Towards training-free appearance-based localization : probabilistic models for whole-image descriptors

Whole image descriptors have recently been shown to be remarkably robust to perceptual change especially compared to local features. However, whole-image-based localization systems typically rely on heuristic methods for determining appropriate matching thresholds in a particular environment. These environment-specific tuning requirements and the lack of a meaningful interpretation of these arbitrary thresholds limits the general applicability of these systems. In this paper we present a Bayesian model of probability for whole-image descriptors that can be seamlessly integrated into localization systems designed for probabilistic visual input. We demonstrate this method using CAT-Graph, an appearance-based visual localization system originally designed for a FAB-MAP-style probabilistic input. We show that using whole-image descriptors as visual input extends CAT-Graph’s functionality to environments that experience a greater amount of perceptual change. We also present a method of estimating whole-image probability models in an online manner, removing the need for a prior training phase. We show that this online, automated training method can perform comparably to pre-trained, manually tuned local descriptor methods.

An adaptive appearance-based map for long-term topological localization of mobile robots

"This work considers a mobile service robot which uses an appearance-based representation of its workplace as a map, where the current view and the map are used to estimate the current position in the environment. Due to the nature of real-world environments such as houses and offices, where the appearance keeps changing, the internal representation may become out of date after some time. To solve this problem the robot needs to be able to adapt its internal representation continually to the changes in the environment. This paper presents a method for creating an adaptive map for long-term appearance-based localization of a mobile robot using long-term and short-term memory concepts, with omni-directional vision as the external sensor."--publisher website

3D Hand Pose Estimation by Finding Appearance-Based Matches in a Large Database of Training Views

Ongoing work towards appearance-based 3D hand pose estimation from a single image is presented. A large database of synthetic hand views is generated using a 3D hand model and computer graphics. The views display different hand shapes as seen from arbitrary viewpoints. Each synthetic view is automatically labeled with parameters describing its hand shape and viewing parameters. Given an input image, the system retrieves the most similar database views, and uses the shape and viewing parameters of those views as candidate estimates for the parameters of the input image. Preliminary results are presented, in which appearance-based similarity is defined in terms of the chamfer distance between edge images.

An Appearance-Based Framework for 3D Hand Shape Classification and Camera Viewpoint Estimation

An appearance-based framework for 3D hand shape classification and simultaneous camera viewpoint estimation is presented. Given an input image of a segmented hand, the most similar matches from a large database of synthetic hand images are retrieved. The ground truth labels of those matches, containing hand shape and camera viewpoint information, are returned by the system as estimates for the input image. Database retrieval is done hierarchically, by first quickly rejecting the vast majority of all database views, and then ranking the remaining candidates in order of similarity to the input. Four different similarity measures are employed, based on edge location, edge orientation, finger location and geometric moments.

Superpixel-based appearance change prediction for long-term navigation across seasons

Changing environments pose a serious problem to current robotic systems aiming at long term operation under varying seasons or local weather conditions. This paper is built on our previous work where we propose to learn to predict the changes in an environment. Our key insight is that the occurring scene changes are in part systematic, repeatable and therefore predictable. The goal of our work is to support existing approaches to place recognition by learning how the visual appearance of an environment changes over time and by using this learned knowledge to predict its appearance under different environmental conditions. We describe the general idea of appearance change prediction (ACP) and investigate properties of our novel implementation based on vocabularies of superpixels (SP-ACP). Our previous work showed that the proposed approach significantly improves the performance of SeqSLAM and BRIEF-Gist for place recognition on a subset of the Nordland dataset under extremely different environmental conditions in summer and winter. This paper deepens the understanding of the proposed SP-ACP system and evaluates the influence of its parameters. We present the results of a large-scale experiment on the complete 10 h Nordland dataset and appearance change predictions between different combinations of seasons.

Surface based hypothesis verification in intensity images using geometric and appearance data

In this paper we discuss current work concerning Appearance-based and CAD-based vision; two opposing vision strategies. CAD-based vision is geometry based, reliant on having complete object centred models. Appearance-based vision builds view dependent models from training images. Existing CAD-based vision systems that work with intensity images have all used one and zero dimensional features, for example lines, arcs, points and corners. We describe a system we have developed for combining these two strategies. Geometric models are extracted from a commercial CAD library of industry standard parts. Surface appearance characteristics are then learnt automatically by observing actual object instances. This information is combined with geometric information and is used in hypothesis evaluation. This augmented description improves the systems robustness to texture, specularities and other artifacts which are hard to model with geometry alone, whilst maintaining the advantages of a geometric description.

