Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking, because they require very long ...training time and a large number of training samples. In this paper, we present an efficient and very robust tracking algorithm using a single convolutional neural network (CNN) for learning effective feature representations of the target object in a purely online manner. Our contributions are multifold. First, we introduce a novel truncated structural loss function that maintains as many training samples as possible and reduces the risk of tracking error accumulation. Second, we enhance the ordinary stochastic gradient descent approach in CNN training with a robust sample selection mechanism. The sampling mechanism randomly generates positive and negative samples from different temporal distributions, which are generated by taking the temporal relations and label noise into account. Finally, a lazy yet effective updating scheme is designed for CNN training. Equipped with this novel updating algorithm, the CNN model is robust to some long-existing difficulties in visual tracking, such as occlusion or incorrect detections, without loss of the effective adaption for significant appearance changes. In the experiment, our CNN tracker outperforms all compared state-of-the-art methods on two recently proposed benchmarks, which in total involve over 60 video sequences. The remarkable performance improvement over the existing trackers illustrates the superiority of the feature representations, which are learned purely online via the proposed deep learning framework.
Most of the conventional face hallucination methods assume the input image is sufficiently large and aligned, and all require the input image to be noise-free. Their performance degrades drastically ...if the input image is tiny, unaligned, and contaminated by noise. In this paper, we introduce a novel transformative discriminative autoencoder to 8X super-resolve unaligned noisy and tiny (16X16) low-resolution face images. In contrast to encoder-decoder based autoencoders, our method uses decoder-encoder-decoder networks. We first employ a transformative discriminative decoder network to upsample and denoise simultaneously. Then we use a transformative encoder network to project the intermediate HR faces to aligned and noise-free LR faces. Finally, we use the second decoder to generate hallucinated HR images. Our extensive evaluations on a very large face dataset show that our method achieves superior hallucination results and outperforms the state-of-the-art by a large margin of 1.82dB PSNR.
With the availability of low-cost and compact 2.5/3D visual sensing devices, computer vision community is experiencing a growing interest in visual scene understanding of indoor environments. This ...survey paper provides a comprehensive background to this research topic. We begin with a historical perspective, followed by a popular 3D data representation and a comparative analysis of available datasets. Before delving into the application specific details, this survey provides a succinct introduction to the core technologies that are the underlying methods extensively used in this paper. Afterwards, we review the developed techniques according to a taxonomy based on the scene understanding tasks. This covers holistic indoor scene understanding as well as subtasks, such as scene classification, object detection, pose estimation, semantic segmentation, 3D reconstruction, saliency detection, physics-based reasoning, and affordance prediction. Later on, we summarize the performance metrics used for evaluation in different tasks and a quantitative comparison among the recent state-of-the-art techniques. We conclude this review with the current challenges and an outlook toward the open research problems requiring further investigation.
In this paper, we tackle depth estimation and blur removal from a single out-of-focus image. Previously, depth is estimated, and blurred is removed using multiple images; for example, from multiview ...or stereo scenes, but doing so with a single image is challenging. Earlier works of monocular images for depth estimated and deblurring either exploited geometric characteristics or priors using hand-crafted features. Lately, there is enough evidence that deep convolutional neural networks (CNN) significantly improved numerous vision applications; hence, in this article, we present a depth estimation method that leverages rich representations learned from cascaded convolutional and fully connected neural networks operating on a patch-pooled set of feature maps. Furthermore, from this depth, we computationally reconstruct an all-focus image,
i.e.
, removing the blur and achieve synthetic re-focusing, all from a single image. Our method is fast, and it substantially improves depth accuracy over the state-of-the-art alternatives. Our proposed depth estimation approach can be utilized for everyday scenes without any geometric priors or extra information. Furthermore, our experiments on two benchmark datasets consist images of indoor and outdoor scenes,
i.e.
, Make3D and NYU-v2 demonstrate superior performance in comparison with other available depth estimation state-of-the-art methods by reducing the root-mean-squared error by
57%
and
46%
, and state-of-the-art blur removal methods by
0.36 dB
and
0.72 dB
in PSNR, respectively. This improvement in-depth estimation and deblurring is further demonstrated by the superior performance using real defocus images against images captured with a prototype lens.
