Search results for "VISION"
showing 10 items of 5066 documents
OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images
2021
International audience; Spherical cameras and the latest image processing techniques open up new horizons. In particular, methods based on Convolutional Neural Networks (CNNs) now give excellent results for optical flow estimation on perspective images. However, these approaches are highly dependent on their architectures and training datasets. This paper proposes to benefit from years of improvement in perspective images optical flow estimation and to apply it to omnidirectional ones without training on new datasets. Our network, OmniFlowNet, is built on a CNN specialized in perspective images. Its convolution operation is adapted to be consistent with the equirectangular projection. Teste…
A 4K-Input High-Speed Winner-Take-All (WTA) Circuit with Single-Winner Selection for Change-Driven Vision Sensors
2019
Winner-Take-All (WTA) circuits play an important role in applications where a single element must be selected according to its relevance. They have been successfully applied in neural networks and vision sensors. These applications usually require a large number of inputs for the WTA circuit, especially for vision applications where thousands to millions of pixels may compete to be selected. WTA circuits usually exhibit poor response-time scaling with the number of competitors, and most of the current WTA implementations are designed to work with less than 100 inputs. Another problem related to the large number of inputs is the difficulty to select just one winner, since many competitors ma…
Pose classification using support vector machines
2000
In this work a software architecture is presented for the automatic recognition of human arm poses. Our research has been carried on in the robotics framework. A mobile robot that has to find its path to the goal in a partially structured environment can be trained by a human operator to follow particular routes in order to perform its task quickly. The system is able to recognize and classify some different poses of the operator's arms as direction commands like "turn-left", "turn-right", "go-straight", and so on. A binary image of the operator silhouette is obtained from the gray-level input. Next, a slice centered on the silhouette itself is processed in order to compute the eigenvalues …
Face tracking and recognition: from algorithm to implementation
2002
This paper describes a system capable of realizing a face detection and tracking in video sequences. In developing this system, we have used a RBF neural network to locate and categorize faces of different dimensions. The face tracker can be applied to a video communication system which allows the users to move freely in front of the camera while communicating. The system works at several stages. At first, we extract useful parameters by a low-pass filtering to compress data and we compose our codebook vectors. Then, the RBF neural network realizes a face detection and tracking on a specific board.
Hybrid architecture for shape reconstruction and object recognition
1998
The proposed architecture is aimed to recover 3-D- shape information from gray-level images of a scene; to build a geometric representation of the scene in terms of geometric primitives; and to reason about the scene. The novelty of the architecture is in fact the integration of different approaches: symbolic reasoning techniques typical of knowledge representation in artificial intelligence, algorithmic capabilities typical of artificial vision schemes, and analogue techniques typical of artificial neural networks. Experimental results obtained by means of an implemented version of the proposed architecture acting on real scene images are reported to illustrate the system capabilities.
A Neural Solution for a Mobile Robot Navigation into Unknown Indoor Environments Using Visual Landmarks
1998
In this paper we present a neural solution for a mobile robot navigation into unknown indoor environments by using landmarks. Robot navigation task is implemented by two groups of processes based on MLP neural networks classifiers: a Low Level Vision System performs obstacle avoidance and corridor following, while an High Level Vision System extracts landmarks contents and performs goal directed navigation. A path-planner manages the two navigation systems and interacts with the robot hardware. The proposed solution is very strong and flexible and can be used to drive a mobile robot in real indoor environments. In the paper experimental results are also reported.
Problems of coding stereo images in human memory
2010
This paper discusses the memorization and recall by man of a sequence of planar or stereoscopic images, including six frames that contain a planar strip (8×8 positions of the stimulus) or a volume strip (8×4×2 positions). At the recall stage, the subject chose between the stimulus and three distractors in each frame. It is shown that the times for recognition and recall are less for volume stimuli, while the percent of correct responses is greater for planar stimuli. For volume stimuli, the distribution of errors depends on the disparity between the target and the selected distractor. A model based on a heteroassociative neural network reproduces the error distribution for planar but not fo…
Effect of raster resolution and polygon-conversion algorithm on landslide susceptibility mapping
2016
The choice of the proper resolution in landslide susceptibility mapping is a worth considering issue. If, on the one hand, a coarse spatial resolution may describe the terrain morphologic properties with low accuracy, on the other hand, at very fine resolutions, some of the DEM-derived morphometric factors may hold an excess of details. Moreover, the landslide inventory maps are represented throughout geospatial vector data structure, therefore a conversion procedure vector-to-raster is required.This work investigates the effects of raster resolution on the susceptibility mapping in conjunction with the use of different algorithms of vector-raster conversion. The Artificial Neural Network t…
Distinguishing Onion Leaves from Weed Leaves Based on Segmentation of Color Images and a BP Neural Network
2006
A new algorithm to distinguish onion leaves from weed leaves in images is suggested. This algorithm is based on segmentation of color images and on BP neural network. It includes: discarding soil for conserving only plants in the image, color image segmentation, merging small regions by analyzing the frontier rates and the averages of color indices of the regions, at last a BP neural network is used to determine if the small regions belongs to onion leaf or not. The algorithm has been applied to many images and the correct identifiable percents for onion leaves are between 80%~ 90%.
Connectionist models of face processing: A survey
1994
Abstract Connectionist models of face recognition, identification, and categorization have appeared recently in several disciplines, including psychology, computer science, and engineering. We present a review of these models with the goal of complementing a recent survey by Samal and Iyengar [Pattern Recognition25, 65–77 (1992)] of nonconnectionist approaches to the problem of the automatic face recognition. We concentrate on models that use linear autoassociative networks, nonlinear autoassociative (or compression) and/or heteroassociative backpropagation networks. One advantage of these models over some nonconnectionist approaches is that analyzable features emerge naturally from image-b…