Miguel Angel Sotelo
University of Alcalá
265 Papers
1.2K Citations
Miguel Angel Sotelo is an academic researcher from University of Alcalá. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 35, co-authored 235 publications. Previous affiliations of Miguel Angel Sotelo include University of Alabama.
Chat about Author
Papers
Image Sequence Matching Using Both Holistic and Local Features for Loop Closure Detection
TL;DR: A novel loop closure detection method called image sequence matching (ISM), which only uses a low-cost monocular camera, which has high accuracy and great robustness, and a novel clustering method called voting K-nearest neighbor to fuse candidates.
15
Stereo-based pedestrian detection in crosswalks for pedestrian behavioural modelling assessment
David Fernández Llorca,I. Parra,R. Quintero,Carmen Cagigas Fernández,R. Izquierdo,Miguel Angel Sotelo +5 more
- 01 Sep 2014
TL;DR: A sequential feature selection method showed that time-to-collision and pedestrian waiting time (both variables automatically collected) are the most significant parameters when predicting the pedestrian intent, which clearly validates the proposed methodology.
A Novel Multimode Hybrid Control Method for Cooperative Driving of an Automated Vehicle Platoon
TL;DR: The proposed cooperative driving strategy for vehicle platoon is evaluated using simulations, where varying traffic conditions and the influence of cutting off are considered in conjunction with demonstration simulations of a vehicle platoon’s cruising, following, lane changing, overtaking, and moving in/out of garage functions.
15
Perception advances in outdoor vehicle detection for automatic cruise control
S. Álvarez,Miguel Angel Sotelo,Manuel Ocaña,David Fernández Llorca,Ignacio Parra,Luis M. Bergasa +5 more
TL;DR: The vehicle detection system described in this paper provides early detection of passing cars and assigns lane to target vehicles and an intelligent learning approach is proposed in order to better deal with objects variability, illumination conditions, partial occlusions and rotations.
Low level controller for a POMDP based on WiFi observations
TL;DR: Observations from a low level controller applied to an autonomous robotic system using a WiFi-based Partially Observable Markov Decision Process provide a clue for global robot localization from the first iteration of the POMDP algorithm.
14