Extending visual perception with haptic exploration for improved scene understanding

Scene understanding has been investigated from a mainly visual information point of view. Recently depth has been provided an extra wealth of information, allowing more geometric knowledge to fuse into scene understanding. Yet to form a holistic view, especially in robotic applications, one can create even more data by interacting with the world. In fact humans, when growing up, seem to heavily investigate the world around them by haptic exploration. We show an application of haptic exploration on a humanoid robot in cooperation with a learning method for object segmentation. The actions performed consecutively improve the segmentation of objects in the scene.

Scene understanding for auto-calibration of surveillance cameras

In the last decade, several research results have presented formulations for the auto-calibration problem. Most of these have relied on the evaluation of vanishing points to extract the camera parameters. Normally vanishing points are evaluated using pedestrians or the Manhattan World assumption i.e. it is assumed that the scene is necessarily composed of orthogonal planar surfaces. In this work, we present a robust framework for auto-calibration, with improved results and generalisability for real-life situations. This framework is capable of handling problems such as occlusions and the presence of unexpected objects in the scene. In our tests, we compare our formulation with the state-of-the-art in auto-calibration using pedestrians and Manhattan World-based assumptions. This paper reports on the experiments conducted using publicly available datasets; the results have shown that our formulation represents an improvement over the state-of-the-art.

Deeper and wider fully convolutional network coupled with conditional random fields for scene labeling

Deep convolutional neural networks (DCNNs) have been employed in many computer vision tasks with great success due to their robustness in feature learning. One of the advantages of DCNNs is their representation robustness to object locations, which is useful for object recognition tasks. However, this also discards spatial information, which is useful when dealing with topological information of the image (e.g. scene labeling, face recognition). In this paper, we propose a deeper and wider network architecture to tackle the scene labeling task. The depth is achieved by incorporating predictions from multiple early layers of the DCNN. The width is achieved by combining multiple outputs of the network. We then further refine the parsing task by adopting graphical models (GMs) as a post-processing step to incorporate spatial and contextual information into the network. The new strategy for a deeper, wider convolutional network coupled with graphical models has shown promising results on the PASCAL-Context dataset.

High level methods for scene exploration

Virtual worlds exploration techniques are used in a wide variety of domains — from graph drawing to robot motion. This paper is dedicated to virtual world exploration techniques which have to help a human being to understand a 3D scene. An improved method of viewpoint quality estimation is presented in the paper, together with a new off-line method for automatic 3D scene exploration, based on a virtual camera. The automatic exploration method is working in two steps. In the first step, a set of “good” viewpoints is computed. The second step uses this set of points of view to compute a camera path around the scene. Finally, we define a notion of semantic distance between objects of the scene to improve the approach.

