I2SLAB 송인표, 이종민 학생 (지도교수: 이장원), IJCAI2024 논문 채택

I2SLAB (지도교수: 이장원)의 송인표, 이종민(실감미디어공학과) 학생들이 연구한 논문 “

Motion-Aware Heatmap Regression for Human Pose Estimation in Videos” 이 인공지능 분야 최우수 학회 (BK IF=4) International Joint Conferences on Artificial Intelligence (IJCAI) 2024 에 게재 승인되어 8월에 발표될 예정입니다. 본 논문에서 이장원 교수 연구팀은 시간적 종속성을 고려하여 motion blur와 occlusion 속에서 사람 자세의 불확실성을 효과적으로 모델링할 수 있는 motion-aware heatmap 이라는 새로운 아이디어를 제안하였습니다. 논문의 자세한 내용은 다음과 같습니다.

[논문]

Inpyo Song, Jongmin Lee, Moonwook Ryu, and Jangwon Lee, “Motion-Aware Heatmap Regression for Human Pose Estimation in Videos,“ International Joint Conferences on Artificial Intelligence (IJCAI 2024), Aug. 2024.

[Abstract].

We present an approach to solving 2D human pose estimation in videos. The problem of human pose estimation in videos differs from estimating human poses in static images since videos contain a lot of motion related information. Thus, we investigate how to utilize by the information of the human body movements across in a sequence of video frames for estimating human poses in videos. To do this, we introduce a novel heatmap regression method what we call motion-aware heatmap regression. Our approach computes motion vectors in joint keypoints from adjacent frames. We then design a new style of heatmap that we call Motion-Aware Heatmaps to reflect the motion uncertainty of each joint point. Unlike traditional heatmaps, our motion-aware heatmaps not only consider the current joint locations but also account how joints move over time. Furthermore, we introduce a simple yet effective framework designed to incorporate motion information into heatmap regression. We evaluate our motion-aware heatmap regression on PoseTrack(2018, 21) and Sub-JHMDB datasets. Our results validate that the proposed motion-aware heatmaps significantly improve the precision of human pose estimation in videos, particularly in challenging scenarios such as videos like sports game footage with substantial human motions.