Point Light Source Position Estimation From RGB-D Images by Learning Surface Attributes.

The application of sequence stratigraphy concepts to reservoir de scription involves the correlation of different types of (bounding) surfaces from well to well to produce a high resolution reservoir zonation. A stochastic model has been developed for describing the geometry of different types of surfaces, and a reservoir zonation is constructed by simulating a number of surfaces from the base of the reservoir upwards. The surfaces are modelled as transformed Gaussian random fields. Conditioning on observed depths is performed by kriging, including inequality constraints for surfaces not observed in a well due to subsequent erosion. This paper focusses on the stochastic model for a particular type of surface containing erosional valleys. The valleys are modelled by fibre processes and correlated Gaussian random functions. Prior distributions for valley location and geometry are defined and updated to posterior distributions by simulating from the prior model conditioned on the observations. Information such as the depth of the boundaries observed in the wells, and the well pattern with respect to valley orientation, width and sinuosity, is thus utilized in the parameter inference.

The extent of adsorption (Γ21) of DNA from aqueous solution on different hydrophobic and hydrophilic solid surfaces has been compared as a function of pH, temperature, ionic strength of the medium, and denaturants. Γ21 at a given surface (except sephadex) increases with an increase of the nucleotide concentration (X2) of DNA in mole fraction units, but it attains a monolayer saturation value Γ2m when X2 attains a value X2m. In most cases Γ21 increases further when X2 ≫ X2m. Various neutral electrolytes like LiCl, KCl, CsCl, KBr, CaCl2, and Na2SO4, surfactants like SDS and Triton-X 100, the denaturing action of heat, and the addition of acid and alkali have been observed to play an important role during the study of the adsorption of DNA on charcoal powder. Further, a comparative study has been performed to examine the relative affinity of DNA toward different types of solid surfaces. The significant role of different types of surfaces in controlling the adsorption process has been explained in terms of Gibbs' surface excess quantities. The experimental results have been interpreted in terms of maximum work due to the free energy change of DNA adsorption on various solid surfaces and more quantitatively in terms of the standard free energy change (ΔG°) for the saturation of the surface by DNA as a result of the change in the nucleotide concentration in the bulk from zero to unity in mole fraction units.

One of the fundamental problems of computer vision is to extract 3D shape and motion from images. This can be achieved when a scene or object is observed from different viewpoints or over a period of time. There is a wide range of applications, ranging from digitizing cultural heritage to vision-based autonomous robot navigation. This talk will present several approaches to solve this problem. First, we’ll discuss techniques for 3D shape recovery for static objects and scenes. One particular case is the 3D mapping and localization in large environments from images, e.g. urban 3D reconstruction from vehicleborne cameras or localization from cell-phone images. Next, we’ll shift our focus to modeling dynamic scenes, e.g. people who are moving around. In addition to explicitly 3D modeling an event, we'll consider the possibility to perform video-based rendering from casually captured videos. Speaker Bio-Sketch: Marc Pollefeys is a full professor in the Dept. of Computer Science of ETH Zurich since 2007 where he is the head of the Institute for Visual Computing and leads the Computer Vision and Geometry lab. He currently also remains associated with the Dept. of Computer Science of the University of North Carolina at Chapel Hill where he started as an assistant professor in 2002 and became an associate professor in 2005. Before this he was a postdoctoral researcher at the Katholieke Universiteit Leuven in Belgium, where he also received his M.S. and Ph.D. degrees in 1994 and 1999, respectively. His main area of research is computer vision. One of his main research goals is to develop flexible approaches to capture visual representations of real world objects, scenes and events. Dr. Pollefeys has received several prizes for his research, including a Marr prize, an NSF CAREER award, a Packard Fellowship and a European Research Council Starting Grant. He is the author or co-author of more than 130 peer-reviewed publications. He is the General Chair for the European Conference on Computer Vision 2014 (ECCV), was a Program Co-Chair for the IEEE Conference on Computer Vision and Pattern Recognition 2009 (CVPR), was general/program co-chair of the Third Symposium on 3D Data Processing, Visualization and Transmission and has organized workshops and courses at major vision and graphics conferences and has served on the program committees of many conferences. Prof. Pollefeys is/was on the Editorial Board of the IEEE Transactions on Pattern Analysis and Machine Intelligence and the International Journal of Computer Vision as well as several other journals in computer vision, graphics and robotics.

