author={Zdenek Kalal},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Zdenek Kalal
  • Published 1 July 2012
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
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… 
A novel framework for robust long-term object tracking in real-time
An intelligent framework to integrate a tracker and detector is proposed, wherein the tracker module is used to validate the output of the detector with online learning and a correlation filter-based tracker and a cascaded detector are utilized to implement a robust long-term tracking algorithm.
Drift-Free Tracking Surveillance Based on Online Latent Structured SVM and Kalman Filter Modules
This work improves the latent structured support vector machine (SVM) tracker by designing a more robust tracker update step by incorporating two Kalman filter modules, and proposes a hierarchical search strategy that combines Bhattacharyya coefficient similarity analysis and Kalman predictors.
e-TLD: Event-Based Framework for Dynamic Object Tracking
This paper presents a long-term object tracking framework with a moving event camera under general tracking conditions. A first of its kind for these revolutionary cameras, the tracking framework
RobStruck: Improving occlusion handling of structured tracking-by-detection using robust Kalman filter
This work extends the Struck tracker, which is based on structured SVM, to output bounding boxes at multiple scales and uses the Robust Kalman filter to decrease false-positive detections and to increase the tracker resilience to short-time occlusions.
A Bayesian Approach to Tracking Learning Detection
A novel framework based on Tracking-Learning-Detection (TLD), that combine bayesian optimal filtering with pn on-line learning theory to adapt target visual likelihood during tracking, is described.
Learning to Track Multiple Targets
A novel learning framework for tracking multiple objects by detection is proposed, instead of heuristically defining a tracking algorithm, that a discriminative structure prediction model from labeled video data captures the interdependence of multiple influence factors.
Long-term object tracking with a moving event camera
This paper presents a long-term object tracking algorithm for event cameras. A first of its kind for these revolutionary cameras, the tracking framework uses a discriminative representation for the
Independent selection and validation for tracking-learning-detection
This work proposes a mediator method to integrate the motion tracker and detector by combining their estimations and shows that when the mediaton strategy is independent of both tracker/detector metrics, the overall tracking is improved for objects with high appearance variations throughout the video.
Occlusion and Motion Reasoning for Long-Term Tracking
Experimental results show that the proposed principled way to combine occlusion and motion reasoning with a tracking-by-detection approach obtains state-of-the-art results and handles occlusions and viewpoints changes better than competing tracking methods.


Online learning of robust object detectors during unstable tracking
This work proposes a new approach, called Tracking-Modeling-Detection (TMD), that closely integrates adaptive tracking with online learning of the object-specific detector and shows the real-time learning and classification is achievable with random forests.
Object tracking: A survey
The goal of this article is to review the state-of-the-art tracking methods, classify them into different categories, and identify new trends to discuss the important issues related to tracking including the use of appropriate image features, selection of motion models, and detection of objects.
Visual tracking with online Multiple Instance Learning
It is shown that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems, and can therefore lead to a more robust tracker with fewer parameter tweaks.
Robust tracking-by-detection using a detector confidence particle filter
A novel approach for multi-person tracking-by-detection in a particle filtering framework that uses the continuous confidence of pedestrian detectors and online trained, instance-specific classifiers as a graded observation model, which relies only on information from the past and is suitable for online applications.
Context-Aware Visual Tracking
A novel solution to this dilemma by considering the context of the tracking scene by integrating into the tracking process a set of auxiliary objects that are automatically discovered in the video on the fly by data mining.
Incremental Learning for Robust Visual Tracking
A tracking method that incrementally learns a low-dimensional subspace representation, efficiently adapting online to changes in the appearance of the target, and includes a method for correctly updating the sample mean and a forgetting factor to ensure less modeling power is expended fitting older observations.
Coupled Detection and Trajectory Estimation for Multi-Object Tracking
We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. It is formulated in a hypothesis
Feature Harvesting for Tracking-by-Detection
A fast approach to 3–D object detection and pose estimation that owes its robustness to a training phase during which the target object slowly moves with respect to the camera, using a Randomized Tree-based approach to wide-baseline feature matching.
Sparse Bayesian learning for efficient visual tracking
This paper builds a displacement expert which directly estimates displacement from the target region and is demonstrated in real-time tracking systems where the sparsity of the RVM means that only a fraction of CPU time is required to track at frame rate.
Beyond semi-supervised tracking: Tracking should be as simple as detection, but not simpler than recognition
  • S. Stalder, H. Grabner, L. Gool
  • Computer Science
    2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops
  • 2009
A multiple classifier system for model-free tracking that outperforms other on-line tracking methods especially in case of occlusions and presence of similar objects.