Pixel Matching Research Articles

Depth-driven variable-frequency sinusoidal fringe pattern for accuracy improvement in fringe projection profilometry.

Sinusoidal fringe pattern is widely used in optical profilometry; however, the traditional constant-frequency sinusoidal fringe pattern reduces 3D measurement accuracy in the defocus region. To this end, this paper presents a variable-frequency sinusoidal fringe pattern method that is optimized by the measurement depth. The proposed method improves the pixel matching accuracy and thus increases measurement accuracy. This paper theoretically determines the optimal frequency by analyzing the pixel matching error caused by intense noise in a captured image; presents the online frequency optimization along abscissa and ordinate axes in the sinusoidal fringe patterns; and details the encoding and decoding to use variable-frequency fringe patterns for 3D profilometry. Simulations and experiments demonstrate that our proposed method can improve the 3D measurement accuracy and increase measurement robustness.

Depth sensing with coding-free pattern based on topological constraint

Structured light depth sensing with a single-shot pattern is widely employed to capture depth maps for dynamic scenes. For conventional structured light techniques, the projected pattern has to be coded delicately in regards to color, shape, and intensity, in order to assign each pixel with a unique label. However, using such a complicated pattern is a double-edged sword, as although it is effective in labelling pixels, it is also sensitive to environmental noise such as: ambient illumination, textures, uneven albedos, or colors of objects in a scene. In contrast, a coding-free pattern is simply constructed and also insensitive to various environmental noise. Therefore, the coding-free pattern method is capable of robustly sensing the depth for complex scenes. The main challenge in coding-free depth sensing is the ‘correspondence retrieval’ between the projected and captured pattern (i.e. matching pixels between the projected and captured pattern). In this study, we focused on evaluating the correspondence retrieval in a coding-free binary grid pattern. A graph based topological labelling (GBTL) algorithm is proposed to determine the topological coordinates of the intersections of the grid. Then we retrieved the correspondence by using the topology of the grid and the epipolar constraint. We also demonstrated the upper bounds of depth variance by employing the proposed method. The proposed technique alleviates many of the limitations faced with traditional correspondence retrieval. Experimental results showed that the proposed technique performed better (i.e. in terms of precision) than the popular RGB-D cameras Kinect v1 and Kinect v2. Compared with the traditional single-shot techniques, which require complicated patterns, the proposed technique significantly improved the robustness and ease of work, while achieving comparable precision. Additionally, this proposed technique could also be used for both the binary coding-free and the traditional chromatic grid patterns.

RESEARCH ON COORDINATE TRANSFORMATION METHOD OF GB-SAR IMAGE SUPPORTED BY 3D LASER SCANNING TECHNOLOGY

Abstract. In the image plane of GB-SAR, identification of deformation distribution is usually carried out by artificial interpretation. This method requires analysts to have adequate experience of radar imaging and target recognition, otherwise it can easily cause false recognition of deformation target or region. Therefore, it is very meaningful to connect two-dimensional (2D) plane coordinate system with the common three-dimensional (3D) terrain coordinate system. To improve the global accuracy and reliability of the transformation from 2D coordinates of GB-SAR images to local 3D coordinates, and overcome the limitation of traditional similarity transformation parameter estimation method, 3D laser scanning data is used to assist the transformation of GB-SAR image coordinates. A straight line fitting method for calculating horizontal angle was proposed in this paper. After projection into a consistent imaging plane, we can calculate horizontal rotation angle by using the linear characteristics of the structure in radar image and the 3D coordinate system. Aided by external elevation information by 3D laser scanning technology, we completed the matching of point clouds and pixels on the projection plane according to the geometric projection principle of GB-SAR imaging realizing the transformation calculation of GB-SAR image coordinates to local 3D coordinates. Finally, the effectiveness of the method is verified by the GB-SAR deformation monitoring experiment on the high slope of Geheyan dam.

