Fusing Kalman filter with TLD algorithm for target tracking

Sun, Chuen-Tsai; Zhu, Shiping; Liu, Jiawei

doi:10.1109/chicc.2015.7260218

Cited by 14 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the proposed method with the following state-of-the-art trackers: Struck [12], TLD combined with KF (TLD-KF) [31], real-time compressive tracking (RTCT) [35], and tracking with kernelized correlation filters (KCF) [37]. The original source codes of these trackers were downloaded from online websites [46]- [49].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Drift-Free Tracking Surveillance Based on Online Latent Structured SVM and Kalman Filter Modules

Chen

Zhang

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYTracking-by-detection methods consider tracking task as a continuous detection problem applied over video frames. Modern trackingby-detection trackers have online learning ability; the update stage is essential because it determines how to modify the classifier inherent in a tracker. However, most trackers search for the target within a fixed region centered at the previous object position; thus, they lack spatiotemporal consistency. This becomes a problem when the tracker detects an incorrect object during short-term occlusion. In addition, the scale of the bounding box that contains the target object is usually assumed not to change. This assumption is unrealistic for long-term tracking, where the scale of the target varies as the distance between the target and the camera changes. The accumulation of errors resulting from these shortcomings results in the drift problem, i.e. drifting away from the target object. To resolve this problem, we present a drift-free, online learning-based tracking-by-detection method using a single static camera. We improve the latent structured support vector machine (SVM) tracker by designing a more robust tracker update step by incorporating two Kalman filter modules: the first is used to predict an adaptive search region in consideration of the object motion; the second is used to adjust the scale of the bounding box by accounting for the background model. We propose a hierarchical search strategy that combines Bhattacharyya coefficient similarity analysis and Kalman predictors. This strategy facilitates overcoming occlusion and increases tracking efficiency. We evaluate this work using publicly available videos thoroughly. Experimental results show that the proposed method outperforms the state-of-theart trackers. key words: object tracking, support vector machine (SVM), latent structured SVM, online learning, Kalman filter, hierarchical search

show abstract

Section: Resultsmentioning

confidence: 99%

“…Ven et al [30] proposed a multitarget tracker based on multi-PN learning, in which the dissimilarities and relations of tracked objects are incorporated. Sun et al [31] combined TLD with KF to enhance the reliability of the TLD approach.…”

Section: Related Workmentioning

confidence: 99%

Drift-Free Tracking Surveillance Based on Online Latent Structured SVM and Kalman Filter Modules

Chen

Zhang

2018

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The authors suggest that in addition to the mean value, the standard deviation (STD) and the distribution of RSS should be included. Sun and Zhu [30] put forward a hybrid filter algorithm based on the mean filter, median filter and Gaussian filter and RSS data are optimized by using this algorithm. Zhang et al [31] first analyze the influence of the environment on RSS and then the performances of three experimental data processing methods are compared; the Gaussian filter algorithm is considered to be the best.…”

Section: Related Workmentioning

confidence: 99%

A new Wi-Fi dynamic selection of nearest neighbor localization algorithm based on RSS characteristic value extraction by hybrid filtering

Peng

Chen

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

Fingerprinting localization based on Wi-Fi received signal strength (RSS) is the most widely used indoor localization method. It typically includes offline training and online matching phases. The selection of the RSS characteristic value is a key step. The weighted K nearest neighbor (WKNN) algorithm is the most commonly used position-determination algorithm. The mean value of the RSS data collected over a time interval is usually taken as its characteristic value. However, the RSS measurements contain Gaussian and non-Gaussian noise, which cannot be filtered out effectively by the mean value method. The traditional WKNN algorithm adopts a fixed K . However, reference points far away from the test point (TP) may be selected as the nearest neighbors to participate in the position calculation, which may result in accuracy degradation. This paper proposes the weighted dynamic K nearest neighbor algorithm (WDKNN-HF), which utilizes a hybrid of particle filtering and Kalman filtering to extract the RSS characteristic value. In the online matching phase, a dynamic K matching algorithm based on Euclidean distances is developed to determine the coordinates of TPs. Two experiments are conducted in two different indoor scenes. Experimental results demonstrate that the proposed algorithm can obtain better positioning accuracy than existing algorithms, such as KNN, WKNN, enhanced-WKNN (EWKNN) and self-adaptive weighted K nearest neighbor (SAWKNN).

show abstract

“…To improve real-time performance, a concept of ROI is proposed in [9] which means that detection is only executed within the region of interest. For instance, [10] use Calman filter to predict the next region of detection, [11] adopts Pyramid LK optical flow method and [12] adds Meanshift algorithm to TLD to get the region of interest. All the method above can accelerate the process of the tracker.…”

Section: B Existing Defects and Possible Solutionsmentioning

confidence: 99%

An Improved TLD Tracking Algorithm for Fast-moving Object

Zhou¹,

Peng²,

Gong³

et al. 2018

Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)

View full text Add to dashboard Cite

Traditional object tracking is easily affected by deformation, scale changes, illumination changes, partial occlusions and so on. TLD(Tracking-Learning-Detection) is a classic effective algorithm in long-term tracking which can solve these problems well. Meanwhile, the real-time performance of the system should be taken into account while in the actual situation. An improved fast-moving object tracking algorithm based on TLD is proposed in this paper. In the paper, a method of narrowing the region of detection is proposed to effectively minimize the consumption of time, the method is combined with self-prediction of motion direction to ensure the accuracy of detection. To compensate for the possible missing and false detections caused by the reduction of detection region and the changing background, the variance threshold is updated dynamically to let more possible correct bounding boxes pass the variance classifier. Experiments have been conducted to verify the improved TLD algorithm, the results show that our algorithm ensures the accuracy of object tracking and has a good performance on the real-time.

show abstract

Fusing Kalman filter with TLD algorithm for target tracking

Cited by 14 publications

References 8 publications

Drift-Free Tracking Surveillance Based on Online Latent Structured SVM and Kalman Filter Modules

Drift-Free Tracking Surveillance Based on Online Latent Structured SVM and Kalman Filter Modules

A new Wi-Fi dynamic selection of nearest neighbor localization algorithm based on RSS characteristic value extraction by hybrid filtering

An Improved TLD Tracking Algorithm for Fast-moving Object

Contact Info

Product

Resources

About