Real-Time Tracking of Moving Objects with an Active Camera

Daniilidis, Konstantinos; Krauss, C.; Hansen, Marit; Sommer, Gerald

doi:10.1006/rtim.1996.0060

Cited by 60 publications

(39 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A frequency equal to or greater than 25 (Hz) is regarded as real-time [24,25]. Moreover, the response of the manipulator was less than 100 (ms) [15].…”

Section: Performance Analysismentioning

confidence: 99%

An image processing method for changing endoscope direction based on pupil movement

et al. 2016

View full text Add to dashboard Cite

Increased attention has been focused on laparoscopic surgery because of its minimal invasiveness and improved cosmetic properties. However, the procedure of laparoscopic surgery is considerably difficult for surgeons, thus paving the way for the introduction of robotic technology to reduce the surgeon's burden. Thus, we have developed a single-port surgery assistive robot with a master-slave structure that has two surgical manipulators and a sheath manipulator for the alteration of endoscope direction. During the development of the surgical robotic system, achieving intuitive operation is very important. In this paper, we propose a new laparoscope manipulator control system based on the movement of the pupils to enhance intuitive operability. We achieve this using a webcam and an image processing method. After the pupil movement data are obtained, the master computer transforms these data into an output signal, and then the slave computer receives and uses that signal to drive the robot. The details of the system and the pupil detection procedure are explained. The aim of the present experiment is to verify the effectiveness of the image processing method applied to the alteration of endoscope direction control system. For this purpose, we need to determine an appropriate pupil motion activation threshold to begin the sheath manipulator's movement. We used four kinds of activation threshold, measuring the time cost of a particular operation: to move the image of the endoscope to a specific target position. Moreover, we identified an appropriate activation threshold that can be used to determine whether the endoscope is moving.

show abstract

“…A frequency equal to or greater than 25 (Hz) is regarded as real-time [24,25]. Moreover, the response of the manipulator was less than 100 (ms) [15].…”

Section: Performance Analysismentioning

confidence: 99%

An image processing method for changing endoscope direction based on pupil movement

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The pixel-based local optical flow in image sequence can be robustly evaluated by the Lucas-Kanade-Tomasi (LKT) feature tracker [100,101], which effectively selects corner feature points of the reference image patch. In [49], Daniilidis et al apply an FIR-kernel based LKT feature tracker to estimate the optical flow and to infer the motion of objects. The spatial FIR-kernels are binomial approximations to the first derivatives of the Gaussian function.…”

Section: Optical Flowmentioning

confidence: 99%

“…The most common method for moving camera segmentation is the temporal difference [47,48], i.e., the difference between consecutive image frames. Also, the motion of moving camera can be inferred by optical flow [49,50], which estimates the pixel-level motion between two images. The features of images are then tracked and the coordinate between consecutive images is also transformed.…”

Section: Introductionmentioning

confidence: 99%

A Review on Video-Based Human Activity Recognition

et al. 2013

View full text Add to dashboard Cite

This review article surveys extensively the current progresses made toward video-based human activity recognition. Three aspects for human activity recognition are addressed including core technology, human activity recognition systems, and applications from low-level to high-level representation. In the core technology, three critical processing stages are thoroughly discussed mainly: human object segmentation, feature extraction and representation, activity detection and classification algorithms. In the human activity recognition systems, three main types are mentioned, including single person activity recognition, multiple people interaction and crowd behavior, and abnormal activity recognition. Finally the domains of applications are discussed in detail, specifically, on surveillance environments, entertainment environments and healthcare systems. Our survey, which aims to provide a comprehensive state-of-the-art review of the field, also addresses several challenges associated with these systems and applications. Moreover, in this survey, various applications are discussed in great detail, specifically, a survey on the applications in healthcare monitoring systems. OPEN ACCESSComputers 2013, 2 89

show abstract

“…The r-value is initially assumed to be 0 but it is recalculated as imaging sensors get activated. The default end-to-end delay requirement for real-time data is taken to be 0.08 sec [33]. Targets are assumed to start at a random position outside the convex hull.…”

Section: Environment Setupmentioning

confidence: 99%

Energy‐aware delay‐constrained routing in wireless sensor networks

Akkaya

Younis

2004

Int J Communication

View full text Add to dashboard Cite

Abstract. Recent years has witnessed a growing interest in the applications of unattended wireless sensor networks. Typically sensors collect data about their surrounding and forward that data to a gateway (sink). Due to the limitation of the energy supply that these miniaturized sensors have, almost all of the proposed routing protocols have aimed at energy efficiency as the ultimate objective and considered relaying data to a stationary gateway. However, many new issues have been posed by the increasing interest in applications that demand certain quality of service (QoS) guarantees. Such issues even get more challenging when the gateway is mobile. In this paper, we propose an energy-aware approach for routing delay-constrained data. The approach pursues multi-hop packet relaying to minimize transmission energy and employs Weighted Fair Queuing (WFQ) packet scheduling methodology along with leaky bucket constrained data sources in order to provide soft real-time guarantees for data delivery. Such employment of WFQ at each node provides a service differentiation between two different classes of traffic, namely real-time and non-real-time traffic and divides the outgoing link capacity among such classes accordingly. In the case of a mobile gateway, uninterrupted data flow for both types of traffic is achieved by dynamic adjustment of the route setup to react to the gateway's departure out of transmission range of relaying nodes. Simulation results demonstrate the effectiveness of the proposed approach for popular performance metrics.

show abstract

Real-Time Tracking of Moving Objects with an Active Camera

Cited by 60 publications

References 33 publications

An image processing method for changing endoscope direction based on pupil movement

An image processing method for changing endoscope direction based on pupil movement

A Review on Video-Based Human Activity Recognition

Energy‐aware delay‐constrained routing in wireless sensor networks

Contact Info

Product

Resources

About