Céline Craye

Celine Craye, Timothee Lesort, David Filliat et al.

The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual saliency directly on a robot. This model, learned and improved on-the-fly during the robot's exploration provides an efficient tool for localizing relevant objects within their environment. The proposed approach includes two intertwined components. On the one hand, we describe a method for learning and incrementally updating a model of visual saliency from a depth-based object detector. This model of saliency can also be exploited to produce bounding box proposals around objects of interest. On the other hand, we investigate an autonomous exploration technique to efficiently learn such a saliency model. The proposed exploration, called Reinforcement Learning-Intelligent Adaptive Curiosity (RL-IAC) is able to drive the robot's exploration so that samples selected by the robot are likely to improve the current model of saliency. We then demonstrate that such a saliency model learned directly on a robot outperforms several state-of-the-art saliency techniques, and that RL-IAC can drastically decrease the required time for learning a reliable saliency model.

Céline Craye, Fakhri Karray

Driver inattention assessment has become a very active field in intelligent transportation systems. Based on active sensor Kinect and computer vision tools, we have built an efficient module for detecting driver distraction and recognizing the type of distraction. Based on color and depth map data from the Kinect, our system is composed of four sub-modules. We call them eye behavior (detecting gaze and blinking), arm position (is the right arm up, down, right of forward), head orientation, and facial expressions. Each module produces relevant information for assessing driver inattention. They are merged together later on using two different classification strategies: AdaBoost classifier and Hidden Markov Model. Evaluation is done using a driving simulator and 8 drivers of different gender, age and nationality for a total of more than 8 hours of recording. Qualitative and quantitative results show strong and accurate detection and recognition capacity (85% accuracy for the type of distraction and 90% for distraction detection). Moreover, each module is obtained independently and could be used for other types of inference, such as fatigue detection, and could be implemented for real cars systems.