Full text
Available for:
DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Conventional face hallucination methods heavily rely on accurate alignment of low-resolution (LR) faces before upsampling them. Misalignment often leads to deficient results and unnatural artifacts ...for large upscaling factors. However, due to the diverse range of poses and different facial expressions, aligning an LR input image, in particular when it is tiny, is severely difficult. In addition, when the resolutions of LR input images vary, previous deep neural network based face hallucination methods require the interocular distances of input face images to be similar to the ones in the training datasets. Downsampling LR input faces to a required resolution will lose high-frequency information of the original input images. This may lead to suboptimal super-resolution performance for the state-of-the-art face hallucination networks. To overcome these challenges, we present an end-to-end multiscale transformative discriminative neural network devised for super-resolving unaligned and very small face images of different resolutions ranging from 16
×
16 to 32
×
32 pixels in a unified framework. Our proposed network embeds spatial transformation layers to allow local receptive fields to line-up with similar spatial supports, thus obtaining a better mapping between LR and HR facial patterns. Furthermore, we incorporate a class-specific loss designed to classify upright realistic faces in our objective through a successive discriminative network to improve the alignment and upsampling performance with semantic information. Extensive experiments on a large face dataset show that the proposed method significantly outperforms the state-of-the-art.
Full text
Available for:
CEKLJ, DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, SIK, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Images captured under outdoor scenes usually suffer from low contrast and limited visibility due to suspended atmospheric particles, which directly affects the quality of photographs. Despite ...numerous image dehazing methods have been proposed, effective hazy image restoration remains a challenging problem. Existing learning-based methods usually predict the medium transmission by convolutional neural networks (CNNs), but ignore the key global atmospheric light. Different from previous learning-based methods, we propose a flexible cascaded CNN for single hazy image restoration, which considers the medium transmission and global atmospheric light jointly by two task-driven subnetworks. Specifically, the medium transmission estimation subnetwork is inspired by the densely connected CNN while the global atmospheric light estimation subnetwork is a light-weight CNN. Besides, these two subnetworks are cascaded by sharing the common features. Finally, with the estimated model parameters, the haze-free image is obtained by the atmospheric scattering model inversion, which achieves more accurate and effective restoration performance. Qualitatively and quantitatively experimental results on the synthetic and real-world hazy images demonstrate that the proposed method effectively removes haze from such images, and outperforms several state-of-the-art dehazing methods.
We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vector, the norm of ...first and second derivatives of intensity with respect to x and y, etc., characterizes a region of interest. We describe a fast method for computation of covariances based on integral images. The idea presented here is more general than the image sums or histograms, which were already published before, and with a series of integral images the covariances are obtained by a few arithmetic operations. Covariance matrices do not lie on Euclidean space, therefore we use a distance metric involving generalized eigenvalues which also follows from the Lie group structure of positive definite matrices. Feature matching is a simple nearest neighbor search under the distance metric and performed extremely rapidly using the integral images. The performance of the covariance features is superior to other methods, as it is shown, and large rotations and illumination changes are also absorbed by the covariance matrix.
Full text
Available for:
FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Tracking objects across multiple frames is a well-investigated problem in computer vision. The majority of the existing algorithms that assume an accurate initialization is readily available. ...However, in many real-life settings, in particular for applications where the video is streaming in real time, the initialization has to be provided by a human operator. This limitation raises an inevitable uncertainty issue. Here, we first collect a large and new data set of inputs that consists of more than 20 K human initialization clicks, by several subjects under three practical user interface scenarios for the popular TB50 tracking benchmark. We analyze the factors and mechanisms of human input, derive statistical models, and show that human input always contains deviations, which exacerbate further when the relative object-camera motion becomes large. We also design and evaluate alternative refinement schemes, and propose a strategy that refits an object window on the most probable target region after a single click. To compensate for the human initialization errors, our method generates window proposals using objectness cues extracted from color and motion attributes, accumulates them into a likelihood map that is weighted by the initial click position and visual saliency scores, and assigns the final window by the maximum likelihood estimate. Our experiments demonstrate that the presented refinement strategy effectively reduces human input errors.
Non-rigid 3D shape retrieval has become an active and important research topic in content-based 3D object retrieval. The aim of this paper is to measure and compare the performance of ...state-of-the-art methods for non-rigid 3D shape retrieval. The paper develops a new benchmark consisting of 600 non-rigid 3D watertight meshes, which are equally classified into 30 categories, to carry out experiments for 11 different algorithms, whose retrieval accuracies are evaluated using six commonly utilized measures. Models and evaluation tools of the new benchmark are publicly available on our web site 1.
► We develop a new benchmark consisting of 600 non-rigid 3D watertight meshes. ► We evaluate and compare 11 non-rigid 3D shape retrieval methods. ► We find that no single method performs best for all kinds of objects. ► Models and evaluation tools of the new benchmark are publicly available.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK