Short Description High-quality depth sequences are required by lots of applications such as 3DTV and film industry. The current range cameras are based on time of flight (TOF) and provide either low-resolution (e.g. Mesa SR4000) or mid-resolution (e.g. Kinect 2) depth maps. Commonly, these cameras are used along with a…
Short Description In this project we address the problem of recognizing human actions in a video sequence. Unlike previous approaches, we aim at developing a method able to continuously recognize and segment actions. For this purpose a per-frame rather than a per-video representation is needed. This means that the data…
Short Descrption The PERCEPTION team investigates the computational principles underlying human-robot interaction. Under this broad topic, this master project will investigate the use of computer vision and audio signal processing methods enabling a robot to localize events that are both seen and heard, such as a group of people engaged in a…
July 16th, 2014: All the positions were provided, the call for applicants is closed. The PERCEPTION group is seeking for PhD students to develop advanced methods for activity recognition and human-robot interaction based on joint visual and auditory processing. We are particularly interested in students with strong background in computer vision,…
Deadline for sending applications: 30 November 2013. Project proposed by Radu Horaud and Antoine Deleforge. We propose to address the interesting and challenging problem of sound-source localization. A sound source is generally localized using the time-difference of arrival (TDOA) between pairs of microphones. In general, the microphones are arranged in…
Deadline for sending applications: 30 November 2013. Project proposed by Radu Horaud, Marianne Clausel, and Georgios Evangelidis. The most successful image representation frameworks are based on the detection and localization of interest points, or keypoints [1]. Interest points are present in an image whenever the local image structure is rich,…
Deadline for sending applications: 30 November 2013. Project proposed by Georgios Evangelidis and Radu Horaud. The PERCEPTION team at INRIA investigates stereoscopic vision. Over years we have studied the geometry of binocular vision, e.g., [1] and developed several stereo matching algorithms based on seed-growing [2,3,4]. The seed-growing principle is very…
Deadline for sending applications: 30 November 2013. Project proposed by Laurent Girin and Radu Horaud. The PERCEPTION team at INRIA investigates audiovisual scene analysis for a humanoid robot. In particular, the team is interested in implementing advanced “social skills” on the consumer robot NAO (http://www.aldebaran-robotics.com/fr/). The challenge is to provide NAO…
