Optical flow background estimation for real-time pan/tilt camera object tracking

Doyle, Daniel; Jennings, Alan; Black, Jonathan

doi:10.1016/j.measurement.2013.10.025

Cited by 53 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The methods are primarily distinguished according to application scenarios. For example, in [62], which could be one of the most influential works in this field, Doyle et al combine the methods of optical flow and Kalman filter.…”

Section: ) Kalman Filtermentioning

confidence: 99%

Progress and Outlook of Visual Tracking: Bibliographic Analysis and Perspective

Liu

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Benefitting from continuous progress in computer architecture and computer vision algorithms, the visual tracking field has earned its rapid development in recent years. This paper surveys this interesting field through bibliographic analysis on the Web-of-Science literature from 1990 to 2019. Specifically, statistical analysis methods are used to obtain the most productive authors and countries/regions, the most cited papers, and so on. In order to realize an in-depth analysis, the co-authors, co-keywords and keywordauthor co-occurrence networks are built to intuitively exhibit the evolution of research hotspots and the collaboration patterns among worldwide researchers. Brief introductions of the topics that occur frequently in co-keywords networks are provided as well. Furthermore, existing challenges and future research directions within the visual tracking field are discussed, revealing that tracking-by-detection and deep learning will continue receiving much attention. In addition, the parallel vision approach should be adopted for training and evaluating visual tracking models in a virtual-real interaction manner. INDEX TERMS Visual tracking, bibliographic analysis, collaboration patterns, research hotspots, parallel vision.

show abstract

Section: ) Kalman Filtermentioning

confidence: 99%

Progress and Outlook of Visual Tracking: Bibliographic Analysis and Perspective

Liu

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Many researchers have developed object tracking methods and systems that provide a visual representation to robustly describe the spatiotemporal characteristics of object appearance [2]. Object tracking methods using a global visual representation that reflects the global statistical characteristics of an image region to be tracked have been proposed on the basis of various global image features such as optical flows [3,4,5], color histograms [6,7,8], and texture histograms [9,10,11]. By encoding the object appearance information from the selected interest points in images, local-feature-based object tracking methods have also been proposed on the basis of local features such as scale invariant feature transform (SIFT) [12,13], Haar-like features [14,15], the histogram of oriented gradient (HOG) [16,17,18], and the local binary pattern (LBP) [19,20,21].…”

Section: Introductionmentioning

confidence: 99%

Pixel-Level and Robust Vibration Source Sensing in High-Frame-Rate Video Analysis

Jiang

Aoyama

Takaki

et al. 2016

Sensors

View full text Add to dashboard Cite

We investigate the effect of appearance variations on the detectability of vibration feature extraction with pixel-level digital filters for high-frame-rate videos. In particular, we consider robust vibrating object tracking, which is clearly different from conventional appearance-based object tracking with spatial pattern recognition in a high-quality image region of a certain size. For 512 × 512 videos of a rotating fan located at different positions and orientations and captured at 2000 frames per second with different lens settings, we verify how many pixels are extracted as vibrating regions with pixel-level digital filters. The effectiveness of dynamics-based vibration features is demonstrated by examining the robustness against changes in aperture size and the focal condition of the camera lens, the apparent size and orientation of the object being tracked, and its rotational frequency, as well as complexities and movements of background scenes. Tracking experiments for a flying multicopter with rotating propellers are also described to verify the robustness of localization under complex imaging conditions in outside scenarios.

show abstract

“…Many tracking methods exist including kernel-based methods (e.g., optical flow) and contour-based methods (e.g., snakes-based tracking). 3,4 Various techniques have been demonstrated for tumor tracking on 2D images across image modalities, including template matching and manifold learning, among others. [5][6][7][8] In this work, we evaluate the feasibility of tracking user-specified regions across cine frames using a matching objective for a well-established feature vector in image processing called a scale-invariant feature transform (SIFT) descriptor that is constructed for every pixel.…”

Section: Introductionmentioning

confidence: 99%

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

et al. 2015

View full text Add to dashboard Cite

Tracking results show high fidelity in assessing intrafractional motion observed on cine-MR acquisitions. Incorporating harmonic analysis during a training period improves the robustness of the tracking for challenging targets. The concomitant gating optimization procedure should allow for physicians to quantitatively assess gating effectiveness quickly just prior to treatment in a patient-specific manner.

show abstract

Optical flow background estimation for real-time pan/tilt camera object tracking

Cited by 53 publications

References 23 publications

Progress and Outlook of Visual Tracking: Bibliographic Analysis and Perspective

Progress and Outlook of Visual Tracking: Bibliographic Analysis and Perspective

Pixel-Level and Robust Vibration Source Sensing in High-Frame-Rate Video Analysis

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

Contact Info

Product

Resources

About