Coloring Channel Representations for Visual Tracking

Danelljan, Martin; Hager, G; Khan, Fahad Shahbaz; Felsberg, Michael

doi:10.1007/978-3-319-19665-7_10

Cited by 23 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the CSK tracker only used greyscale features to train the filter, and this largely limited its performance. To overcome this disadvantage, Danelljan et al [21] integrated the image's color properties into the CSK tracker, and experiments showed that this method significantly improved its performance. Then, with the kernelized correlation filter (KCF)/discriminative correlation filter (DCF) tracker [22] designed by Henriques et al, the process of feature extraction was further optimized.…”

Section: Correlation-filter-based Trackersmentioning

confidence: 99%

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Xing

2020

Sensors

View full text Add to dashboard Cite

In the field of visual tracking, trackers based on a convolutional neural network (CNN) have had significant achievements. The fully-convolutional Siamese (SiamFC) tracker is a typical representation of these CNN trackers and has attracted much attention. It models visual tracking as a similarity-learning problem. However, experiments showed that SiamFC was not so robust in some complex environments. This may be because the tracker lacked enough prior information about the target. Inspired by the key idea of a Staple tracker and Kalman filter, we constructed two more models to help compensate for SiamFC’s disadvantages. One model contained the target’s prior color information, and the other the target’s prior trajectory information. With these two models, we design a novel and robust tracking framework on the basis of SiamFC. We call it Histogram–Kalman SiamFC (HKSiamFC). We also evaluated HKSiamFC tracker’s performance on dataset of the online object tracking benchmark (OTB) and Temple Color (TC128), and it showed quite competitive performance when compared with the baseline tracker and several other state-of-the-art trackers.

show abstract

Section: Correlation-filter-based Trackersmentioning

confidence: 99%

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Xing

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Thus, the result N d {x d } is a continuous feature map with a period of T to be used for further computation. CFWCR framework negates hand-crafted features such as HOG [18] and CN [19], and adopts CNN features to extract feature maps. Specifically, they use VGG-M [23] network pretrained on ILSVRC [24] dataset to extract multi-resolution continuous feature maps, and employ the first and the fifth convolutional layer as two deep feature channels.…”

Section: Base Frameworkmentioning

confidence: 99%

“…Kernelized correlation filter is proposed to get a multi-channel extension of linear correlation filters [9]. To integrate multi-resolution feature maps, continuous convolution operators for visual tracking are also proposed [4] and utilized by many state-of-the-art trackers, such as ECO [3] and CFWCR [12], among which CFWCR exploits the great power of deep convolutional neural networks (CNN) features without using any hand-crafted features such as HOG [18] or color names [19], and achieves great performance in both accuracy and robustness. Afterwards, there are also trackers focusing on foreground feature selection [14] and reliability learning [20].…”

Section: Introductionmentioning

confidence: 99%

Background perception for correlation filter tracker

Zhang

et al. 2020

J Wireless Com Network

View full text Add to dashboard Cite

Visual object tracking is one of the most fundamental tasks in the field of computer vision, and it has numerous applications in many realms such as public surveillance, human-computer interaction, robotics, etc. Recently, discriminative correlation filter (DCF)-based trackers have achieved promising results in short-term tracking problems. Most of them focus on extracting reliable features from the foreground of input images to construct a robust and informative description of the target. However, it is often ignored that the image background which contains the surrounding context of the target is often similar across consecutive frames and thus can be beneficial to locating the target. In this paper, we propose a background perception regulation term to additionally exploit useful background information of the target. Specifically, invalid description of the target can be avoided when either background or foreground information becomes unreliable by assigning similar importance to both of them. Moreover, a novel model update strategy is further proposed. Instead of updating the model by frame, we introduce an output evaluation score, which serves to supervise the tracking process and select high-confidence results for model update, thus paving a new way to avoid model corruption. Extensive experiments on OTB-100 dataset well demonstrate the effectiveness of the proposed method BPCF, which gets an AUC score of 0.689 and outperforms most of the state-of-the-art.

show abstract

“…Bolme et al [5] firstly introduce correlation filter into visual tracking with grayscale samples, keeping the object scale fixed in tracking . Afterwards, some methods [9,10,11,6,12,13] improve performance with the help of multi-channel features, such as HOG [14] or Color-Names [15]. KCF [6] and MKCF [13] make kernelized extensions of linear correlation filter to further improve the performance.…”

Section: Related Workmentioning

confidence: 99%

Region-filtering correlation tracking

Fan

et al. 2019

Knowledge-Based Systems

View full text Add to dashboard Cite

Recently, correlation filters have demonstrated the excellent performance in visual tracking. However, the base training sample region is larger than the object region, including the Interference Region (IR). The IRs in training samples from cyclic shifts of the base training sample severely degrade the quality of a tracking model. In this paper, we propose the novel Region-filtering Correlation Tracking (RFCT) to address this problem. We immediately filter training samples by introducing a spatial map into the standard CF formulation. Compared with existing correlation filter trackers, our proposed tracker has the following advantages: (1) The correlation filter can be learned on a larger search region without the interference of the IR by a spatial map. (2) Due to processing training samples by a spatial map, it is more general way to control background information and target information in training samples. The values of the spatial map are not restricted, then a better spatial map can be explored. (3) The weight proportions of accurate filters are increased to alleviate model corruption. Experiments are performed on two benchmark datasets: OTB-2013 and OTB-2015. Quantitative evaluations on these benchmarks demonstrate that the proposed RFCT algorithm performs favorably against several state-of-the-art methods.

show abstract

Coloring Channel Representations for Visual Tracking

Cited by 23 publications

References 31 publications

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter

Background perception for correlation filter tracker

Region-filtering correlation tracking

Contact Info

Product

Resources

About