Search

International audience; In recent years, due to the reasonable price of RGB-D devices, the use of skeletal-based data in the field of human-computer interaction has attracted a lot of attention. Being free from problems such as complex backgrounds as well as changes in light is another reason for the popularity of this type of data. In the existing methods, the use of joint and bone information has had significant results in improving the recognition of human movements and even emotions. However, how to combine these two types of information in the best possible way to define the relationship between joints and bones is a problem that has not yet been solved. In this article, we used the Laban Movement Analysis (LMA) to build a robust descriptor and present a precise description of the connection of the different parts of the body to itself and its surrounding environment while performing a gesture. To do this, in addition to the distances between the hip center and other joints of the body and the changes of the quaternion angles in time, we define the triangles formed by the different parts of the body and calculate their area. We also calculate the area of the single conforming 3-D boundary around all the joints of the body. We use a long short-term memory (LSTM) network to evaluate this descriptor. The proposed algorithm is implemented on five public datasets: NTU RGB+D 120, SYSU 3D HOI, FLORENCE 3D ACTIONS, MSR Action3D and UTKinect-Action3D datasets, and the results are compared with those available in the literature.

International audience; The robustness of object detection algorithms plays a prominent role in real-world applications, especially in the uncontrolled environments due to distortions during image acquisition. It has been proved that object detection methods suffer from in-capture distortions to perform a reliable detection. In this study, we present a performance evaluation framework of the state-of-the-art object detection methods on a dedicated dataset containing images with various distortions at different levels of severity. Furthermore, we propose an original strategy of image distortion generation applied to the MSCOCO dataset that combines some local and global distortions to reach a better realism. We have shown that training with this distorted dataset improves the robustness of models by 31.5%. Finally, we provided a custom dataset including the natural images distorted from MS-COCO to perform a more relevant evaluation of the robustness concerning distortions. The database and the generation source codes of the different distortions are publicly available.

International audience; A common issue of the parallel robot is that has a large number of dynamicparameters, which requires a lot of processing time, whether in dynamic modeling,identification or control. The optimization and estimation of inertial parametersof a large DoF number of robotic system is crucial to tune the model-basedcontrol law in order to improve the robot accuracy. In this paper, we present an optimizednumber of dynamic parameters, called base inertial parameters. As a result,only 90 base inertial parameters affect the evr@ simulator instead of 210 standardone. Torque signals evaluation from experimental parallel platform and the developedanalytical form show the effectiveness of the obtained results.

Motion recognition from videos is actually a very complex task due to the high variability of motions. This paper describes the challenges of human motion recognition, especially motion representation step with relevant features. Our descriptor vector is inspired from Laban Movement Analysis method. We propose discriminative features using the Random Forest algorithm in order to remove redundant features and make learning algorithms operate faster and more effectively. We validate our method on MSRC-12 and UTKinect datasets.

International audience; Human motion recognition has been extensively increased in recent years due to its importance in a wide range of applications , such as human-computer interaction, intelligent surveillance, augmented reality, content-based video compression and retrieval, etc. However, it is still regarded as a challenging task especially in realistic scenarios. It can be seen as a general machine learning problem which requires an effective human motion representation and an efficient learning method. In this work, we introduce a novel descriptor based on Laban Movement Analysis technique, a formal and universal language for human movement, to capture both quantitative and qualitative aspects of movement. We use Discrete Hidden Markov Model (DHMM) for training and classification motions. We improve the classification algorithm by proposing two DHMMs for each motion class to process the motion sequence in two different directions, forward and backward. Such modification allows avoiding the misclassification that can happen when recognizing similar motions. Two experiments are conducted. In the first one, we evaluate our method on a public dataset, the Microsoft Research Cambridge-12 Kinect gesture data set (MSRC-12) which is a widely used dataset for evaluating action/gesture recognition methods. In the second experiment, we build a dataset composed of 10 gestures (Introduce yourself, waving, Dance, move, turn left, turn right, stop, sit down, increase velocity, decrease velocity) performed by 20 persons. The evaluation of the system includes testing the efficiency of our descriptor vector based on LMA with basic DHMM method and comparing the recognition results of the modified DHMM with the original one. Experiment results demonstrate that our method outperforms most of existing methods that used the MSRC-12 dataset, and a near perfect classification rate in our dataset.