Local Block Matching Research Articles

A local multi-block with various constraints approach for stereo vision in StereoPi

The conventional local block matching algorithms are fast but have an accuracy issue, making them unsuitable to be implemented on real-time applications. This paper studies a local block matching algorithm with different cost computations, combining a cost aggregation with various blocks' shape and sizes, using the computer and StereoPi. Compared to other local block matching algorithms, the Ranking-Gradient-Similarity Multi-Block (RGSMB) algorithm can extract information with a higher cost uniqueness within the predefined local window. Using KITTI 2015 as input data, RGSMB has better accuracy than other local block matching approaches. It is at least 5% better than Census Transform (CT), 23% better than Ranking Transform (RT), and 62% better than Sum of Absolute Differences (SAD) in terms of accuracy. Furthermore, it can achieve lower computational costs on the StereoPi, a low-cost computer vision embedded system. The RGSMB can achieve 2.5 fps with the right image resolution and parameter settings.

Human skeleton mutual learning for person re-identification

Person re-identification refers to matching people across non-overlapping camera views on different locations and at different times. In the case of changes in perspective, light, background, veil, and person's clothing, traditional method cannot achieve person recognition effectively and reliably. In this paper, we propose a novel biometric metric learning method named Human Skeleton Mutual Learning person re-identification (HSMLP-Reid). The purpose of HSML person re-identification method (HSMLP-Reid) largely aims to use the new pedestrian local segmentation method proposed in this paper combined with the global skeleton information to solve the influence of background and local posture change. Firstly, bottom-up method is used to estimate the pedestrian posture and skeleton and the joint points of the pedestrians will be marked in this process. A new local segmentation method proposed in this paper named joint segmentation is used to locally segment pedestrians and perform local block matching. Furthermore, we learn the global skeleton information by defined joint distances from the pedestrian 2D skeleton estimation by the bottom-up method and use global skeleton information to global skeleton matching. Finally, we use local match and global skeleton match for mutual learning. Local match based on pedestrian nodes and global skeleton match based on pedestrian skeleton are based on biometrics. We learn the classification loss and metric learning loss to train model. Metric loss includes global skeletal distance and local block metric distance. Extensive experimental results on the large-scale Market1501, CUHK03 and CUHK-SYSU data sets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the state-of-the-art methods.

Despeckling of Carotid Artery Ultrasound Images with a Calculus Approach.

Carotid artery images indicate any presence of plaque content, which may lead to atherosclerosis and stroke. Early identification of the disease is possible by taking B-mode ultrasound images in the carotid artery. Speckle is the inherent noise content in the ultrasound images, which essentially needs to be minimized. The objective of the proposed method is to convert the multiplicative speckle noise into additive, after which the frequency transformations can be applied. The method uses simple differentiation and integral calculus and is named variable gradient summation. It differs from the conventional homomorphic filter, by preserving the edge features to a great extent and better denoising. The additive image is subjected to wavelet decomposition and further speckle filtering with three different filters Non Local Means (NLM), Vectorial Total Variation (VTV) and Block Matching and 3D filtering (BM3D) algorithms. By this approach, the components dependent on the image are identified and the unwanted noise content existing in the high frequency portion of the image is removed. Experiments conducted on a set of 300 B-mode ultrasound carotid artery images and the simulation results prove that the proposed method of denoising gives enhanced results as compared to the conventional process in terms of the performance evaluation methods like peak signal to noise ratio, mean square error, mean absolute error, root mean square error, structural similarity, quality factor, correlation and image enhancement factor.

Image Haze Removal via Reference Retrieval and Scene Prior.

Photography of hazy scene typically suffers from low-contrast which degrades the visibility of the scene. The performance of single-image dehazing methods is limited by the priors or constraints. In this paper, we present an effective method for haze removal, which utilizes its retrieved correlated haze-free images as external information. The correlated haze-free images are with scene prior offering scene structure and local high frequency information for dehazing, although variations in viewpoints, scales, and illumination conditions exist. To utilize those reference more effectively, global geometric registration and local block matching toward the hazy input are performed to reinforce the spatial correlations. Based on the registration, different kinds of external information are estimated. In addition, we combine that additional external information with internal constraint and regularization for estimating scene transmission map. Experiments demonstrate that our approach can produce dehazing results with better visual quality compared with other state-of-the-art methods.

