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 presents a technique for motion detection that incorporates several innovative mechanisms. For example, our proposed technique stores, for each pixel, a set of values taken in the past at the same location or in the neighborhood. It then compares this set to the current pixel value in order to determine whether that pixel belongs to the background, and adapts the model by choosing randomly which values to substitute from the background model. This approach differs from those based upon the classical belief that the oldest values should be replaced first. Finally, when the pixel is found to be part of the background, its value is propagated into the background model of a neighboring pixel. We describe our method in full details (including pseudo-code and the parameter values used) and compare it to other background subtraction techniques. Efficiency figures show that our method outperforms recent and proven state-of-the-art methods in terms of both computation speed and detection rate. We also analyze the performance of a downscaled version of our algorithm to the absolute minimum of one comparison and one byte of memory per pixel. It appears that even such a simplified version of our algorithm performs better than mainstream techniques.

/pdf/vibe-a-universal-background-subtraction-algorithm-for-video-3hbi5ckurx.pdf

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

http://www.bioimageanalysis.org/wp/wp-content/uploads/formidable/Survey_unsupervisedEvaluation.pdf

Image segmentation evaluation: A survey of unsupervised methods

Change detection is one of the most commonly encountered low-level tasks in computer vision and video processing. A plethora of algorithms have been developed to date, yet no widely accepted, realistic, large-scale video dataset exists for benchmarking different methods. Presented here is a unique change detection benchmark dataset consisting of nearly 90,000 frames in 31 video sequences representing 6 categories selected to cover a wide range of challenges in 2 modalities (color and thermal IR). A distinguishing characteristic of this dataset is that each frame is meticulously annotated for ground-truth foreground, background, and shadow area boundaries — an effort that goes much beyond a simple binary label denoting the presence of change. This enables objective and precise quantitative comparison and ranking of change detection algorithms. This paper presents and discusses various aspects of the new dataset, quantitative performance metrics used, and comparative results for over a dozen previous and new change detection algorithms. The dataset, evaluation tools, and algorithm rankings are available to the public on a website1 and will be updated with feedback from academia and industry in the future.

/pdf/changedetection-net-a-new-change-detection-benchmark-dataset-40tofje93g.pdf

Changedetection.net: A new change detection benchmark dataset

The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 62 trackers are presented. The number of tested trackers makes VOT 2015 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2015 challenge that go beyond its VOT2014 predecessor are: (i) a new VOT2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2014 evaluation methodology by introduction of a new performance measure. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.

/pdf/the-visual-object-tracking-vot2015-challenge-results-21ckmkuglu.pdf

The Visual Object Tracking VOT2015 Challenge Results

Background subtraction is a crucial step in many automatic video content analysis applications. While numerous acceptable techniques have been proposed so far for background extraction, there is still a need to produce more efficient algorithms in terms of adaptability to multiple environments, noise resilience, and computation efficiency. In this paper, we present a powerful method for background extraction that improves in accuracy and reduces the computational load. The main innovation concerns the use of a random policy to select values to build a samples-based estimation of the background. To our knowledge, it is the first time that a random aggregation is used in the field of background extraction. In addition we propose a novel policy that propagates information between neighboring pixels of an image. Experiment detailed in this paper show how our method improves on other widely used techniques, and how it outperforms these techniques for noisy images.

/pdf/vibe-a-powerful-random-technique-to-estimate-the-background-4xfdvin75r.pdf

ViBE: A powerful random technique to estimate the background in video sequences

This paper presents an innovative method to interpret the content of a video scene using a depth camera. Cameras that provide distance instead of color information are part of a promising young technology but they come with many difficulties: noisy signals, small resolution, and ambiguities, to cite a few.

By taking advantage of the robustness to noise of a recent background subtraction algorithm, our method is able to extract useful information from the depth signals. We further enhance the robustness of the algorithm by combining this information with that of an RGB camera. In our experiments, we demonstrate this increased robustness and conclude by showing a practical example of an immersive application taking advantage of our algorithm.

Combining Color, Depth, and Motion for Video Segmentation

Frontal-view gait recognition by intra- and inter-frame rectangle size distribution

The present invention relates to a Visual Background Extractor (VIBE) consisting in a method for detecting a background in an image selected from a plurality of related images. Each one of said set of images is formed by a set of pixels, and captured by an imaging device. This background detection method comprising the steps of: establishing, for a determined pixel position in said plurality of images, a background history comprising a plurality of addresses, in such a manner as to have a sample pixel value stored in each address; comparing the pixel value corresponding to said determined pixel position in the selected image with said background history, and, if said pixel value from the selected image substantially matches at least a predetermined number of said sample pixel values: classifying said determined pixel position as belonging to the image background; and—updating said background history by replacing the sample pixel values in one randomly chosen address of said background history with said pixel value from the selected image. The method of the invention is applicable a.o. for video surveillance purposes, videogame interaction and imaging devices with embedded data processors.

Olivier Barnich

Papers

ViBe: A Universal Background Subtraction Algorithm for Video Sequences

ViBE: A powerful random technique to estimate the background in video sequences

Combining Color, Depth, and Motion for Video Segmentation

Frontal-view gait recognition by intra- and inter-frame rectangle size distribution

Visual background extractor