Showing papers on "Orientation (computer vision) published in 2013"

Advances in Spectral-Spatial Classification of Hyperspectral Images

Abstract: Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes characteristics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.

Accurate 3D comparison of complex topography with terrestrial laser scanner: Application to the Rangitikei canyon (N-Z)

Abstract: Surveying techniques such as terrestrial laser scanner have recently been used to measure surface changes via 3D point cloud (PC) comparison. Two types of approaches have been pursued: 3D tracking of homologous parts of the surface to compute a displacement field, and distance calculation between two point clouds when homologous parts cannot be defined. This study deals with the second approach, typical of natural surfaces altered by erosion, sedimentation or vegetation between surveys. Current comparison methods are based on a closest point distance or require at least one of the PC to be meshed with severe limitations when surfaces present roughness elements at all scales. To solve these issues, we introduce a new algorithm performing a direct comparison of point clouds in 3D. The method has two steps: (1) surface normal estimation and orientation in 3D at a scale consistent with the local surface roughness; (2) measurement of the mean surface change along the normal direction with explicit calculation of a local confidence interval. Comparison with existing methods demonstrates the higher accuracy of our approach, as well as an easier workflow due to the absence of surface meshing or Digital Elevation Model (DEM) generation. Application of the method in a rapidly eroding, meandering bedrock river (Rangitikei River canyon) illustrates its ability to handle 3D differences in complex situations (flat and vertical surfaces on the same scene), to reduce uncertainty related to point cloud roughness by local averaging and to generate 3D maps of uncertainty levels. We also demonstrate that for high precision survey scanners, the total error budget on change detection is dominated by the point clouds registration error and the surface roughness. Combined with mm-range local georeferencing of the point clouds, levels of detection down to 6 mm (defined at 95% confidence) can be routinely attained in situ over ranges of 50 m. We provide evidence for the self-affine behaviour of different surfaces. We show how this impacts the calculation of normal vectors and demonstrate the scaling behaviour of the level of change detection. The algorithm has been implemented in a freely available open source software package. It operates in complex 3D cases and can also be used as a simpler and more robust alternative to DEM differencing for the 2D cases.

Visual saliency estimation by nonlinearly integrating features using region covariances.

Abstract: To detect visually salient elements of complex natural scenes, computational bottom-up saliency models commonly examine several feature channels such as color and orientation in parallel. They compute a separate feature map for each channel and then linearly combine these maps to produce a master saliency map. However, only a few studies have investigated how different feature dimensions contribute to the overall visual saliency. We address this integration issue and propose to use covariance matrices of simple image features (known as region covariance descriptors in the computer vision community; Tuzel, Porikli, & Meer, 2006) as meta-features for saliency estimation. As low-dimensional representations of image patches, region covariances capture local image structures better than standard linear filters, but more importantly, they naturally provide nonlinear integration of different features by modeling their correlations. We also show that first-order statistics of features could be easily incorporated to the proposed approach to improve the performance. Our experimental evaluation on several benchmark data sets demonstrate that the proposed approach outperforms the state-of-art models on various tasks including prediction of human eye fixations, salient object detection, and image-retargeting.

Global Fusion of Relative Motions for Robust, Accurate and Scalable Structure from Motion

Abstract: Multi-view structure from motion (SfM) estimates the position and orientation of pictures in a common 3D coordinate frame. When views are treated incrementally, this external calibration can be subject to drift, contrary to global methods that distribute residual errors evenly. We propose a new global calibration approach based on the fusion of relative motions between image pairs. We improve an existing method for robustly computing global rotations. We present an efficient a contrario trifocal tensor estimation method, from which stable and precise translation directions can be extracted. We also define an efficient translation registration method that recovers accurate camera positions. These components are combined into an original SfM pipeline. Our experiments show that, on most datasets, it outperforms in accuracy other existing incremental and global pipelines. It also achieves strikingly good running times: it is about 20 times faster than the other global method we could compare to, and as fast as the best incremental method. More importantly, it features better scalability properties.

