Patch Based Multiple Instance Learning Algorithm for Object Tracking

Wang, Zhenjie; Wang, Lijia; Zhang, Hua

doi:10.1155/2017/2426475

Cited by 6 publications

(6 citation statements)

References 18 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many computer visions tasks where MIL is being used for example object detection [182], face detection [68] and action recognition [6]. Various researcher have employed MIL to track targets [1], [10], [140], [160], [165], [169]. Babenko et al [10] proposed a novel MIL Boosting (MILBoost) algorithm to label ambiguity of instances using Haar features.…”

Section: Multiple Instance Learning Based Trackermentioning

confidence: 99%

Tracking Noisy Targets: A Review of Recent Object Tracking Approaches

Fiaz¹,

Mahmood²,

Jung³

2018

Preprint

View full text Add to dashboard Cite

Visual object tracking is an important computer vision problem with numerous real-world applications including human-computer interaction, autonomous vehicles, robotics, motion-based recognition, video indexing, surveillance and security. In this paper, we aim to extensively review the latest trends and advances in the tracking algorithms and evaluate the robustness of trackers in the presence of noise. The first part of this work comprises a comprehensive survey of recently proposed tracking algorithms. We broadly categorize trackers into correlation filter based trackers and the others as noncorrelation filter trackers. Each category is further classified into various types of trackers based on the architecture of the tracking mechanism. In the second part of this work, we experimentally evaluate tracking algorithms for robustness in the presence of additive white Gaussian noise. Multiple levels of additive noise are added to the Object Tracking Benchmark (OTB) 2015, and the precision and success rates of the tracking algorithms are evaluated. Some algorithms suffered more performance degradation than others, which brings to light a previously unexplored aspect of the tracking algorithms. The relative rank of the algorithms based on their performance on benchmark datasets may change in the presence of noise. Our study concludes that no single tracker is able to achieve the same efficiency in the presence of noise as under noise-free conditions; thus, there is a need to include a parameter for robustness to noise when evaluating newly proposed tracking algorithms.

show abstract

Section: Multiple Instance Learning Based Trackermentioning

confidence: 99%

Tracking Noisy Targets: A Review of Recent Object Tracking Approaches

Fiaz¹,

Mahmood²,

Jung³

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…KCF [71] CF2 [114] HCFT* [113] HDT [130] LCT [116] ILCT [115] MCPF [195] fDSST [34] STAPLE [12] LMCF [156] RAJSSC [188] JSSC [187] CREST [142] PTAV [45] MUSTer [72] DNT [26] STCT [157] SRDCF [36] deepSRDCF [35] SRDCFdecon [37] MRCT-AS [73] CCOT [38] ECO [33] BACF [77] CSRDCF [111] CACF [121] STRCF [97] SCT [29] ACFN [27] DMSRDCF [56] SiameseFC [13] CFNet [148] DCFNet [158] Dsiam [64] EAST [74] SINT [145] SINT++ [160] YCNN [20] GOTURN [69] RDM [30] MILTrack [9] FMIL [166] CMIL [1] PMIL [161] CSR [139] Yang's MIL [168] SST [194] RSST [196] CLRST …”

Section: Graph Based Trackersmentioning

confidence: 99%

“…Multiple-Instance-Learning (MIL) was introduced by Dietterich and is widely used in many computer visions tasks where MIL is being used for example object detection [182], face detection [61] and action recognition [6]. Various researcher have employed MIL to track targets [1,9,139,161,166,168]. In MIL based tracking, training samples are placed in bags instead of considering individual patches, and labels are given at bags level.…”

Section: Multiple-instance-learning Basedmentioning

confidence: 99%

See 1 more Smart Citation

Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends

Fiaz¹,

Mahmood²,

Javed³

et al. 2018

Preprint

View full text Add to dashboard Cite

In recent years visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year. It is because tracking has wide applications in various real world problems such as humancomputer interaction, autonomous vehicles, robotics, surveillance and security just to name a few. In the current study, we review latest trends and advances in the tracking area and evaluate the robustness of di erent trackers based on the feature extraction methods. e rst part of this work comprises a comprehensive survey of the recently proposed trackers. We broadly categorize trackers into Correlation Filter based Trackers (CFTs) and Non-CFTs. Each category is further classi ed into various types based on the architecture and the tracking mechanism. In the second part, we experimentally evaluated 24 recent trackers for robustness, and compared handcra ed and deep feature based trackers. We observe that trackers using deep features performed be er, though in some cases a fusion of both increased performance signi cantly. In order to overcome the drawbacks of the existing benchmarks, a new benchmark Object Tracking and Temple Color (OTTC) has also been proposed and used in the evaluation of di erent algorithms. We analyze the performance of trackers over eleven di erent challenges in OTTC, and three other benchmarks. Our study concludes that Discriminative Correlation Filter (DCF) based trackers perform be er than the others. Our study also reveals that inclusion of di erent types of regularizations over DCF o en results in boosted tracking performance. Finally, we sum up our study by pointing out some insights and indicating future trends in visual object tracking eld.

show abstract

“…The development of face tracking system based on this work was proposed by [5]. Recently, Wang et al [6] proposed multiple instance learning based on the use of a patch, where an object is divided into many blocks. Unfortunately, extensive experiments using a benchmark dataset have not been performed on their research.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Shallow Features for Performance Improvement of Histogram of Oriented Gradients in Visual Object Tracking

Wibowo

Lee

Kim

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Histogram of oriented gradients (HOG) is a feature descriptor typically used for object detection. For object tracking, this feature has certain drawbacks when the target object is influenced by a change in motion or size. In this paper, the use of convolutional shallow features is proposed to improve the performance of HOG feature-based object tracking. Because the proposed method works based on a correlation filter, the response maps for each feature are summed in order to obtain the final response map. The location of the target object is then predicted based on the maximum value of the optimized final response map. Further, a model update is used to overcome the change in appearance of the target object during tracking. A performance evaluation of the proposed method is obtained by using Visual Object Tracking 2015 (VOT2015) benchmark dataset and its protocols. The results are then provided based on their accuracy-robustness (AR) rank. Furthermore, through a comparison with several state-of-the-art tracking algorithms, the proposed method was shown to achieve the highest rank in terms of accuracy and a third rank for robustness. In addition, the proposed method significantly improves the robustness of HOG-based features.

show abstract

Patch Based Multiple Instance Learning Algorithm for Object Tracking

Cited by 6 publications

References 18 publications

Tracking Noisy Targets: A Review of Recent Object Tracking Approaches

Tracking Noisy Targets: A Review of Recent Object Tracking Approaches

Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends

Convolutional Shallow Features for Performance Improvement of Histogram of Oriented Gradients in Visual Object Tracking

Contact Info

Product

Resources

About