Tracking a Human Fast and Reliably Against Occlusion and Human-Crossing

Huynh, Xuan-Phung; Choi, In-Ho; Kim, Yong-Guk

doi:10.1007/978-3-319-29451-3_37

Cited by 3 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KCF tracker, the minimum output sum of squared error (MOSSE) tracker, and the improved KCF tracker proposed in paper [ 41 ] could not track the micro-object correctly, whereas our tracker successfully tracked all frames ( Figure 23 ). The established trackers coped poorly with the fast motions of the micro-object.…”

Section: Numerical Results and Discussionmentioning

confidence: 86%

“…Finally, the predicted target position is refined by the detected value. The authors of [ 41 ] selected the position of an occluded target using a threshold value

. If the detected value of the KCF tracker is less than

, the Kalman filter is updated using the detected value, and the result is set as the target location.…”

Section: Tracking Algorithm For the Moving Targetmentioning

confidence: 99%

“…In an experimental evaluation, the scale-adaptive tracker showed a promising ability to change the scale of a target. By integrating a Kalman filer with KCF, Huynh developed a new tracking method that overcomes occlusion and human-crossing [ 41 ]. The KCF in their method estimates the target position based on the Kalman filter prediction and updates the kernel model accordingly.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Kalman Filter-Based Kernelized Correlation Filter Algorithm for Pose Measurement of a Micro-Robot

et al. 2021

View full text Add to dashboard Cite

This paper proposes a moving-target tracking algorithm that measures the pose of a micro-robot with high precision and high speed using the Kalman filter-based kernelized correlation filter (K2CF) algorithm. The adaptive Kalman filter can predict the state of linearly and nonlinearly fast-moving targets. The kernelized correlation filter algorithm then accurately detects the positions of the moving targets and uses the detection results to modify the moving states of the targets. This paper verifies the performance of the algorithm on a monocular vision measurement platform and using a pose measurement method. The K2CF algorithm was embedded in the micro-robot’s attitude measurement system, and the tracking performances of three different trackers were compared under different motion conditions. Our tracker improved the positioning accuracy and maintained real-time operation. In a comparison study of K2CF and many other algorithms on Object Tracking Benchmark-50 and Object Tracking Benchmark-100 video sequences, the K2CF algorithm achieved the highest accuracy. In the 400 mm × 300 mm field of view, when the target radius is about 3 mm and the inter-frame acceleration displacement does not exceed 5.6 mm, the root-mean-square error of position and attitude angle can satisfy the precision requirements of the system.

show abstract

Section: Numerical Results and Discussionmentioning

confidence: 86%

“…Finally, the predicted target position is refined by the detected value. The authors of [ 41 ] selected the position of an occluded target using a threshold value

. If the detected value of the KCF tracker is less than

, the Kalman filter is updated using the detected value, and the result is set as the target location.…”

Section: Tracking Algorithm For the Moving Targetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Kalman Filter-Based Kernelized Correlation Filter Algorithm for Pose Measurement of a Micro-Robot

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A more recent algorithm developed is Kernelized Correlation Filter [13], which tracks based on the histogram of oriented gradients (HOG) of the object of interest; this allows the routine to run at approximately 130-150 Hz with an accuracy of more than 90 percent [14]. However, the routine's accuracy is still hampered by the occlusion problem.…”

Section: Visual Trackingmentioning

confidence: 99%