Fourier Ptychography Microscopy enables reconstructing both intensity and phase high-resolution wide-field images from multiple captures under varying illumination directions. The capture process is classically modeled using a neural network. The reconstructed object is iteratively optimized by gradient descent so the network output matches the captures. Although, this process hinges on a precise estimation of the system geometry. While previous works alternate object image refinement and LEDs positional misalignment correction, we show that geometry estimation can be efficiently integrated into the object reconstruction process, so achieving system self-calibration, and enhancing the quality of reconstructed images.

Elongated objects have various shapes and can shift, rotate, change scale, and be rigid or deform by flexing, articulating, and vibrating, with examples as varied as a glass bottle, a robotic arm, a surgical suture, a finger pair, a tram, and a guitar string. This generally makes tracking of poses of elongated objects very challenging. We describe a unified, configurable framework for tracking the pose of elongated objects, which move in the image plane and extend over the image region. Our method strives for simplicity, versatility, and efficiency. The object is decomposed into a chained assembly of segments of multiple parts that are arranged under a hierarchy of tailored spatio-temporal constraints. In this hierarchy, segments can rescale independently while their elasticity is controlled with global orientations and local distances. While the trend in tracking is to design complex, structure-free algorithms that update object appearance on-line, we show that our tracker, with the novel but remarkably simple, structured organization of parts with constant appearance, reaches or improves state-of-the-art performance. Most importantly, our model can be easily configured to track exact pose of arbitrary, elongated objects in the image plane. The tracker can run up to 100 fps on a desktop PC, yet the computation time scales linearly with the number of object parts. To our knowledge, this is the first approach to generic tracking of elongated objects.

Haar-like features are ubiquitous in computer vision, e.g. for Viola and Jones face detection or local descriptors such as Speeded-Up-Robust-Features. They are classically computed in one pass over integral image by reading the values at the feature corners. Here we present a new, general parsing formalism for convolving them more efficiently. Our method is fully automatic and applicable to an arbitrary set of Haar-like features. The parser reduces the number of memory accesses which are the main computational bottleneck during convolution on modern computer architectures. It first splits the features into simpler kernels. Then it aligns and reuses them where applicable forming an ensemble of recursive convolution trees, which can be computed faster. This is illustrated with experiments, which show a significant speed-up over the classic approach.

We propose a novel probabilistic tracking algorithm based on an elastic blob ensemble (EBE) which is applicable to track flexible objects. It outputs a coarse motion cue in the form of the object's location and orientation together with the location of the blobs. The main assumption is that the orientation of the whole object does not change much between neighboring frames. A discrete solution space is created in the current frame around the blobs' positions from the previous frame. Our model then promotes solutions whose orientations are close to the prior orientation, which match the modeled to the observed appearance well, and which follow modeled spatial configuration. It combines the strengths of three popular approaches to visual tracking : mean-shift tracker, particle filtering, and pictorial structures. As a result, the proposed framework tracks human upper body composed of head, torso, and hips at the rate of 40 fps on a regular desktop PC.

Particle filtering is known as a robust approach for motion tracking by vision, at the cost of heavy computation in a high dimensional pose space. In this work, we describe a number of heuristics that we demonstrate to jointly improve robustness and real-time for motion capture. 3D human motion capture by monocular vision without markers can be achieved in realtime by registering a 3D articulated model on a video. First, we search the high-dimensional space of 3D poses by generating new hypotheses (or particles) with equivalent 2D projection by kinematic flipping. Second, we use a semi-deterministic particle prediction based on local optimization. Third, we deterministi-cally resample the probability distribution for a more efficient selection of particles. Particles (or poses) are evaluated using a match cost function and penalized with a Gaussian probability pose distribution learned off-line. In order to achieve real-time, measurement step is parallelized on GPU using the OpenCL API. We present experimental results demonstrating robust real-time 3D motion capture with a consumer computer and webcam.

This paper presents GpuCV, an open source multi-platform library for easily developing GPU-accelerated image processing and Computer Vision operators and applications. It is meant for computer vision scientist not familiar with GPU technologies. It is designed to be compatible with Intel's OpenCV library by offering GPU-accelerated operators that can be integrated into native OpenCV applications. The GpuCV framework transparently manages hardware capabilities, data synchronization, activation of low level GLSL and CUDA programs, on-the-fly benchmarking and switching to the most efficient implementation and finally offers a set of image processing operators with GPU acceleration available.

This paper presents a state of the art report on using graphics hardware for image processing and computer vision. Then we describe GPUCV, an open library for easily developing GPU accelerated image processing and analysis operators and applications

This paper presents a comparison of original couplings between color filter array demosaicking methods and wavelet compression (JPEG2000). We focus on an application handling huge microscopy images (64 K/spl times/64 K pixels) for telediagnosis. Whereas coding is usually achieved after interpolation, we also consider demosaicking after decompression in order to optimize image quality for a given size of data. We also study the JPEG2000 stream structure for interactive visualization.

We present a method for 3D human motion capture using a single camera, without markers and without a priori knowledge on gestures. It is based on registering a 3D articulated model on color images with respect to biomechanical constraints. Gestures regularization is discussed as a way to cope with projection ambiguities. Computation is reduced by registering only the moving parts of the body.

A three-dimensional (3D) reconstruction of the vessel lumen from two angiographic views, based on the reconstruction of a series of cross-sections, is proposed. Assuming uniform mixing of contrast medium and background subtraction, the cross-section of each vessel is reconstructed through a binary representation. A priori information about both the slice to be reconstructed and the relationships between adjacent slices are incorporated to lessen ambiguities on the reconstruction. Taking into account the knowledge of normal vessel geometry, an initial solution of each slice is created using an elliptic model-based method. This initial solution is then deformed to be made consistent with projection data while being constrained into a connected realistic shape. For that purpose, properties on the expected optimal solution are described through a Markov random field. To find an optimal solution, a specific optimization algorithm based on simulated annealing is used. The method performs well both on single vessels and on branching vessels possessing an additional inherent ambiguity when viewed at oblique angles. Results on 2D slice independent reconstruction and 3D reconstruction of a stack of spatially continuous 2D slices are presented for single vessels and bifurcations.