Proceedings Article10.1109/CVPR.2017.62
Superpixel-Based Tracking-by-Segmentation Using Markov Chains
Donghun Yeo,Jeany Son,Bohyung Han,Joon Hee Han +3 more
- 01 Jul 2017
- pp 511-520
TL;DR: A simple but effective tracking-by-segmentation algorithm using Absorbing Markov Chain on superpixel segmentation, where target state is estimated by a combination of bottom-up and top-down approaches, and target segmentation is propagated to subsequent frames in a recursive manner.
read more
Abstract: We propose a simple but effective tracking-by-segmentation algorithm using Absorbing Markov Chain (AMC) on superpixel segmentation, where target state is estimated by a combination of bottom-up and top-down approaches, and target segmentation is propagated to subsequent frames in a recursive manner. Our algorithm constructs a graph for AMC using the superpixels identified in two consecutive frames, where background superpixels in the previous frame correspond to absorbing vertices while all other superpixels create transient ones. The weight of each edge depends on the similarity of scores in the end superpixels, which are learned by support vector regression. Once graph construction is completed, target segmentation is estimated using the absorption time of each superpixel. The proposed tracking algorithm achieves substantially improved performance compared to the state-of-the-art segmentation-based tracking techniques in multiple challenging datasets.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Fast Online Object Tracking and Segmentation: A Unifying Approach
Qiang Wang,Li Zhang,Luca Bertinetto,Weiming Hu,Philip H. S. Torr +4 more
- 01 Jun 2019
TL;DR: This method improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task, and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second.
Siam R-CNN: Visual Tracking by Re-Detection
Paul Voigtlaender,Jonathon Luiten,Philip H. S. Torr,Bastian Leibe +3 more
- 14 Jun 2020
TL;DR: This work presents Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking, and combines this with a novel tracklet-based dynamic programming algorithm to model the full history of both the object to be tracked and potential distractor objects.
Structured Siamese Network for Real-Time Visual Tracking
Yunhua Zhang,Lijun Wang,Jinqing Qi,Dong Wang,Mengyang Feng,Huchuan Lu +5 more
- 08 Sep 2018
TL;DR: A local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking and can be formulated as the inference process of a conditional random field and implemented by differentiable operations, allowing the entire model to be trained in an end-to-end manner.
Deep Learning for Visual Tracking: A Comprehensive Survey
TL;DR: In this paper , the authors systematically investigate the current DL-based visual tracking methods, benchmark datasets, and evaluation metrics, and extensively evaluate and analyzes the leading visual tracking algorithms.
303
Video Object Segmentation and Tracking: A Survey
TL;DR: This survey aims to provide a comprehensive review of the state-of-the-art VOST methods, classify these methods into different categories, and identify new trends.
165
References
Fully convolutional networks for semantic segmentation
Jonathan Long,Evan Shelhamer,Trevor Darrell +2 more
- 07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
TL;DR: A new superpixel algorithm is introduced, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels and is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
"GrabCut": interactive foreground extraction using iterated graph cuts
Carsten Rother,Vladimir Kolmogorov,Andrew Blake +2 more
- 01 Aug 2004
TL;DR: A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
Online Object Tracking: A Benchmark
Yi Wu,Jongwoo Lim,Ming-Hsuan Yang +2 more
- 23 Jun 2013
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.
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.
3.7K