Determining reflectance properties of an object using range andbrightness images

The authors discuss a method of recovering reflectance properties of a surface from a range image given by a range finder and a brightness image given by a standard TV camera. The Torrance-Sparrow model is used for the reflectance model. The model consists of the Lambertian and specular components: its reflectance properties consist of the relative strength between the Lambertian and specular components and specular sharpness as well as light source direction. An iterative least square fitting method is used to obtain these parameters based on the range and brightness images. An input image is segmented into four different parts using the parameters: Lambertian reflection, specular reflection, interreflection, and shadow part. The authors also reconstruct ideal images that consist of only Lambertian or specular reflection     

Determination of three-dimensional object location and orientationfrom range images

A technique for determining the distortion parameters (location and orientation) of general three-dimensional objects from a single range image view is introduced. The technique is based on an extension of the straight-line Hough transform to three-dimensional space. It is very efficient and robust, since the dimensionality of the feature space is low and since it uses range images directly (with no preprocessing such as segmentation and edge or gradient detection). Because the feature space separates the translation and rotation effects, a hierarchical algorithm to detect object rotation and translation is possible. The new Hough space can also be used as a feature space for discriminating among three-dimensional objects     

Three-dimensional object recognition using laser range sensor

Image information provided by cameras is strongly affected by environmental influence of an object’s circumjacent and circumference. In order to reduce environmental influence, a system which was integrated distance information provided from a laser range sensor (LRS) and image information provided by a camera was developed, and consisted of an object extraction section and a recognition processing section. In this paper the effectiveness of the system was inspected by performing an object extraction experiment using the combined integrated distance information and image information. From these results, this system could remove a background and a floor surface by using the distance information, and simpler object extraction was enabled. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Optimal registration of object views using range data

This paper deals with robust registration of object views in the presence of uncertainties and noise in depth data. Errors in registration of multiple views of a 3D object severely affect view integration during automatic construction of object models. We derive a minimum variance estimator (MVE) for computing the view transformation parameters accurately from range data of two views of a 3D object. The results of our experiments show that view transformation estimates obtained using MVE are significantly more accurate than those computed with an unweighted error criterion for registration     

Fast and automatic object pose estimation for range images on the GPU

We present a pose estimation method for rigid objects from single range images. Using 3D models of the objects, many pose hypotheses are compared in a data-parallel version of the downhill simplex algorithm with an image-based error function. The pose hypothesis with the lowest error value yields the pose estimation (location and orientation), which is refined using ICP. The algorithm is designed especially for implementation on the GPU. It is completely automatic, fast, robust to occlusion and cluttered scenes, and scales with the number of different object types. We apply the system to bin picking, and evaluate it on cluttered scenes. Comprehensive experiments on challenging synthetic and real-world data demonstrate the effectiveness of our method.     

Efficient data structures for model-based 3-D object recognitionand localization from range images

An effective method of surface characterization of 3D objects using surface curvature properties and an efficient approach to recognizing and localizing multiple 3D free-form objects (free-form object recognition and localization) are presented. The approach is surface based and is therefore not sensitive to noise and occlusion, forms hypothesis by local analysis of surface shapes, does not depend on the visibility of complete objects, and uses information from a CAD database in recognition and localization. A knowledge representation scheme for describing free-form surfaces is described. The data structure and procedures are well designed, so that the knowledge leads the system to intelligent behavior. Knowledge about surface shapes is abstracted from CAD models to direct the search in verification of vision hypotheses. The knowledge representation used eases processes of knowledge acquisition, information retrieval, modification of knowledge base, and reasoning for solution     

Accurate integration of multi-view range images using k-means clustering

3D modelling finds a wide range of applications in industry. However, due to the presence of surface scanning noise, accumulative registration errors, and improper data fusion, reconstructed object surfaces using range images captured from multiple viewpoints are often distorted with thick patches, false connections, blurred features and artefacts. Moreover, the existing integration methods are often expensive in the sense of both computational time and data storage. These shortcomings limit the wide applications of 3D modelling using the latest laser scanning systems. In this paper, the k-means clustering approach (from the pattern recognition and machine learning literatures) is employed to minimize the integration error and to optimize the fused point locations. To initialize the clustering approach, an automatic method is developed, shifting points in the overlapping areas between neighbouring views towards each other, so that the initialized cluster centroids are in between the two overlapping surfaces. This results in more efficient and effective integration of data. While the overlapping areas were initially detected using a single distance threshold, they are then refined using the k-means clustering method. For more accurate integration results, a weighting scheme reflecting the imaging principle is developed to integrate the corresponding points in the overlapping areas. The fused point set is finally triangulated using an improved Delaunay method, guaranteeing a watertight surface. A comparative study based on real images shows that the proposed algorithm is efficient in the sense of either running time or memory usage and reduces significantly the integration error, while desirably retaining geometric details of 3D object surfaces of interest.     

