There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object's location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector's errors and updates it to avoid these errors in the future. We study how to identify the detector's errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: (1) P-expert estimates missed detections, and (2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches.

Tracking-Learning-Detection

https://www.eecs.qmul.ac.uk/~andrea/papers/2009_NeuComp_AbnormalityNonLinearSubspace_Tziakos_Cavallaro_Xu.pdf

Event monitoring via local motion abnormality detection in non-linear subspace

We present a content-aware multi-camera selection technique that uses object- and frame-level features. First objects are detected using a color-based change detector. Next trajectory information for each object is generated using multi-frame graph matching. Finally, multiple features including size and location are used to generate an object score. At frame-level, we consider total activity, event score, number of objects and cumulative object score. These features are used to generate score information using a multivariate Gaussian distribution. The algorithm. The best view is selected using a Dynamic Bayesian Network (DBN), which utilizes camera network information. DBN employs previous view information to select the current view thus increasing resilience to frequent switching. The performance of the proposed approach is demonstrated on three multi-camera setups with semi-overlapping fields of view: a basketball game, an indoor airport surveillance scenario and a synthetic outdoor pedestrian dataset. We compare the proposed view selection approach with a maximum score based camera selection criterion and demonstrate a significant decrease in camera flickering. The performance of the proposed approach is also validated through subjective testing.

/pdf/content-and-task-based-view-selection-from-multiple-video-3iytxphdqz.pdf

Content and task-based view selection from multiple video streams

Robust multi-dimensional motion features for first-person vision activity recognition

We present an algorithm for the estimation of the relative camera position in a network of cameras with non-overlapping fields of view. The algorithm estimates the missing trajectory information in the unobserved areas of the multi-sensor configuration using both parametric and non-parametric algorithms. First, Kalman filtering is used to estimate the trajectories in the unobserved regions. Next, linear regression estimates the position of the target based upon the motion model generated from the measured positions in the field of view of each sensor. Finally, the relative orientation of the sensors is calculated using the observed and estimated target position from adjacent cameras. We demonstrate the algorithm on both synthetic and real data.

http://www.eecs.qmul.ac.uk/~andrea/papers/2007_ICASSP_CameraLocalization_Anjum_Cavallaro.pdf

Relative Position Estimation of Non-Overlapping Cameras

Advanced video surveillance applications require two successive phases: image analysis and content understanding. The first phase analyzes and extracts the characteristics of the video sequence. It defines the regions or the objects of interest according to their spatial/temporal properties. This image analysis results in a segmentation of the video sequence. This is interpreted by the content understanding phase according to the specific scenario and surveillance requirements. This paper addresses the image analysis problem for a video surveillance system. We apply a statistical model-based change detection technique that defines the areas of interest in the image. This method provides a reliable detection of the moving areas in the scene. It does not require fine tuning of any threshold along the sequence and it is computationally efficient. However, it is not able to provide an accurate spatial descriptions of the objects. In particular it fails in distinguishing shadows and reflections from real moving objects. In order to improve the spatial coherence of the change detection results, each area detected as changed is analyzed separately. Its spatial and temporal descriptors are integrated in a multi-feature clustering algorithm. This is able to distinguish the regions belonging to real objects from the regions representing their shadows and/or reflections. A successive refinement labels as background all those regions that are sufficiently similar to the background. The selective procedure we propose minimizes the computational load since only the changed areas in the image are processed. We test this method on both indoor and outdoor surveillance sequences. All the results show a correct segmentation of the scene. Moreover, each object defined in the segmentation is described in terms of its spatial and temporal properties. These results represent a valid input for a later content understanding procedure in several surveillance scenarios.

Andrea Cavallaro

Papers

Event monitoring via local motion abnormality detection in non-linear subspace

Content and task-based view selection from multiple video streams

Robust multi-dimensional motion features for first-person vision activity recognition

Relative Position Estimation of Non-Overlapping Cameras

Image Analysis for Video Surveillance Based on Spatial Regularization of a Statistical Model-Based Change Detection