Occluded Object Recognition Research Articles

Distortion-tolerant 3D recognition of occluded objects using computational integral imaging

In a computational three-dimensional (3D) volumetric reconstruction integral imaging (II) system, volume pixels (voxels) of the scene are reconstructed plane by plane. Therefore, foreground occluding objects and background occluded objects can be reconstructed separately when there is enough spatial separation between the occluding object and the occluded object. Using volumetric computational II reconstruction, we are able to recognize distorted and occluded objects with correlation based recognition algorithms. We present experimental results which show recognition of 3D rotated and occluded targets in a reconstructed scene. We also show the ability of the proposed technique to recognize distorted and occluded 3D non-training targets.

Three-dimensional recognition of occluded objects by using computational integral imaging

We have proposed a method to recognize partially occluded three-dimensional (3D) objects by using 3D volumetric reconstruction integral imaging (II). An II system captures multiple perspectives of occluded objects by using a microlens array. The reconstruction of the occluded 3D scene and target recognition are done digitally to reduce the effects of the occlusion. To verify system performance, we have implemented an optimum filter for object recognition. Both two-dimensional (2D) images and 3D II volumetric reconstructed images are considered. The correlation results of occluded 3D images for volumetric reconstruction show substantial improvements compared with those for conventional 2D imaging of occluded images.

Homomorphic graph matching of articulated objects by an integrated recognition scheme

Abstract In the last few years, several attempts have been made to the study of object recognition under affine transformation, but all these studies have concentrated on graph isomorphism. There has not been any discussion of solving the graph homomorphism problem under affine transformation to date. Therefore, in this paper, an integrated approach, which combines the advantages of both the genetic algorithm and Hopfield neural network, is proposed for solving object recognition under this condition. The genetic algorithm is first used, to find the near-optimal solution including all the poses of the model in the scene. Then the Hopfield network is implemented and repeated to find each pose of the model. This method can solve occluded object recognition problems, and it can also obtain the homomorphic mapping indicating multiple occurrences of a model in the scene. The system is used to recognize articulated objects, and we do not need to know in advance that there is one in the scene. Kinematic properties like the position of the joint, relative displacement can be found for the articulated object. Through experiments, we can demonstrate that the proposed method is robust.

Pigeon's recognition of occluded objects: differential effect of training experience

Pigeon's recognition of occluded objects: differential effect of training experience

Stochastic models for recognition of occluded targets

Recognition of occluded objects in synthetic aperture radar (SAR) images is a significant problem for automatic target recognition. Stochastic models provide some attractive features for pattern matching and recognition under partial occlusion and noise. In this paper, we present a hidden Markov modeling based approach for recognizing objects in SAR images. We identify the peculiar characteristics of SAR sensors and using these characteristics we develop feature based multiple models for a given SAR image of an object. The models exploiting the relative geometry of feature locations or the amplitude of SAR radar return are based on sequentialization of scattering centers extracted from SAR images. In order to improve performance we integrate these models synergistically using their probabilistic estimates for recognition of a particular target at a specific azimuth. Experimental results are presented using both synthetic and real SAR images.

Effects of occlusion on pigeons' visual object recognition.

Casual observation suggests that pigeons and other animals can recognize occluded objects; yet laboratory research has thus far failed to show that pigeons can do so. In a series of experiments, we investigated pigeons' ability to 'name' shaded, textured stimuli by associating each with a different response. After first learning to recognize four unoccluded objects, pigeons had to recognize the objects when they were partially occluded by another surface or when they were placed on top of another surface; in each case, recognition was weak. Following training with the unoccluded stimuli and with the stimuli placed on top of the occluder, pigeons' recognition of occluded objects dramatically improved. Pigeons' improved recognition of occluded objects was not limited to the trained objects but transferred to novel objects as well. Evidently, the recognition of occluded objects requires pigeons to learn to discriminate the object from the occluder; once this discrimination is mastered, occluded objects can be better recognized.

