Search results for "InGaN"
showing 10 items of 1214 documents
A Neural Architecture for 3D Segmentation
2003
An original neural scheme for segmentation of range data is presented, which is part of a more general 3D vision system for robotic applications. The entire process relies on a neural architecture aimed to perform first order image irradiance analysis, that is local estimation of magnitude and orientation of the image irradiance gradient.
Adaptive Attitude Control of a Rigid Body with Input and Output Quantization
2022
Author's accepted manuscript. © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. In this paper, the adaptive attitude tracking the problem of a rigid body is investigated where the input and output are transmitted via a network. To reduce the communication burden in a network, a quantizer is introduced in both uplink and downlink communication channels. An adaptiv…
Effect of Camera Angle on Perception of Trust and Attractiveness
2017
Film theories have long proposed that the vertical camera angle influences how the scene and the character in it are interpreted. An elevated camera (high-angle shot) should diminish the qualities of the actor, whereas a lowered camera (low-angle shot) should elevate the actor in perspective as well as in the viewer’s opinion. We were interested in how this holds up for the impression of trustworthiness and attractiveness that the spectator receives of the actor. We filmed 12 actors in a scenario inspired by a TV show called Split or Steal, which features a one-time version of the prisoner’s dilemma. Subjects had to rate trustworthiness and attractiveness of the actors, and also judge if t…
Fully automatic face recognition system using a combined audio-visual approach
2005
This paper presents a novel audio and video information fusion approach that greatly improves automatic recognition of people in video sequences. To that end, audio and video information is first used independently to obtain confidence values that indicate the likelihood that a specific person appears in a video shot. Finally, a post-classifier is applied to fuse audio and visual confidence values. The system has been tested on several news sequences and the results indicate that a significant improvement in the recognition rate can be achieved when both modalities are used together.
Augmented Mirror: Interactive Augmented Reality System Based on Kinect
2011
Part 1: Long and Short Papers; International audience; In this paper we present a virtual character controlled by an actor in real time, who talks with an audience through an augmented mirror. The application, which integrates video images, the avatar and other virtual objects within an Augmented Reality system, has been implemented using a mixture of technologies: two kinect systems for motion capture, depth map and real images, a gyroscope to detect head movements, and control algorithms to manage avatar emotions.
A Comparative Study on Fuzzy-Clustering-Based Lip Region Segmentation Methods
2011
As the first step of many lip-reading or visual speaker authentication systems, lip region segmentation is of vital importance. And fuzzy clustering based methods have been widely used in lip segmentation. In this paper, four fuzzy clustering based lip segmentation methods have been elaborated with their underlying rationale. Experiments have been carried out evaluate their performance comparatively. From the experimental results, SFCM has the best efficiency and FCMST has the best segmentation accuracy.
Optical security and encryption with totally incoherent light
2001
We present a method for securing and encrypting information optically by use of totally incoherent illumination. Encryption is performed with a multichannel optical processor working under natural (both temporal and spatially incoherent) light. In this way, the information that is to be secured can be codified by use of color signals and self-luminous displays. The encryption key is a phase-only mask, providing high security from counterfeiting. Output encrypted information is recorded as an intensity image that can be easily stored and transmitted optically or electrically. Decryption or authentication can also be performed optically or digitally. Experimental results are presented.
Sequential Lip Region Segmentation Using Fuzzy Clustering with Spatial and Temporal Information
2012
For many visual speech recognition and visual speaker authentication systems, lip region extraction is of vital important. In order to segment the lip region accurately and robustly from a lip sequence, a new fuzzy-clustering based algorithm is proposed. In the proposed method, a new dissimilarity measure is introduced to take all the color, spatial and temporal information into consideration. An iterative optimization method is employed to derive the optimal lip region membership map and the final segmentation result. From the experimental results, it is observed that the proposed algorithm can provide superior results compared with other traditional methods.
A Two-Dimensional Autoregressive Model for MIMO Wideband Mobile Radio Channels
2008
In this work, we propose the multichannel two- dimensional (2D) autoregressive (AR) model for multiple-input multiple-output (MIMO) wideband mobile wireless channels. The parameters of the proposed model can be estimated from the real- world measurement data. For this purpose, we suggest using a straightforward extension of the prediction error minimization (PEM) algorithm. We also address the problem of possible instability of the multichannel 2D AR model. A model stabilization procedure based on numerical optimization techniques is proposed. The performance of the multichannel 2D AR model has been evaluated based on the synthetic data generated using two different channel simulators.
Background subtraction for aerial surveillance conditions
2014
International audience; The first step in a surveillance system is to create a representation of the environment. Background subtraction is widely used algorithm to define a part of an image that most time remains stationary in a video. In surveillance tasks, this model helps to recognize those outlier objects in an area under monitoring. Set up a background model on moving platforms (intelligent cars, UAVs, etc.) is a challenging task due camera motion when images are acquired. In this paper, we propose a method to support instabilities caused by aerial images fusing spatial and temporal information about image motion. We used frame difference as first approximation, then age of pixels is …