20,758 research outputs found
Motion-aware noise filtering for deblurring of noisy and blurry image
No full textImage noise can present a serious problem in motion deblurring. While most state-of-the-art motion deblurring algorithms can deal with small levels of noise, in many cases such as low-light imaging, the noise is large enough in the blurred image that it cannot be handled effectively by these algorithms. In this paper, we propose a technique for jointly denoising and deblurring such images that elevates the performance of existing motion deblurring algorithms. Our method takes advantage of estimated motion blur kernels to improve denoising, by constraining the denoised image to be consistent with the estimated camera motion (i.e., no high frequency noise features that do not match the motion blur). This improved denoising then leads to higher quality blur kernel estimation and deblurring performance. The two operations are iterated in this manner to obtain results superior to suppressing noise effects through regularization in deblurring or by applying denoising as a preprocess. This is demonstrated in experiments both quantitatively and qualitatively using various image examples
Single image defocus map estimation using local contrast prior
No full textImage defocus estimation is useful for several applications including deblurring, blur magnification, measuring image quality, and depth of field segmentation. In this paper, we present a simple yet effective approach for estimating a defocus blur map based on the relationship of the contrast to the image gradient in a local image region. We call this relationship the local contrast prior. The advantage of our approach is that it does not require filter banks or frequency decomposition of the input image; instead we only need to compare local gradient profiles with the local contrast. We discuss the idea behind the local contrast prior and demonstrate its effectiveness on a variety of experiments
ELD-Net: An Efficient Deep Learning Architecture for Accurate Saliency Detection
No full textRecent advances in saliency detection have utilized deep learning to obtain high-level features to detect salient regions in scenes. In this paper, we propose ELD-Net, a unified deep learning framework for accurate and efficient saliency detection. We show that hand-crafted features can provide complementary information to enhance saliency detection that uses only high-level features. Our method uses both low-level and high-level features for saliency detection. High-level features are extracted using GoogLeNet, and low-level features evaluate the relative importance of a local region using its differences from other regions in an image. The two feature maps are independently encoded by the convolutional and the ReLU layers. The encoded low-level and high-level features are then combined by concatenation and convolution. Finally, a linear fully connected layer is used to evaluate the saliency of a queried region. A full resolution saliency map is obtained by querying the saliency of each local region of an image. Since the high-level features are encoded at low resolution, and the encoded high-level features can be reused for every query region, our ELD-Net is very fast. Our experiments show that our method outperforms state-of-the-art deep learning-based saliency detection methods.
Video Matting Using Multi-frame Nonlocal Matting Laplacian
No full textWe present an algorithm for extracting high quality temporally coherent alpha mattes of objects from a video. Our approach extends the conventional image matting approach, i.e. closed-form matting, to video by using multi-frame nonlocal matting Laplacian. Our multi-frame nonlocal matting Laplacian is dened over a nonlocal neighborhood in spatial temporal domain, and it solves the alpha mattes of several video frames all together simultaneously. To speed up computation and to reduce memory requirement for solving the multi-frame nonlocal matting Laplacian, we use the approximate nearest neighbor(ANN) to nd the nonlocal neighborhood and the k-d tree implementation to divide the nonlocal matting Laplacian into several smaller linear systems. Finally, we adopt the nonlocal mean regularization to enhance temporal coherence of the estimated alpha mattes and to correct alpha matte errors at low contrast regions. We demonstrate the eectiveness of our approach on various examples with qualitative comparisons to the results from previous matting algorithms
PCA Based Computation of Illumination-Invariant Space for Road Detection
No full textIllumination changes such as shadows significantly affect the accuracy of various road detection methods, especially for vision-based approaches with an on-board monocular camera. To efficiently consider such illumination changes, we propose a PCA based technique, PCA-II, that finds the minimum projection space from an input RGB image, and then use the space as the illumination-invariant space for road detection. Our PCA based method shows 20 times faster performance on average over the prior entropy based method, even with a higher detection accuracy.
To demonstrate its wide applicability to the road detection problem, we test the invariant space with both bottomup and top-down approaches. For a bottom-up approach, we suggest a simple patch propagation method that utilizes the property of the invariant space, and show its higher accuracy over other state-of-the-art road detection methods running in a bottom-up manner. For a top-down approach, we consider the space as an additional feature to the original RGB to train convolutional neural networks. We were also able to observe robust performance improvement of using the invariant space over the original CNN based methods that do not use the space, only with a minor runtime overhead, e.g., 50 ms per image. These results demonstrate benefits of our PCA-based illumination-invariant space computation
A simulation based method for vehicle motion prediction
No full textThe movement of a vehicle is much affected by surrounding environments such as road shapes and other traffic participants. This paper proposes a new vehicle motion prediction method to predict future motion of an on-road vehicle which is observed by a stereo camera system mounted on a moving vehicle. Our proposed algorithm considers not only the history movement of the observed vehicle, but also the environment configuration around the vehicle. To find feasible paths under a dynamic road environment, the Rapidly-Exploring Random Tree (RRT) is used. A simulation based method is then applied to generate future trajectories by combining results from RRT and a motion prediction algorithm modelled as a Gaussian Mixture Model (GMM). Our experiments show that our approach can predict future motion of a vehicle accurately, and outperforms previous works where only motion history is considered for motion prediction
Modeling the Calibration Pipeline of the Lytro Camera for High Quality Light-Field Image Reconstruction
No full textAsymmetric Stereo with Catadioptric Lens: High Quality Image Generation for Intelligent Robot
No full text- …