Joint 3D Scene Reconstruction and Class Segmentation

Abstract: Both image segmentation and dense 3D modeling from images represent an intrinsically ill-posed problem. Strong regularizers are therefore required to constrain the solutions from being 'too noisy'. Unfortunately, these priors generally yield overly smooth reconstructions and/or segmentations in certain regions whereas they fail in other areas to constrain the solution sufficiently. In this paper we argue that image segmentation and dense 3D reconstruction contribute valuable information to each other's task. As a consequence, we propose a rigorous mathematical framework to formulate and solve a joint segmentation and dense reconstruction problem. Image segmentations provide geometric cues about which surface orientations are more likely to appear at a certain location in space whereas a dense 3D reconstruction yields a suitable regularization for the segmentation problem by lifting the labeling from 2D images to 3D space. We show how appearance-based cues and 3D surface orientation priors can be learned from training data and subsequently used for class-specific regularization. Experimental results on several real data sets highlight the advantages of our joint formulation.

A Generalized Laplacian of Gaussian Filter for Blob Detection and Its Applications

Abstract: In this paper, we propose a generalized Laplacian of Gaussian (LoG) (gLoG) filter for detecting general elliptical blob structures in images. The gLoG filter can not only accurately locate the blob centers but also estimate the scales, shapes, and orientations of the detected blobs. These functions can be realized by generalizing the common 3-D LoG scale-space blob detector to a 5-D gLoG scale-space one, where the five parameters are image-domain coordinates (x, y), scales (σx, σy), and orientation (θ), respectively. Instead of searching the local extrema of the image's 5-D gLoG scale space for locating blobs, a more feasible solution is given by locating the local maxima of an intermediate map, which is obtained by aggregating the log-scale-normalized convolution responses of each individual gLoG filter. The proposed gLoG-based blob detector is applied to both biomedical images and natural ones such as general road-scene images. For the biomedical applications on pathological and fluorescent microscopic images, the gLoG blob detector can accurately detect the centers and estimate the sizes and orientations of cell nuclei. These centers are utilized as markers for a watershed-based touching-cell splitting method to split touching nuclei and counting cells in segmentation-free images. For the application on road images, the proposed detector can produce promising estimation of texture orientations, achieving an accurate texture-based road vanishing point detection method. The implementation of our method is quite straightforward due to a very small number of tunable parameters.

Effects of image reconstruction on fiber orientation mapping from multichannel diffusion MRI: reducing the noise floor using SENSE.

Abstract: Purpose: To examine the effects of the reconstruction algorithm of magnitude images from multi-channel diffusion MRI on fibre orientation estimation. Theory and Methods: It is well established that the method used to combine signals from different coil elements in multi-channel MRI can have an impact on the properties of the reconstructed magnitude image. Utilising a root-sum-of-squares (RSoS) approach results in a magnitude signal that follows an effective non-central-distribution. As a result, the noise floor, the minimum measurable in the absence of any true signal, is elevated. This is particularly relevant for diffusion-weighted MRI, where the signal attenuation is of interest. Results: In this study, we illustrate problems that such image reconstruction characteristics may cause in the estimation of fibre orientations, both for model-based and model-free approaches, when modern 32-channel coils are employed. We further propose an alternative image reconstruction method that is based on sensitivity encoding (SENSE) and preserves the Rician nature of the single-channel, magnitude MR signal. We show that for the same k-space data, RSoS can cause excessive overfitting and reduced precision in orientation estimation compared to the SENSE-based approach. Conclusion: These results highlight the importance of choosing the appropriate image reconstruction method for tractography studies that use multi-channel receiver coils for diffusion MRI acquisition.

