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

Perspective deformations on the image plane make the analysis of object behaviors difficult in surveillance video. In this paper, we improve the results of trajectory-based scene analysis by using single camera calibration for perspective rectification. First, the ground-plane view is estimated from perspective images captured from a single camera. Next, unsupervised fuzzy clustering is applied on the transformed trajectories to group similar behaviors and to isolate outliers. We evaluate the proposed approach on real outdoor surveillance scenarios with standard datasets and show that perspective rectification improves the accuracy of the trajectory clustering results.

/pdf/single-camera-calibration-for-trajectory-based-behavior-3ji7keli9h.pdf

Single camera calibration for trajectory-based behavior analysis

This document presents the video data set that has been recently collected within the FP7 APIDIS project [1]. The acquisition setting was deployed around a basket-ball court, and consists in a set of 7 calibrated IP cameras, each one collecting 2 Mpixels frames at a rate higher than 20 frames/sec. After an approximate temporal synchronization of the video streams and the definition of an homography to link the ground points in every views, the video data have been augmented through the definition and collection of metadata. Those metadata are expected to support efficient browsing of the content, and automatic personalized summarization of the event captured by the distributed set of cameras. Metadata include (1) low-level feature distributions, (2) object trajectories, and (3) events of interest attributes. The data and metadata are publicly available upon email request to the APIDIS partners.

Distributed video acquisition and annotation for sport-event summarization

This paper presents a centralized algorithm for multi-scale observation of multiple moving targets using a team of Micro Aerial Vehicles (MAVs). The proposed algorithm is appropriate when MAVs can observe targets at different elevations with the objective of jointly maximizing duration and resolution of observation for each target. The MAVs share the workload using a greedy assignment of locations and targets to MAVs. The proposed algorithm uses a quad-tree data structure to model the movement decisions of MAVs as well as the variable qualities (resolutions) of observations. We consider cases where there is uncertainty in the target observations (i.e., measurement noise), the number of targets is larger than that of the MAVs and the combined field of views (FOVs) of the sensors cannot cover the whole search region. Simulation results confirm the effectiveness of the proposed algorithm.

Multiscale observation of multiple moving targets using Micro Aerial Vehicles

We present a full-reference and a no-reference perceptual video quality metric that incorporate both low-level and high-level aspects of vision. Low-level aspects include color perception, contrast sensitivity, masking as well as artifact analysis. High-level aspects take into account the cognitive behavior of an observer when watching a video by means of semantic segmentation. Using the special case of semantic face segmentation, we evaluate the proposed segmentation-driven perceptual quality metrics using a range of test sequences and demonstrate an improvement of their prediction performance.

/pdf/segmentation-driven-perceptual-quality-metrics-tujkj7s0ti.pdf

Segmentation-driven perceptual quality metrics

Images shared on social media are routinely analysed by classifiers for content annotation and user profiling. These automatic inferences reveal to the service provider sensitive information that a naive user might want to keep private. To address this problem, we present a method designed to distort the image data so as to hinder the inference of a classifier without affecting the utility for social media users. The proposed approach is based on the Fast Gradient Sign Method (FGSM) and limits the likelihood that automatic inference can expose the true class of a distorted image. Experimental results on a scene classification task show that the proposed method, private FGSM, achieves a desirable trade-off between the drop in classification accuracy and the distortion on the private classes of the Places365-Standard dataset using ResNet50. The classifier is misled 94.40% of the times in the top-5 classes with only a small average reduction of three image quality measures (SSIM, PSNR, BRISQUE).

Andrea Cavallaro

Papers

Single camera calibration for trajectory-based behavior analysis

Distributed video acquisition and annotation for sport-event summarization

Multiscale observation of multiple moving targets using Micro Aerial Vehicles

Segmentation-driven perceptual quality metrics

Scene Privacy Protection