著者

Hitoshi Nishimura Kazuyuki Tasaka Yasutomo Kawanishi Hiroshi Murase

出版者

The Institute of Image Information and Television Engineers

雑誌

ITE Transactions on Media Technology and Applications (ISSN:21867364)

巻号頁・発行日

vol.8, no.4, pp.269-279, 2020 (Released:2020-10-01)

参考文献数

39

被引用文献数

3

---

In this paper, we propose a multiple human tracking method with alternately updating trajectories and mult iframe action features (MHT-MAF). Even though occlusion or motion blur occurs due to the sudden movement of the drone, ID switches are prevented by the stable MAF. In the experiments, we verified the effectiveness of the proposed method using the Okutama-Action dataset. Our code is available online (https://github.com/hitottiez/mht-paf).

著者

Hitoshi NISHIMURA Naoya MAKIBUCHI Kazuyuki TASAKA Yasutomo KAWANISHI Hiroshi MURASE

出版者

The Institute of Electronics, Information and Communication Engineers

雑誌

IEICE Transactions on Information and Systems (ISSN:09168532)

巻号頁・発行日

vol.E103.D, no.6, pp.1265-1275, 2020-06-01 (Released:2020-06-01)

参考文献数

34

被引用文献数

1

---

Multiple human tracking is widely used in various fields such as marketing and surveillance. The typical approach associates human detection results between consecutive frames using the features and bounding boxes (position+size) of detected humans. Some methods use an omnidirectional camera to cover a wider area, but ID switch often occurs in association with detections due to following two factors: i) The feature is adversely affected because the bounding box includes many background regions when a human is captured from an oblique angle. ii) The position and size change dramatically between consecutive frames because the distance metric is non-uniform in an omnidirectional image. In this paper, we propose a novel method that accurately tracks humans with an association metric for omnidirectional images. The proposed method has two key points: i) For feature extraction, we introduce local rectification, which reduces the effect of background regions in the bounding box. ii) For distance calculation, we describe the positions in a world coordinate system where the distance metric is uniform. In the experiments, we confirmed that the Multiple Object Tracking Accuracy (MOTA) improved 3.3 in the LargeRoom dataset and improved 2.3 in the SmallRoom dataset.