Search

This guest editorial introduces the Special Section on Quality Control by Artificial Vision VI.

In this study, the object association issue is tackled in order to ensure a correct affiliation of perceived objects with known ones. The proposed approach is based on the evidence theory and includes multiple object features in order to manage pairing issues in a complex environment. Two heterogeneous information sources are built based on kinematic features related to the objects: their position and size on one hand and their direction of motion on the other hand. A study on the estimation of the belief expressed by these independent sources is performed. The multiple features are managed through a hierarchical fusion which includes two levels of combination. The first level is a pairwise combination, fusing position and orientation data of each pair of objects and the second one processes sequentially the previously combined information over all possible associations. This paper also investigates the effectiveness of the association according to different combination operators at both levels. The performance of the proposed approach is demonstrated in the Intelligent Transportation Systems context for which environmental perception is crucial. The validation exploits a large amount of real data issued from a camera and a 3D LiDAR from the KITTI database.

International audience; In the past few years, a new type of camera has been emerging on the market: a digital camera capable of capturing both the intensity of the light emanating from a scene and the direction of the light rays. This camera technology called a light-field camera uses an array of lenses placed in front of a single image sensor, or simply, an array of cameras attached together. An optical device is proposed: a four minilens ring that is inserted between the lens and the image sensor of a digital camera. This device prototype is able to convert a regular digital camera into a light-field camera as it makes it possible to record four subaperture images of the scene. It is a compact and cost-effective solution to perform both postcapture refocusing and depth estimation. The minilens ring makes also the plenoptic camera versatile; it is possible to adjust the parameters of the ring so as to reduce or increase the size of the projected image. Together with the proof of concept of this device, we propose a method to estimate the positions of each optical component depending on the observed scene (object size and distance) and the optics parameters. Real-world results are presented to validate our device prototype.

International audience; In computer vision, the epipolar geometry embeds the geometrical relationship between two views of a scene. This geometry is degenerated for planar scenes as they do not provide enough constraints to estimate it without ambiguity. Nearly planar scenes can provide the necessary constraints to resolve the ambiguity. But classic estimators such as the 5-point or 8-point algorithm combined with a random sampling strategy are likely to fail in this case because a large part of the scene is planar and it requires lots of trials to get a nondegenerated sample. However, the planar part can be associated with a homographic model and several links exist between the epipolar geometry and homographies. The epipolar geometry can indeed be recovered from at least two homographies or one homgraphy and two noncoplanar points. The latter fits a wider variety of scenes, as it is unsure to be able to find a second homography in the noncoplanar points. This method is called plane-and-parallax. The equivalence between the parallax and the epipolar lines allows to recover the epipole as their common intersection and the epipolar geometry. Robust implementations of the method are rarely given, and we encounter several limitations in our implementation. Noisy image features and outliers make the lines not to be concurrent in a common point. Also off-plane features are unequally influenced by the noise level. We noticed that the bigger the parallax is, the lesser the noise influence is. We, therefore, propose a model for the parallax that takes into account the noise on the features location to cope with the previous limitations. We call our method the “parallax beam.” The method is validated on the KITTI vision benchmark and on synthetic scenes with strong planar degeneracy. The results show that the parallax beam improves the estimation of the camera motion in the scene with planar degeneracy and remains usable when there is not any particular planar structure in the scene.

International audience; This paper describes an efficient method for the detection of triangular traffic signs on grey-scale images. This method is based on the proposed RSLD (RANSAC Symmetric Lines Detection) algorithm which transforms triangle detection into a simple segment detection. A multi-scale approach allows the detection of any warning and yield traffic signs, whatever their distance to the vehicle. This algorithm is applied to a set of selected corners obtained with a coding gradient method. Baseline detection uses the scale of selected triangles to confirm the presence of traffic signs. The study demonstrates that RSLD is a low computation method compared to standard triangle detection. The performance of the method proposed is compared with recently published methods on road sign databases, which use colour information. An equivalent detection rate is obtained with this algorithm, working on grey-scale images. This algorithm is implemented and runs in real time at 30 frames per second.

International audience; —This paper presents an object tracking algorithm using belief functions applied to vision-based traffic sign recognition systems. This algorithm tracks detected sign candidates over time in order to reduce false positives due to data fusion formalization. In the first stage, regions of interest (ROIs) are detected and combined using the transferable belief model semantics. In the second stage, the local pignistic probability algorithm generates the associations maximizing the belief of each pairing between detected ROIs and ROIs tracked by multiple Kalman filters. Finally, the tracks are analyzed to detect false positives. Due to a feedback loop between the multi-ROI tracker and the ROI detector, the solution proposed reduces false positives by up to 45%, whereas computation time remains very low.

International audience; — This paper tackles the problem of tracking-based Traffic Sign Recognition (TSR) systems. It presents an integrated object detection, association and tracking approach based on a spatio-temporal data fusion. This algorithm tracks detected sign candidates in order to reduce false positives. Regions Of Interest (ROIs) potentially containing traffic signs are determined from the vehicle-mounted camera images. An original corner detector associated to pixel coding ensures the detection efficiency. The ROIs are combined using the Transfer-able Belief Model semantics. The associations maximizing the pairwise belief between the detected ROIs and ROIs tracked by multiple Kalman filters are processed. The track evolution helps to detect false positives. Thanks to this solution and to a feedback loop between the tracking algorithm and the ROI detector, a false positive reduction of 45% is assessed.

