摘要 :
The stereo matching algorithm is one of the important methods for 3D surface reconstruction. A stereo matching process produces a disparity map which provides the depth of information required in 3D reconstruction. This map consis...
展开
The stereo matching algorithm is one of the important methods for 3D surface reconstruction. A stereo matching process produces a disparity map which provides the depth of information required in 3D reconstruction. This map consists of disparity values of two corresponding points. Furthermore, the accuracy of 3D reconstruction depends on how precise the disparity being estimated on each pixel location. To get a good 3D reconstruction result, the propose stereo matching algorithm must be strong against the radiometric differences and edge distortions. Hence, this article proposes a new stereo matching algorithm with high accuracy for 3D surface reconstruction. First stage, Sum of Gradient Matching (SG) is proposed which uses magnitude differences with fixed window size. The gradient matching is strong against the radiometric distortions due to different characteristics of the input stereo cameras. Second stage, the Adaptive Support Weight (ASW) with iterative Guided Filter (ASW iGF) is proposed to improve the edges of object matching. The last stage, Joint Weighted Guided Filter (JWGF) is suggested to reduce the remaining noise on the disparity map. Based on the standard quantitative benchmarking stereo dataset, the proposed work in this article produces good results and performs much better compared with before the proposed framework. This new algorithm is also competitive with some established methods in the literature.
收起
摘要 :
Abstract Studying animal locomotion improves our understanding of motor control and aids in the treatment of motor impairment. Mice are a premier model of human disease and are the model system of choice for much of basic neurosci...
展开
Abstract Studying animal locomotion improves our understanding of motor control and aids in the treatment of motor impairment. Mice are a premier model of human disease and are the model system of choice for much of basic neuroscience. Placement of the tips of appendages, here paws, is typically critical for locomotion. Tracking paws from a video is difficult, however, due to frequent occlusions and collisions. We propose a method and provide software to track the paws of rodents. We use a superpixel-based method to segment the paws, direct linear transform to perform 3D reconstruction, a 3D Kalman filter (KF) to solve the matching problem and label paws across frames, and spline fits through time to resolve common collisions. The automated method was compared to manual tracking. The method had an average of 2.54 mistakes requiring manual correction per 1000 frames with a maximum of 5.29 possible errors while these values were estimates of the expected errors. We present an algorithm and its implementation to track the paws of running rodents. This algorithm can be applied to different animals as long as the tips of the legs can be differentiated from the background and other parts of the body using color features. The presented algorithm provides a robust tool for future studies in multiple fields, where precise quantification of locomotor behavior from a high-speed video is required. We further present a graphical user interface (GUI) to track, visualize, and edit the tracking data.
收起
摘要 :
Reservoir simulations and history matching are critical for fine-tuning reservoir production strategies, improving understanding of the subsurface formation, and forecasting remaining reserves. Production data have long been incor...
展开
Reservoir simulations and history matching are critical for fine-tuning reservoir production strategies, improving understanding of the subsurface formation, and forecasting remaining reserves. Production data have long been incorporated for adjusting reservoir parameters. However, the sparse spatial sampling of this data set has posed a significant challenge for efficiently reducing uncertainty of reservoir parameters. Seismic, electromagnetic, gravity and InSAR techniques have found widespread applications in enhancing exploration for oil and gas and monitoring reservoirs. These data have however been interpreted and analyzed mostly separately, rarely exploiting the synergy effects that could result from combining them. We present a multi-data ensemble Kalman filter-based history matching framework for the simultaneous incorporation of various reservoir data such as seismic, electromagnetics, gravimetry and InSAR for best possible characterization of the reservoir formation. We apply an ensemble-based sensitivity method to evaluate the impact of each observation on the estimated reservoir parameters. Numerical experiments for different test cases demonstrate considerable matching enhancements when integrating all data sets in the history matching process. Results from the sensitivity analysis further suggest that electromagnetic data exhibit the strongest impact on the matching enhancements due to their strong differentiation between water fronts and hydrocarbons in the test cases. (C) 2015 Elsevier B.V. All rights reserved.
收起
摘要 :
The Laplacian pyramid-based block-matching 3-D filtering (BM3D) is proposed (LPBM3D) for despeckling the speckle image. For BM3D in each pyramid layer, the criterion used to collect blocks in the 3-D groups to the actual data stat...
展开
The Laplacian pyramid-based block-matching 3-D filtering (BM3D) is proposed (LPBM3D) for despeckling the speckle image. For BM3D in each pyramid layer, the criterion used to collect blocks in the 3-D groups to the actual data statistics is devised. An adaptive wavelet thresholding operator that depends on both noise level and signal characteristics is proposed. The performance of the proposed LPBM3D method has been compared with the state-of-the-art methods, including the recently proposed nonlocal mean (NLM) and BM3D method. Experimental results show that the visual quality and evaluation indexes outperform the other methods with no edge preservation. The proposed algorithm effectively realizes both despeckling and edge preservation.
收起
摘要 :
This research presents an algorithm for three-dimensional (3-D) pose tracking of a rigid object by processing sequences of monocular images. The pose trajectory of the object is estimated by performing linear correlation between t...
展开
This research presents an algorithm for three-dimensional (3-D) pose tracking of a rigid object by processing sequences of monocular images. The pose trajectory of the object is estimated by performing linear correlation between the current scene and a filter bank constructed from different views of a 3-D model of the target, which are created synthetically with computer graphics. The pose tracking is guided by particle filters that dynamically adapt the filter bank by taking into account the kinematics of the target in the scene. Experimental results obtained with the proposed algorithm in processing synthetic and real images are presented and discussed. These results show that the proposed algorithm achieves a higher accuracy of pose tracking in terms of objective metrics, in comparison with that of existing similar algorithms.
