Human tracking from a mobile agent: Optical flow and Kalman filter arbitration

Motai, Yuichi; Jha, Sumit Kumar; Kruse, Daniel

doi:10.1016/j.image.2011.06.005

Cited by 44 publications

(23 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Legs can easily be confused with tables and chairs, so they must be filtered out by mapping the environment. Some authors propose filtering [42], [43] or sensor fusion techniques [44], [45], [46], [47], [48] in order to improve tracking performance. The use of stereo vision cameras for person tracking has also been reported [49], in combination with LRF [50], or LRF and color-image segmentation [51], [52].…”

Section: B Person Followingmentioning

confidence: 99%

Comparison of Interaction Modalities for Mobile Indoor Robot Guidance: Direct Physical Interaction, Person Following, and Pointing Control

Jevtić

Doisy

Parmet

et al. 2015

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

Abstract-Three advanced natural interaction modalities for mobile robot guidance in an indoor environment were developed and compared using two tasks and quantitative metrics to measure performance and workload. The first interaction modality is based on direct physical interaction requiring the human user to push the robot in order to displace it. The second and third interaction modalities exploit a 3D vision-based human-skeleton tracking allowing the user to guide the robot by either walking in front of it or by pointing towards a desired location. In the first task, the participants were asked to guide the robot between different rooms in a simulated physical apartment requiring rough movement of the robot through designated areas. The second task evaluated robot guidance in the same environment through a set of waypoints, which required accurate movements. The three interaction modalities were implemented on a generic differential drive mobile platform equipped with a pan-tilt system and a Kinect camera. Task completion time and accuracy were used as metrics to assess the users' performance, while the NASA-TLX questionnaire was used to evaluate the users' workload. A study with 24 participants indicated that choice of interaction modality had significant effect on completion time (F(2,61)=84.874, p<0.001), accuracy (F(2,29)=4.937, p=0.016), and workload (F(2,68)=11.948, p<0.001). The direct physical interaction required less time, provided more accuracy and less workload than the two contactless interaction modalities. Between the two contactless interaction modalities, the person-following interaction modality was systematically better than the pointing-control one: the participants completed the tasks faster with less workload. Index Terms-Human-robot interaction, mobile robots, direct physical interaction, person tracking, person following, gesture recognition

show abstract

Section: B Person Followingmentioning

confidence: 99%

Comparison of Interaction Modalities for Mobile Indoor Robot Guidance: Direct Physical Interaction, Person Following, and Pointing Control

Jevtić

Doisy

Parmet

et al. 2015

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

show abstract

“…Visual object tracking [1][2][3] has been employed in various fields such as video surveillance [4,5], driver assistance systems [6,7], and robotics [8]. Optical flow (OF) [9][10][11] is one of the most widely used visual tracking methods.…”

Section: Introductionmentioning

confidence: 99%

“…Song et al [19] employed the OF scheme to spot distinctive feature points in a region of interest (ROI) selected near the expected position estimated by the KF. Motai et al [8] proposed the KF and OF arbitration (KOA) under a certain switching rule depending on the movement of the target object. However, in these algorithms, the KF's intrinsic problems due to the filter structure remain.…”

Section: Introductionmentioning

confidence: 99%

Arbitration algorithm of FIR filter and optical flow based on ANFIS for visual object tracking

et al. 2015

View full text Add to dashboard Cite

“…In this paper we propose a novel optical flow method that combines the optical flow algorithm with the local mean algorithm and the self-adaptive threshold algorithm to detect objects directly in complex environments without extracting and updating a reference background image, which is an adaptive object detection approach without the need of using complex preprocessing procedure. The advantages of the presented method are that it can deal with the camera shake effectively, and has the ability to self-adaptively vary with the different object size and the different number of objects, and some object state parameters concerned such as displacement and direction can be gained [15], which are useful in the object tracking application. …”

Section: Introductionmentioning

confidence: 99%

A self-adaptive optical flow method for the moving object detection in the video sequences

Xin

Hou

Dong

et al. 2014

Optik

View full text Add to dashboard Cite

Human tracking from a mobile agent: Optical flow and Kalman filter arbitration

Cited by 44 publications

References 35 publications

Comparison of Interaction Modalities for Mobile Indoor Robot Guidance: Direct Physical Interaction, Person Following, and Pointing Control

Comparison of Interaction Modalities for Mobile Indoor Robot Guidance: Direct Physical Interaction, Person Following, and Pointing Control

Arbitration algorithm of FIR filter and optical flow based on ANFIS for visual object tracking

A self-adaptive optical flow method for the moving object detection in the video sequences

Contact Info

Product

Resources

About