In the better case, the pre-specified performances required to derive the controller will no longer be satisfied if some actuators saturate, because of, for example, perturbations or a setpoint change.
The closed-loop system may also evolve towards some other operation state with the risk that when the saturation ends, it cannot come back to the expected operating state. Motivations and interests in the analysis and synthesis of controllers for systems submitted to nonlinearities (saturations) on both actuators and sensors originate from those practical problems. Actuator saturation is one of the common nonlinearities present in various control systems. Which can limit the performance of a closed-loop system with undesirable results like large overshoots, large settling time, lag and instability, etc. It has caused accidents of power plants and many air-crafts.
We are currently working on a traffic signs detection-recognition-tracking system.
This work is done in collaboration with LE2I (France - Le Creusot) under supervision of Yohan Fougerolle.
Our contribution is threefold:
Proposition of a new naive detection based on color and shape retrieval.
Using the information of the detection, we propose to recognize traffic sign using machine learning methods.
In order to perform to accelerate the process of detection-recognition, we propose to introduce a tracking module information already extracted in the two previous stages.
The source code of this implementation is available in GitHub.
We develop a method allowing to track any kind of object inside a video.
Our method belongs to the group of features-based tracking method. In fact, features are detected in two consecutive images and correspondences are found.
Geometric transformation is estimated using the previous matching by the aid of a robust estimator.
The method proposes the following advantages:
Real-time computation.
Scale invariant.
Rotation invariant.
Partially robust to illumination changes.
Partially robust to occlusions.
More details can be found in the above publication:
G. Lemaitre, E. Vargiu, J.A. Lorenzo Fernández and F. Miralles,
"Real-Time 2D Face Detection and Features-based Tracking in Video",
IADIS Multi Conference in Computer Science in Computer Graphics, Visualization, Computer Vision and Image Processing 2012. Lisbon: Portugal (July 2012)
In this paper, pruning techniques for the AdaBoost classifier are evaluated specially aimed for continuous learning in sensor mining applications. To assess the methods, three pruning schemes are evaluated using standard machine-learning benchmark datasets, simulated drifting datasets and real world cases.
Early results obtained show that the pruning methodologies approach and sometimes out-perform the no-pruned version of the classifier, being at the same time more easily adaptable to the drift in the training distribution.
Future works are planned in order to evaluate the approach in terms of time efficiency and big-data extensions.
More details can be found in the above publication:
M. Rastgoo, G. Lemaitre, X. Rafael, F. Miralles and P. Casale,
"Pruning AdaBoost for Continuous Sensors Mining Applications",
Ubiquitous Data Mining Workshop, 20th European Conference in Artificial Intelligence 2012. Montpellier: France (August 2012)