Automatic camera calibration in close-range photogrammetry

Abstract: Automatic camera calibration via self-calibration with the aid of coded targets is now very much the norm in closerange photogrammetry. This is irrespective of whether the cameras to be calibrated are high-end metric, or the digital SLRs and consumer-grade models that are increasingly being employed for image-based 3D measurement. Automation has greatly simplified the calibration task, but there are real prospects that important camera calibration issues may be overlooked in what has become an almost black-box operation. This paper discusses the impact of a number of such issues, some of which relate to the functional model adopted for self-calibration, and others to practical aspects which need to be taken into account when pursuing optimal calibration accuracy and integrity. Issues discussed include interior orientation stability, calibration reliability, focal plane distortion, image point distribution, variation in lens distortion with image scale, colour imagery and chromatic aberration, and whether 3D object space control is warranted. By appreciating and accounting for these issues, users of automatic camera calibration will enhance the prospect of achieving an optimal recovery of scene-independent camera calibration parameters.

Airborne Vehicle Detection in Dense Urban Areas Using HoG Features and Disparity Maps

Abstract: Vehicle detection has been an important research field for years as there are a lot of valuable applications, ranging from support of traffic planners to real-time traffic management. Especially detection of cars in dense urban areas is of interest due to the high traffic volume and the limited space. In city areas many car-like objects (e.g., dormers) appear which might lead to confusion. Additionally, the inaccuracy of road databases supporting the extraction process has to be handled in a proper way. This paper describes an integrated real-time processing chain which utilizes multiple occurrence of objects in images. At least two subsequent images, data of exterior orientation, a global DEM, and a road database are used as input data. The segments of the road database are projected in the non-geocoded image using the corresponding height information from the global DEM. From amply masked road areas in both images a disparity map is calculated. This map is used to exclude elevated objects above a certain height (e.g., buildings and vegetation). Additionally, homogeneous areas are excluded by a fast region growing algorithm. Remaining parts of one input image are classified based on the `Histogram of oriented Gradients (HoG)' features. The implemented approach has been verified using image sections from two different flights and manually extracted ground truth data from the inner city of Munich. The evaluation shows a quality of up to 70 percent.

Automated non-rigid registration and mosaicing for robust imaging of distinct retinal capillary beds using speckle variance optical coherence tomography

Abstract: Variance processing methods in Fourier domain optical coherence tomography (FD-OCT) have enabled depth-resolved visualization of the capillary beds in the retina due to the development of imaging systems capable of acquiring A-scan data in the 100 kHz regime. However, acquisition of volumetric variance data sets still requires several seconds of acquisition time, even with high speed systems. Movement of the subject during this time span is sufficient to corrupt visualization of the vasculature. We demonstrate a method to eliminate motion artifacts in speckle variance FD-OCT images of the retinal vasculature by creating a composite image from multiple volumes of data acquired sequentially. Slight changes in the orientation of the subject’s eye relative to the optical system between acquired volumes may result in non-rigid warping of the image. Thus, we use a B-spline based free form deformation method to automatically register variance images from multiple volumes to obtain a motion-free composite image of the retinal vessels. We extend this technique to automatically mosaic individual vascular images into a widefield image of the retinal vasculature.

Adaptive reconstruction method for three-dimensional orientation imaging

Abstract: An adaptive orientation reconstruction algorithm is developed for near-field high-energy X-ray diffraction microscopy. When combined with a spatially adaptive extension the algorithm results in a factor of 10–1000 speed-up over the existing forward modeling reconstruction method while preserving most of the spatial and orientation resolution characteristics. Tests of the reconstruction code based on simulated structures and real data on a complex microstructure are presented. Simulated structures include intra-granular orientation gradients and noisy detector images. It is shown that resolution in both real space and orientation space degrades gracefully as complexity and detector noise increase.

Method of Improving Orientation and Color Balance of Digital Images Using Face Detection Information

Abstract: A method of generating one or more new spatial and chromatic variation digital images uses an original digitally-acquired image which including a face or portions of a face. A group of pixels that correspond to a face within the original digitally-acquired image is identified. A portion of the original image is selected to include the group of pixels. Values of pixels of one or more new images based on the selected portion are automatically generated, or an option to generate them is provided, in a manner which always includes the face within the one or more new images. Such method may be implemented to automatically establish the correct orientation and color balance of an image. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.

