This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep learning-based methods either fail to separate object instances, or fail to detect objects that were not seen during training. SceneCut automatically decomposes a scene into meaningful regions which either represent objects or scene surfaces. The decomposition is qualified by an unified energy function over objectness and geometric fitting. We show how this energy function can be optimized efficiently by utilizing hierarchical segmentation trees. Moreover, we leverage a pre-trained convolutional oriented boundary network to predict accurate boundaries from images, which are used to construct high-quality region hierarchies. We evaluate SceneCut on several different indoor environments, and the results show that SceneCut significantly outperforms all the existing methods.

For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic mapping. In this paper we address the problem of building environmental maps that include both semantically meaningful, object-level entities and point- or mesh-based geometrical representations. We simultaneously build geometric point cloud models of previously unseen instances of known object classes and create a map that contains these object models as central entities. Our system leverages sparse, feature-based RGB-D SLAM, image-based deep-learning object detection and 3D unsupervised segmentation.

We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly encode object qualities and spatial interactions. But the corresponding optimisation problem is typically difficult or intractable, and many of the best current methods rely on Monte Carlo Markov Chain (MCMC) simulation, which converges slowly in a large solution space. We propose an efficient point process inference for largescale object detection using discrete energy minimization. In particular, we approximate the solution space by a finite set of object proposals and cast the point process density function to a corresponding energy function of binary variables whose values indicate which object proposals are accepted. We resort to the local submodular approximation (LSA) based trust-region optimisation to find the optimal solution. Furthermore we analyse the error of LSA approximation, and show how to adjust the point process energy to dramatically speed up the convergence without harming the optimality. We demonstrate the superior efficiency and accuracy of our method using a variety of large-scale object detection applications such as crowd human detection, birds, cells counting/localization.

Modern SLAM systems with a depth sensor are able to reliably reconstruct dense 3D geometric maps of indoor scenes. Representing these maps in terms of meaningful entities is a step towards building semantic maps for autonomous robots. One approach is to segment the 3D maps into semantic objects using Conditional Random Fields (CRF), which requires large 3D ground truth datasets to train the classification model. Additionally, the CRF inference is often computationally expensive. In this paper, we present an unsupervised geometric-based approach for the segmentation of 3D point clouds into objects and meaningful scene structures. We approximate an input point cloud by an adjacency graph over surface patches, whose edges are then classified as being either on or off. We devise an effective classifier which utilises both global planar surfaces and local surface convexities for edge classification. More importantly, we propose a novel global plane extraction algorithm for robustly discovering the underlying planes in the scene. Our algorithm is able to enforce the extracted planes to be mutually orthogonal or parallel which conforms usually with human-made indoor environments. We reconstruct 654 3D indoor scenes from NYUv2 sequences to validate the efficiency and effectiveness of our segmentation method.

Fuzzy logic has been used as a means of interpreting vague, incomplete and even contradictory information into a compromised rule base in artificial intelligence such as machine decision–making. Within this context, fuzzy logic can be applied in the field of expert systems to provide additional flexibilities in constructing a working rule base: different experts’ opinions can be incorporated into the same rule base, and each opinion can be modeled in a rather vague notion of human language. As some illustrative application examples, this paper describes how fuzzy logic can be used in expert systems. More precisely, it demonstrates the following applications: (i) a healthcare diagnostic system, (ii) an autofocus camera lens system and (iii) a financial decision system. For each application, basic rules are described, the calculation method is outlined and numerical simulation is provided. These applications demonstrate the suitability and performance of fuzzy logic in expert systems.

The authors present a constraint formulation that yields a real-numbered solution to the frequency-domain Prony algorithm. This is done by requiring that all the roots of the Z-transform of the solution be on the unit circle. They make appropriate transformations that map this unit circle onto a left half plane, which then allows them to use Sturn's theorem to check the number of roots in the left half plane. This newly formulated constraint is incorporated in the Prony method in the frequency domain. One of the applications of the method is in the decomposition of a mixture of delayed versions of a signal, where the constraints guarantee that the solution for the time delays are real.>

In this paper, we investigate in detail the properties of the maximum likelihood estimator of the generalized p-Gaussian (gpG) probability density function (pdf) from N independent identically distributed (iid) samples, especially in the context of the deconvolution problem under gpG white noise. In the first part, we describe the properties of the estimator independently of the application. In the second part, we obtain the solution of the above-mentioned deconvolution problem as the solution of a minimum norm problem in an lpnormed space. In the present paper, we show that such a minimum norm solution is the maximum likelihood estimate of the system function parameters and show that such an estimate is unbiased, with the lower bound of the variance of the error equal to the Cramer-Rao lower bound, and the upper bound derived from the concept of a generalized inverse, both of which we also give.