Analysis of subject specific grasping patterns.

Existing haptic feedback devices are limited in their capabilities and are often cumbersome and heavy. In addition, these devices are generic and do not adapt to the users' grasping behavior. Potentially, a human-oriented design process could generate an improved design. While current research done on human grasping was aimed at finding common properties within the research population, we investigated the dynamic patterns that make human grasping behavior distinct rather than generalized, i.e. subject specific. Experiments were conducted on 31 subjects who performed grasping tasks on five different objects. The kinematics and kinetics parameters were measured using a motion capture system and force sensors. The collected data was processed through a pipeline of dimensionality reduction and clustering algorithms. Using finger joint angles and reaction forces as our features, we were able to classify these tasks with over 95% success. In addition, we examined the effects of the objects' mechanical properties on those patterns and the significance of the different features for the differentiation. Our results suggest that grasping patterns are, indeed, subject-specific; this, in turn, could suggest that a device capable of providing personalized feedback can improve the user experience and, in turn, increase the usability in different applications. This paper explores an undiscussed aspect of human dynamic patterns. Furthermore, the collected data offer a valuable dataset of human grasping behavior, containing 1083 grasp instances with both kinetics and kinematics data.

From biokinematics to a robotic active vision system.

Barn owls move their heads in very particular motions, compensating for the quasi-immovability of their eyes. These efficient predators often perform peering side-to-side head motions when scanning their surroundings and seeking prey. In this work, we use the head movements of barn owls as a model to bridge between biological active vision and machine vision. The biomotions are measured and used to actuate a specially built robot equipped with a depth camera for scanning. We hypothesize that the biomotions improve scan accuracy of static objects. Our experiments show that barn owl biomotion-based trajectories consistently improve scan accuracy when compared to intuitive scanning motions. This constitutes proof-of-concept evidence that the vision of robotic systems can be enhanced by bio-inspired viewpoint manipulation. Such biomimetic scanning systems can have many applications, e.g. manufacturing inspection or in autonomous robots.

SIFTing Through Scales.

Scale invariant feature detectors often find stable scales in only a few image pixels. Consequently, methods for feature matching typically choose one of two extreme options: matching a sparse set of scale invariant features, or dense matching using arbitrary scales. In this paper, we turn our attention to the overwhelming majority of pixels, those where stable scales are not found by standard techniques. We ask, is scale-selection necessary for these pixels, when dense, scale-invariant matching is required and if so, how can it be achieved? We make the following contributions: (i) We show that features computed over different scales, even in low-contrast areas, can be different and selecting a single scale, arbitrarily or otherwise, may lead to poor matches when the images have different scales. (ii) We show that representing each pixel as a set of SIFTs, extracted at multiple scales, allows for far better matches than single-scale descriptors, but at a computational price. Finally, (iii) we demonstrate that each such set may be accurately represented by a low-dimensional, linear subspace. A subspace-to-point mapping may further be used to produce a novel descriptor representation, the Scale-Less SIFT (SLS), as an alternative to single-scale descriptors. These claims are verified by quantitative and qualitative tests, demonstrating significant improvements over existing methods. A preliminary version of this work appeared in [1] .

Unsupervised learning of categorical segments in image collections.

Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a flexible probabilistic model, for representing the shape and appearance of each segment, with the popular "bag of visual words" model for recognition. If applied to a collection of images, our framework can simultaneously discover the segments of each image and the correspondence between such segments, without supervision. Such recurring segments may be thought of as the "parts" of corresponding objects that appear multiple times in the image collection. Thus, the model may be used for learning new categories, detecting/classifying objects, and segmenting images, without using expensive human annotation.

Context-aware saliency detection.

We propose a new type of saliency­context-aware saliency­which aims at detecting the image regions that represent the scene. This definition differs from previous definitions whose goal is to either identify fixation points or detect the dominant object. In accordance with our saliency definition, we present a detection algorithm which is based on four principles observed in the psychological literature. The benefits of the proposed approach are evaluated in two applications where the context of the dominant objects is just as essential as the objects themselves. In image retargeting, we demonstrate that using our saliency prevents distortions in the important regions. In summarization, we show that our saliency helps to produce compact, appealing, and informative summaries.

Approximate nearest subspace search.

Subspaces offer convenient means of representing information in many pattern recognition, machine vision, and statistical learning applications. Contrary to the growing popularity of subspace representations, the problem of efficiently searching through large subspace databases has received little attention in the past. In this paper, we present a general solution to the problem of Approximate Nearest Subspace search. Our solution uniformly handles cases where the queries are points or subspaces, where query and database elements differ in dimensionality, and where the database contains subspaces of different dimensions. To this end, we present a simple mapping from subspaces to points, thus reducing the problem to the well-studied Approximate Nearest Neighbor problem on points. We provide theoretical proofs of correctness and error bounds of our construction and demonstrate its capabilities on synthetic and real data. Our experiments indicate that an approximate nearest subspace can be located significantly faster than the nearest subspace, with little loss of accuracy.

Statistical analysis of dynamic actions.

Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents.