Search results for "VISION"
showing 10 items of 5066 documents
Intelligent eye
2010
This paper describes Intelligent Eye, a mobile phone interactive leisure guide that offers location-based multimedia information. The information offered is related to the user's position, so the main goal of this work is the development of an efficient system to detect where the user is pointing his/her camera at by means of a content-based image retrieval algorithm (CBIR). The CBIR procedure uses color histograms in the HS color space extracted from images, and employs Kullback-Leibler divergence as the similarity measure. Intelligent Eye can be used in a wide range of camera-equipped mobile phones; however, efficiency is improved if GPS data is available. In order to outperform other sys…
Remote photoplethysmography device with adaptive illumination for skin microcirculation assessment
2020
Measuring blood perfusion is important in medical care. However, currently available devices to measure blood perfusion are bulky, expensive and not easy-to-use. In this work a compact and portable low-cost prototype device for remote monitoring of palm skin microcirculation has been developed. Presented device consists of precisely controlled near-infrared illuminators (760nm peak wavelength) and video camera. The device with the custom designed software provides stable uniform illumination of curved skin surfaces, using feedback algorithm. Verification tests of this device showed improvements in the quality of skin blood perfusion maps in the case when the feedback system was used.
2D-3D Camera Fusion for Visual Odometry in Outdoor Environments
2014
International audience; Accurate estimation of camera motion is very important for many robotics applications involving SfM and visual SLAM. Such accuracy is attempted by refining the estimated motion through nonlinear optimization. As many modern robots are equipped with both 2D and 3D cameras, it is both highly desirable and challenging to exploit data acquired from both modalities to achieve a better localization. Existing refinement methods, such as Bundle adjustment and loop closing, may be employed only when precise 2D-to-3D correspondences across frames are available. In this paper, we propose a framework for robot localization that benefits from both 2D and 3D information without re…
Photoplethysmography imaging algorithm for continuous monitoring of regional anesthesia
2016
An efficient photoplethy smography imaging system and advanced algorithm for continuous monitoring of skin microcirculation was developed. The system comprises compact device and computer with software for visualizing of skin blood volume changes. The software is able to process high-resolution microcirculation amplitude maps in real-time. It was tested in clinical environment during the regional anesthesia procedures. The Eulerian-based method showed improved sensitivity and higher resolution of microcirculation maps.
Repair Mechanisms for Broadcast Transmissions in Hybrid Cellular & DVB-H Systems
2006
This paper proposes a framework for investigating potential infrastructure cost savings in hybrid cellular and DVB- H systems by performing efficient error repair of broadcast transmissions. The main idea is to reuse as much as possible the existing network infrastructure to provide mobile TV services. The cellular system is not only employed to collect information, but also to send repair data to the users whose conditions are temporarily affected by noise, interference and fading. To enable an easy and efficient implementation of the repair mechanisms we adopt the use of application layer - forward error correction (AL-FEC) with digital fountain coding.
Application Layer FEC for Mobile TV Delivery in IP Datacast Over DVB-H Systems
2009
In this paper we investigate the potential gain that can be obtained in DVB-H using application layer forward error correction (AL-FEC) to perform a multi-burst protection of the transmission for improving the reception of streaming services for mobile terminals. Compared to the conventional approach with link layer multi protocol encapsulation FEC (MPE-FEC), this technique allows to increase the robustness of the DVB-H transmission not only as a function of the capacity devoted for error repair (FEC overhead), but also as a function of the number of bursts jointly encoded. The main drawback of this approach is an increase of the network latency, that can be translated into a larger service…
Learning Flow-Based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision
2020
Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training. We propose a novel Flow-based Feature Warping Model (FFWM) which can learn to synthesize photo-realistic and illumination preserving frontal images with illumination inconsistent supervision. Specifically, an Illumination Preserving Module (IPM) is proposed to learn illumination preserving image synthesis from illumination inconsistent image pairs. IPM includes two pathways which collaborate to ensure the synthesized frontal images are illumination preserving and wit…
Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation
2021
International audience; Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively i…
No-reference mesh visual quality assessment via ensemble of convolutional neural networks and compact multi-linear pooling
2020
Abstract Blind or No reference quality evaluation is a challenging issue since it is done without access to the original content. In this work, we propose a method based on deep learning for the mesh visual quality assessment without reference. For a given 3D model, we first compute its mesh saliency. Then, we extract views from the 3D mesh and the corresponding mesh saliency. After that, the views are split into small patches that are filtered using a saliency threshold. Only the salient patches are selected and used as input data. After that, three pre-trained deep convolutional neural networks are employed for feature learning: VGG, AlexNet, and ResNet. Each network is fine-tuned and pro…
Towards General Purpose Object Detection: Deep Dense Grid Based Object Detection
2020
Object detection is one of the most challenging and very important branch of computer vision. Some of the challenging aspect of a detection network is the fact that an object can appear anywhere in the image, be partially occluded by another object, might appear in crowd or have greatly varying scales. Consequently, we propose a fine grained and equally spaced dense grid cells throughout an input image be responsible of detecting an object. We re-purpose an already existing deep state-of-the-art detector or classifier into deep and dense detector. Our dense object detector uses binary class encoding and hence suitable for very large multi-class object detector. We also propose a more flexib…