Data‐driven recovery of hand depth using CRRF on stereo images

Hand pose is emerging as an important interface for human–computer interaction. This study presents a data‐driven method to estimate a high‐quality depth map of a hand from a stereoscopic camera input by introducing a novel superpixel‐based regression framework that takes advantage of the smoothness of the depth surface of the hand. To this end, the authors introduce conditional regressive random forest (CRRF), a method that combines a conditional random field (CRF) and an RRF to model the mapping from a stereo red, green and blue image pair to a depth image. The RRF provides a unary term that adaptively selects different stereo‐matching measures as it implicitly determines matching pixels in a coarse‐to‐fine manner. While the RRF makes depth prediction for each superpixel independently, the CRF unifies the prediction of depth by modelling pairwise interactions between adjacent superpixels. Experimental results show that CRRF can generate a depth image more accurately than the leading contemporary techniques using an inexpensive stereo camera.

Flow-guided hair removal for automated skin lesion identification

In this paper, we propose a method for removing hairs automatically from skin lesion images. To achieve this, we employ an edge-detection technique based on edge-tangent flow. To detect only hair-like structures, rather than contour boundaries, we propose a novel, specialized method for detecting hairs. Regardless of the personal characteristics of the hairs, hairy regions are detected because our method detects coherent thin lines of consistent width. We then restore the hairy regions detected by the proposed method by using the texture synthesis method. Our method restores the regions occluded by hairs with very few remarkable artifacts, because we utilize pixels that actually exist in the source image to restore the occluded areas by searching for the best matching pixels.

Offline signature verification using shape correspondence

Biometrics has always been an integral part of human identification and verification, with offline signature verification being a most crucial component of it. It is a challenging task as the signatures are time variant. To address the above difficulty, this paper presents a novel approach to identify the correspondence between pixels of different signatures using an adaptive weighted combination of shape context distance and Euclidean distance. These correspondences are then used for the transformation of query signature plane to reference signature plane using thin plate spline transformation. The distances between signatures are computed using plane transformation, a shape descriptor, and the farness between matched pixels. The computed distances are then fed to the support vector machine (SVM) classifier to determine the merit of genuineness. With the proposed methodology, better accuracy is obtained. The results exhibit an accuracy of 89.58% using proposed method on GPDS synthetic signature database.

Offline signature verification using shape correspondence

Biometrics has always been an integral part of human identification and verification, with offline signature verification being a most crucial component of it. It is a challenging task as the signatures are time variant. To address the above difficulty, this paper presents a novel approach to identify the correspondence between pixels of different signatures using an adaptive weighted combination of shape context distance and Euclidean distance. These correspondences are then used for the transformation of query signature plane to reference signature plane using thin plate spline transformation. The distances between signatures are computed using plane transformation, a shape descriptor, and the farness between matched pixels. The computed distances are then fed to the support vector machine (SVM) classifier to determine the merit of genuineness. With the proposed methodology, better accuracy is obtained. The results exhibit an accuracy of 89.58% using proposed method on GPDS synthetic signature database.

Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization

Automatic colorization is generally classified into two groups: propagation-based methods and reference-based methods. In reference-based automatic colorization methods, color image(s) are used as reference(s) to reconstruct original color of a gray target image. The most important task here is to find the best matching pairs for all pixels between reference and target images in order to transfer color information from reference to target pixels. A lot of attractive local feature-based image matching methods have already been developed for the last two decades. Unfortunately, as far as we know, there are no optimal matching methods for automatic colorization because the requirements for pixel matching in automatic colorization are wholly different from those for traditional image matching. To design an efficient matching algorithm for automatic colorization, clustering pixel with low computational cost and generating descriptive feature vector are the most important challenges to be solved. In this paper, we present a novel method to address these two problems. In particular, our work concentrates on solving the second problem (designing a descriptive feature vector); namely, we will discuss how to learn a descriptive texture feature using scaled sparse texture feature combining with a nonlinear transformation to construct an optimal feature descriptor. Our experimental results show our proposed method outperforms the state-of-the-art methods in terms of robustness for color reconstruction for automatic colorization applications.