This paper presents a multiple point hierarchical approach to the stereo correspondence problem in computer vision. The low-level processing employs an area-and-token hybrid method to obtain, for distinctive points in one image, a set of points in the other image that are candidates for correspondence. The refinement of the set of low-level correspondences obtained is performed by a high-level N-point simultaneous correspondence process, a new constraint introduced for this problem. The high-level processing uses a genetic algorithm approach for searching the solution space. Experimental results show the effectiveness of the method on real world scenes.

3D reconstruction from a single image is a classical problem in computer vision. However, it still poses great challenges for the reconstruction of daily-use objects with irregular shapes. In this paper, we propose to learn 3D reconstruction knowledge from informally captured RGB-D images, which will probably be ubiquitously used in daily life. The learning of 3D reconstruction is defined as a category modeling problem, in which a model for each category is trained to encode category-specific knowledge for 3D reconstruction. The category model estimates the pixel-level 3D structure of an object from its 2D appearance, by taking into account considerable variations in rotation, 3D structure, and texture. Learning 3D reconstruction from ubiquitous RGB-D images creates a new set of challenges. Experimental results have demonstrated the effectiveness of the proposed approach.

In this paper, we consider the problem of estimating the 3D position and intensity of multiple light sources without using any light probe or user interaction. The proposed approach is twofold and relies on RGB-D data acquired with a low cost 3D sensor. First, we separate albedo/texture and illumination using lightness ratios between pairs of points with the same reflectance property but subject to different lighting conditions. Our selection algorithm is robust in presence of challenging textured surfaces. Then, estimated illumination ratios are integrated, at each frame, within an iterative process to recover position and intensity of light sources responsible of cast shadows. Estimated lighting characteristics are finally used to achieve realistic Augmented Reality (AR).

One of the fundamental problems in computer vision is the background-foreground segmentation and most of the strategies have severe drawbacks when working with natural images, where there are extreme conditions such as illumination changes combined with sudden background differences or other noise; moreover if the system has to face real-time restrictions. In this case authors focus on a variation of the U-net architecture to obtain the segmentation of the objects (fishes) in every single frame. The U-net has some interesting properties to explore in the case of image segmentation, such as multi-scale parameter combination. The reported preliminary results, working in a context of a multi-target fish tracking are promising, and envisions an approach that could provide a real-time response to long-lasting experiments using HQ video for multi-target tracking in real-time Computer vision systems.

Novel view synthesis is a classic problem in computer vision. It refers to the generation of previously unseen views of a scene from a set of sparse input images taken from different viewpoints. One example of novel view synthesis is the interpolation of views in between the two images of a stereo camera. Another classic problem in computer vision is video frame interpolation, which is important for video processing. It refers to the generation of video frames in between existing ones and is commonly used to increase the frame rate of a video or to match the frame rate to the refresh rate of the monitor that the video is being displayed on. Interestingly, off-the-shelf video frame interpolation can directly be employed to successfully perform view interpolation to address the aforementioned stereo view interpolation problem. Video frame interpolation can be seen as temporal novel view synthesis. However, this perspective is usually not considered and novel view synthesis generally concerns generating unseen views in space rather than time. For this reason, the set of sparse input images that is used for spatial novel view synthesis is commonly either captured at the same time, or it is assumed that the scene is static. This paradigm limits the applicability of novel view synthesis in real-world scenarios though. This thesis addresses three applications of novel view synthesis and provides practical solutions that do not require difficult-to-acquire multi-view imagery: video frame interpolation which performs temporal video-to-video synthesis, synthesizing the 3D Ken Burns effect from a single image which performs spatial image-to-video synthesis, synthesizing video action shots which performs spatiotemporal video-to-video and video-to-image synthesis. These applications not only explore different dimensions of time and space, they also perform novel view synthesis on everyday image and video footage. This is in stark contrast to the large body of existing work which focuses on spatial novel view synthesis while requiring multiple input views that were either captured at the same time or under the assumption of a static scene.