Registration between actual mobile device position and environmental model

Abstract: A user interface enables a user to calibrate the position of a three dimensional model with a real-world environment represented by that model. Using a device's sensor, the device's location and orientation is determined. A video image of the device's environment is displayed on the device's display. The device overlays a representation of an object from a virtual reality model on the video image. The position of the overlaid representation is determined based on the device's location and orientation. In response to user input, the device adjusts a position of the overlaid representation relative to the video image.

A comparison of dense matching algorithms for scaled surface reconstruction using stereo camera rigs

Abstract: Photogrammetric methods for dense 3D surface reconstruction are increasingly available to both professional and amateur users who have requirements that span a wide variety of applications. One of the key concerns in choosing an appropriate method is to understand the achievable accuracy and how choices made within the workflow can alter that outcome. In this paper we consider accuracy in two components: the ability to generate a correctly scaled 3D model; and the ability to automatically deliver a high quality data set that provides good agreement to a reference surface. The determination of scale information is particularly important, since a network of images usually only provides angle measurements and thus leads to unscaled geometry. A solution is the introduction of known distances in object space, such as base lines between camera stations or distances between control points. In order to avoid using known object distances, the method presented in this paper exploits a calibrated stereo camera utilizing the calibrated base line information from the camera pair as an observational based geometric constraint. The method provides distance information throughout the object volume by orbiting the object. In order to test the performance of this approach, four topical surface matching methods have been investigated to determine their ability to produce accurate, dense point clouds. The methods include two versions of Semi-Global Matching as well as MicMac and Patch-based Multi-View Stereo (PMVS). These methods are implemented on a set of stereo images captured from four carefully selected objects by using (1) an off-the-shelf low cost 3D camera and (2) a pair of Nikon D700 DSLR cameras rigidly mounted in close proximity to each other. Inter-comparisons demonstrate the subtle differences between each of these permutations. The point clouds are also compared to a dataset obtained with a Nikon MMD laser scanner. Finally, the established process of achieving accurate point clouds from images and known object space distances are compared with the presented strategies. Results from the matching demonstrate that if a good imaging network is provided, using a stereo camera and bundle adjustment with geometric constraints can effectively resolve the scale. Among the strategies for dense 3D reconstruction, using the presented method for solving the scale problem and PMVS on the images captured with two DSLR cameras resulted in a dense point cloud as accurate as the Nikon laser scanner dataset.

Federated mobile device positioning

Abstract: A user interface enables a user to calibrate the position of a three dimensional model with a real-world environment represented by that model. Using a device's sensor suite, the device's location and orientation is determined. A video image of the device's environment is displayed on the device's display. The device overlays a representation of an object from a virtual reality model on the video image. The position of the overlaid representation is determined based on the device's location and orientation. In response to user input, the device adjusts a position of the overlaid representation relative to the video image.

Image Analysis in Earth Sciences: Microstructures and Textures of Earth Materials

Abstract: Part I Looking at Images.- 1 Images and Microstructures.- 2 Acquiring Images.- 3 Digital Image Processing.- 4 Pre-processing.- Part II Segmentation: Finding and Defining the Object.- 5 Segmentation by Point Operations.- 6 Post-processing.- 7 Segmentation by Neighborhood Operations.- 8 Image Analysis.- 9 Test Images.- Part III Measuring Size and Volume.- 10 Volume Determinations.- 11 2-D Grain Size Distributions.- 12 3-D Grain Size.- 13 Fractal Grain Size Distributions.- Part IV Quantifying Shape and Orientation.- 14 Particle Fabrics.- 15 Surface Fabrics.- 16 Strain Fabrics.- 17 Shape Descriptors.- Part V Spatial Relationships.- 18 Spatial Distributions.- 19 Spatial Frequencies.- 20 Autocorrelation Function.- Part VI Orientation Imaging.- 21 Crystal Orientation and Interference Color.- 22 Computer-Integrated Polarization Microscopy.- 23 Orientation and Misorientation Imaging.- Index.