UAV Based Agricultural Planning and Landslide Monitoring

The use of Unmanned Aerial Vehicle (UAV) tools has become widespread in map production, land surveying, landslide, erosion monitoring, monitoring of agricultural activities, aerial crop surveying, forest fire detection and monitoring operations. In this study, GEO 2 UAV manufactured by TEKNOMER equipped with SONY A6000 camera has been used. The flight plan have been performed with 100 m altitude, with 80% longitudinal and 60% side overlapping. Ground Control Points (GCPs) have been observed with Topcon and Trimble GNSS geodetic receivers. Recorded GNSS signals have been processed with LGO V.8.4 software to get sensitive location information. 985 photos have been taken for the 344 hectares the agricultural area. 291 photos have been taken for 50 hectares the landslide area. All photos were processed by PIX4D software. For the agricultural area, 25 GCPs and for the landslide area, 8 GCPs have been included in the evaluation. 3D images were produced with pixel matching algorithms. As a result, the RMS evaluation was obtained as ±0.054 m for the agricultural area and as ±0.018 m for the landslide area. UAV images have indisputable contributions to the management of catastrophes such as landslides and earthquakes, and it is impossible to make terrestrial measurements in areas where disaster impact continues.

Automated Skin Detection using Fuzzy Logic based Pixel Matching Algorithm

Objectives: Skin detection is the initial process of any automatic face recognition system. One of the fore most common approaches to detect the faces in facial pictures can be done by an automatic face detection method. In this paper, a new type of facial skin detection using the combination of Fuzzy and Pixel matching algorithms is proposed. Method/Statistical Analysis: The proposed system has three steps. Initially, the input facial color image is transformed in to a grey scale image and then, it is sharpened using a filter. Secondly, the pixels of the different types of facial grey scale images are computed. Finally, the computed pixels are compared with the original grey scale image based on the fuzzy rules. This process is done for the first pixel to the last pixel so that all the pixels which are present in the entire image can be included in the overall process. Findings: The algorithm is tested for different types of facial images for both the accuracy and the time taken to complete the skin detection process. The results of the experiments reveal that an accurate skin detection rate of 94.42% for the combination of fuzzy based pixel matching along with the dimension reduction methodology. Application/ Improvements: Future enhancements in this work are to propose an efficient algorithm to detect the facial images of group of faces present in a single image. Keywords: Dimension Reduction, Facial Image, Fuzzy Logic, Pixel Matching Algorithm, Skin Texture Analysis, Skin Detection

Quantitative analysis of relative geolocation accuracy of the TerraSAR-X enhanced ellipsoid corrected product

High-resolution commercial synthetic aperture radar (SAR) satellites with resolutions of several meters have recently been used for effective disaster monitoring. One study reported the earthquake’s displacement using the pixel matching method with both pre- and postevent TerraSAR-X data, with a validated accuracy of ∼30 cm at global navigation satellite system (GNSS) Earth observation network (GEONET) reference points. However, it is insufficient to determine the accuracy using analysis of only a couple of data points per orbit. In addition, the errors were not reported because the number of data samples was too small to discuss the statistics. In order to better understand displacement accuracy, we analyzed displacement features using the pixel matching method to evaluate the relative geolocation accuracies of the TerraSAR-X product. First, we used fast Fourier transform oversampling 16 times to develop the pixel matching method for estimating the displacement at the subpixel level using the TerraSAR-X StripMap dataset. Second, we applied this methodology to 20 pairs of images from the Tokyo metropolitan area and calculated the displacement for each image pair. Third, we conducted spatial and temporal analyses in order to understand the displacement features. Finally, we evaluated the displacement accuracy by comparison with GEONET and solid earth tide data as a reference.

1×3画素マッチングによる高速動きベクトル検出イメージセンサの設計(高機能イメージセンシングとその応用)

1×3画素マッチングによる高速動きベクトル検出イメージセンサの設計(高機能イメージセンシングとその応用)

Estimation of the interpolation error of a three-step rotation algorithm using recorded images with rotated test pattern as ground truth