International audience; This paper presents new methods to calibrate a head-mounted Eye Tracker (ET) automatically, as well as a new way to obtain an estimated point of regard (POR), taking account of the parallax. Calibration is performed in real time; it is easy for the user who just needs to look at one calibration pattern for a few seconds before starting. This method provides a very important couple of points which helps to use a local relationship to compute the POR instead of a global one. This approach significantly improves the precision of the points of regard when the scene camera is mounted with a short focal lens. An estimation of POR when the user looks somewhere outside the calibration distance is also proposed. This estimation is based on an ET modelling such as a stereovision system, to take account of the parallax effect. The aim of this study is to simplify the use of ET techniques for "non-initiated" people, especially here learner drivers.

International audience; Industrial textile fabric with functionalization always has a high standard requirement. Take polytetrafluoroethylene (PTFE) conveyor belt as an example, the base fabrics must be of first-rate quality, with no weaving faults or broken fibers on coated surface [1]. In a previous work, we have proposed an original method to measure the height of the fiber based on variable homography. This measurement is based on a single camera acquiring two successive frames. This scheme is working well, but measurement depends on conveyor speed used for scrolling fabric. In this paper, we propose an improvement by using a new acquisition device based on two mini-lenses assembled as a dual-objective. With this device, variable homography modeling leads to 3-D online inspection whatever fabric speed with a simplified calibration procedure compared to classic stereovision approaches.

International audience; Fabric's smoothness is a key factor to determine the quality of finished textile products and has great influence on the functionality of industrial textiles and high-end textile products. With popularization of the 'zero defect' industrial concept, identifying and measuring defective material in the early stage of production is of great interest for the industry. In the current market, many systems are able to achieve automatic monitoring and control of fabric, paper, and nonwoven material during the entire production process, however online measurement of hairiness is still an open topic and highly desirable for industrial applications1. In this paper we propose a computer vision approach to compute epipole by using variable homography, which can be used to measure emergent fiber length on textile fabrics. The main challenges addressed in this paper are the application of variable homography on textile monitoring and measurement, as well as the accuracy of the estimated calculation. We propose that a fibrous structure can be considered as a two-layer structure, and then show how variable homography combined with epipolar geometry can estimate the length of the fiber defects. Simulations are carried out to show the effectiveness of this method. The true length of selected fibers is measured precisely using a digital optical microscope, and then the same fibers are tested by our method. Our experimental results suggest that smoothness monitored by variable homography is an accurate and robust method of quality control for important industrial fabrics.

In this paper, we propose a new approach for calculating a user’s real point of regard (POR) using a head mounted binocular eye tracking system. We show that the coupling of one of the user’s eyes and the scene camera can be considered as a stereovision system. We then propose a new description for binocular eye trackers, in which we model them via pairs of stereovision systems having the scene camera in common. In this model, we use a hybrid fundamental matrix which allows to take into account the spherical shape of the eyeball model we use. Whatever the distance our model does not require any a priori information on the user’s morphology to calculate the POR.

We propose a model of depth camera based on a four-lens device. This device is used for validating alternate approaches for calibrating multi-view cameras and also for computing disparity or depth images. Calibration method arises from previous works, where principles of variable homography were extended for 3-D measurement. In this paper, calibration is performed between two contiguous views obtained on the same image sensor. This approach leads to propose a new approach for simplifying calibration, by using the properties of the variable homography. The second part of this paper addresses new principles for obtaining disparity images without any matching. A fast algorithm using a contour propagation algorithm is proposed without requiring structured or random pattern projection. These principles are proposed in a framework of quality control by vision, for inspection in natural illumination. By preserving scene photometry, some other standard controls, as for example calipers, shape recognition, or barcode reading, can be done conjointly with 3-D measurements. Approaches presented in this paper are evaluated. Firstly, we show that rapid calibration is relevant for devices mounted with multi lenses. Secondly, synthetic and real experimentations validate our method for computing depth images.

International audience; 3-D optical fluorescent microscopy becomes nowadays an efficient tool for volumic investigation of living biological samples. Using optical sectioning technique, a stack of 2-D images is obtained. However, due to the nature of the system optical transfer function and non-optimal experimental conditions, acquired raw data usually suffer from some distortions. In order to carry out biological analysis, raw data have to be restored by deconvolution. The system identification by the point-spread function is useful to obtain the knowledge of the actual system and experimental parameters, which is necessary to restore raw data. It is furthermore helpful to precise the experimental protocol. In order to facilitate the use of image processing techniques, a multi-platform-compatible software package called VIEW3D has been developed. It integrates a set of tools for the analysis of fluorescence images from 3-D wide-field or confocal microscopy. A number of regularisation parameters for data restoration are determined automatically. Common geometrical measurements and morphological descriptors of fluorescent sites are also implemented to facilitate the characterisation of biological samples. An example of this method concerning cytogenetics is presented.

Session: Image Analysis II; International audience; In this research two methods for recognizing water droplets that are formed during dropwise condensation on the flat and pillared substrates are presented. The aim of these methods is to binarize the gray scale images of the droplets taken by a CCD camera in order to extract the information related to the droplets size and density.