Hermetic glass-to-metal sealing (GMTS) technology combines metal and glass and can be used to construct vacuum tubes; electric discharge tubes; semiconductor diodes; reed switches; and pressure-tight glass-to-metal windows, optical windows, and lenses in electronics or electronic systems. The hermetic and mechanically strong seals engineered using GTMS are highly reliable, making them suitable for deployment in harsh environments and for applications requiring high performance. However, it has always been challenging to precisely and robustly join glass and metal due to the significant disparities in their properties. In this study, the laser transmission welding of borosilicate glass and aluminum alloy using a pulsed Nd:YAG laser to achieve hermetic glass–metal seals was experimentally investigated. This research focused on various processing parameters and the influence of surface conditions on bonding quality. Three different types of surfaces—a polished surface, a surface subjected to preoxidation, and a laser-modified surface—were compared. To evaluate the weld strength, shear-tensile separation forces were measured. The analysis of fracture and separation encompassed detailed examinations of the weld morphology, microstructure, and elemental composition. The results revealed that increasing the laser welding energy initially enhanced the weld strength until a saturation point was reached. Among the three different surface treatments tested, the laser surface modification of aluminum alloy yielded the highest weld strength. The maximum achieved bond force exceeded 35.38 N, demonstrating the feasibility of using cost-effective pulsed laser welding for glass-to-metal sealing. The results were significantly better than those from previous research in which aluminum alloy surfaces were pretreated using microarc oxidation.

Graph and hypergraph matching are fundamental problems in computer vision, which have been receiving a steadily growing attention in the last two decades due to the recent modern algorithms and models that are both fast and accurate. Graph and hypergraph matching are successful in tackling many real-world tasks that require 2D and 3D feature matching and alignment. Matching is a general problem in vision and graphs have always been quintessential for modeling information that has both local and longer range connections. Therefore, graph matching will continue to influence computer vision and robotics research, crossing over many different mathematical and computational models, including Bayesian networks, conditional and Markov random fields, spectral graph models, and, more recently, deep neural networks. While graph matching is limited to using pairwise relationships, hypergraph matching permits the use of relationships between sets of features of any order. Consequently, it carries the promise to make matching more robust to changes in scale, deformations, and outliers. In this chapter, we present several key ideas, computational models, and optimization methods that introduced in the literature the possibility to learn graph and hypergraph matching in a semi-supervised or even completely unsupervised fashion. We start by describing two methods for solving graph and hypergraph matching based on spectral matching and integer projected fixed point methods, introduced in Chap. 1. Then, based on the same intuition (also discussed in Chap. 1) that correct assignments form a strong cluster of agreements, we follow up by introducing the main approach to learning as it applies to graph and hypergraph matching, as well as the more general Maximum A Posteriori (MAP) inference problem in probabilistic graphical models (MRFs and CRFs). In the last part of the chapter, we demonstrate experimentally the effectiveness of the algorithms presented and, whenever possible, provide extensive comparisons to other top published methods. Moreover, we show that our learning approach is general and can significantly boost the performance of different state-of-the-art matching algorithms in the literature.

In this paper we derive analytical solutions for potential problems on different types of surfaces, such as cylinders, cones and spheres. These solutions complement the solution obtained for a sphere. Besides examining modes of truncation for a sphere, we also provide a complete coverage of all modes of truncation for cylinders and cones. Our interest focuses on two-dimensional conducting surfaces, that are fed with point sources of current. Our solution gave explicitly the voltage distribution on these surfaces, results that can straight-forwardly be applied to pressure profiles of a fluid flow in a gap between surfaces. Yet since every physical set-up takes place in the R 3 space, some adjustments were required. We focused on three types of geometric surfaces: cylinder, cone and sphere. As being effectively two-dimensional problems, the use of analytic functions and conformal maps has been used to obtain analytical solutions for all these geometries, all are mapped into the complex plane. Special attention is paid to examine particular cases of truncated ends by taking into account boundary conditions and flux considerations. We used reflections on cylinder inversions on cone and explore a spherical version of inversion on a sphere in order to satisfy the boundary conditions.