Abstract Nowadays, the surgical microscope is the goldstandard for microsurgical procedures. Additional functionalities such as surgical navigation, data injection or imageoverlay are providing additional valuable information to the surgeon. For substituting the conventional optical system by a fully-digital multi-camera setup the three dimensional (3D) reconstruction of the scenery in the field of view is required. However, for in camera-based systems, an exact alignment of the cameras is a challenging task. Therefore, a final adjustment through a digital image rotation becomes necessary. Even though the digital rotation is a commonly used procedure, it leads to unavoidable errors because of the discretized grid of the image. Previous research reported in literature has demonstrated that the method of digitally rotating the images combined with the Fourier interpolation delivers the results of best quality. Nevertheless, the performance evaluation of this algorithm was carried out rotating an image in multiple threestep rotations to a total of 90 or 180 degrees and comparing it to the original image rotated in one step. This is a valid approach because a rotation of 90 or 180 degrees does not produce rotation artifacts. In this research project, we verify the performance of the three-step rotation algorithm using recorded images for which the test pattern was rotated as ground truth. A series of photographs with a rotation angle of 3 to 45 degrees was created. The advantage of this setup is that the result of the digital rotation can be directly compared to the recorded image. In addition, with the knowledge obtained about the interpolation error, we can improve pixel matching in the further triangulation used for 3D reconstruction. By doing so, the estimation of the interpolation error helps to reduce the triangulation error.

Comparison of SIFT, Bi-SIFT, and Tri-SIFT and their frequency spectrum analysis

This paper aims to explore frequency behavior of isotropic (regular SIFT) and anisotropic (Bi-SIFT and Tri-SIFT) versions of the scale-space keypoint detection algorithm SIFT. We introduced a new smoothing function Trilateral filter that can be used in formation of a scale-space as an alternative to the Gaussian scale-space. The number of matching pixels, warping error, and scatteredness are employed in comparison. We made the comparison out of face dataset and object dataset for scale, orientation, and view-angle transformations as well as lighting and compression variations. The comparison results show that anisotropic smoothing detects more keypoints than isotropic one. The Tri-SIFT is more robust to variation in viewpoint angle.

A robust method for the reconstruction of disparity maps based on multilevel processing of stereo color image pairs

A novel method for the reconstruction of disparity maps (DMs) with robust properties to nonideal registration conditions, reflections, and noise in stereo color image pairs has been substantiated for the first time. The novel approach proposes a scheme for image DM reconstruction where Jaccard distance metric is used as a proximity criterion in stereo image pair matching. A physical interpretation of the method that allows the quality of the formed DMs to be improved significantly is given. A processing block diagram has been developed in accordance with the novel approach. Simulations of the novel DM reconstruction method have shown an advantage of the proposed DM reconstruction scheme in terms of generally recognized criteria, such as the structural similarity index measure and the bad matching pixels, and when visually comparing the formed DMs.

A fast pixel matching method based on phase feature extraction in online phase-measuring profilometry

A fast pixel matching method based on phase feature extraction in online phase-measuring profilometry is proposed, which is used to solve the problem where the object motion is along a straight line. The movement of the object results in the displacement of images in the captured deformed patterns, so pixel matching is carried out to modify the positions of images, which not only realizes the point-to-point correspondence of the object, but extracts the equivalent phase-shifting deformed patterns. So, the 3D surface shape of the object moving on the pipeline can be reconstructed successfully with an equivalent phase-shifting algorithm. The equiphase surface phase feature extracted from the phase distributions of the object obtained by Fourier transform profilometry is used to assist pixel matching in this paper. Normalization and further binarization of the phase feature extraction improve pixel matching’s accuracy and speed. The simulation and experiments verify the feasibility and validity of the proposed method.

NDC-IVM: An automatic segmentation of optic disc and cup region from medical images for glaucoma detection

Glaucoma is an eye disease that usually occurs with the increased Intra-Ocular Pressure (IOP), which damages the vision of eyes. So, detecting and classifying Glaucoma is an important and demanding task in recent days. For this purpose, some of the clustering and segmentation techniques are proposed in the existing works. But, it has some drawbacks that include inefficient, inaccurate and estimates only the affected area. In order to solve these issues, a Neighboring Differential Clustering (NDC) — Intensity Variation Masking (IVM) are proposed in this paper. The main intention of this work is to extract and diagnose the abnormal retinal image by identifying the optic disc. This work includes three stages such as, preprocessing, clustering and segmentation. At first, the given retinal image is preprocessed by using the Gaussian Mask Updated (GMU) model for eliminating the noise and improving the quality of the image. Then, the cluster is formed by extracting the threshold and patterns with the help of NDC technique. In the segmentation stage, the weight is calculated for pixel matching and ROI extraction by using the proposed IVM method. Here, the novelty is presented in the clustering and segmentation processes by developing NDC and IVM algorithms for accurate Glaucoma identification. In experiments, the results of both existing and proposed techniques are evaluated in terms of sensitivity, specificity, accuracy, Hausdorff distance, Jaccard and dice metrics.

