Insect inspired behaviours for the autonomous control of mobile robots

Animals navigate through various uncontrolled environments with seemingly little effort. Flying insects, especially, are quite adept at manoeuvring in complex, unpredictable and possibly hostile environments. Through both simulation and real-world experiments, we demonstrate the feasibility of equipping a mobile robot with the ability to navigate a corridor environment, in real time, using principles based on insect-based visual guidance. In particular we have used the bees’ navigational strategy of measuring object range in terms of image velocity. We have also shown the viability and usefulness of various other insect behaviours: (i) keeping walls equidistant, (ii) slowing down when approaching an object, (iii) regulating speed according to tunnel width, and (iv) using visual motion as a measure of distance travelled.

Multichannel biomedical time series clustering via hierarchical probabilistic latent semantic analysis

Biomedical time series clustering that automatically groups a collection of time series according to their internal similarity is of importance for medical record management and inspection such as bio-signals archiving and retrieval. In this paper, a novel framework that automatically groups a set of unlabelled multichannel biomedical time series according to their internal structural similarity is proposed. Specifically, we treat a multichannel biomedical time series as a document and extract local segments from the time series as words. We extend a topic model, i.e., the Hierarchical probabilistic Latent Semantic Analysis (H-pLSA), which was originally developed for visual motion analysis to cluster a set of unlabelled multichannel time series. The H-pLSA models each channel of the multichannel time series using a local pLSA in the first layer. The topics learned in the local pLSA are then fed to a global pLSA in the second layer to discover the categories of multichannel time series. Experiments on a dataset extracted from multichannel Electrocardiography (ECG) signals demonstrate that the proposed method performs better than previous state-of-the-art approaches and is relatively robust to the variations of parameters including length of local segments and dictionary size. Although the experimental evaluation used the multichannel ECG signals in a biometric scenario, the proposed algorithm is a universal framework for multichannel biomedical time series clustering according to their structural similarity, which has many applications in biomedical time series management.

On the perceived location of global motion

We measured the effects of coherent motion of one set of dots on the perceived location of Gaussian envelopes formed by luminance modulation of a second set of dots. Perceived shifts in envelope location in the direction of coherent motion were obtained even when the dots forming the envelopes did not physically move in the direction of coherent motion. In such cases, perceived shifts coincided with stimulus configurations that permitted motion integration of the envelope dots with the coherently moving dots, for example, when envelope dots moved in random directions as opposed to being static. In subsequent experiments we explored the type of motion integration underlying the positional shifts obtained. We discounted the possibility that the visual system incorrectly attributes motion signals associated with coherently moving dots to envelope dots by demonstrating that positional shifts could be obtained even when the coherent dots were laterally displaced to either side of the envelope dots such that the regions occupied by the dots did not overlap. We also discounted spatio-temporal summation within the receptive fields of low-spatial-frequency motion-sensitive mechanisms by demonstrating that positional shifts persisted even when the dot displays were high-pass filtered. These results, coupled with the observation that the proportion of coherently moving dots required to produce positional shifts correlated well with global motion thresholds measured for the same dot configurations, suggests that visual processes which underlie motion-dependent positional shifts are based at least in part on cooperative interactions of the type implicated in global motion.

Translating text into motion : performance analysis for singers and directors

The study proposes a method of interpretation, which gives the contemporary singer-actor and director a method of performance analysis considering both the visual and the auditory aspects of vocal performance. The analysis begins with an analysis of the structure, which maps out the key ideas and translates them into main states of mind. The text analysis is followed by an analysis of the musical treatment of the text, also scanning for extra dramatic meaning inherent in vocal line and musical accompaniment. The so isolated dramatic ideas in text and musical structure and content are finally discussed in terms of their physical aspects, using the system of gesture as practiced by actors and singers before, during and beyond the Baroque period. The method is exemplified by the obbligato recitative "In quali eccessi" from Donna Elvira’s scene in the second act of the opera "Don Giovanni" by L. Da Ponte and W. A. Mozart. The musical example includes gestural notation and a table gestural notation symbols.

3D virtual haptic cone for intuitive vehicle motion control

Haptic technology provides the ability for a system to recreate the sense of touch to a human operator, and as such offers wide reaching advantages. The ability to interact with the human's tactual modality introduces haptic human-machine interaction to replace or augment existing mediums such as visual and audible information. A distinct advantage of haptic human-machine interaction is the intrinsic bilateral nature, where information can be communicated in both directions simultaneously. This paper investigates the bilateral nature of the haptic interface in controlling the motion of a remote (or virtual) vehicle and presents the ability to provide an additional dimension of haptic information to the user over existing approaches [1-4]. The 3D virtual haptic cone offers the ability to not only provide the user with relevant haptic augmentation pertaining to the task at hand, as do existing approaches, however, to also simultaneously provide an intuitive indication of the current velocities being commanded.

The roles of object-image relative motion and static depth information in the perception of heading

Investigates visual information that enables human to effectively guide their movement through the environment. This problem is fundamental to the study of human behaviour, since survival is contingent upon the acquisition of resources that lie in different locations throughout the environment.

Visual object clustering via mixed-norm regularization

Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data. This principle is motivated from an ideal modeling of data points according to linear algebra theory. However, real data in computer vision are unlikely to follow the ideal model perfectly. In this paper, we exploit the mixed norm regularization for sparse subspace clustering. This regularization term is a convex combination of the l1norm, which promotes sparsity at the individual level and the block norm l2/1 which promotes group sparsity. Combining these powerful regularization terms will provide a more accurate modeling, subsequently leading to a better solution for the affinity matrix used in sparse subspace clustering. This could help us achieve better performance on motion segmentation and face clustering problems. This formulation also caters for different types of data corruptions. We derive a provably convergent algorithm based on the alternating direction method of multipliers (ADMM) framework, which is computationally efficient, to solve the formulation. We demonstrate that this formulation outperforms other state-of-arts on both motion segmentation and face clustering.

CCTV scene perspective distortion estimation from low-level motion features

Our aim is to estimate the perspective-effected geometric distortion of a scene from a video feed. In contrast to most related previous work, in this task we are constrained to use low-level spatiotemporally local motion features only. This particular challenge arises in many semiautomatic surveillance systems that alert a human operator to potential abnormalities in the scene. Low-level spatiotemporally local motion features are sparse (and thus require comparatively little storage space) and sufficiently powerful in the context of video abnormality detection to reduce the need for human intervention by more than 100-fold. This paper introduces three significant contributions. First, we describe a dense algorithm for perspective estimation, which uses motion features to estimate the perspective distortion at each image locus and then polls all such local estimates to arrive at the globally best estimate. Second, we also present an alternative coarse algorithm that subdivides the image frame into blocks and uses motion features to derive block-specific motion characteristics and constrain the relationships between these characteristics, with the perspective estimate emerging as a result of a global optimization scheme. Third, we report the results of an evaluation using nine large sets acquired using existing closed-circuit television cameras, not installed specifically for the purposes of this paper. Our findings demonstrate that both proposed methods are successful, their accuracy matching that of human labeling using complete visual data (by the constraints of the setup unavailable to our algorithms).