SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking

Kim, Hanul; Lee, Dae-Youn; Sim, Jae-Young; Kim, Chang-Su

doi:10.1109/iccv.2015.345

Cited by 107 publications

(81 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our tracker achieves 36.7% gain in PR and 36.9% gain in SR over Struck [1]. By using a simple patch weighting strategy and training with adaptive scale samples, the performance shows that our tracker provides comparable PR scores, and higher SR score compared with SOWP [3]. PAWSSa tracker improves the SR score by 2.6% considering gradually small changes between frames, PAWSSb improves the SR score by 4.8% by incorporating scales estimated by the external KLT tracker.…”

Section: Online Tracking Benchmark (Otb)mentioning

confidence: 92%

“…2. Unlike the weighting strategy in [12,3] by analysing the similarities between neighbouring patches, our patch weighting method is simple and straightforward to implement, the weight update for each patch is independent from each other, and only relies on the colour histogram based segmentation model. We show examples of the patch weight evolvement in Figure 1.…”

Section: Probabilistic Segmentation Model For Patch Weightingmentioning

confidence: 99%

“…Tracking-by-detection is one of the highly successful paradigms for visual object tracking [1,2,3,4]. A typical tracking-by-detection algorithm treats the tracking problem as a classification task, it begins with a detector initialized with a bounding region in the first frame, and updates the detection model over time with collected positive and negative samples.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Patch-based adaptive weighting with segmentation and scale (PAWSS) for visual tracking in surgical video

Allan

Bodenstedt

et al. 2019

Medical Image Analysis

View full text Add to dashboard Cite

Tracking-by-detection algorithms are widely used for visual tracking, where the problem is treated as a classification task where an object model is updated over time using online learning techniques. In challenging conditions where an object undergoes deformation or scale variations, the update step is prone to include background information in the model appearance or to lack the ability to estimate the scale change, which degrades the performance of the classifier. In this paper, we incorporate a Patch-based Adaptive Weighting with Segmentation and Scale (PAWSS) tracking framework that tackles both the scale and background problems. A simple but effective colour-based segmentation model is used to suppress background information and multi-scale samples are extracted to enrich the training pool, which allows the tracker to handle both incremental and abrupt scale variations between frames. Experimentally, we evaluate our approach on the online tracking benchmark (OTB) dataset and Visual Object Tracking (VOT) challenge datasets. The results show that our approach outperforms recent state-of-the-art trackers, and it especially improves the successful rate score on the OTB dataset, while on the VOT datasets, PAWSS ranks among the top trackers while operating at real-time frame rates.

show abstract

Section: Online Tracking Benchmark (Otb)mentioning

confidence: 92%

Section: Probabilistic Segmentation Model For Patch Weightingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Patch-based adaptive weighting with segmentation and scale (PAWSS) for visual tracking in surgical video

Allan

Bodenstedt

et al. 2019

Medical Image Analysis

View full text Add to dashboard Cite

show abstract

“…For the past several decades, it has been common to use a form of well-studied target representations, such as points, lines, and target patches in tracking (Yilmaz et al, 2006, Zhang et al, 2014, Kim et al, 2015. Despite reported success in some benchmark sequences, these methods are sensitive to noise and background clutter.…”

Section: Related Workmentioning

confidence: 99%

“…These trackers can be categorized as either generative or discriminative which use appearance-based models to distinguish the target from the background. Researchers have also introduced sophisticated features and descriptors (Kim et al, 2015, Rublee et al, 2011, Zhang et al, 2014, yet there are still many issues in practical applications. The main limitation of these low-level hand-crafted features is that they only address the texture of the object which may frequently change.…”

Section: Introductionmentioning

confidence: 99%

Visual Tracking Utilizing Object Concept From Deep Learning Network

Xiao

Yilmaz

Lia

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Despite having achieved good performance, visual tracking is still an open area of research, especially when target undergoes serious appearance changes which are not included in the model. So, in this paper, we replace the appearance model by a concept model which is learned from large-scale datasets using a deep learning network. The concept model is a combination of high-level semantic information that is learned from myriads of objects with various appearances. In our tracking method, we generate the target's concept by combining the learned object concepts from classification task. We also demonstrate that the last convolutional feature map can be used to generate a heat map to highlight the possible location of the given target in new frames. Finally, in the proposed tracking framework, we utilize the target image, the search image cropped from the new frame and their heat maps as input into a localization network to find the final target position. Compared to the other state-of-the-art trackers, the proposed method shows the comparable and at times better performance in real-time.

show abstract