Partially Occluded Object Recognition Using Statistical Models

In this paper, we present a new Bayesian framework for partially occluded object recognition based on matching extracted local features on a one-to-one basis with object features. We introduce two different statistical models for occlusion: one model assumes that each feature in the model can be occluded independent of whether any other features are occluded, whereas the second model uses spatially correlated occlusion to represent the extent of occlusion. Using these models, the object recognition problem reduces to finding the object hypothesis with largest generalized likelihood. We develop fast algorithms for finding the optimal one-to-one correspondence between scene features and object features to compute the generalized likelihoods under both models. We conduct experiments illustrating the differences between the two occlusion models using different quantitative metrics. We also evaluate the recognition performance of our algorithms using examples extracted from object silhouettes and synthetic aperture radar imagery, and illustrate the performance advantages of our approach over alternative algorithms.

RECOGNITION OF 2D STANDALONE AND OCCLUDED OBJECTS USING WAVELET TRANSFORM

A planar curve descriptor which is invariant to translation, size, rotation and starting point in tracing the boundary is developed based on the periodized wavelet transform. Coefficients obtained from the transform are divided into different bands, and feature vectors are extracted for the recognition of two-dimensional closed boundary curves. The weight vectors which include the width of different bands are also derived to differentiate spurious results arising from noisy samples. The technique is further extended for the recognition of occluded objects by incorporating local features into the features vector to form a feature map. Matching the likeliness of a part of the feature map with that of the reference feature maps indicates which class the occluded object belongs to. Experimental results were obtained to show the effectiveness of the proposed technique.

View-based object recognition using saliency maps

We introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and offers the locality of representation required for occluded object recognition. To compare two saliency map graphs, we introduce two graph similarity algorithms. The first computes the topological similarity between two SMGs, providing a coarse-level matching of two graphs. The second computes the geometrical similarity between two SMGs, providing a fine-level matching of two graphs. We test and compare these two algorithms on a large database of model object views.

Recognition of Partially Occluded Objects with Back-Propagation Neural Network

The problem of occlusion in a two-dimensional scene introduces errors into many existing vision algorithms that cannot be resolved. Occlusion occurs where two or more objects in a given image touch or overlap one another. Since occlusion will be present in all but the most constrained environment, the recognition of partially occluded objects is important for industrial machine vision applications to solve real problems in the military domain and in factory automation. A new method is proposed in this paper to identify and locate objects lying on a flat surface. The method is based on a local and compact description of the objects' boundaries and a new fast recognition method involving neural networks. The merit of such approach is that it provides strong robustness for partially occluded object recognition. The method is integrated into a vision system that couples with an industrial robot arm to provide automatic picking and repositioning of partially occluded industrial parts.

A spatiotemporal neural network for recognizing partially occluded objects

In this paper, a spatiotemporal neural network for partially occluded object recognition is presented. The system consists of two major components: a feature extraction process and a spatiotemporal modular neural network. The former is made up of a sequence of preprocessing techniques including thresholding, boundary extraction, Gaussian filtering, and a split-and-merge algorithm to generate features that will represent the objects to be recognized. These acquired features are invariant to rotation, translation, and scaling and can serve as input to the spatiotemporal network that utilizes the concept of tap delay to account for spatial correlation between consecutive input features. A shape perceiver is designed into the network to extract continued parts of an object as well as to enable the inclusion of each object's unique characteristics into the system. Traditional neural network approaches for recognizing partially occluded objects have encountered significant problems because of the incomplete boundaries of the objects. In our approach, by creatively installing tap delays, the system can escape this limitation. Experimental results show that the proposed system can produce satisfactory results in efficiently and effectively recognizing partially occluded objects. Furthermore, intrinsic to this system is the ease by which it can be realized through parallel implementation, thus minimizing the tremendous time spent in matching object contours stored in a model database, as is the case in conventional recognition systems.