Understanding the curve-polygon object

In this paper the new method of understanding of the curve-polygon object is presented. The method of understanding of the curve-polygon object is part of the research aimed at developing a shape understanding method able to perform complex visual tasks connected with visual thinking. The shape understanding method is implemented as the shape understanding system (SUS). Understanding includes, among others, obtaining the visual concept in process of the visual reasoning, naming and visual explanation by generation an object from a required class. In this paper generation of the object from the selected well defined class, the curve-polygon class, as well as assigning the visual object into one of the shape classes is presented. The generation of the visual objects is used in SUS during learning of the visual concept, explanatory process and self-correcting process. The visual object is assigned into one of the shape classes during the visual reasoning process. The visual reasoning, presented in this paper, in contrast to other forms of reasoning depends on the type of objects which are analysed. In this paper visual reasoning that assigns an object to the curve-polygon class is presented. The shape understanding system consists of different types of experts that perform different processing and reasoning tasks. The self-correcting expert, that implements the new method of testing and reasoning, is invoked to test ability of the system to understand the concept of the curve-polygon shape.     

Shape-based object extraction in high-resolution remote-sensing images using deep Boltzmann machine

In this article, we proposed a novel method based on deep learning shape priors for object extraction in high-resolution (HR) remote-sensing images. Specifically, the deep Boltzmann machines (DBMs) are applied to model the shape priors via the unsupervised training process, which qualify for the advantages of deep learning method, especially the powerful feature learning and modelling ability. The deep shape model is integrated into a new energy function to eliminate the influence of disturbing background. The energy function combines image appearance information and region information. A new region term in the function is proposed to eliminate the influence of object shadow. The process of object extraction is achieved by minimizing the energy function with an iterative optimization algorithm and the Split Bregman method is applied to derive a global solution during the minimization process. Quantitative and qualitative experiments are conducted on the aircraft data set acquired by QuickBird with 60 cm resolution and the results demonstrate the effectiveness of the proposed method.     

Reversible data hiding for high dynamic range images using edge information

Multimedia Tools and Applications - In this work, a reversible data hiding (RDH) algorithm is proposed for high dynamic range (HDR) images containing an additional luminance channel. Since...     

A block-oriented restoration in gray-scale images using full range autoregressive model

This paper introduces a novel approach, i.e. block oriented-restoration, based on a Family of Full Range Autoregressive (FRAR) model to restore the information lost, and this adopts the Bayesian approach to estimate the parameters of the model. The Bayesian approach, by combining the prior information and the observed data known as posterior distribution, makes inferences. The loss of information caused is due to errors in communication channels, through which the data are transmitted. In most applications, the data are transmitted block wise. Even if there is loss of a single bit in a block, it causes loss in the whole block and the impact may reflect on its consecutive blocks. In the proposed technique, such damaged blocks are identified, and to restore it, a priori information is searched and extracted from uncorrupted regions of the image; this information and the pixels in the neighboring region of the damaged block are utilized to estimate the parameters of the model. The estimated parameters are employed to restore the damaged block. The proposed algorithm takes advantage of linear dependency of the neighboring pixels of the damaged block and takes them as source to predict the pixels of the damaged block. The restoration is performed at two stages: first, the lone blocks are restored; second, the contiguous blocks are restored. It produces very good results and is comparable with other existing schemes.     