We report the development of a biped-robot system with real-time surface recognition and walking-speed adjustment to control the robot motion during walking on different types of surfaces. Four types of test surfaces (i.e. rough foam (RF), smooth foam (SF), thin carpet (TC) and smooth table (ST)) are considered in the system verification. For surface-property recognition we use ultra-thin-membrane force sensors, mounted under the robot feet, and a classification circuit, implemented on an Arduino Uno board. The walking-speed adjustment is performed with an external control circuit, which receives the surface-recognition signal from the classification circuit and sends a feedback signal to the robot controller (i.e. RCB-4HV) for adjusting the walking speed accordingly. We applied the nearest-neighbor-classification algorithm with the Euclidean-distance measure and a set of reference data, to distinguish between the four test surfaces based on the robot's real-time walking pattern. The mean absolute value (MAV) feature descriptor is used to generate four different types of reference walking pattern, corresponding to the four different surfaces. In our experiments it is observed, that the ST surface performs best in terms of average surface-recognition latency (SRL) (~3.6 sec) during walking on same surface. On the other hand, the surface transition from TC to SF showed minimum surface-transition latency (STL) (~8.2 sec) with correct speed change from 135 to 160 robot-motor-configuration frames per stride (frames/stride), while the transition from SF to TC surfaces showed maximum STL (~11.6 sec) including speed change from 160 to 135 frames/stride. The obtained results are useful for development of the next generation of surface-recognition and speed-adjustment systems, implemented in humanoid robots to enable balanced and stable walking in environments with multiple changed surface properties.

Toward designing intelligent PDEs for computer vision: An optimal control approach

Detection and Recognition of the surface roughness in the images is a topic which has received a lot of attention in the field of image processing. In this paper, a new non-contact measurement method of surface roughness, by texture analysis, is developed based on Charge Coupled Device (CCD) image in planning operations. The surface image of the workpiece is first acquired using the A102f CCD digital camera. The image captured will be converted to others kinds of images (Binary, and Gray scale) to be suitable for the detection algorithms used for the different types of surface. The main Image processing approaches is used such as Smoothing process, Noise reduction, Edge detection, Region Splitting, and Hough Transform etc. The predicted surface finish values using this measurement method are found to correlate well with the conventional stylus surface finish ( Ra ) values.

Motion and structure estimation are elementary problems of computer vision. These are active areas of research, even though the first methods were proposed several decades ago. We develop new approaches for motion and structure estimation for autonomous driving. An autonomous vehicle requires an accurate model of its environment, wrong decisions made by an autonomous car can have severe consequences. We assume the monocular setup, where only a single camera is mounted on the car. Outdoor traffic sequences are challenging for optical flow estimation. The high speed of the car causes large displacements in the optical flow field, the lighting conditions are unstable and there can be strong distortions due to reflections and difficult weather conditions. We propose new discrete methods, which determine optical flow as optimal configuration of probabilistic graphical models. The first approach selects sparse locations in the reference frame, and matches them across the second image. The best correspondences, which match constraints from a multiple view configuration, are considered motion vectors in a graphical model. In a second approach, we solve for dense optical flow by approximating the original infeasible graphical model with a sequence of reduced models. The monocular configuration poses challenges to the estimation of scene structure, camera positions and scene parameters need to be estimated jointly. The geometry of multiple views creates blind spots in the images, and adds a scale ambiguity, which both to not exist in a setup with multiple cameras. We propose two methods for structure estimation. The first approach determines the energy optimal camera track, given optical flow and depth observations. A further approach estimates camera motion and a piecewise planar scene description jointly from a single optical flow field. The scene description contains depth and plane normal information. We evaluate our approaches for motion and structure estimation on different real world and rendered datasets. In addition to evaluation on publicly available evaluation data, we evaluate on a new rendered dataset with ground truth plane normals.