Neuro-fuzzy reasoning for occluded object recognition

To tackle the problem of occluded object recognition first we give a new interpretation to the multidimensional fuzzy reasoning and then realize that new interpretation through backpropagation-type neural network. At the learning stage of the neural network, fuzzy linguistic statements are used. Once learned, the nonfuzzy features of an occluded object can be classified. At the time of classification of the nonfuzzy features of an occluded object we use the concept of fuzzy singleton. An effective approach to recognize an unknown scene which consists of a set of occluded objects is to detect a number of significant (local) features on the boundary of the unknown scene. Thus the major problems fall into the selection of the appropriate set of features (local) for representing the object in the training stage, as well as in the detection of these features in the recognition process. The features should be invariant to scale, orientation and minor distortions in boundary shape. The performance of the proposed scheme is tested through several examples.

Silhouette-based occluded object recognition through curvature scale space

A complete and practical system for occluded object recognition has been developed which is very robust with respect to noise and local deformations of shape (due to weak perspective distortion, segmentation errors and non-rigid material) as well as scale, position and orientation changes of the objects. The system has been tested on a wide variety of free-form 3D objects. An industrial application is envisaged where a fixed camera and a light-box are utilized to obtain images. Within the constraints of the system, every rigid 3D object can be modeled by a limited number of classes of 2D contours corresponding to the object's resting positions on the light-box. The contours in each class are related to each other by a 2D similarity transformation. The Curvature Scale Space technique [26, 28] is then used to obtain a novel multi-scale segmentation of the image and the model contours. Object indexing [16, 32, 36] is used to narrow down the search space. An efficient local matching algorithm is utilized to select the best matching models.

Deformable template recognition of multiple occluded objects

Based on deformable templates, the paper formulates an integrated and flexible Bayesian recognition system of multiple occluded objects. Various local dependence properties of the model are obtained to reduce the computational cost with the increase in the number of objects. Numerical results for a synthetic image and for a real image of mushrooms are discussed.

A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks

This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.

Local feature detector using 3-point matching and dynamic programming

A local feature detection scheme for the recognition of occluded objects is developed and reported in this paper. A 3-point matching algorithm is developed to reduce the local feature matching trial. An elastic matching technique using dynamic programming provides the capability of handling the non-linearly distorted features. Also, the proposed scheme is computationally efficient. A set of handtools is selected to evaluate the performance of the algorithm, and the results are encouraging.

Invariant and Occluded Object Recognition Based on Graph Matching

Invariant and occluded object recognition based on graph matching The paper describes an algorithm for object recognition using neural network. The objects may be occluded and may have any changes in position, orientation and scale. The paper aims to generate project ideas for the final year students at the university and also to provide a basis for further research.

Robust matching process: a dominant point approach

A robust local feature matching scheme for recognition of occluded objects is developed and reported in this letter. The proposed scheme is computation efficient and can handle the nonlinear distorted local features. A set of handtools is selected to evaluate the performance of the algorithm and the results are encouraging.

Edge replacement in the recognition of occluded objects

The Generalized Hough Transform recognizes objects more successfully when all edges are visible. To facilitate recognition, this paper introduces a preliminary Generalized Hough process that restores edges which were invisible because of occlusion or because of lack of contrast between occluding and occluded areas. Space and time complexity of Generalized Hough processes are reduced by chained hashing techniques. Experimental results show that recognition of occluded objects via a Generalized Hough Transform is improved if occluding objects are first recognized and subtracted out of the input picture, and occluded edges are then reconstructed prior to recognition of occluded objects.

Dominant point matching algorithm

A novel dominant point matching algorithm is designed and developed for occluded object recognition. The developed algorithm is capable of grouping all scattered dominant points on an object boundary, due to occlusion, into a single representation for recognition. A set of handtools is selected to evaluate the performance of the algorithm and the results are encouraging.