Bayesian scene analysis for multi-camera 3D tracking and camera positioning

Los sistemas de seguimiento mono-cámara han demostrado su notable capacidad para el análisis de trajectorias de objectos móviles y para monitorización de escenas de interés; sin embargo, tanto su robustez como sus posibilidades en cuanto a comprensión semántica de la escena están fuertemente limitadas por su naturaleza local y monocular, lo que los hace insuficientes para aplicaciones realistas de videovigilancia. El objetivo de esta tesis es la extensión de las posibilidades de los sistemas de seguimiento de objetos móviles para lograr un mayor grado de robustez y comprensión de la escena. La extensión propuesta se divide en dos direcciones separadas. La primera puede considerarse local, ya que está orientada a la mejora y enriquecimiento de las posiciones estimadas para los objetos móviles observados directamente por las cámaras del sistema; dicha extensión se logra mediante el desarrollo de un sistema multi-cámara de seguimiento 3D, capaz de proporcionar consistentemente las posiciones 3D de múltiples objetos a partir de las observaciones capturadas por un conjunto de sensores calibrados y con campos de visión solapados. La segunda extensión puede considerarse global, dado que su objetivo consiste en proporcionar un contexto global para relacionar las observaciones locales realizadas por una cámara con una escena de mucho mayor tamaño; para ello se propone un sistema automático de localización de cámaras basado en las trayectorias observadas de varios objetos móviles y en un mapa esquemático de la escena global monitorizada. Ambas líneas de investigación se tratan utilizando, como marco común, técnicas de estimación bayesiana: esta elección está justificada por la versatilidad y flexibilidad proporcionada por dicho marco estadístico, que permite la combinación natural de múltiples fuentes de información sobre los parámetros a estimar, así como un tratamiento riguroso de la incertidumbre asociada a las mismas mediante la inclusión de modelos de observación específicamente diseñados. Además, el marco seleccionado abre grandes posibilidades operacionales, puesto que permite la creación de diferentes métodos numéricos adaptados a las necesidades y características específicas de distintos problemas tratados. El sistema de seguimiento 3D con múltiples cámaras propuesto está específicamente diseñado para permitir descripciones esquemáticas de las medidas realizadas individualmente por cada una de las cámaras del sistema: esta elección de diseño, por tanto, no asume ningún algoritmo específico de detección o seguimiento 2D en ninguno de los sensores de la red, y hace que el sistema propuesto sea aplicable a redes reales de vigilancia con capacidades limitadas tanto en términos de procesamiento como de transmision. La combinación robusta de las observaciones capturadas individualmente por las cámaras, ruidosas, incompletas y probablemente contaminadas por falsas detecciones, se basa en un metodo de asociación bayesiana basado en geometría y color: los resultados de dicha asociación permiten el seguimiento 3D de los objetos de la escena mediante el uso de un filtro de partículas. El sistema de fusión de observaciones propuesto tiene, como principales características, una gran precisión en términos de localización 3D de objetos, y una destacable capacidad de recuperación tras eventuales errores debidos a un número insuficiente de datos de entrada. El sistema automático de localización de cámaras se basa en la observación de múltiples objetos móviles y un mapa esquemático de las áreas transitables del entorno monitorizado para inferir la posición absoluta de dicho sensor. Para este propósito, se propone un novedoso marco bayesiano que combina modelos dinámicos inducidos por el mapa en los objetos móviles presentes en la escena con las trayectorias observadas por la cámara, lo que representa un enfoque nunca utilizado en la literatura existente. El sistema de localización se divide en dos sub-tareas diferenciadas, debido a que cada una de estas tareas requiere del diseño de algoritmos específicos de muestreo para explotar en profundidad las características del marco desarrollado: por un lado, análisis de la ambigüedad del caso específicamente tratado y estimación aproximada de la localización de la cámara, y por otro, refinado de la localización de la cámara. El sistema completo, diseñado y probado para el caso específico de localización de cámaras en entornos de tráfico urbano, podría tener aplicación también en otros entornos y sensores de diferentes modalidades tras ciertas adaptaciones. ABSTRACT Mono-camera tracking systems have proved their capabilities for moving object trajectory analysis and scene monitoring, but their robustness and semantic possibilities are strongly limited by their local and monocular nature and are often insufficient for realistic surveillance applications. This thesis is aimed at extending the possibilities of moving object tracking systems to a higher level of scene understanding. The proposed extension comprises two separate directions. The first one is local, since is aimed at enriching the inferred positions of the moving objects within the area of the monitored scene directly covered by the cameras of the system; this task is achieved through the development of a multi-camera system for robust 3D tracking, able to provide 3D tracking information of multiple simultaneous moving objects from the observations reported by a set of calibrated cameras with semi-overlapping fields of view. The second extension is global, as is aimed at providing local observations performed within the field of view of one camera with a global context relating them to a much larger scene; to this end, an automatic camera positioning system relying only on observed object trajectories and a scene map is designed. The two lines of research in this thesis are addressed using Bayesian estimation as a general unifying framework. Its suitability for these two applications is justified by the flexibility and versatility of that stochastic framework, which allows the combination of multiple sources of information about the parameters to estimate in a natural and elegant way, addressing at the same time the uncertainty associated to those sources through the inclusion of models designed to this end. In addition, it opens multiple possibilities for the creation of different numerical methods for achieving satisfactory and efficient practical solutions to each addressed application. The proposed multi-camera 3D tracking method is specifically designed to work on schematic descriptions of the observations performed by each camera of the system: this choice allows the use of unspecific off-the-shelf 2D detection and/or tracking subsystems running independently at each sensor, and makes the proposal suitable for real surveillance networks with moderate computational and transmission capabilities. The robust combination of such noisy, incomplete and possibly unreliable schematic descriptors relies on a Bayesian association method, based on geometry and color, whose results allow the tracking of the targets in the scene with a particle filter. The main features exhibited by the proposal are, first, a remarkable accuracy in terms of target 3D positioning, and second, a great recovery ability after tracking losses due to insufficient input data. The proposed system for visual-based camera self-positioning uses the observations of moving objects and a schematic map of the passable areas of the environment to infer the absolute sensor position. To this end, a new Bayesian framework combining trajectory observations and map-induced dynamic models for moving objects is designed, which represents an approach to camera positioning never addressed before in the literature. This task is divided into two different sub-tasks, setting ambiguity analysis and approximate position estimation, on the one hand, and position refining, on the other, since they require the design of specific sampling algorithms to correctly exploit the discriminative features of the developed framework. This system, designed for camera positioning and demonstrated in urban traffic environments, can also be applied to different environments and sensors of other modalities after certain required adaptations.