A study of a matching pixel by pixel (MPP) algorithm to establish an empirical model of water quality mapping, as based on unmanned aerial vehicle (UAV) images

Linear regression models are a popular choice for the relationships between water quality parameters and bands (or band ratios) of remote sensing data. However, this research regards the phenomena of mixed pixels, specular reflection, and water fluidity as the challenges to establish a robust regression model. Based on the data of measurements in situ and remote sensing data, this study presents an enumeration-based algorithm, called matching pixel by pixel (MPP), and tests its performance in an empirical model of water quality mapping. Four small reservoirs, which cover a mere several hundred-thousand m2, in Kinmen, Taiwan, are selected as the study sites. The multispectral sensors, carried on an unmanned aerial vehicle (UAV), are adopted to acquire remote sensing data regarding water quality parameters, including chlorophyll-a (Chl-a), Secchi disk depth (SDD), and turbidity in the reservoirs. The experimental results indicate that, while MPP can reduce the influence of specular reflection on regression model establishment, specular reflection does hamper the correction of thematic map production. Due to water fluidity, sampling in situ should be followed by UAV imaging as soon as possible. Excluding turbidity, the obtained estimation accuracy can satisfy the national standard.

Stereo vision with Equal Baseline Multiple Camera Set (EBMCS) for obtaining depth maps of plants

This paper presents a method of improving the estimation of distances between an autonomous harvesting robot and plants with ripe fruits by using the vision system based on five cameras. The system is called Equal Baseline Multiple Camera Set (EBMCS). EBMCS has some features of a camera matrix and a camera array. EBMCS is regarded as a set of stereo cameras for estimating distances by obtaining disparity maps and depth maps. This paper introduces Exceptions Excluding Merging Method (EEMM) which makes it possible to improve the quality of disparity maps by integrating maps acquired from individual stereo cameras included in EBMCS. The method was tested with eight different stereo matching algorithms including Efficient Large-scale Stereo Matching (ELAS), algorithms implemented in the OpenCV library and algorithms available in Middlebury Stereo Vision Page. Experiments were performed on input data sets which contained images of strawberry plants, cherry trees and redcurrant plants. The bad matching pixels (BMP) metric was used for measuring the error rate in disparity maps used in the distance estimation. The results of experiments showed that, on average, the EEMM merging method used with EBMCS consisting of five cameras reduces the error rate of the distance estimation by 26.55% in comparison to results obtained from stereoscopy based on a single stereo camera. The best results were acquired by using with five cameras a stereo matching algorithm based on a graph cut.

Stereo Camera-based Pre-Focusing Method and Its Application to Detection of Pedestrians Entering The Street

For mobile stereo camera systems, constructing three-dimensional (3D) surroundings was an important process to ensure safe navigation; however, it was very time consuming. To decrease the number of traffic accidental deaths, pedestrians entering the street needed to be efficiently detected. Thus, a pre-focusing method (PFM) was proposed to decrease the time required to retrieve matching pixel pairs in stereo pair images. The method PFM provided pre-focused stereo pair images in which an object at a pre-determined distance displays no disparity between images. Pre-focusing was performed by applying a perspective transformation to the image pair, whose coefficients were obtained via a calibration stage of the PFM. An object at the distance was extracted by evaluating the spatial similarity between the pre-focused stereo pair images without scanning in order to find matching point pairs. To avoid errors due to edges and uniform areas, the smooth test, which was a nonparametric test, was introduced to evaluate the spatial similarity. A watching window was introduced to detect the pedestrians. In this study, the method PFM was successfully applied to actual video data captured by a stereo video camera mounted on a bicycle.