RESUMEN
An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of people in each frame and estimate their configurations. But, finding people and localizing their limbs is hard because people can move fast and unpredictably, can appear in a variety of poses and clothes, and are often surrounded by limb-like clutter. We develop a completely automatic system that works in two stages; it first builds a model of appearance of each person in a video and then it tracks by detecting those models in each frame ("tracking by model-building and detection"). We develop two algorithms that build models; one bottom-up approach groups together candidate body parts found throughout a sequence. We also describe a top-down approach that automatically builds people-models by detecting convenient key poses within a sequence. We finally show that building a discriminative model of appearance is quite helpful since it exploits structure in a background (without background-subtraction). We demonstrate the resulting tracker on hundreds of thousands of frames of unscripted indoor and outdoor activity, a feature-length film ("Run Lola Run"), and legacy sports footage (from the 2002 World Series and 1998 Winter Olympics). Experiments suggest that our system 1) can count distinct individuals, 2) can identify and track them, 3) can recover when it loses track, for example, if individuals are occluded or briefly leave the view, 4) can identify body configuration accurately, and 5) is not dependent on particular models of human motion.
Asunto(s)
Inteligencia Artificial , Interpretación de Imagen Asistida por Computador/métodos , Almacenamiento y Recuperación de la Información/métodos , Movimiento , Reconocimiento de Normas Patrones Automatizadas/métodos , Grabación en Video/métodos , Imagen de Cuerpo Entero/métodos , Algoritmos , Humanos , Aumento de la Imagen/métodos , Imagenología Tridimensional/métodos , Reproducibilidad de los Resultados , Sensibilidad y EspecificidadRESUMEN
This paper argues that tracking, object detection, and model building are all similar activities. We describe a fully automatic system that builds 2D articulated models known as pictorial structures from videos of animals. The learned model can be used to detect the animal in the original video--in this sense, the system can be viewed as a generalized tracker (one that is capable of modeling objects while tracking them). The learned model can be matched to a visual library; here, the system can be viewed as a video recognition algorithm. The learned model can also be used to detect the animal in novel images--in this case, the system can be seen as a method for learning models for object recognition. We find that we can significantly improve the pictorial structures by augmenting them with a discriminative texture model learned from a texture library. We develop a novel texture descriptor that outperforms the state-of-the-art for animal textures. We demonstrate the entire system on real video sequences of three different animals. We show that we can automatically track and identify the given animal. We use the learned models to recognize animals from two data sets; images taken by professional photographers from the Corel collection, and assorted images from the Web returned by Google. We demonstrate quite good performance on both data sets. Comparing our results with simple baselines, we show that, for the Google set, we can detect, localize, and recover part articulations from a collection demonstrably hard for object recognition.
Asunto(s)
Inteligencia Artificial , Interpretación de Imagen Asistida por Computador/métodos , Modelos Anatómicos , Modelos Biológicos , Reconocimiento de Normas Patrones Automatizadas/métodos , Fotograbar/métodos , Grabación en Video/métodos , Algoritmos , Animales , Simulación por Computador , Aumento de la Imagen/métodos , Imagenología Tridimensional/métodos , Almacenamiento y Recuperación de la Información/métodos , MovimientoRESUMEN
Syntheses of racemic forms of the main secondary metabolites of Quararibea funebris, (+/-)-funebrine, (+/-)-funebral, and their biogenetic precursor (+/-)-(2S,3S,4R)-gamma-hydroxyalloisoluecine lactone have been developed. In synthetic studies, a new variation of the Paal-Knorr condensation employing titanium isopropoxide was utilized to construct the pyrrole lactone moiety. Two efficient synthetic approaches to the key (+/-)-gamma-amino lactone have been developed, one based on Claisen chemistry and the other on addition reactions to the butenolide ring of beta-angelicalactone. The restricted rotation around the C(sp(3))-N(sp(2)) bond in the pyrrole lactone structures of (+/-)-funebrine, (+/-)-funebral, and related aldehydes has been probed by conformational dynamic studies, and the barriers for interconversion between conformations have been measured by full NMR line-shape analysis. Molecular mechanics (MMX) and a (1)H-(1)H NOE study indicate a distinct preferred conformation for (+/-)-funebrine.