Bayesian scene analysis for multi-camera 3D tracking and camera positioning

Los sistemas de seguimiento mono-cámara han demostrado su notable capacidad para el análisis de trajectorias de objectos móviles y para monitorización de escenas de interés; sin embargo, tanto su robustez como sus posibilidades en cuanto a comprensión semántica de la escena están fuertemente limitadas por su naturaleza local y monocular, lo que los hace insuficientes para aplicaciones realistas de videovigilancia. El objetivo de esta tesis es la extensión de las posibilidades de los sistemas de seguimiento de objetos móviles para lograr un mayor grado de robustez y comprensión de la escena. La extensión propuesta se divide en dos direcciones separadas. La primera puede considerarse local, ya que está orientada a la mejora y enriquecimiento de las posiciones estimadas para los objetos móviles observados directamente por las cámaras del sistema; dicha extensión se logra mediante el desarrollo de un sistema multi-cámara de seguimiento 3D, capaz de proporcionar consistentemente las posiciones 3D de múltiples objetos a partir de las observaciones capturadas por un conjunto de sensores calibrados y con campos de visión solapados. La segunda extensión puede considerarse global, dado que su objetivo consiste en proporcionar un contexto global para relacionar las observaciones locales realizadas por una cámara con una escena de mucho mayor tamaño; para ello se propone un sistema automático de localización de cámaras basado en las trayectorias observadas de varios objetos móviles y en un mapa esquemático de la escena global monitorizada. Ambas líneas de investigación se tratan utilizando, como marco común, técnicas de estimación bayesiana: esta elección está justificada por la versatilidad y flexibilidad proporcionada por dicho marco estadístico, que permite la combinación natural de múltiples fuentes de información sobre los parámetros a estimar, así como un tratamiento riguroso de la incertidumbre asociada a las mismas mediante la inclusión de modelos de observación específicamente diseñados. Además, el marco seleccionado abre grandes posibilidades operacionales, puesto que permite la creación de diferentes métodos numéricos adaptados a las necesidades y características específicas de distintos problemas tratados. El sistema de seguimiento 3D con múltiples cámaras propuesto está específicamente diseñado para permitir descripciones esquemáticas de las medidas realizadas individualmente por cada una de las cámaras del sistema: esta elección de diseño, por tanto, no asume ningún algoritmo específico de detección o seguimiento 2D en ninguno de los sensores de la red, y hace que el sistema propuesto sea aplicable a redes reales de vigilancia con capacidades limitadas tanto en términos de procesamiento como de transmision. La combinación robusta de las observaciones capturadas individualmente por las cámaras, ruidosas, incompletas y probablemente contaminadas por falsas detecciones, se basa en un metodo de asociación bayesiana basado en geometría y color: los resultados de dicha asociación permiten el seguimiento 3D de los objetos de la escena mediante el uso de un filtro de partículas. El sistema de fusión de observaciones propuesto tiene, como principales características, una gran precisión en términos de localización 3D de objetos, y una destacable capacidad de recuperación tras eventuales errores debidos a un número insuficiente de datos de entrada. El sistema automático de localización de cámaras se basa en la observación de múltiples objetos móviles y un mapa esquemático de las áreas transitables del entorno monitorizado para inferir la posición absoluta de dicho sensor. Para este propósito, se propone un novedoso marco bayesiano que combina modelos dinámicos inducidos por el mapa en los objetos móviles presentes en la escena con las trayectorias observadas por la cámara, lo que representa un enfoque nunca utilizado en la literatura existente. El sistema de localización se divide en dos sub-tareas diferenciadas, debido a que cada una de estas tareas requiere del diseño de algoritmos específicos de muestreo para explotar en profundidad las características