Methods, Devices, Systems, Circuits and Associated Computer Executable Code for Detecting and Predicting the Position, Orientation and Trajectory of Surgical Tools

Abstract: The present invention includes methods, devices, systems, circuits and associated computer executable code for detecting and predicting the position and trajectory of surgical tools. According to some embodiments of the present invention, images of a surgical tool within or in proximity to a patient may be captured by a radiographic imaging system. The images may be processed by associated processing circuitry to determine and predict position, orientation and trajectory of the tool based on 3D models of the tool, geometric calculations and mathematical models describing the movement and deformation of surgical tools within a patient body.

Navigation system including optical and non-optical sensors

Abstract: Systems and methods that utilize optical sensors and non-optical sensors to determine the position and/or orientation of objects. A navigation system includes an optical sensor for receiving optical signals from markers and a non-optical sensor, such as a gyroscope, for generating non-optical data. A navigation computer determines positions and/or orientations of objects based on optical and non-optical data.

Monocular Image 3D Human Pose Estimation under Self-Occlusion

Abstract: In this paper, an automatic approach for 3D pose reconstruction from a single image is proposed. The presence of human body articulation, hallucinated parts and cluttered background leads to ambiguity during the pose inference, which makes the problem non-trivial. Researchers have explored various methods based on motion and shading in order to reduce the ambiguity and reconstruct the 3D pose. The key idea of our algorithm is to impose both kinematic and orientation constraints. The former is imposed by projecting a 3D model onto the input image and pruning the parts, which are incompatible with the anthropomorphism. The latter is applied by creating synthetic views via regressing the input view to multiple oriented views. After applying the constraints, the 3D model is projected onto the initial and synthetic views, which further reduces the ambiguity. Finally, we borrow the direction of the unambiguous parts from the synthetic views to the initial one, which results in the 3D pose. Quantitative experiments are performed on the Human Eva-I dataset and qualitatively on unconstrained images from the Image Parse dataset. The results show the robustness of the proposed approach to accurately reconstruct the 3D pose form a single image.

Exploring Patterns of Gradient Orientations and Magnitudes for Face Recognition

Abstract: A novel direction for efficiently describing face images is proposed by exploring the relationships between both gradient orientations and magnitudes of different local image structures. Presented in this paper are not only a novel feature set called patterns of orientation difference (POD) but also several improvements to our previous algorithm called patterns of oriented edge magnitudes (POEM). The whitened principal component analysis (PCA) dimensionality reduction technique is applied upon both the POEM- and POD-based representations to get more compact and discriminative face descriptors. We then show that the two methods have complementary strength and that by combining the two algorithms, one obtains stronger results than either of them considered separately. By experiments carried out on several common benchmarks, including the FERET database with both frontal and nonfrontal images as well as the very challenging LFW data set, we prove that our approach is more efficient than contemporary ones in terms of both higher performance and lower complexity.

Vehicle self-localization with high-precision digital maps

Abstract: Cooperative driver assistance functions benefit from sharing information on the local environments of individual road users by means of communication technology and advanced sensor data fusion methods. However, the consistent integration of environment models as well as the subsequent interpretation of traffic situations impose high requirements on the self-localization accuracy of vehicles. This paper presents methods and models for a map-based vehicle self-localization approach. Basically, information from the vehicular environment perception (using a monocular camera and laser scanner) is associated with data of a high-precision digital map in order to deduce the vehicle's position. Within the Monte-Carlo localization approach, the association of road markings is reduced to a prototype fitting problem which can be solved efficiently due to a map model based on smooth arc splines. Experiments on a rural road show that the localization approach reaches a global positioning accuracy in both lateral and longitudinal direction significantly below one meter and an orientation accuracy below one degree even at a speed up to 100 km/h in real-time.

