Multicamera human detection and tracking supporting natural interaction with large-scale displays

Zabulis, Xenophon; Grammenos, Dimitris; Sarmis, Thomas; Tzevanidis, Konstantinos; Padeleris, Pashalis; Koutlemanis, Panagiotis; Argyros, Antonis A.

doi:10.1007/s00138-012-0408-6

Cited by 21 publications

(28 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some methods are known to calculate 3D information with multiple single-view cameras, instead of depth cameras, in disparate locations (e.g., region-based stereo). This method is actually used in [9]- [11]. However, measurement accuracy drops when occlusion occurs as mentioned in Sect.…”

Section: Resultsmentioning

confidence: 99%

“…In practice, Mittal et al [9] used 16 cameras to cover an area of 3.5 m × 3.5 m; Muñoz-Salinas et al [10] used five cameras to cover an area of 3 m × 3 m; Zabulis et al [11] used eight cameras to cover an area of 4 m × 4.5 m, and Fleuret et al [20] used four cameras to cover an area of 5.5 m × 5.5 m.…”

Section: Resultsmentioning

confidence: 99%

“…For human tracking, face recognition and head detection are also informative cues that provide better occlusion robustness [6], [7]. Multi-view tracking is also a potential solution for occlusion [8]- [11]. In addition, multiple cameras can offer coverage of a larger area than can a single camera [12].…”

Section: Multi-view Trackingmentioning

confidence: 99%

“…Zabulis et al [11] developed an interactive display that is aware of visitors' walk-through path, which is computed by their proposed tracking method. They first conducted volume intersection with eight cameras in order to reconstruct the human volume, and then, projected the volume onto a ground plane.…”

Section: Multi-view Trackingmentioning

confidence: 99%

“…If image acquisition is synchronized, as in existing multi-view approaches [9]- [11], [20], then (4) is sufficient, because measurements from different views at time t originate from the same position. However, with asynchronous multiple cameras, the OMs need to be shifted according to the speed of movement, which is dependent on each individual.…”

Section: Algorithm 1 Trajectory Creationmentioning

confidence: 99%

See 4 more Smart Citations

Occlusion-Robust Human Tracking with Integrated Multi-View Depth Imagery

Fukushi

Kumazawa

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Kenichiro FUKUSHI†a) and Itsuo KUMAZAWA † †b) , Members SUMMARYIn this paper, we present a computer vision-based human tracking system with multiple stereo cameras. Many widely used methods, such as KLT-tracker, update the trackers "frame-to-frame," so that features extracted from one frame are utilized to update their current state. In contrast, we propose a novel optimization technique for the "multi-frame" approach that computes resultant trajectories directly from video sequences, in order to achieve high-level robustness against severe occlusion, which is known to be a challenging problem in computer vision. We developed a heuristic optimization technique to estimate human trajectories, instead of using dynamic programming (DP) or an iterative approach, which makes our method sufficiently computationally efficient to operate in realtime. Six video sequences where one to six people walk in a narrow laboratory space are processed using our system. The results confirm that our system is capable of tracking cluttered scenes in which severe occlusion occurs and people are frequently in close proximity to each other. Moreover, minimal information is required for tracking, instead of full camera images, which is communicated over the network. Hence, commonly used network devices are sufficient for constructing our tracking system. key words: human tracking, multi-view, multi-frame, stereo vision, depth camera, occlusion robust IntroductionComputer vision-based human tracking has received increasing attention recently. Applications include ambient intelligence, human-computer interaction, human behavior analysis and security. Computer vision (CV) allows tracking systems that operate without such sensors as RFID, GPS, or smart phones. However, a problem known as "occlusion" in CV-based tracking exists, which occurs when a person being tracked goes behind other people or objects. Full occlusion disables any cues for tracking, and partial occlusion changes the appearance of the person, causing tracking difficulties.Earlier work has identified several promising strategies. First, multi-view tracking approaches are employed to reduce the blind areas caused by occlusion. Tracking or feature extraction is conducted for each camera, and then the final tracking result is produced by fusing the evidence from all of the views. The problem is how to match regions observed from different viewpoints. Researchers proposed

show abstract

Section: Resultsmentioning

confidence: 99%