Share This Author
Simple online and realtime tracking
- A. Bewley, ZongYuan Ge, Lionel Ott, F. Ramos, B. Upcroft
- Computer ScienceIEEE International Conference on Image Processing…
- 2 February 2016
Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers.
Gaussian process occupancy maps*
The technique can handle noisy data, potentially from multiple sources, and fuse it into a robust common probabilistic representation of the robot’s surroundings, and provides inferences with associated variances into occluded regions and between sensor beams, even with relatively few observations.
Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent
A new technique for environment representation through continuous occupancy mapping that improves on the popular occupancy grip maps, and allows for efficient stochastic gradient optimization where each measurement is only processed once during learning in an online manner is devised.
Planning Long Dynamically-Feasible Maneuvers for Autonomous Vehicles
An algorithm for generating complex dynamically-feasible maneuvers for autonomous vehicles traveling at high speeds over large distances based on performing anytime incremental search on a multiresolution, dynamically- Feasible lattice state space is presented.
Malicious Software Classification Using Transfer Learning of ResNet-50 Deep Neural Network
- Edmar R. S. Rezende, G. Ruppert, T. Carvalho, F. Ramos, Paulo Lício de Geus
- Computer Science16th IEEE International Conference on Machine…
- 1 December 2017
A malware family classification approach using a deep neural network based on the ResNet-50 architecture that can effectively be used to classify malware families with an accuracy of 98.62% is presented.
Gaussian Process modeling of large scale terrain
- S. Vasudevan, F. Ramos, E. Nettleton, H. Durrant-Whyte
- Computer ScienceIEEE International Conference on Robotics and…
- 12 May 2009
A single Non-Stationary (Neural Network) Gaussian Process is shown to be powerful enough to model large and complex terrain, handling issues relating to discontinuous data effectively and a local approximation methodology based on KD-Trees is proposed in order to ensure local smoothness and yet preserve the characteristic features of rich andcomplex terrain data.
Bayesian Optimisation for informative continuous path planning
- Román Marchant, F. Ramos
- Business, Computer ScienceIEEE International Conference on Robotics and…
- 29 September 2014
A layered Bayesian Optimisation approach that uses two Gaussian Processes, one to model the phenomenon and the other tomodel the quality of selected paths to tackle the exploration-exploitation trade off in a principled manner is devised.
Multi-scale Conditional Random Fields for first-person activity recognition
A feature extraction method from accelerometer and video; a classification algorithm integrating both locomotive (body motions) and stationary activities (without or with small motions); a novel multi-scale dynamic graphical model structure for structured classification over time.
Malicious Software Classification Using VGG16 Deep Neural Network’s Bottleneck Features
- Edmar R. S. Rezende, G. Ruppert, T. Carvalho, Antonio Theophilo, F. Ramos, Paulo Lício de Geus
- Computer Science
The experimental results showed that the VGG16 deep neural network approach can effectively be used to classify malware families with an accuracy of 92.97%, outperforming similar approaches proposed in the literature which require feature engineering and considerable domain expertise.
Sequential Bayesian Optimisation for Spatial-Temporal Monitoring
This work forms Sequential Bayesian Optimisation (SBO) with side-state information within a Partially Observed Markov Decision Process (POMDP) framework that can accommodate discrete and continuous observation spaces and shows that the SBO POMDP optimisation outperforms myopic and non-myopic alternatives.