Journal ArticleDOI
Occlusion-Aware Real-Time Object Tracking
Reads0
Chats0
TLDR
A new real-time occlusion-aware visual tracking algorithm that achieves better performance than state-of-the-art methods based on a novel two-stage classifier with circulant structure with kernel, named integrated circulan structure kernels (ICSK).Abstract:
The online learning methods are popular for visual tracking because of their robust performance for most video sequences. However, the drifting problem caused by noisy updates is still a challenge for most highly adaptive online classifiers. In visual tracking, target object appearance variation, such as deformation and long-term occlusion, easily causes noisy updates. To overcome this problem, a new real-time occlusion-aware visual tracking algorithm is introduced. First, we learn a novel two-stage classifier with circulant structure with kernel, named integrated circulant structure kernels (ICSK). The first stage is applied for transition estimation and the second is used for scale estimation. The circulant structure makes our algorithm realize fast learning and detection. Then, the ICSK is used to detect the target without occlusion and build a classifier pool to save these classifiers with noisy updates. When the target is in heavy occlusion or after long-term occlusion, we redetect it using an optimal classifier selected from the classifier-pool according to an entropy minimization criterion. Extensive experimental results on the full benchmark demonstrate our real-time algorithm achieves better performance than state-of-the-art methods.read more
Citations
More filters
Proceedings ArticleDOI
Tracking rapid body deformation using sparse representation of deep features
TL;DR: A framework based on sparse representation using dictionary learning which identifies humans in low-resolution videos despite rapid deformations to the body shape is proposed and it is shown that human representation, using deep features obtained using a convolutional neural network, remains sparse even during highly articulated motion.
Proceedings ArticleDOI
HOOT: Heavy Occlusions in Object Tracking Benchmark
TL;DR: The HOOT dataset as discussed by the authors is a large dataset for visual object tracking with high occlusion levels, where the median percentage of occluded frames per-video is 68%.
Journal ArticleDOI
High-precision and real-time visual tracking algorithm based on the Siamese network for autonomous driving
Journal ArticleDOI
Sparse Regularized Correlation Filter for UAV Object Tracking with adaptive Contextual Learning and Keyfilter Selection
TL;DR:
Journal ArticleDOI
Selective Video Object Cutout
TL;DR: Huang et al. as discussed by the authors presented a pyramid histogram based confidence map that incorporates structure information into appearance statistics and employed an efficient measure of uncertainty propagation using local classifiers to determine the image regions where the object labels might be ambiguous.
References
More filters
Journal ArticleDOI
High-Speed Tracking with Kernelized Correlation Filters
TL;DR: A new kernelized correlation filter is derived, that unlike other kernel algorithms has the exact same complexity as its linear counterpart, which is called dual correlation filter (DCF), which outperform top-ranking trackers such as Struck or TLD on a 50 videos benchmark, despite being implemented in a few lines of code.
Proceedings ArticleDOI
Online Object Tracking: A Benchmark
TL;DR: Large scale experiments are carried out with various evaluation criteria to identify effective approaches for robust tracking and provide potential future research directions in this field.
Journal ArticleDOI
Tracking-Learning-Detection
TL;DR: A novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection, and develops a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: P-expert estimates missed detections, and N-ex Expert estimates false alarms.
Proceedings ArticleDOI
Visual object tracking using adaptive correlation filters
TL;DR: A new type of correlation filter is presented, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame, which enables the tracker to pause and resume where it left off when the object reappears.
Book ChapterDOI
Exploiting the circulant structure of tracking-by-detection with kernels
TL;DR: Using the well-established theory of Circulant matrices, this work provides a link to Fourier analysis that opens up the possibility of extremely fast learning and detection with the Fast Fourier Transform, which can be done in the dual space of kernel machines as fast as with linear classifiers.