Geometry vs appearance for discriminating between posed and spontaneous emotions

Spontaneous facial expressions differ from posed ones in appearance, timing and accompanying head movements. Still images cannot provide timing or head movement information directly. However, indirectly the distances between key points on a face extracted from a still image using active shape models can capture some movement and pose changes. This information is superposed on information about non-rigid facial movement that is also part of the expression. Does geometric information improve the discrimination between spontaneous and posed facial expressions arising from discrete emotions? We investigate the performance of a machine vision system for discrimination between posed and spontaneous versions of six basic emotions that uses SIFT appearance based features and FAP geometric features. Experimental results on the NVIE database demonstrate that fusion of geometric information leads only to marginal improvement over appearance features. Using fusion features, surprise is the easiest emotion (83.4% accuracy) to be distinguished, while disgust is the most difficult (76.1%). Our results find different important facial regions between discriminating posed versus spontaneous version of one emotion and classifying the same emotion versus other emotions. The distribution of the selected SIFT features shows that mouth is more important for sadness, while nose is more important for surprise, however, both the nose and mouth are important for disgust, fear, and happiness. Eyebrows, eyes, nose and mouth are important for anger.

In the pursuit of effective affective computing : the relationship between features and registration

For facial expression recognition systems to be applicable in the real world, they need to be able to detect and track a previously unseen person's face and its facial movements accurately in realistic environments. A highly plausible solution involves performing a "dense" form of alignment, where 60-70 fiducial facial points are tracked with high accuracy. The problem is that, in practice, this type of dense alignment had so far been impossible to achieve in a generic sense, mainly due to poor reliability and robustness. Instead, many expression detection methods have opted for a "coarse" form of face alignment, followed by an application of a biologically inspired appearance descriptor such as the histogram of oriented gradients or Gabor magnitudes. Encouragingly, recent advances to a number of dense alignment algorithms have demonstrated both high reliability and accuracy for unseen subjects [e.g., constrained local models (CLMs)]. This begs the question: Aside from countering against illumination variation, what do these appearance descriptors do that standard pixel representations do not? In this paper, we show that, when close to perfect alignment is obtained, there is no real benefit in employing these different appearance-based representations (under consistent illumination conditions). In fact, when misalignment does occur, we show that these appearance descriptors do work well by encoding robustness to alignment error. For this work, we compared two popular methods for dense alignment-subject-dependent active appearance models versus subject-independent CLMs-on the task of action-unit detection. These comparisons were conducted through a battery of experiments across various publicly available data sets (i.e., CK+, Pain, M3, and GEMEP-FERA). We also report our performance in the recent 2011 Facial Expression Recognition and Analysis Challenge for the subject-independent task.

OpenRatSLAM : an open source brain-based SLAM system

RatSLAM is a navigation system based on the neural processes underlying navigation in the rodent brain, capable of operating with low resolution monocular image data. Seminal experiments using RatSLAM include mapping an entire suburb with a web camera and a long term robot delivery trial. This paper describes OpenRatSLAM, an open-source version of RatSLAM with bindings to the Robot Operating System framework to leverage advantages such as robot and sensor abstraction, networking, data playback, and visualization. OpenRatSLAM comprises connected ROS nodes to represent RatSLAM’s pose cells, experience map, and local view cells, as well as a fourth node that provides visual odometry estimates. The nodes are described with reference to the RatSLAM model and salient details of the ROS implementation such as topics, messages, parameters, class diagrams, sequence diagrams, and parameter tuning strategies. The performance of the system is demonstrated on three publicly available open-source datasets.

Autotransporters of Escherichia coli : a sequence-based characterization

Autotransporter (AT) proteins are found in all Escherichia coli pathotypes and are often associated with virulence. In this study we took advantage of the large number of available E. coli genome sequences to perform an in-depth bioinformatic analysis of AT-encoding genes. Twenty-eight E. coli genome sequences were probed using an iterative approach, which revealed a total of 215 AT-encoding sequences that represented three major groups of distinct domain architecture: (i) serine protease AT proteins, (ii) trimeric AT adhesins and (iii) AIDA-I-type AT proteins. A number of subgroups were identified within each broad category, and most subgroups contained at least one characterized AT protein; however, seven subgroups contained no previously described proteins. The AIDA-I-type AT proteins represented the largest and most diverse group, with up to 16 subgroups identified from sequence-based comparisons. Nine of the AIDA-I-type AT protein subgroups contained at least one protein that possessed functional properties associated with aggregation and/or biofilm formation, suggesting a high degree of redundancy for this phenotype. The Ag43, YfaL/EhaC, EhaB/UpaC and UpaG subgroups were found in nearly all E. coli strains. Among the remaining subgroups, there was a tendency for AT proteins to be associated with individual E. coli pathotypes, suggesting that they contribute to tissue tropism or symptoms specific to different disease outcomes.

Research of Face Location System Based on Human Vision Simulations

In this paper we present a robust face location system based on human vision simulations to automatically locate faces in color static images. Our method is divided into four stages. In the first stage we use a gauss low-pass filter to remove the fine information of images, which is useless in the initial stage of human vision. During the second and the third stages, our technique approximately detects the image regions, which may contain faces. During the fourth stage, the existence of faces in the selected regions is verified. Having combined the advantages of Bottom-Up Feature Based Methods and Appearance-Based Methods, our algorithm performs well in various images, including those with highly complex backgrounds.