3D Scene Reconstruction from Multiple Spherical Stereo Pairs

Abstract: We propose a 3D environment modelling method using multiple pairs of high-resolution spherical images. Spherical images of a scene are captured using a rotating line scan camera. Reconstruction is based on stereo image pairs with a vertical displacement between camera views. A 3D mesh model for each pair of spherical images is reconstructed by stereo matching. For accurate surface reconstruction, we propose a PDE-based disparity estimation method which produces continuous depth fields with sharp depth discontinuities even in occluded and highly textured regions. A full environment model is constructed by fusion of partial reconstruction from spherical stereo pairs at multiple widely spaced locations. To avoid camera calibration steps for all camera locations, we calculate 3D rigid transforms between capture points using feature matching and register all meshes into a unified coordinate system. Finally a complete 3D model of the environment is generated by selecting the most reliable observations among overlapped surface measurements considering surface visibility, orientation and distance from the camera. We analyse the characteristics and behaviour of errors for spherical stereo imaging. Performance of the proposed algorithm is evaluated against ground-truth from the Middlebury stereo test bed and LIDAR scans. Results are also compared with conventional structure-from-motion algorithms. The final composite model is rendered from a wide range of viewpoints with high quality textures.

Accurate Estimation of Human Body Orientation From RGB-D Sensors

Abstract: Accurate estimation of human body orientation can significantly enhance the analysis of human behavior, which is a fundamental task in the field of computer vision. However, existing orientation estimation methods cannot handle the various body poses and appearances. In this paper, we propose an innovative RGB-D-based orientation estimation method to address these challenges. By utilizing the RGB-D information, which can be real time acquired by RGB-D sensors, our method is robust to cluttered environment, illumination change and partial occlusions. Specifically, efficient static and motion cue extraction methods are proposed based on the RGB-D superpixels to reduce the noise of depth data. Since it is hard to discriminate all the 360 ° orientation using static cues or motion cues independently, we propose to utilize a dynamic Bayesian network system (DBNS) to effectively employ the complementary nature of both static and motion cues. In order to verify our proposed method, we build a RGB-D-based human body orientation dataset that covers a wide diversity of poses and appearances. Our intensive experimental evaluations on this dataset demonstrate the effectiveness and efficiency of the proposed method.

An evaluation on different number of ground control points in unmanned aerial vehicle photogrammetric block

Abstract: . This paper presents a novel method of unmanned aerial vehicle image processing using photogrammetric technique. The study area consist different slope class which involves undulating area around the Skudai area, Malaysia. All photogrammetric methods were applied in this study including selection of test area, flight planning, camera calibration and image processing orientation. A new ground control point configurations is introduced in this study as a generic approach in unmanned aerial vehicle photogrammetric block. These configurations are used to determine the best photogrammetric results based on number of ground control points in the photogrammetric block during image processing. The objective of this study is to determine the best configuration for photogrammetric block in order to produce the best photogrammetric products. Photogrammetric image processing involves two main orientations which are known as interior orientation and exterior orientation. Interior orientation involves the parameters of camera in order to calibrate the image in the same position as during the image acquisition. Exterior orientation involves the measurement of tie points to tie up all images in the strips until photogrammetric block. In this study, six ground control point configurations were tested to determine the best photogrammetric results. In this study, two main photogrammetric results were produced namely digital orthophoto and digital elevation model. The verification results show that all configurations recorded coefficient percentage of more than 97% accuracy for the six configurations. The validation results conclude that ground control point plays an important role in photogrammetric block to acquire the accurate photogrammetric results. In this study eight and nine ground control point configurations are the best configurations among the others. Qualitatively, vector plot error for easting and northing coordinates can be viewed graphically to distinguish the error and direction for all configurations which has been proposed in this study.

User-guided object identification

Abstract: A user attempting to obtain information about an object can capture image information including a view of that object, and the image information can be used with a matching or identification process to provide information about that type of object to the user. In order to narrow the search space to a specific category, and thus improve the accuracy of the results and the speed at which results can be obtained, the user can be guided to capture image information with an appropriate orientation. An outline or other graphical guide can be displayed over image information captured by a computing device, in order to guide the user in capturing the object from an appropriate direction and with an appropriate scale for the type of matching and/or information used for the matching. Such an approach enables three-dimensional objects to be analyzed using conventional two-dimensional identification algorithms, among other such processes.