Recent advances on multicue object tracking: a survey

Walia, Gurjit Singh; Kapoor, Rajiv

doi:10.1007/s10462-015-9454-6

Cited by 52 publications

(19 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further challenges that are eminent in stereo camera vision arise from fixing camera set-ups. Having small apex angles, which are combined to the fixed cameras, actually leads to having only partial simultaneously visible parts of a scenario [45]. Consequently, this requires overlapping the images so that they can merge to form spatial impressions, thereby deteriorating the stereo vision quality by a significant degree [46].…”

Section: B Discussionmentioning

confidence: 99%

See 1 more Smart Citation

3D Face Tracking Using Stereo Cameras: A Review

et al. 2020

View full text Add to dashboard Cite

This review considers previous research, regarding the background and applications of 3D facetracking systems with a focus on stereo camera-based systems. Stereo cameras are less expensive than laser ranging systems, and they are widely available on devices such as smart phones. This review aims to spur further development and applications of face tracking in this domain. Many studies on face tracking have used concepts such as the Kanade-Lucas-Tomasi method, particle filters, tracking-learning-detecting, probability hypothesis density, mean shift/cam shift, and others. As imaging constraints are relaxed, facial tracking becomes more challenging. This review presents an exposition of the most common challenges in face tracking, such as occlusion and clutter, pose variations, changes in facial resolution, illumination variations, and facial deformation. Five forms of pose estimation are discussed: appearance template methods, detector arrays, flexible models, geometric methods, and tracking methods. Applications of the listed 3D face tracking systems are also discussed, including face modelling, film editing, access control, security, and surveillance.

show abstract

Section: B Discussionmentioning

confidence: 99%

“…Proof has also been provided for discarding the first few eigenfaces [40]. The only problem with this technique is that it causes degradation of the system performance for frontal input images that are taken under frontal illumination [45], [54].…”

Section: A Robustness To Pose and Illumination Variationsmentioning

confidence: 99%

3D Face Tracking Using Stereo Cameras: A Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We compare with related tracking algorithms including the ST [15], LRT [1], LRST [8],ℓ1 [5] and IST [16] methods. We present some representative results in this section.…”

Section: B Qualitative Evaluationmentioning

confidence: 99%

“…The design of flexible and reasonable tracking model which can adapt to aforementioned appearance variations is an important subject [1] . Some existing algorithms based on statistic principles were widely used in visual tracking domain for their effective experimental results on the controlled environments.…”

Section: Introductionmentioning

confidence: 99%

A New Discriminative Tracking Method Applied in Multi-rotor Unmanned Aircraft

Wu¹,

Zeng²

2017

Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)

View full text Add to dashboard Cite

Abstract-Aiming at difficulties for vehicle tracking on the specific scenes such as fast motion, rotation, drastic illumination and scale change, a new discriminative tracking algorithm for moving vehicles is proposed in this paper. We incorporate low-rank sparse representation and dictionary learning with the classical particle filter algorithm. Based on unmanned multi-rotor aircraft, we apply the enhanced algorithm to track selected vehicle in the urban road, demonstrate the performance of our method on the process of vehicle tracking in above scenes. The proposed approach is different from conventional discriminative tracking algorithm. Compared with related methods, experimental results show that the proposed algorithm improves the synthesized efficiency of tracking process, the experiments based on standard testing videos demonstrate that tracking successful rate is significantly improved.

show abstract

“…Thermal infrared imaging offers a tremendous advantage in differentiating human subjects from background by virtue of temperature differences [165][166][167].…”

Section: Future Workmentioning

confidence: 99%

Occupant-aware thermal comfort control with elevated air speed

Yin¹

View full text Add to dashboard Cite

comfort model is used to obtain the relationship between the air speed and thermal comfort. This relationship is used to determine the desired air speed under different environmental conditions. The fan is then controlled to give the desired air speed, taking into account the occupant-fan distance. For multiple occupants, a patented technology for cooperatively controlling a system of fans to provide optimized air movement is developed. A cost-effective calibration method to obtain the relationship between air speed and fan speed setting is proposed to predict airflow in the actual environment. Fans operation is optimized by minimizing the maximum deviation between the actual air speed generated by fans and the desired air speed. This minimax-error problem is reformulated as a linear programming problem which can be solved readily using standard methods. To obtain occupancy information, a received signal strength (RSS)-based indoor tracking system is implemented. A common problem with RSS-based indoor tracking is the disturbances encountered in dynamic and complex indoor environments. The proposed system uses the generalized t-distribution (GT) to model the disturbances. A recursive filtering algorithm based on the GT noise model is developed. Because of the more accurate noise model, the proposed filter can produce better position estimates than that of the Kalman filter which makes the usual assumption of Gaussian noise. An equation to compute the variance of the estimation error is also derived. The variance equation can be used as an analytic tool for designing and assessing the tracking system. Both theoretical and experimental results show that the variance of the estimation error from the proposed filter is less than that from the Kalman filter. The experiments also show that the filter with GT noise model can handle outlier better than the Kalman filter.

show abstract

Recent advances on multicue object tracking: a survey

Cited by 52 publications

References 107 publications

3D Face Tracking Using Stereo Cameras: A Review

3D Face Tracking Using Stereo Cameras: A Review

A New Discriminative Tracking Method Applied in Multi-rotor Unmanned Aircraft

Occupant-aware thermal comfort control with elevated air speed

Contact Info

Product

Resources

About