Social comparison and body image in non or infrequent exercisers and exercisers

Body image refers to an individual's internal representation ofhis/her outer self (Cash, 1994; Thompson, Heinberg, Altabe, & Tantleff-Dunn, 1999). It is a multidimensional construct which includes an individual's attitudes towards hislher own physical characteristics (Bane & McAuley, 1998; Cash, 1994; Cash, 2004; Davison & McCabe, 2005; Muth & Cash, 1997; Sabiston, Crocker, & Munroe-Chandler, 2005). Social comparison is the process of thinking about the self in relation to others in order to determine if one's opinions and abilities are adequate and to assess one's social status (Festinger, 1954; Wood, 1996). Research investigating the role of social comparisons on body image has provided some information on the types and nature of the comparisons that are made. The act of making social comparisons may have a negative impact on body image (van den Berg et ai., 2007). Although exercise may improve body image, the impact of social comparisons in exercise settings may be less positive, and there may be differences in the social comparison tendencies between non or infrequent exercisers and exercisers. The present study examined the nature of social comparisons that female collegeaged non or infrequent exercisers and exercisers made with respect to their bodies, and the relationship of these social comparisons to body image attitudes. Specifically, the frequency and direction of comparisons on specific tal-gets and body dimensions were examined in both non or infrequent exercisers and exercisers. Finally, the relationship between body-image attitudes and the frequency and direction with which body-related social comparisons were made for non or infrequent exercisers and exercisers were examined. One hundred and fifty-two participants completed the study (n = 70 non or ill infrequent exercisers; n = 82 exercisers). Participants completed measures of social physique anxiety (SPA), body dissatisfaction, body esteem, body image cognitions, leisure time physical activity, and social comparisons. Results suggested that both groups (non or infrequent exercisers and exercisers) generally made social comparisons and most frequently made comparisons with same-sex friends, and least frequently with same-sex parents. Also, both groups made more appearance-related comparisons than non-appearance-related comparisons. Further, both groups made more negative comparisons with almost all targets. However, non or infrequent exercisers generally made more negative comparisons on all body dimensions, while exercisers made negative comparisons only on weight and body shape dimensions. MANOV As were conducted to examine if any differences on social comparisons between the two groups existed. Results of the MANOVAs indicated that frequency of comparisons with targets, the frequency of comparisons on body dimensions, and direction of comparisons with targets did not differ based on exercise status. However, the direction of comparison of specific body dimensions revealed a significant (F (7, 144) = 3.26,p < .05; 1]2 = .132) difference based on exercise status. Follow-up ANOVAs showed significant differences on five variables: physical attractiveness (F (1, 150) = 6.33,p < .05; 1]2 = .041); fitness (F(l, 150) = 11.89,p < .05; 1]2 = .073); co-ordination (F(I, 150) = 5.61,p < .05; 1]2 = .036); strength (F(I, dO) = 12.83,p < .05; 1]2 = .079); muscle mass or tone (F(l, 150) = 17.34,p < .05; 1]2 = 1.04), with exercisers making more positive comparisons than non or infrequent exercisers. The results from the regression analyses for non or infrequent exercisers showed appearance orientation was a significant predictor of the frequency of social comparisons N (B = .429, SEB = .154, /3 = .312,p < .01). Also, trait body image measures accounted for significant variance in the direction of social comparisons (F(9, 57) = 13.43,p < .001, R2adj = .68). Specifically, SPA (B = -.583, SEB = .186, /3 = -.446,p < .01) and body esteem-weight concerns (B = .522, SEB = .207, /3 = .432,p < .01) were significant predictors of the direction of comparisons. For exercisers, regressions revealed that specific trait measures of body image significantly predicted the frequency of comparisons (F(9, 71) = 8.67,p < .001, R2adj = .463). Specifically, SPA (B = .508, SEB = .147, /3 = .497,p < .01) and appearance orientation (B = .457, SEB = .134, /3 = .335,p < .01) were significant predictors of the frequency of social comparisons. Lastly, for exercisers, the results for the regression of body image measures on the direction of social comparisons were also significant (F(9, 70) = 14.65,p < .001, R2adj = .609) with body dissatisfaction (B = .368, SEB = .143, /3 = .362,p < .05), appearan.ce orientation (B = .256, SEB = .123, /3 = .175,p < .05), and fitness orientation (B = .423, SEB = .194, /3 = .266,p < .05) significant predictors of the direction of social comparison. The results indicated that young women made frequent social comparisons regardless of exercise status. However, exercisers m,a de more positive comparisons on all the body dimensions than non or infrequent exercisers. Also, certain trait body image measures may be good predictors of one's body comp~son tendencies. However, the measures which predict comparison tendencies may be different for non or infrequent exercisers and exercisers. Future research should examine the effects of social comparisons in different populations (i.e., males, the obese, older adults, etc.). Implications for practice and research were discussed.