Search

There is a large variety of trackers, which have been proposed in the literature during the last two decades with some mixed success. Object tracking in realistic scenarios is a difficult problem, therefore, it remains a most active area of research in computer vision. A good tracker should perform well in a large number of videos involving illumination changes, occlusion, clutter, camera motion, low contrast, specularities, and at least six more aspects. However, the performance of proposed trackers have been evaluated typically on less than ten videos, or on the special purpose datasets. In this paper, we aim to evaluate trackers systematically and experimentally on 315 video fragments covering above aspects. We selected a set of nineteen trackers to include a wide variety of algorithms often cited in literature, supplemented with trackers appearing in 2010 and 2011 for which the code was publicly available. We demonstrate that trackers can be evaluated objectively by survival curves, Kaplan Meier statistics, and Grubs testing. We find that in the evaluation practice the F-score is as effective as the object tracking accuracy (OTA) score. The analysis under a large variety of circumstances provides objective insight into the strengths and weaknesses of trackers. [ABSTRACT FROM AUTHOR]

This paper conceives of tracking as the developing distinction of a foreground against the background. In this manner, fast changes in the object or background appearance can be dealt with. When modelling the target alone (and not its distinction from the background), changes of lighting or changes of viewpoint can invalidate the internal target model. As the main contribution, we propose a new model for the detection of the target using foreground/background texture discrimination. The background is represented as a set of texture patterns. During tracking, the algorithm maintains a set of discriminant functions each distinguishing one pattern in the object region from background patterns in the neighborhood of the object. The idea is to train the foreground/background discrimination dynamically, that is while the tracking develops. In our case, the discriminant functions are efficiently trained online using a differential version of Linear Discriminant Analysis (LDA). Object detection is performed by maximizing the sum of all discriminant functions. The method employs two complementary sources of information: it searches for the image region similar to the target object, and simultaneously it seeks to avoid background patterns seen before. The detection result is therefore less sensitive to sudden changes in the appearance of the object than in methods relying solely on similarity to the target. The experiments show robust performance under severe changes of viewpoint or abrupt changes of lighting. [ABSTRACT FROM AUTHOR]

We propose a new method for object tracking in image sequences using template matching. To update the template, appearance features are smoothed temporally by robust Kalman filters, one to each pixel. The resistance of the resulting template to partial occlusions enables the accurate detection and handling of more severe occlusions. Abrupt changes of lighting conditions can also be handled, especially when photometric invariant color features are used. The method has only a few parameters and is computationally fast enough to track objects in real time. [ABSTRACT FROM AUTHOR]

We present the ALOI collection of 1,000 objects recorded under various imaging circumstances. In order to capture the sensory variation in object recordings, we systematically varied viewing angle, illumination angle, and illumination color for each object, and additionally captured wide-baseline stereo images. We recorded over a hundred images of each object, yielding a total of 110,250 images for the collection. These images are made publicly available for scientific research purposes. [ABSTRACT FROM AUTHOR]

Multimedia event detection (MED) is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition. Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. SESAME's performance in the 2012 TRECVID MED evaluation was one of the best reported. [ABSTRACT FROM AUTHOR]