del marco desarrollado: por un lado, análisis de la ambigüedad del caso específicamente tratado y estimación aproximada de la localización de la cámara, y por otro, refinado de la localización de la cámara. El sistema completo, diseñado y probado para el caso específico de localización de cámaras en entornos de tráfico urbano, podría tener aplicación también en otros entornos y sensores de diferentes modalidades tras ciertas adaptaciones. ABSTRACT Mono-camera tracking systems have proved their capabilities for moving object trajectory analysis and scene monitoring, but their robustness and semantic possibilities are strongly limited by their local and monocular nature and are often insufficient for realistic surveillance applications. This thesis is aimed at extending the possibilities of moving object tracking systems to a higher level of scene understanding. The proposed extension comprises two separate directions. The first one is local, since is aimed at enriching the inferred positions of the moving objects within the area of the monitored scene directly covered by the cameras of the system; this task is achieved through the development of a multi-camera system for robust 3D tracking, able to provide 3D tracking information of multiple simultaneous moving objects from the observations reported by a set of calibrated cameras with semi-overlapping fields of view. The second extension is global, as is aimed at providing local observations performed within the field of view of one camera with a global context relating them to a much larger scene; to this end, an automatic camera positioning system relying only on observed object trajectories and a scene map is designed. The two lines of research in this thesis are addressed using Bayesian estimation as a general unifying framework. Its suitability for these two applications is justified by the flexibility and versatility of that stochastic framework, which allows the combination of multiple sources of information about the parameters to estimate in a natural and elegant way, addressing at the same time the uncertainty associated to those sources through the inclusion of models designed to this end. In addition, it opens multiple possibilities for the creation of different numerical methods for achieving satisfactory and efficient practical solutions to each addressed application. The proposed multi-camera 3D tracking method is specifically designed to work on schematic descriptions of the observations performed by each camera of the system: this choice allows the use of unspecific off-the-shelf 2D detection and/or tracking subsystems running independently at each sensor, and makes the proposal suitable for real surveillance networks with moderate computational and transmission capabilities. The robust combination of such noisy, incomplete and possibly unreliable schematic descriptors relies on a Bayesian association method, based on geometry and color, whose results allow the tracking of the targets in the scene with a particle filter. The main features exhibited by the proposal are, first, a remarkable accuracy in terms of target 3D positioning, and second, a great recovery ability after tracking losses due to insufficient input data. The proposed system for visual-based camera self-positioning uses the observations of moving objects and a schematic map of the passable areas of the environment to infer the absolute sensor position. To this end, a new Bayesian framework combining trajectory observations and map-induced dynamic models for moving objects is designed, which represents an approach to camera positioning never addressed before in the literature. This task is divided into two different sub-tasks, setting ambiguity analysis and approximate position estimation, on the one hand, and position refining, on the other, since they require the design of specific sampling algorithms to correctly exploit the discriminative features of the developed framework. This system, designed for camera positioning and demonstrated in urban traffic environments, can also be applied to different environments and sensors of other modalities after certain required adaptations.

