Joan Serrat (PI), Felipe Lumbreras, José Manuel Álvarez, Antonio M. López
Continuous innovations in automotive lighting technology pose the problem of how to assess new headlights systems. For car manufacturers, assessment is mostly relative: given a headlights system to be tested, how does it compare with another, maybe from a different supplier, in terms of features such as light intensity, homogeneity or reach? This comparison is best performed dynamically, asking experts actually to drive along a certain testing track to write down later the visual impressions that they remember. However, this procedure suffers from several drawbacks: comparisons cannot be repeated, are not retrospective, and cannot be properly shared with other people since the only record is a paper form. To overcome these, it is proposed to record, for each headlights system, a video sequence of what the driver sees with a camera attached to the windshield screen. The problem becomes now how to compare a pair of such sequences. Two issues must be addressed: the temporal alignment or synchronization of the two sequences, and then the spatial alignment or registration of all the corresponding frames. In this paper a semiautomatic but fast procedure for the former, and an automatic method for the later are proposed. In addition, an alternative to the joint visualization of corresponding frames called the bird's-eye view transform is explored, and a simple fusion technique for better visualization of the headlights differences in two sequences is proposed. Results are provided for a number of headlights with different light sources and from several vehicle brands, in the form of both still images and video sequences.
Antonio M. López (PI), Joan Serrat, Felipe Lumbreras, José C. Rubio, R. Baldrich, David Gerónimo.
Series of four large projects with Volkswagen AG on head-light lamps control with auto-calibration. During nighttime high beams are sparsely used by drivers even when required by the traffic situation. Thus, the intelligent automatic control of vehicles’ headlight is of great relevance. Since dazzling other drivers must be avoided, detection of oncoming and preceding vehicles is required. The detection must reach such a long distance that only camera based approaches are reliable. In this case, to detect a vehicle means identifying its head or tail lights. The main challenge is to distinguish these lights from reflections due to infrastructure elements. In order to confront such a challenge we have developed a nighttime vehicle detection system whose core is a novel classifier–based module which can label each detected target as vehicle or non–vehicle. However, in general it is unrealistic to assume a classifier, or a set of them, providing the perfect detection rate and no false alarms. Therefore, we propose to explore the temporal coherence of the targets classification. The system works in nighttime under wet and dry conditions.
Determining the position of other vehicles on the road is a key information to help driver assistance systems to increase driver’s safety. Accordingly, the work presented in this paper addresses the problem of detecting the vehicles in front of our own one and estimating their 3D position by using a single monochrome camera. Rather than using predefined high level image features as symmetry, shadow search, etc., our proposal for the vehicle detection is based on a learning process that determines, from a training set, which are the best features to distinguish vehicles from non–vehicles.
Being On-Lane: Lane markings detection system (2002)
SEAT CT and Volkswagen AG
Antonio M. López (PI), Cristina Cañero, Joan Serrat, Felipe Lumbreras
Detection of lane markings based on a camera sensor can be a low cost solution to lane departure warning and lateral control. However, reliable detection is difficult due to cast shadows, vehicles occluding the marks, wear, vehicle motion, etc. In our work we propose to use the ridgeness as a low-level descriptor to detect and characterize the lane markings. RANSAC is used to fit a parametric model to the curvature of the lanes in the image.
Lane markings resemble mountains, and their ridge corresponds to the center of the lane markings.
Joan Serrat (PI), Sergi González, Xavier Varona, Xavier Roca and Antonio M. López
Hearing aid devices can be customized to the inner ear channel shape of each person. P3 is a prototype for 3d digitization of hearing aid moulds.
Series of surgical material inspection Projects (1999-2007)
Antonio M. López (PI), Ernest Valveny, Coen Antens, Juan R. Jiménez
Surgical material during operations must be sterilie in order to assure the safest conditions. An aluminum sachet with thread and needle, fitted inside a transparent container is used in order to let the surgeon and assistants to minimize the contact with the material. Of course, perfect conditions of the materials inside the sachets is required, not only to minimize the time spent in the operation but also to assure the best conditions of the process. Note that the assistants do not touch at any moment the materials contained inside the envelope. Our development consisted in inspecting the printed text in the aluminum container (sachet) that has the material. The solution also inspects the material conditions and their correct position inside the sachet and the transparent envelope that carries the sachet.
Elements to be inspected: needle and thread are inside a card, which is fit inside a sachet, which is finally fitted in a transparent envelope thought to be manipulated without touching the materials inside (only the surgeon does). Finally, the envelopes are grouped in boxes of 24/26.
The solution also consisted in developing a hardware system (illumination, cameras and structure), as can be partially seen in the figure below. The illumination has to be carefully designed in order to highlight the shapes and shadows of the material, which is then exploited by computer vision techniques to detect the elements and possible defects.
Three of the cameras which inspect the material.
Some of the defects to be detected were the wrong position of needle and thread inside the envelope, an undesired folding of the aluminum sachet, or the incorrect position of the sachet with respect to the envelope, which could dull the process of releasing the sachet from the envelope by the assistant during an operation.
The development was also supported by public projects PTR1995-0892-OP and PET2006_0744 of the Spanish Ministry of Science and Education.
The B|Braun-CVC joint work was selected as a case of study for the book “El papel de los centros tecnológicos en el proceso innovador. Análisis de su relación con las empresas”, Lluis Santamaría, Alex Rialp, José Rialp, Documentos de Economía Industrial Nº 20, Barcelona.