Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Our goal is to develop a visual monitoring system that passively observes moving objects in a site and learns patterns of activity from those observations. For extended sites, the system will require multiple cameras. Thus, key elements of the system are motion tracking, camera coordination, activity classification, and event detection. In this paper, we focus on motion tracking and show how one can use observed motion to learn patterns of activity in a site. Motion segmentation is based on an adaptive background subtraction method that models each pixel as a mixture of Gaussians and uses an online approximation to update the model. The Gaussian distributions are then evaluated to determine which are most likely to result from a background process. This yields a stable, real-time outdoor tracker that reliably deals with lighting changes, repetitive motions from clutter, and long-term scene changes. While a tracking system is unaware of the identity of any object it tracks, the identity remains the same for the entire tracking sequence. Our system leverages this information by accumulating joint co-occurrences of the representations within a sequence. These joint co-occurrence statistics are then used to create a hierarchical binary-tree classification of the representations. This method is useful for classifying sequences, as well as individual instances of activities in a site.

/pdf/learning-patterns-of-activity-using-real-time-tracking-4pcdy8vvvh.pdf

Learning patterns of activity using real-time tracking

A view-based approach to the representation and recognition of human movement is presented. The basis of the representation is a temporal template-a static vector-image where the vector value at each point is a function of the motion properties at the corresponding spatial location in an image sequence. Using aerobics exercises as a test domain, we explore the representational power of a simple, two component version of the templates: The first value is a binary value indicating the presence of motion and the second value is a function of the recency of motion in a sequence. We then develop a recognition method matching temporal templates against stored instances of views of known actions. The method automatically performs temporal segmentation, is invariant to linear changes in speed, and runs in real-time on standard platforms.

/pdf/the-recognition-of-human-movement-using-temporal-templates-5e8eze1cen.pdf

The recognition of human movement using temporal templates

Dynamic Bayesian Networks: Representation, Inference and Learning by Kevin Patrick Murphy Doctor of Philosophy in Computer Science University of California, Berkeley Professor Stuart Russell, Chair Modelling sequential data is important in many areas of science and engineering. Hidden Markov models (HMMs) and Kalman filter models (KFMs) are popular for this because they are simple and flexible. For example, HMMs have been used for speech recognition and bio-sequence analysis, and KFMs have been used for problems ranging from tracking planes and missiles to predicting the economy. However, HMMs and KFMs are limited in their “expressive power”. Dynamic Bayesian Networks (DBNs) generalize HMMs by allowing the state space to be represented in factored form, instead of as a single discrete random variable. DBNs generalize KFMs by allowing arbitrary probability distributions, not just (unimodal) linear-Gaussian. In this thesis, I will discuss how to represent many different kinds of models as DBNs, how to perform exact and approximate inference in DBNs, and how to learn DBN models from sequential data. In particular, the main novel technical contributions of this thesis are as follows: a way of representing Hierarchical HMMs as DBNs, which enables inference to be done in O(T ) time instead of O(T ), where T is the length of the sequence; an exact smoothing algorithm that takes O(log T ) space instead of O(T ); a simple way of using the junction tree algorithm for online inference in DBNs; new complexity bounds on exact online inference in DBNs; a new deterministic approximate inference algorithm called factored frontier; an analysis of the relationship between the BK algorithm and loopy belief propagation; a way of applying Rao-Blackwellised particle filtering to DBNs in general, and the SLAM (simultaneous localization and mapping) problem in particular; a way of extending the structural EM algorithm to DBNs; and a variety of different applications of DBNs. However, perhaps the main value of the thesis is its catholic presentation of the field of sequential data modelling.

/pdf/dynamic-bayesian-networks-representation-inference-and-yy4fhfxdcj.pdf

Dynamic bayesian networks: representation, inference and learning

http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

This paper describes a probabilistic syntactic approach to the detection and recognition of temporally extended activities and interactions between multiple agents. The fundamental idea is to divide the recognition problem into two levels. The lower level detections are performed using standard independent probabilistic event detectors to propose candidate detections of low-level features. The outputs of these detectors provide the input stream for a stochastic context-free grammar parsing mechanism. The grammar and parser provide longer range temporal constraints, disambiguate uncertain low-level detections, and allow the inclusion of a priori knowledge about the structure of temporal events in a given domain. We develop a real-time system and demonstrate the approach in several experiments on gesture recognition and in video surveillance. In the surveillance application, we show how the system correctly interprets activities of multiple interacting objects.