收起
摘要 :
BM3D-based denoising has been showing high performance in restoring images damaged by additive white noise and there has been intense research on this method and its variants. In this paper, we make three improvements on BM3D (Blo...
展开
BM3D-based denoising has been showing high performance in restoring images damaged by additive white noise and there has been intense research on this method and its variants. In this paper, we make three improvements on BM3D (Block-matching and 3-dimensional filtering). Block matching performs poor and affect denoising performance, especially if noise intensity is high. In the paper, we first proposed a new block similarity metric that accounts for characteristic of noise contained in the observed images in order to guarantee accuracy of block matching even in presence of high intensity noise. Second, block size is a crucial hyperparameter for BM3D. The optimal block size varies with the characteristic of images. However, it is difficult to determine such an optimal block size. We proposed a method to mitigate this difficulty in determining optimal block sizes by combining BM3D and multi-scaled images. Finally, in Aggregation of BM3D, the same weight is assigned to every block in three-dimensional structures. In fact, however, the degree with which noise is removed in each block is different. We presented a method of assigning different weights to blocks according to their respective denoising degrees. Experimental results show that the proposed method is competitive with BM3D and even many of state-of-the-art methods. Actually, it brings about 0.1 similar to 0.6 dB pickup in the PSNR (Peak Signal to Noise Ratio) value. Also, we recommend that it may get better results by applying ideas proposed in this paper individually to state-of-the-art methods.
收起
摘要 :
In general, a typical iris recognition system includes iris imaging, iris liveness detection, iris image quality assessment, and iris recognition. This paper presents an algorithm focusing on the last two steps. The novelty of thi...
展开
In general, a typical iris recognition system includes iris imaging, iris liveness detection, iris image quality assessment, and iris recognition. This paper presents an algorithm focusing on the last two steps. The novelty of this algorithm includes improving the speed and accuracy of the iris segmentation process, assessing the iris image quality such that only the clear images are accepted so as to reduce the recognition error, and producing a feature vector with discriminating texture features and a proper dimensionality so as to improve the recognition accuracy and computational efficiency. The Hough transform, polynomial fitting technique, and some morphological operations are used for the segmentation process. The phase data from 1D Log-Gabor filter is extracted and encoded efficiently to produce a proper feature vector. Experimental tests were performed using CASIA iris database (756 samples). These tests prove that the proposed algorithm has an encouraging performance.
收起
摘要 :
This paper proposes novel algorithms to detect pavement lane markings on two-dimensional (2D) laser images via three stages. First, a new matched filter is developed to generate strongest responses at pavement lane markings. Secon...
展开
This paper proposes novel algorithms to detect pavement lane markings on two-dimensional (2D) laser images via three stages. First, a new matched filter is developed to generate strongest responses at pavement lane markings. Second, a novel hybrid thresholding method is proposed to preserve strong responses while eliminating weak responses. Last, the Shape Examination is conducted to verify if the geometric shapes of detected objects are similar to the pattern of pavement lane markings, resulting in a higher confidence level. The experimental results on six real pavement sections demonstrated that the proposed algorithms achieved high F-measures greater than 92% for pavement lane markings in excellent or fair conditions. In addition, the F-measures were higher than 82% even for the two sections with lane markings in severe conditions, which should reflect the efficiency of the proposed algorithms. (C) 2018 Elsevier Ltd. All rights reserved.
收起
摘要 :
This paper presents a new bilateral filtering method specially designed for practical stereo vision systems. Parallel algorithms are preferred in these systems due to the real-time performance requirement. Edge-preserving filters ...
展开
This paper presents a new bilateral filtering method specially designed for practical stereo vision systems. Parallel algorithms are preferred in these systems due to the real-time performance requirement. Edge-preserving filters like the bilateral filter have been demonstrated to be very effective for high-quality local stereo matching. A hardware-efficient bilateral filter is thus proposed in this paper. When moved to an NVIDIA GeForce GTX 580 GPU, it can process a one megapixel color image at around 417 frames per second. This filter can be directly used for cost aggregation required in any local stereo matching algorithm. Quantitative evaluation shows that it outperforms all the other local stereo methods both in terms of accuracy and speed on Middlebury benchmark. It ranks 12th out of over 120 methods on Middlebury data sets, and the average runtime (including the matching cost computation, occlusion handling, and post processing) is only 15 milliseconds (67 frames per second).
收起
摘要 :
Building a spatially consistent model is a key functionality to endow a mobile robot with autonomy. Without an initial map or an absolute localization means, it requires to concurrently solve the localization and mapping problems....
展开
Building a spatially consistent model is a key functionality to endow a mobile robot with autonomy. Without an initial map or an absolute localization means, it requires to concurrently solve the localization and mapping problems. For this purpose, vision is a powerful sensor, because it provides data from which stable features can be extracted and matched as the robot moves. But it does not directly provide 3D information, which is a difficulty for estimating the geometry of the environment. This article presents two approaches to the SLAM problem using vision: one with stereovision, and one with monocular images. Both approaches rely on a robust interest point matching algorithm that works in very diverse environments. The stereovision based approach is a classic SLAM implementation, whereas the monocular approach introduces a new way to initialize landmarks. Both approaches are analyzed and compared with extensive experimental results, with a rover and a blimp.
收起