Hybrid object labelling in digital images

The application of a technique for labelling connected components based on the classical recursive technique is studied. The recursive approach permits labelling, counting, and characterizing objects with a single pass. Its main drawback lies on its very nature: Big objects require a high number of recursive calls, which require a large stack to store local variables and register values. Thus, the risk of stack overflow imposes an impractical limit on image size. The hybrid alternative combines recursion with iterative scanning and can be directly substituted into any program already using the recursive technique. I show how this alternative drastically reduces the number of consecutive recursive calls, and thus the required stack size, while improving overall performance. The method is tested on sets of uniform random binary images and binary images with a random distribution of overlapping square blocks. These test sets provide insight on the adequacy of the algorithm for different applications. The performance of the proposed technique is compared with the classical recursive technique and with an iterative two-pass algorithm using the Union-Find data structure, and the results show an overall increase of speed. The performance of the algorithm in real world machine vision applications is also shown.     

Accurate object recognition in the underwater images using learning algorithms and texture features

Underwater image processing is very challenging due to its environmental conditions and poor sunlight. Images captured from the ocean using autonomous vehicles are often non-uniformly illuminated and contain noise due to the underlying environment. Object recognition is a challenging task under water due to the variation in the environment, target shape and orientation. Traditional algorithms based on spatial information may not lead to accurate segmentation as the intensity variation is often less in underwater images. Texture information representing the characteristics of the object is needed. Statistical features like autocorrelation, sum average, sum variance and sum entropy were extracted. These were fed as input to learning algorithms and training was done to effectively classify the object of interest and background. Chain coding was further applied for object recognition. The proposed methodology achieved a maximum classification accuracy of 96%.     

Edge-region-based segmentation of range images

In this correspondence, we present a new computationally efficient three-dimensional (3-D) object segmentation technique. The technique is based on the detection of edges in the image. The edges can be classified as belonging to one of the three categories: fold edges, semistep edges (defined here), and secondary edges. The 3-D image is sliced to create equidepth contours (EDCs). Three types of critical points are extracted from the EDCs. A subset of the edge pixels is extracted first using these critical points. The edges are grown from these pixels through the application of some masks proposed in this correspondence. The constraints of the masks can be adjusted depending on the noise present in the image. The total computational effort is small since the masks are applied only over a small neighborhood of critical points (edge regions). Furthermore, the algorithm can be implemented in parallel, as edge growing from different regions can be carried out independently of each other     

Discovering hierarchical object models from captioned images

We address the problem of automatically learning the recurring associations between the visual structures in images and the words in their associated captions, yielding a set of named object models that can be used for subsequent image annotation. In previous work, we used language to drive the perceptual grouping of local features into configurations that capture small parts (patches) of an object. However, model scope was poor, leading to poor object localization during detection (annotation), and ambiguity was high when part detections were weak. We extend and significantly revise our previous framework by using language to drive the perceptual grouping of parts, each a configuration in the previous framework, into hierarchical configurations that offer greater spatial extent and flexibility. The resulting hierarchical multipart models remain scale, translation and rotation invariant, but are more reliable detectors and provide better localization. Moreover, unlike typical frameworks for learning object models, our approach requires no bounding boxes around the objects to be learned, can handle heavily cluttered training scenes, and is robust in the face of noisy captions, i.e., where objects in an image may not be named in the caption, and objects named in the caption may not appear in the image. We demonstrate improved precision and recall in annotation over the non-hierarchical technique and also show extended spatial coverage of detected objects.     

Estimation-detection of object boundaries in noisy images

Estimation of boundaries of objects in noisy images is considered when the objects and the background are statistically characterized. The noise is assumed white, additive, and Gaussian. Optimal recursive estimators in a joint estimation-detection context are derived. Applications to binary pictures are illustrated.     

Example-based object detection in images by components

We present a general example-based framework for detecting objects in static images by components. The technique is demonstrated by developing a system that locates people in cluttered scenes. The system is structured with four distinct example-based detectors that are trained to separately find the four components of the human body: the head, legs, left arm, and right arm. After ensuring that these components are present in the proper geometric configuration, a second example-based classifier combines the results of the component detectors to classify a pattern as either a “person” or a “nonperson.” We call this type of hierarchical architecture, in which learning occurs at multiple stages, an adaptive combination of classifiers (ACC). We present results that show that this system performs significantly better than a similar full-body person detector. This suggests that the improvement in performance is due to the component-based approach and the ACC data classification architecture. The algorithm is also more robust than the full-body person detection method in that it is capable of locating partially occluded views of people and people whose body parts have little contrast with the background