Detectors, Deep learning, Image recognition, Sgd(stochastic gradient descent), Visual scene analysis, Visual data |
| 摘要： | This project, kicked off in September of 2015, aimed at developing analytical and computational tools to infer optimal representations for decision and control actions based on visual data. Specifically, corresponding to (classes of) tasks, different representations can be designed. For localization tasks, EO imaging and inertial sensors can be used to develop a representation that is minimal-sufficient (an attributed point cloud) and invariant to changes of illumination and partial occlusion. The result is a posterior estimate of the sensor trajectory in SE(3) given all measurements up to the current time, marginalized with respect to all nuisance variability. Semantic understanding of the scene requires more sophisticated representations than point cloud. |
| 报告类型： | 科技报告 |
相关文献
- Survey of Iceberg Sensing by Satellite Imagery. Cost and Operational Effectiveness Analysis for Selected International Ice Patrol Mission Alternatives. Annex I.
- Beyond the cockpit: The visual world as a flight instrument
- FIELD STUDY OF DRIVER'S CURVE-DETECTION PERFORMANCE IN DAYTIME AND NIGHTTIME.
- Towards Autonomous Miniature Rotorcrafts in Cluttered Environments for Scene Understanding.
- The Relationship of Sector Characteristics to Operational Errors
- Autonomous UAV Landing in a Box on a Moving Platform.
检索历史
应用推荐