Cognitive Surveillance Architecture for Scenario Understanding

Uno de los mayores retos para la comunidad científica es conseguir que las máquinas posean en un futuro la capacidad del sistema visual y cognitivo humanos, de forma que, por ejemplo, en entornos de video vigilancia, puedan llegar a proporcionar de manera automática una descripción fiable de lo que está ocurriendo en la escena. En la presente tesis, mediante la propuesta de un marco de trabajo de referencia, se discuten y plantean los pasos necesarios para el desarrollo de sistemas más inteligentes capaces de extraer y analizar, a diferentes niveles de abstracción y mediante distintos módulos de procesamiento independientes, la información necesaria para comprender qué está sucediendo en un conjunto amplio de escenarios de distinta naturaleza. Se parte de un análisis de requisitos y se identifican los retos para este tipo de sistemas en la actualidad, lo que constituye en sí mismo los objetivos de esta tesis, contribuyendo así a un modelo de datos basado en el conocimiento que permitirá analizar distintas situaciones en las que personas y vehículos son los actores principales, dejando no obstante la puerta abierta a la adaptación a otros dominios. Así mismo, se estudian los distintos procesos que se pueden lanzar a nivel interno así como la necesidad de integrar mecanismos de realimentación a distintos niveles que permitan al sistema adaptarse mejor a cambios en el entorno. Como resultado, se propone un marco de referencia jerárquico que integra las capacidades de percepción, interpretación y aprendizaje para superar los retos identificados en este ámbito; y así poder desarrollar sistemas de vigilancia más robustos, flexibles e inteligentes, capaces de operar en una variedad de entornos. Resultados experimentales ejecutados sobre distintas muestras de datos (secuencias de vídeo principalmente) demuestran la efectividad del marco de trabajo propuesto respecto a otros propuestos en el pasado. Un primer caso de estudio, permite demostrar la creación de un sistema de monitorización de entornos de parking en exteriores para la detección de vehículos y el análisis de plazas libres de aparcamiento. Un segundo caso de estudio, permite demostrar la flexibilidad del marco de referencia propuesto para adaptarse a los requisitos de un entorno de vigilancia completamente distinto, como es un hogar inteligente donde el análisis automático de actividades de la vida cotidiana centra la atención del estudio. ABSTRACT One of the most ambitious objectives for the Computer Vision and Pattern Recognition research community is that machines can achieve similar capacities to the human's visual and cognitive system, and thus provide a trustworthy description of what is happening in the scene under surveillance. Thus, a number of well-established scenario understanding architectural frameworks to develop applications working on a variety of environments can be found in the literature. In this Thesis, a highly descriptive methodology for the development of scene understanding applications is presented. It consists of a set of formal guidelines to let machines extract and analyse, at different levels of abstraction and by means of independent processing modules that interact with each other, the necessary information to understand a broad set of different real World surveillance scenarios. Taking into account the challenges that working at both low and high levels offer, we contribute with a highly descriptive knowledge-based data model for the analysis of different situations in which people and vehicles are the main actors, leaving the door open for the development of interesting applications in diverse smart domains. Recommendations to let systems achieve high-level behaviour understanding will be also provided. Furthermore, feedback mechanisms are proposed to be integrated in order to let any system to understand better the environment and the logical context around, reducing thus the uncertainty and noise, and increasing its robustness and precision in front of low-level or high-level errors. As a result, a hierarchical cognitive architecture of reference which integrates the necessary perception, interpretation, attention and learning capabilities to overcome main challenges identified in this area of research is proposed; thus allowing to develop more robust, flexible and smart surveillance systems to cope with the different requirements of a variety of environments. Once crucial issues that should be treated explicitly in the design of this kind of systems have been formulated and discussed, experimental results shows the effectiveness of the proposed framework compared with other proposed in the past. Two case studies were implemented to test the capabilities of the framework. The first case study presents how the proposed framework can be used to create intelligent parking monitoring systems. The second case study demonstrates the flexibility of the system to cope with the requirements of a completely different environment, a smart home where activities of daily living are performed. Finally, general conclusions and future work lines to further enhancing the capabilities of the proposed framework are presented.

