Occlusion and Motion Reasoning for Long-Term Tracking

Yang, Hua; Alahari, Karteek; Schmid, Cordelia

doi:10.1007/978-3-319-10599-4_12

Cited by 61 publications

(44 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that ALE is not scale-invariant [? ] and that it is thus not generally possible to perform ROC analysis using object-based metrics (as the false-positive rate cannot be computed) [4]. Therefore, in accordance with [4, 5, ?…”

Section: Resultsmentioning

confidence: 99%

Hybrid Retargeting for High-Speed Targeted Optical Biopsies

Mouton

Lacombe

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. With the increasing maturity of optical biopsy techniques, routine clinical use has become more widespread. This wider adoption of the technique demands effective tracking and retargeting of the biopsy sites, as no visible markers are left following examination. This study presents a high-speed framework for intra-procedural retargeting of probebased optical biopsies in gastrointestinal endoscopy. A probe tip localisation method using active shape models and geometric heuristics, which eliminates the traditional dependency on shaft visibility, is proposed for automated initialisation. Partial occlusion and tissue deformation are addressed by exploiting the benefits of indirect and direct tracking through a novel combination of geometric association and online learning. Robustness to rapid endoscope motion and improvements in computational efficiency are achieved by restricting processing to the automatically detected video content area and through a feature-based rejection of non-informative frames. Performance evaluation in phantom and in-vivo environments demonstrates accurate biopsy site initialisation, robust retargeting and significant improvements over the state-of-the-art in processing time and memory usage.

show abstract

Section: Resultsmentioning

confidence: 99%

Hybrid Retargeting for High-Speed Targeted Optical Biopsies

Mouton

Lacombe

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…CFT approaches, e.g., [19,21,27,50], can be considered as an extension of the categoryfree single target approaches to the MOT setting. In the single target case, the initial target bounding box is given as input, and a specialized tracker is learned on-line, e.g., via the Track-Learn-Detect approach [24].…”

Section: Related Workmentioning

confidence: 99%

Online Domain Adaptation for Multi-Object Tracking

Gaidon¹,

Vig²

2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

Automatically detecting, labeling, and tracking objects in videos depends first and foremost on accurate category-level object detectors. These might, however, not always be available in practice, as acquiring high-quality large scale labeled training datasets is either too costly or impractical for all possible real-world application scenarios. A scalable solution consists in re-using object detectors pre-trained on generic datasets. This work is the first to investigate the problem of on-line domain adaptation of object detectors for causal multi-object tracking (MOT). We propose to alleviate the dataset bias by adapting detectors from category to instances, and back: (i) we jointly learn all target models by adapting them from the pre-trained one, and (ii) we also adapt the pre-trained model on-line. We introduce an on-line multi-task learning algorithm to efficiently share parameters and reduce drift, while gradually improving recall. Our approach is applicable to any linear object detector, and we evaluate both cheap "mini-Fisher Vectors" and expensive "off-the-shelf" ConvNet features. We quantitatively measure the benefit of our domain adaptation strategy on the KITTI tracking benchmark and on a new dataset (PASCAL-to-KITTI) we introduce to study the domain mismatch problem in MOT.

show abstract

“…Besides model fusion, the motion trajectory can be also used for more robust tracking. Hua et al [18] proposed a principled way to combine occlusion and motion reasoning, which is based on long-term trajectories labeled as object or background tracks modeled by an energy formulation. In Hua's tracking scheme, the occlusions can be identified by the overlap between labeled tracks and detected regions.…”

Section: Introductionmentioning

confidence: 99%

Bayesian tracking fusion framework with online classifier ensemble for immersive visual applications

Zhang

Zhuo

Zhang

et al. 2015

Multimed Tools Appl

View full text Add to dashboard Cite

During the last decade, the development of the immersive virtual reality (VR) has achieved a great progress in different application areas. For more advanced large-scale immersive VR environments or systems, one of the most challenge is to accurately track the position of the user's body part such as head when he/she is immersived in the environment to feel the changes among the synthetic stereoscopic image sequences. Unfortunately, accurate tracking is not easy in the virtual reality scenarios due to the variety types of existing intrinsic and extrinsic changes when tracking is on-the-fly. Especially for the single tracker, a long time accurate tracking is usually not possible because of the model adaption problem in different environments. Recent trend of research in tracking is to incorporate multiple trackers into a compositive learning framework and utilize the advantages of different trackers for more effective tracking. Therefore, in this paper, we propose a novel Bayesian tracking fusion framework with online classifier ensemble strategy. The proposed tracking formulates a fusion framework for online learning of multiple trackers by modeling a cumulative loss minimization process. With an optimal pair-wise sampling Multimed Tools Appl scheme for the SVM classifier, the proposed fusion framework can achieve more accurate tracking performance when compared with the other state-of-art trackers. In addition, the experiments on the standard benchmark database also verify that the proposed tracking is able to handle the challenges in many immersive VR applications and environments.

show abstract

Occlusion and Motion Reasoning for Long-Term Tracking

Cited by 61 publications

References 49 publications

Hybrid Retargeting for High-Speed Targeted Optical Biopsies

Hybrid Retargeting for High-Speed Targeted Optical Biopsies

Online Domain Adaptation for Multi-Object Tracking

Bayesian tracking fusion framework with online classifier ensemble for immersive visual applications

Contact Info

Product

Resources

About