Verified Robust Optical Flow Guided Local Block-Matching and 4D Filtering

Verified Robust Optical Flow Guided Local Block-Matching and 4D Filtering

Fast Tracking of the Left Ventricle Using Global Anatomical Affine Optical Flow and Local Recursive Block Matching

We present a novel method for segmentation and tracking of the left ventricle (LV) in 4D ultrasound sequences using a combination of automatic segmentation at the end-diastolic frame and tracking using both a global optical flow-based tracker and local block matching. The core novelty of the proposed algorithm relies on the recursive formulation of the block-matching problem, which introduces temporal consistency on the patterns being tracked. The proposed method offers a competitive solution, with average segmentation errors of 2.29 and 2.26mm in the training (#=15) and testing (#=15) datasets respectively.

Effective Scanned-Certification Image Retrieval Based on Local Object and Block Matching

Scanned certifications are widely used in China as proof of past achievements. To avoid repetitive usage of the same certification in various awards or funding applications, we design and implement a scanned-certification image retrieval system based on local object and block matching. The seal is used as a salient feature and a modified Hough round detection method is applied for extraction. And local round seals are combined with blocks attributes of the seals to build image indexes. Experimental results will demonstrate the effectiveness of the system. Additionally, we conduct experiments on single color histogram, which further demonstrates the effectiveness of the proposed image retrieval method.

A finger-knuckle-print recognition algorithm using phase-based local block matching

This paper proposes a Finger-Knuckle-Print (FKP) recognition algorithm using Band-Limited Phase-Only Correlation (BLPOC)-based local block matching. The phase information obtained from 2D Discrete Fourier Transform (DFT) of images contains important information of image representation. The phase-based image matching, especially BLPOC-based image matching, is successfully applied to image recognition tasks for biometric recognition applications. To calculate the matching score, the proposed algorithm corrects the global and local deformation between FKP images using phase-based correspondence matching and the BLPOC-based local block matching, respectively. Experimental evaluation using the PolyU FKP database demonstrates the efficient recognition performance of the proposed algorithm compared with the state-of-the-art conventional algorithms.

Fast and Robust 3D Correspondence Matching and Its Application to Volume Registration

SUMMARY This paper presents a fast and accurate volume correspondence matching method using 3D Phase-Only Correlation (POC). The proposed method employs (i) a coarse-to-fine strategy using multi-scale volume pyramids for correspondence search and (ii) high-accuracy POC-based local block matching for finding dense volume correspondence with subvoxel displacement accuracy. This paper also proposes its GPU implementation to achieve fast and practical computation of volume registration. Experimental evaluation shows that the proposed approach exhibits higher accuracy and lower computational cost compared with conventional method. We also demonstrate that the GPU implementation of the proposed method can align two volume data in several seconds, which is suitable for practical use in the image-guided radiation therapy.

Motion compensation for intravascular ultrasound palpography

Rupture of vulnerable plaques in coronary arteries is the major cause of acute coronary syndromes. Most vulnerable plaques consist of a thin fibrous cap covering an atheromous core. These plaques can be identified using intravascular ultrasound (IVUS) palpography, which measures radial strain by cross-correlating RF signals at different intraluminal pressures. Multiple strain images (i.e., partial palpograms) are averaged per heart cycle to produce a more robust compounded palpogram. However, catheter motion due to cardiac activity causes misalignment of the RF signals and thus of the partial palpograms, resulting in less valid strain estimates. To compensate for in-plane catheter rotation and translation, we devised four methods based on block matching. The global rotation block matching (GRBM) and contour mapping (CMAP) methods measure catheter rotation, and local block matching (LBM) and catheter rotation and translation (CRT) estimate displacements of local tissue regions. These methods were applied to nine in vivo pullback acquisitions, made with a 20 MHz phased-array transducer. We found that all these methods significantly increase the number of valid strain estimates in the partial and compounded palpograms (P < 0.008). The best method, LBM, attained an average increase of 17% and 15%, respectively. Implementation of this method should improve the information coming from IVUS palpography, leading to better vulnerable plaque detection.