Two algorithms are introduced for the computation of discrete integral transforms with a multiscale approach operating in discrete three-dimensional (3-D) volumes while considering its real-time implementation. The first algorithm, referred to as 3-D discrete Radon transform of planes, will compute the summation set of values lying in discrete planes in a cube that imitates, in discrete data, the integrals on two-dimensional planes in a 3-D volume similar to the continuous Radon transform. The normals of these planes, equispaced in ascents, cover a quadrilateralized hemisphere and comprise 12 dodecants. The second proposed algorithm, referred to as the 3-D discrete John transform of lines, will sum elements lying on discrete 3-D lines while imitating the behavior of the John or x-ray continuous transform on 3-D volumes. These discrete integral transforms do not perform interpolation on input or intermediate data, and they can be computed using only integer arithmetic with linearithmic complexity, thus outperforming the methods based on the Fourier slice-projection theorem for real-time applications. We briefly prove that these transforms have fast inversion algorithms that are exact for discrete inputs.
In this paper, we propose a depth estimation framework for light field camera arrays. The goal of the proposed framework is to compute consistent depth information over the multiple cameras which is hardly achieved by conventional approaches based on the pairwise stereo matching. We first perform stereo matchings on adjacent image pairs using a convolutional neural network-based correspondence scoring model. Once the local disparity maps are estimated, we consolidate the disparity values to make them globally sharable over the multiple views. We finally refine the depth values in the image domain by introducing a novel image segmentation method considering edges in the image to obtain a semantic-aware global depth map. The proposed framework is evaluated on three different real world scenarios, and the experimental results validate that our proposed method produces accurate and consistent depth maps for images captured by the light field camera arrays.
Object tracking is a core technique in many computer vision applications. The problem becomes especially challenging when the target object is fully or even partially occluded. A recent work has shown the feasibility of utilizing plenoptic imaging techniques to resolve such occlusion problems. Specifically, it constructs focal stacks from plenoptic image sequences and selects an optimal image sequences from the stacks that can maximize the tracking accuracy. Even though the technique has proven the merit of using plenoptic images in the object tracking, there is still room for improvement. In this paper, we propose two simple but effective algorithms to improve both accuracy and robustness of object tracking based on plenoptic images. We first propose to use an image sharpening technique to reduce the blur that the refocused images inheritably have. The image sharpening makes the shape of objects more distinct, and thus a higher accuracy in the object tracking can be achieved. We also propose an adaptive bounding box proposal algorithm to overcome difficult cases where the size of the target object in the image space drastically changes. This improves the robustness in the object tracking compared to prior techniques which assumed fixed sized objects. We validate our proposed algorithms on two different scenarios, and the experimental results confirm the benefit of our method.
Object tracking is an important problem in computer vision research. Among the difficulties of object tracking, the problem of partial and full occlusion is one of the most serious and challenging problems. To address the problem, we proposed methods to object tracking using plenoptic image sequences. Our methods take advantage of the refocusing capability that plenoptic imaging provides. The proposed methods input the sequences of focal stacks constructed by applying the refocusing algorithm on the plenoptic image sequences. The proposed image selection algorithms select the sequence of optimal images that can maximize the tracking accuracy from the sequence of focal stacks. Focus measure approach and confidence measure approach were proposed as image selection methods and both approaches were validated by the experiments using three groups of plenoptic image sequences that include heavily occluded target objects. The experimental results showed that the proposed methods were promising comparing to the conventional 2-D object tracking algorithms.
Object tracking is a very important problem in computer vision research. Among the difficulties of object tracking, partial occlusion problem is one of the most serious and challenging problems. To address the problem, we proposed novel approaches to object tracking on plenoptic image sequences. Our approaches take advantage of the refocusing capability that plenoptic images provide. Our approaches input the sequences of focal stacks constructed from plenoptic image sequences. The proposed image selection algorithms select the sequence of optimal images that can maximize the tracking accuracy from the sequence of focal stacks. Focus measure approach and confidence measure approach were proposed for image selection and both of the approaches were validated by the experiments using thirteen plenoptic image sequences that include heavily occluded target objects. The experimental results showed that the proposed approaches were satisfactory comparing to the conventional 2D object tracking algorithms.