Semi-binary based video features for activity representation

Efficient and effective feature detection and representation is an important consideration when processing videos, and a large number of applications such as motion analysis, 3D scene understanding, tracking etc. depend on this. Amongst several feature description methods, local features are becoming increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational complexity, their performance is still too limited for real world applications. Furthermore, rapid increases in the uptake of mobile devices has increased the demand for algorithms that can run with reduced memory and computational requirements. In this paper we propose a semi binary based feature detectordescriptor based on the BRISK detector, which can detect and represent videos with significantly reduced computational requirements, while achieving comparable performance to the state of the art spatio-temporal feature descriptors. First, the BRISK feature detector is applied on a frame by frame basis to detect interest points, then the detected key points are compared against consecutive frames for significant motion. Key points with significant motion are encoded with the BRISK descriptor in the spatial domain and Motion Boundary Histogram in the temporal domain. This descriptor is not only lightweight but also has lower memory requirements because of the binary nature of the BRISK descriptor, allowing the possibility of applications using hand held devices.We evaluate the combination of detectordescriptor performance in the context of action classification with a standard, popular bag-of-features with SVM framework. Experiments are carried out on two popular datasets with varying complexity and we demonstrate comparable performance with other descriptors with reduced computational complexity.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

Fast Learning VIEWNET Architectures for Recognizing 3-D Objects from Multiple 2-D Views

The recognition of 3-D objects from sequences of their 2-D views is modeled by a family of self-organizing neural architectures, called VIEWNET, that use View Information Encoded With NETworks. VIEWNET incorporates a preprocessor that generates a compressed but 2-D invariant representation of an image, a supervised incremental learning system that classifies the preprocessed representations into 2-D view categories whose outputs arc combined into 3-D invariant object categories, and a working memory that makes a 3-D object prediction by accumulating evidence from 3-D object category nodes as multiple 2-D views are experienced. The simplest VIEWNET achieves high recognition scores without the need to explicitly code the temporal order of 2-D views in working memory. Working memories are also discussed that save memory resources by implicitly coding temporal order in terms of the relative activity of 2-D view category nodes, rather than as explicit 2-D view transitions. Variants of the VIEWNET architecture may also be used for scene understanding by using a preprocessor and classifier that can determine both What objects are in a scene and Where they are located. The present VIEWNET preprocessor includes the CORT-X 2 filter, which discounts the illuminant, regularizes and completes figural boundaries, and suppresses image noise. This boundary segmentation is rendered invariant under 2-D translation, rotation, and dilation by use of a log-polar transform. The invariant spectra undergo Gaussian coarse coding to further reduce noise and 3-D foreshortening effects, and to increase generalization. These compressed codes are input into the classifier, a supervised learning system based on the fuzzy ARTMAP algorithm. Fuzzy ARTMAP learns 2-D view categories that are invariant under 2-D image translation, rotation, and dilation as well as 3-D image transformations that do not cause a predictive error. Evidence from sequence of 2-D view categories converges at 3-D object nodes that generate a response invariant under changes of 2-D view. These 3-D object nodes input to a working memory that accumulates evidence over time to improve object recognition. ln the simplest working memory, each occurrence (nonoccurrence) of a 2-D view category increases (decreases) the corresponding node's activity in working memory. The maximally active node is used to predict the 3-D object. Recognition is studied with noisy and clean image using slow and fast learning. Slow learning at the fuzzy ARTMAP map field is adapted to learn the conditional probability of the 3-D object given the selected 2-D view category. VIEWNET is demonstrated on an MIT Lincoln Laboratory database of l28x128 2-D views of aircraft with and without additive noise. A recognition rate of up to 90% is achieved with one 2-D view and of up to 98.5% correct with three 2-D views. The properties of 2-D view and 3-D object category nodes are compared with those of cells in monkey inferotemporal cortex.