Coded structured light is considered one of the most reliable techniques for recovering the surface of objects. This technique is based on projecting a light pattern and viewing the illuminated scene from one or more points of view. Since the pattern is coded, correspondences between image points and points of the projected pattern can be easily found. The decoded points can be triangulated and 3D information is obtained. We present an overview of the existing techniques, as well as a new and deÿnitive classiÿcation of patterns for structured light sensors. We have implemented a set of representative techniques in this ÿeld and present some comparative results. The advantages and constraints of the di erent patterns are also discussed.

No abstract

The three-dimensional reconstruction of real objects is an important topic in computer vision. Most of the acquisition systems are limited to reconstruct a partial view of the object obtaining in blind areas and occlusions, while in most applications a full reconstruction is required. Many authors have proposed techniques to fuse 3D surfaces by determining the motion between the different views. The first problem is related to obtaining a rough registration when such motion is not available. The second one is focused on obtaining a fine registration from an initial approximation. In this paper, a survey of the most common techniques is presented. Furthermore, a sample of the techniques has been programmed and experimental results are reported to determine the best method in the presence of noise and outliers, providing a useful guide for an interested reader including a Matlab toolbox available at the webpage of the authors.

The role of CMOS Image Sensors since their birth around the 1960s, has been changing a lot. Unlike the past, current CMOS Image Sensors are becoming competitive with regard to Charged Couple Device (CCD) technology. They offer many advantages with respect to CCD, such as lower power consumption, lower voltage operation, on-chip functionality and lower cost. Nevertheless, they are still too noisy and less sensitive than CCDs.Noise and sensitivity are the key-factors to compete with industrial and scientific CCDs. It must be pointed out also that there are several kinds of CMOS Image sensors, each of them to satisfy the huge demand in different areas, such as Digital photography, industrial vision, medical and space applications, electrostatic sensing, automotive, instrumentation and 3D vision systems.In the wake of that, a lot of research has been carried out, focusing on problems to be solved such as sensitivity, noise, power consumption, voltage operation, speed imaging and dynamic range. In this paper, CMOS Image Sensors are reviewed, providing information on the latest advances achieved, their applications, the new challenges and their limitations. In conclusion, the State-of-the-art of CMOS Image Sensors. q

Camera calibrating is a crucial problem for further metric scene measurement. Many techniques and some studies concerning calibration have been presented in the last few years. However, it is still di cult to go into details of a determined calibrating technique and compare its accuracy with respect to other methods. Principally, this problem emerges from the lack of a standardized notation and the existence of various methods of accuracy evaluation to choose from. This article presents a detailed review of some of the most used calibrating techniques in which the principal idea has been to present them all with the same notation. Furthermore, the techniques surveyed have been tested and their accuracy evaluated. Comparative results are shown and discussed in the article. Moreover, code and results are available in internet. ?

No abstract

In recent years, several convolutional neural network (CNN) methods have been proposed for the automated white matter lesion segmentation of multiple sclerosis (MS) patient images, due to their superior performance compared with those of other state-of-the-art methods. However, the accuracies of CNN methods tend to decrease significantly when evaluated on different image domains compared with those used for training, which demonstrates the lack of adaptability of CNNs to unseen imaging data. In this study, we analyzed the effect of intensity domain adaptation on our recently proposed CNN-based MS lesion segmentation method. Given a source model trained on two public MS datasets, we investigated the transferability of the CNN model when applied to other MRI scanners and protocols, evaluating the minimum number of annotated images needed from the new domain and the minimum number of layers needed to re-train to obtain comparable accuracy. Our analysis comprised MS patient data from both a clinical center and the public ISBI2015 challenge database, which permitted us to compare the domain adaptation capability of our model to that of other state-of-the-art methods. In both datasets, our results showed the effectiveness of the proposed model in adapting previously acquired knowledge to new image domains, even when a reduced number of training samples was available in the target dataset. For the ISBI2015 challenge, our one-shot domain adaptation model trained using only a single case showed a performance similar to that of other CNN methods that were fully trained using the entire available training set, yielding a comparable human expert rater performance. We believe that our experiments will encourage the MS community to incorporate its use in different clinical settings with reduced amounts of annotated data. This approach could be meaningful not only in terms of the accuracy in delineating MS lesions but also in the related reductions in time and economic costs derived from manual lesion labeling.

No abstract