object detection is one of the key components in modern computer vision systems. While the detection of a specific rigid object under changing viewpoints was considered hard just a few years ago, current research stri...
详细信息
object detection is one of the key components in modern computer vision systems. While the detection of a specific rigid object under changing viewpoints was considered hard just a few years ago, current research strives to detect and recognize classes of non-rigid, articulated objects. Hampered by the omnipresent confusing information due to clutter and occlusion, the focus has shifted from holistic approaches for object detection to representations of individual object parts linked by structural information, along with richer contextual descriptions of object configurations. Along this line of research, we present a practicable and expandable probabilistic framework for parts-based objectclass representation, enabling the detection of rigid and articulated objectclasses in arbitrary views. We investigate learning of this representation from labelled training images and infer globally optimal solutions to the contextual MAP-detection problem, using A (*)-search with a novel lower-bound as admissible heuristic. An assessment of the inference performance of Belief-Propagation and Tree-Reweighted Belief Propagation is obtained as a by-product. The generality of our approach is demonstrated on four different datasets utilizing domain dependent information cues.
In the transition from industrial to service robotics, robots will have to deal with increasingly unpredictable and variable environments. We present a system that is able to recognize objects of a certain class in an...
详细信息
In the transition from industrial to service robotics, robots will have to deal with increasingly unpredictable and variable environments. We present a system that is able to recognize objects of a certain class in an image and to identify their parts for potential interactions. The method can recognize objects from arbitrary viewpoints and generalizes to instances that have never been observed during training, even if they are partially occluded and appear against cluttered backgrounds. Our approach builds on the implicit shape model of Leibe et al. We extend it to couple recognition to the provision of meta-data useful for a task and to the case of multiple viewpoints by integrating it with the dense multi-view correspondence finder of Ferrari et al. Meta-data can be part labels but also depth estimates, information on material types, or any other pixelwise annotation. We present experimental results on wheelchairs, cars, and motorbikes.
We present an efficient method for learning part-based objectclass models from unsegmented images represented as sets of salient features. A model includes parts' appearance, as well as location and scale relatio...
详细信息
We present an efficient method for learning part-based objectclass models from unsegmented images represented as sets of salient features. A model includes parts' appearance, as well as location and scale relations between parts. The objectclass is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model's parameters, however, are optimized to reduce a loss function of the training error, as in discriminative methods. We show how boosting techniques can be extended to optimize the relational model proposed, with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features. The method has an advantage over purely generative and purely discriminative approaches for learning from sets of salient features, since generative method often use a small number of parts and features, while discriminative methods tend to ignore geometrical relations between parts. Experimental results are described, using some bench-mark data sets and three sets of newly collected data, showing the relative merits of our method in recognition and localization tasks.
We propose a new approach for recognizing objectclasses which is based on the intuitive idea that human beings are able to perform the task well given only thumbnails (coarse scale version) of images. Unlike previous...
详细信息
ISBN:
(纸本)9781424414833
We propose a new approach for recognizing objectclasses which is based on the intuitive idea that human beings are able to perform the task well given only thumbnails (coarse scale version) of images. Unlike previous work which uses local image features at fine scales, our approach uses thumbnails directly, and captures their high-order correlations at coarse scales through deep multi-layer neural networks based on Restricted Boltzmann Machines. Specifically, the pretraining stage of such networks takes on the role of feature extraction. Experimental results show that the proposed approach is comparable to other state-of-the-art recognition methods in terms of accuracy. The merits of the proposed approach come from the simplicity of the workflow and the parallelizability of the implementation structure.
We propose a method of automatically labeling landmarks on target images, which are used for training a constellation model to recognize general objectclass. First, we randomly sample local features (parts) and gener...
详细信息
ISBN:
(纸本)9781424421961
We propose a method of automatically labeling landmarks on target images, which are used for training a constellation model to recognize general objectclass. First, we randomly sample local features (parts) and generate hierarchical representations of images in a similar way to the "standard model" of visual cortex. Second, we pick out a unique location of each part among those local maxima in S2 layers by a matching procedure. Third, we model the spatial relations among parts as a sparse GMRF (Gaussian Markov Random Fields) graph, and learn the links by a lasso-based approach. object localization in new images proceeds by maximizing the posterior of an object observed at a particular configuration. Our model is a thoroughly automatic scheme to perform "feature binding" Experimental results on the CalTech101 database demonstrate that the proposed algorithm locates the components more precisely and outperforms the "standard model" in object detection.
暂无评论