K-Shortest Pathsを用いた多人数追跡におけるデータ削減による高速化

Translated title of the contribution: Performance enhancement of multi-human tracking based on K-Shortest Paths by data reduction

秦 希望, 西川 由理, 中山 俊, 小澤 順, 藤澤 克樹

    Research output: Contribution to journalArticlepeer-review

    Abstract

    <p>Object tracking is a challenging problem and it has been improving dramatically in recent years. In this paper, we perform parallelized multi-object tracking system. Object tracking problem has 2 difficulties; one is to detect objects collect, and the other is to track collect using the collect object detection. Jerome et al. performed a multi-object tracking system using K-Shortest Paths to avoid these problems efficiently. However, it is difficult to calculate in parallel because of the iterations calculation of shortest paths on the graph while changing the weight of graph. In our method, we divided time intervals to apply KSP method from Probability Occupancy Map(POM), which is also obtained via using KSP method. Performance evaluation shows our algorithm is 5.4 times faster than the original KSP with 87% accuracy.</p>
    Translated title of the contributionPerformance enhancement of multi-human tracking based on K-Shortest Paths by data reduction
    Original languageJapanese
    Pages (from-to)2D103-2D103
    Journal人工知能学会全国大会論文集
    Volume2018
    Issue number0
    DOIs
    Publication statusPublished - 2018

    Fingerprint Dive into the research topics of 'Performance enhancement of multi-human tracking based on K-Shortest Paths by data reduction'. Together they form a unique fingerprint.

    Cite this