S
Stephan Hasler
Researcher at Honda
Publications - 26
Citations - 229
Stephan Hasler is an academic researcher from Honda. The author has contributed to research in topics: Object detection & Mobile robot. The author has an hindex of 8, co-authored 25 publications receiving 207 citations.
Papers
More filters
Journal ArticleDOI
Active 3D Object Localization Using a Humanoid Robot
Alexander Andreopoulos,Stephan Hasler,Heiko Wersing,Herbert Janssen,John K. Tsotsos,Edgar Körner +5 more
TL;DR: A target probability updating scheme is described, providing an efficient solution to the selection of the best next viewpoint in the problem of actively searching for an object in a 3-D environment under the constraint of a maximum search time using a visually guided humanoid robot with 26 degrees of freedom.
Journal ArticleDOI
A vision architecture for unconstrained and incremental learning of multiple categories
Stephan Kirstein,Stephan Kirstein,Alexander Denecke,Alexander Denecke,Stephan Hasler,Heiko Wersing,Horst-Michael Gross,Edgar Körner +7 more
TL;DR: This work presents an integrated vision architecture capable of incrementally learning several visual categories based on natural hand-held objects and imposes no restrictions on the viewing angle of presented objects, relaxing the common constraint on canonical views.
Proceedings ArticleDOI
System approach for multi-purpose representations of traffic scene elements
Jens Schmuedderich,Nils Einecke,Stephan Hasler,Alexander Gepperth,Bram Bolder,Robert Kastner,Mathias Franzius,Sven Rebhan,Benjamin Dittes,Heiko Wersing,Julian Eggert,Jannik Fritsch,Christian Goerick +12 more
TL;DR: This work presents the most recent integrated system performing object detection in challenging environments and demonstrates that the used generic hypothesis representations allow successful application to a variety of tasks including object detection, movement estimation, and risk assessment by time-to-contact evaluation.
Journal ArticleDOI
Biased Competition in Visual Processing Hierarchies: A Learning Approach Using Multiple Cues
TL;DR: A large-scale hierarchical system for object detection fusing bottom-up processing results with top-down (model or task-driven) attentional modulation, which results in object-specific hypothesis facilitation/suppression in certain image regions which are applicable to different object detection mechanisms.
Journal ArticleDOI
Combining Reconstruction and Discrimination with Class-Specific Sparse Coding
TL;DR: Two new methods that extend the traditional sparse coding approach with supervised components are presented to increase the suitability of the learned features for classification tasks while keeping most of their general representation capability.