Content based access for a massive database of human observation video

Joyeux, Laurent; Doyle, Erika; Denman, Hugh; Crawford, A. C.; Bousseau, A.; Kokaram, Anil; Fuller, Ray W.

doi:10.1145/1026711.1026720

Cited by 2 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Detection of the hands positions (green diamonds) of a child performing a psychological exercise [7]. The peaks of the skin colour projection give the candidate positions (red circles).…”

Section: Resultsmentioning

confidence: 99%

“…The application aims at detecting the position of the hands of a child performing a psychological exercise [7] as presented in figure 2.…”

Section: Application To a Simple Case Studymentioning

confidence: 99%

“…Candidates are found by projecting the colour skin segmentation [7] of the frames on the horizontal axis and taking the main peaks of the projection as candidates for the hands positions (see figure 2). The likelihood of these candidates is proportional to the value of the projection.…”

Section: Application To a Simple Case Studymentioning

confidence: 99%

See 2 more Smart Citations

Off-line multiple object tracking using candidate selection and the Viterbi algorithm

Pitié¹,

Berrani²,

Kokaram³

et al. 2005

IEEE International Conference on Image Processing 2005

Self Cite

View full text Add to dashboard Cite

This paper presents a probabilistic framework for off-line multiple object tracking. At each timestep, a small set of deterministic candidates is generated which is guaranteed to contain the correct solution. Tracking an object within video then becomes possible using the Viterbi algorithm. In contrast with particle filter methods where candidates are numerous and random, the proposed algorithm involves a few candidates and results in a deterministic solution. Moreover, we consider here off-line applications where past and future information is exploited. This paper shows that, although basic and very simple, this candidate selection allows the solution of many tracking problems in different real-world applications and offers a good alternative to particle filter methods for off-line applications.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The application aims at detecting the position of the hands of a child performing a psychological exercise [7] as presented in figure 2.…”

Section: Application To a Simple Case Studymentioning

confidence: 99%

See 1 more Smart Citation

Off-line multiple object tracking using candidate selection and the Viterbi algorithm

Pitié¹,

Berrani²,

Kokaram³

et al. 2005

IEEE International Conference on Image Processing 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DysVideo [8] project at Trinity College was set up to observe the development of 400 children aged below 6 years. Each child is observed through 3 sessions of 20 minutes, each 6 months apart.…”

Section: Detecting Episodes In Observational Psychologymentioning

confidence: 99%

“…Previous published work by the authors [8] discussed preliminary system design and the start of tool development. The testers use a palmpilot to generate DTMF audio tones at the start and end of each recorded session that are recorded simultaneously onto one audio channel as the video recording proceeds.…”

Section: Detecting Episodes In Observational Psychologymentioning

confidence: 99%

Exploiting temporal discontinuities for event detection and manipulation in video streams

Denman

Doyle

Kokaram

et al. 2005

Proceedings of the 7th ACM SIGMM International Workshop on Multimedia Information Retrieval

View full text Add to dashboard Cite

Discontinuities in any information bearing signal serve to represent much of the vital or interesting content in that signal. A sharp loud noise in a movie could be a gun, or something breaking. In sports like tennis, cricket or snooker/pool it would indicate a point scoring event. In both cases the discontinuity is likely to be semantically relevant without further inference being necessary, once a particular domain is adopted. This paper discusses the importance of temporal motion discontinuities in inferring events in visual media. Two particular application domains are considered: content based audio/video synchronisation and event spotting in observational Psychology.

show abstract

Content based access for a massive database of human observation video

Cited by 2 publications

References 6 publications

Off-line multiple object tracking using candidate selection and the Viterbi algorithm

Off-line multiple object tracking using candidate selection and the Viterbi algorithm

Exploiting temporal discontinuities for event detection and manipulation in video streams

Contact Info

Product

Resources

About