Time filter

Source Type

Brest, France

Ouerhani Y.,ACTRIS Brest | Desthieux M.,ACTRIS Brest | Alfalou A.,Equipe Vision
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

In this paper, we propose and validate a new system used to explore road assets. In this work we are interested on the vertical road signs. To do this, we are based on the combination of road signs detection, recognition and identification using data provides by sensors. The proposed approach consists on using panoramic views provided by the innovative device, VIAPIX®1, developed by our company ACTRIS2. We are based also on the optimized correlation technique for road signs recognition and identification on pictures. Obtained results shows the interest on using panoramic views compared to results obtained using images provided using only one camera. © 2015 SPIE. Source

Alfalou A.,Equipe Vision | Brosseau C.,University of Western Brittany
Optics Communications | Year: 2013

We report a method of simultaneous compression and encryption of multiple images based on a specific spectral fusion. This method is able to manipulate target images with close spectral characteristics. For that purpose, we introduce an optimized algorithm for the task of simultaneously compressing and encrypting phase-shifting digital holograms (PSIDH) for three-dimensional object reconstruction. This technique is based on a spectral fusion, without overlapping, of interference patterns I corresponding to phase shifts. We first divide the spectral plane into several areas and optimize the bandwidth of the spectral domain. Each area is affected to a spectrum of an intensity pattern IPSIDH. A two-level encryption of these patterns is realized. First, we apply a discrete cosine transform (DCT) spectral fusion after addition of an input key image. Then, each DCT-spectral interference pattern is multiplied with a specific random intensity function to uniformly distribute the spectral intensity. To validate our approach, many numerical simulations are performed. The simplicity and robustness of our tests make this algorithm appealing for object reconstruction. © 2013 Elsevier B.V. Source

Ouerhani Y.,ACTRIS Brest | Alfalou A.,Equipe Vision | Desthieux M.,University of Western Brittany | Brosseau C.,University of Western Brittany
Optics and Lasers in Engineering | Year: 2016

We present a three-step approach based on the commercial VIAPIX® module for road traffic sign recognition and identification. Firstly, detection in a scene of all objects having characteristics of traffic signs is performed. This is followed by a first-level recognition based on correlation which consists in making a comparison between each detected object with a set of reference images of a database. Finally, a second level of identification allows us to confirm or correct the previous identification. In this study, we perform a correlation-based analysis by combining and adapting the Vander Lugt correlator with the nonlinear joint transformation correlator (JTC). Of particular significance, this approach permits to make a reliable decision on road traffic sign identification. We further discuss a robust scheme allowing us to track a detected road traffic sign in a video sequence for the purpose of increasing the decision performance of our system. This approach can have broad practical applications in the maintenance and rehabilitation of transportation infrastructure, or for drive assistance. © 2016. Source

Ouerhani Y.,Equipe Vision | Jridi M.,Equipe Vision | Alfalou A.,Equipe Vision | Brosseau C.,European University of Brittany
Optics Communications | Year: 2013

The key outcome of this work is to propose and validate a fast and robust correlation scheme for face recognition applications. The robustness of this fast correlator is ensured by an adapted pre-processing step for the target image allowing us to minimize the impact of its (possibly noisy and varying) amplitude spectrum information. A segmented composite filter is optimized, at the very outset of its fabrication, by weighting each reference with a specific coefficient which is proportional to the occurrence probability. A hierarchical classification procedure (called two-level decision tree learning approach) is also used in order to speed up the recognition procedure. Experimental results validating our approach are obtained with a prototype based on GPU implementation of the all-numerical correlator using the NVIDIA GPU GeForce 8400GS processor and test samples from the Pointing Head Pose Image Database (PHPID), e.g. true recognition rates larger than 85% with a run time lower than 120 ms have been obtained using fixed images from the PHPID, true recognition rates larger than 77% using a real video sequence with 2 frame per second when the database contains 100 persons. Besides, it has been shown experimentally that the use of more recent GPU processor like NVIDIA-GPU Quadro FX 770M can perform the recognition of 4 frame per second with the same length of database. © 2012 Elsevier B.V. Source

Elbouz M.,Equipe Vision | Alfalou A.,Equipe Vision | Brosseau C.,University of Western Brittany | Ben Haj Yahia N.,Equipe Vision | Alam M.S.,University of South Alabama
Optics Communications | Year: 2015

We present an optimized system specially designed for the tracking and recognition of moving subjects in a confined environment (such as an elderly remaining at home). In the first step of our study, we use a VanderLugt correlator (VLC) with an adapted pre-processing treatment of the input plane and a postprocessing of the correlation plane via a nonlinear function allowing us to make a robust decision. The second step is based on an optical joint transform correlation (JTC)-based system (NZ-NL-correlation JTC) for achieving improved detection and tracking of moving persons in a confined space. The proposed system has been found to have significantly superior discrimination and robustness capabilities allowing to detect an unknown target in an input scene and to determine the target's trajectory when this target is in motion. This system offers robust tracking performance of a moving target in several scenarios, such as rotational variation of input faces. Test results obtained using various real life video sequences show that the proposed system is particularly suitable for real-time detection and tracking of moving objects. © 2015 Elsevier B.V. All rights reserved. Source

Discover hidden collaborations