http://www.cs.toronto.edu/~dross/presentations/Ross_IvanovBobick.pdf

Recognition of visual activities and interactions by stochastic parsing

The KidsRoom is a perceptually-based, interactive, narrative playspace for children. Images, music, narration, light, and sound effects are used to transform a normal child's bedroom into a fantasy land where children are guided through a reactive adventure story. The fully automated system was designed with the following goals: (1) to keep the focus of user action and interaction in the physical and not virtual space; (2) to permit multiple, collaborating people to simultaneously engage in an interactive experience combining both real and virtual objects; (3) to use computer-vision algorithms to identify activity in the space without requiring the participants to wear any special clothing or devices; (4) to use narrative to constrain the perceptual recognition, and to use perceptual recognition to allow participants to drive the narrative; and (5) to create a truly immersive and interactive room environment.

We believe the KidsRoom is the first multi-person, fully-automated, interactive, narrative environment ever constructed using non-encumbering sensors. This paper describes the KidsRoom, the technology that makes it work, and the issues that were raised during the system's development. 1 

A demonstration of the project, which complements the material presented here and includes videos, images, and sounds from each part of the story is available at .

/pdf/the-kidsroom-a-perceptually-based-interactive-and-immersive-4q4sxtdqch.pdf

The KidsRoom: A Perceptually-Based Interactive and Immersive Story Environment

The ability to learn is a potentially compelling and important quality for interactive synthetic characters. To that end, we describe a practical approach to real-time learning for synthetic characters. Our implementation is grounded in the techniques of reinforcement learning and informed by insights from animal training. It simplifies the learning task for characters by (a) enabling them to take advantage of predictable regularities in their world, (b) allowing them to make maximal use of any supervisory signals, and (c) making them easy to train by humans.We built an autonomous animated dog that can be trained with a technique used to train real dogs called "clicker training". Capabilities demonstrated include being trained to recognize and use acoustic patterns as cues for actions, as well as to synthesize new actions from novel paths through its motion space.A key contribution of this paper is to demonstrate that by addressing the three problems of state, action, and state-action space discovery at the same time, the solution for each becomes easier. Finally, we articulate heuristics and design principles that make learning practical for synthetic characters.

/pdf/integrated-learning-for-interactive-synthetic-characters-44zcoi8wu0.pdf

Integrated learning for interactive synthetic characters

This paper describes a simple method of fast background subtraction based upon disparity verification that is invariant to arbitrarily rapid run-time changes in illumination. Using two or more cameras, the method requires the off-line construction of disparity fields mapping the primary background images. At runtime, segmentation is performed by checking background image to each of the additional auxiliary color intensity values at corresponding pixels. If more than two cameras are available, more robust segmentation can be achieved and, in particular, the occlusion shadows can be generally eliminated as well. Because the method only assumes fixed background geometry, the technique allows for illumination variation at runtime. Since no disparity search is performed, the algorithm is easily implemented in real-time on conventional hardware.

Fast Lighting Independent Background Subtraction

A new approach to the recognition of temporal behaviours and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference problem into two levels. The lower level is performed using standard independent probabilistic temporal event detectors such as hidden Markov models (HMMs) to propose candidate detections of low level temporal features. The outputs of these detectors provide the input stream for a stochastic context-free grammar parsing mechanism. The grammar and parser provide longer range temporal constraints, disambiguate uncertain low level detections, and allow the inclusion of a priori knowledge about the structure of temporal events in a given domain. To achieve such a system we provide techniques for generating a discrete symbol stream from continuous low level detectors and for enforcing temporal exclusion constraints during parsing. We demonstrate the approach in several experiments using both visual and other sensing data.

/pdf/action-recognition-using-probabilistic-parsing-3qdogzktef.pdf

Yuri A. Ivanov

Papers

Recognition of visual activities and interactions by stochastic parsing

The KidsRoom: A Perceptually-Based Interactive and Immersive Story Environment

Integrated learning for interactive synthetic characters

Fast Lighting Independent Background Subtraction

Action recognition using probabilistic parsing