Ego2Top: Matching Viewers in Egocentric and Top-view Videos

Ardeshir, Shervin; Borji, Ali

doi:10.48550/arxiv.1607.06986

Cited by 2 publications

(20 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the following, we first describe our previous method introduced in [1] which solely solves the viewer assignment (section 3.3). We then describe our new two iterative algorithms in section 3.4, which aims to simultaneously estimate the time-delays and find the best assignments.…”

Section: Graph Matchingmentioning

confidence: 99%

“…The shortcoming of the similarity definition in [1] is that it does not enforce any sort of consistency among the timedelays assigned to different egocentric videos. In fact, the problem of viewer assignment, and time-delays of the egocentric videos are interconnected.…”

Section: Joint Optimization Over Assignment and Timedelaysmentioning

confidence: 99%

“…As a result, we define the objective to jointly optimize the time-delays and the assignment. Intuitively, putting constraints on the time-delays, will put constraints on the solution space, as some of the solutions using [1] might implicitly assign invalid (inconsistent) timedelays to the egocentric videos.…”

Section: Joint Optimization Over Assignment and Timedelaysmentioning

confidence: 99%

“…However, our experiments show that in most cases where human detection results are not that confident or the video length is too short, this feature by itself does not results in a high assignment accuracy. explore the effect of the two different initializations in terms of assignment and ranking and compare it with [1]. Matching Score Based Optimization: In our second approach, we attempt to find the optimal values for t d and x simultaneously using an iterative-alternative approach.…”

Section: Spectral Optimizationmentioning

confidence: 99%

“…In order to evaluate our method, we use the same dataset by Ardeshir and Borji [1], [11]. It contains several test sets.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Egocentric Meets Top-View

Ardeshir

Borji

2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Thanks to the availability of wearable devices such as GoPro cameras, smart phones, and glasses, we have now access to a plethora of videos captured from the first person perspective. Surveillance cameras and Unmanned Aerial Vehicles (UAVs) also offer tremendous amounts of video data recorded from top and oblique view points. Egocentric and surveillance vision have been studied extensively but separately in the computer vision community. The relationship between these two domains, however, remains unexplored. In this study, we make the first attempt in this direction by addressing two basic yet challenging questions. First, having a set of egocentric videos and a top-view video, does the top-view video contain all or some of the egocentric viewers? In other words, have these videos been shot in the same environment at the same time? Second, if so, how can we identify the egocentric viewers in the top-view video? These problems can become even more challenging when videos are not temporally aligned. We model each view using a graph, and compute the assignment and time-delays in an iterative-alternative fashion using spectral graph matching and time delay estimation. Such an approach handles the temporal misalignment between the egocentric videos and the top-view video.

show abstract

Section: Graph Matchingmentioning

confidence: 99%

Section: Joint Optimization Over Assignment and Timedelaysmentioning

confidence: 99%

Section: Joint Optimization Over Assignment and Timedelaysmentioning

confidence: 99%

Section: Spectral Optimizationmentioning

confidence: 99%

“…In order to evaluate our method, we use the same dataset by Ardeshir and Borji [1], [11]. It contains several test sets.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Egocentric Meets Top-View

Ardeshir

Borji

2019

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos

Ardeshir¹,

Sharma²,

Broji³

2016

Preprint

Self Cite

View full text Add to dashboard Cite

Human identification remains to be one of the challenging tasks in computer vision community due to drastic changes in visual features across different viewpoints, lighting conditions, occlusion, etc. Most of the literature has been focused on exploring human re-identification across viewpoints that are not too drastically different in nature. Cameras usually capture oblique or side views of humans, leaving room for a lot of geometric and visual reasoning. Given the recent popularity of egocentric and top-view vision, re-identification across these two drastically different views can now be explored. Having an egocentric and a top view video, our goal is to identify the cameraman in the content of the top-view video, and also re-identify the people visible in the egocentric video, by matching them to the identities present in the top-view video. We propose a CRF-based method to address the two problems. Our experimental results demonstrates the efficiency of the proposed approach over a variety of video recorded from two views.

show abstract

Ego2Top: Matching Viewers in Egocentric and Top-view Videos

Cited by 2 publications

References 0 publications

Egocentric Meets Top-View

Egocentric Meets Top-View

EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos

Contact Info

Product

Resources

About