Common-sense knowledge for a computer vision system for human action recognition

This work presents a novel approach for human action recognition based on the combination of computer vision techniques and common-sense knowledge and reasoning capabilities. The emphasis of this work is on how common sense has to be leveraged to a vision-based human action recognition so that nonsensical errors can be amended at the understanding stage. The proposed framework is to be deployed in a realistic environment in which humans behave rationally, that is, motivated by an aim or a reason. © 2012 Springer-Verlag.

Common-sense reasoning for human action recognition

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. © 2012 Elsevier B.V. All rights reserved.

Episodic Reasoning for Vision-Based Human Action Recognition

Smart Spaces, Ambient Intelligence, and Ambient Assisted Living are environmental paradigms that strongly depend on their capability to recognize human actions. While most solutions rest on sensor value interpretations and video analysis applications, few have realized the importance of incorporating common-sense capabilities to support the recognition process. Unfortunately, human action recognition cannot be successfully accomplished by only analyzing body postures. On the contrary, this task should be supported by profound knowledge of human agency nature and its tight connection to the reasons and motivations that explain it. The combination of this knowledge and the knowledge about how the world works is essential for recognizing and understanding human actions without committing common-senseless mistakes. This work demonstrates the impact that episodic reasoning has in improving the accuracy of a computer vision system for human action recognition. This work also presents formalization, implementation, and evaluation details of the knowledge model that supports the episodic reasoning.

Kinect and Episodic Reasoning for Human Action Recognition

This paper presents a method for rational behaviour recognition that combines vision-based pose estimation with knowledge modeling and reasoning. The proposed method consists of two stages. First, RGB-D images are used in the estimation of the body postures. Then, estimated actions are evaluated to verify that they make sense. This method requires rational behaviour to be exhibited. To comply with this requirement, this work proposes a rational RGB-D dataset with two types of sequences, some for training and some for testing. Preliminary results show the addition of knowledge modeling and reasoning leads to a significant increase of recognition accuracy when compared to a system based only on computer vision.

Low-rank representation based action recognition

Human action recognition is an important problem in computer vision, which has been applied to many applications. However, how to learn an accurate and discriminative representation of videos based on the features extracted from videos still remains to be a challenging problem. In this paper, we propose a novel method named low-rank representation based action recognition to recognize human actions. Given a dictionary, low-rank representation aims at finding the lowestrank representation of all data, which can capture the global data structures. According to its characteristics, low-rank representation is robust against noises. Experimental results demonstrate the effectiveness of the proposed approach on several publicly available datasets.

Human behaviour recognition in data-scarce domains

This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an unordered bag. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao–Blackwellised Particle Filter. Simulated annealing is used to identify pairs of agents involved in multi-agent activity. We validate our framework using the benchmarked PETS 2006 video surveillance dataset and our own sequences, and achieve a mean recognition F-Score of 0.82. Our approach achieves a mean improvement of 17% over a Hidden Markov Model baseline.

An efficient feature selection method for mobile devices with application to activity recognition

This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modelled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited. An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.

The Social Politics of Breastfeeding: Norms, Situations and Policy Implications

This paper aims to explore the assumptions concerning the dynamics of human action underpinning breastfeeding promotion campaigns in the UK. Drawing on qualitative interviews with mothers, the ways in which three problematic assumptions shape both the promotion and experience of contemporary breastfeeding promotion campaigns are explored, in the light of Joas’s theorisation of action’s creativity and pragmatism. Public health efforts to establish breastfeeding as a rational standard against which good mothering can be judged, in ways which rely on a de-contextualised understanding of human action as instrumentally rational, where bodies are imagined as pliable instruments of human intentions, are explored as they play out in the experiences of women embarking on motherhood. The paper concludes that a target-driven health-promotion policy, relying on a mechanistic account of social and emotional life, is contributing to the burden of early motherhood in ways that are not conducive to infant and maternal health and attachment.

Perceiving and Reenacting Spatiotemporal Characteristics of Walking Sounds

Many studies have examined the processes involved in recognizing types of human action through sound, but little is known about whether the physical characteristics of an action (such as kinetic and kinematic parameters) can be perceived and imitated from sound. Twelve young healthy adults listened to recordings of footsteps on a gravel path taken from walks of different stride lengths (SL) and cadences. In 1 protocol, participants performed a real-time reenactment of the walking action depicted in a sound sample. Second, participants listened to 2 different sound samples and discriminated differences in SL. In a 2nd experiment, these procedures were repeated using synthesized sounds derived from the kinetic interactions between the foot and walking surface. A 3rd experiment examined the influence of altered cadence on participants' ability to discriminate changes in SL. Participants significantly adapted their own SL and cadence according to those depicted in both real and synthesized sounds (p <.01). However, although participants accurately discriminated between large changes in SL, these perceptions were heavily influenced by temporal factors, that is, when cadence changed between samples. These findings show that spatial attributes of action sounds can be both mimicked and discriminated, even when only basic kinetic interactions present within the action are specified. (PsycINFO Database Record (c) 2012 APA, all rights reserved).

A sequential algorithm for sparse support vector classifiers

Support vector machines (SVMs), though accurate, are not preferred in applications requiring high classification speed or when deployed in systems of limited computational resources, due to the large number of support vectors involved in the model. To overcome this problem we have devised a primal SVM method with the following properties: (1) it solves for the SVM representation without the need to invoke the representer theorem, (2) forward and backward selections are combined to approach the final globally optimal solution, and (3) a criterion is introduced for identification of support vectors leading to a much reduced support vector set. In addition to introducing this method the paper analyzes the complexity of the algorithm and presents test results on three public benchmark problems and a human activity recognition application. These applications demonstrate the effectiveness and efficiency of the proposed algorithm.


--------------------------------------------------------------------------------