Multimodal Perception-Based Target Tracking for Child Safety Monitoring in Home Environments

Huijie Liu; Hongyan Zhang; Xiaotao Wang; Renjie Sun; Haitao Zhang

doi:10.6919/ICJE.202506_11(6).0007

Authors

Huijie Liu
Hongyan Zhang
Xiaotao Wang
Renjie Sun
Haitao Zhang

DOI:

https://doi.org/10.6919/ICJE.202506_11(6).0007

Keywords:

Target Tracking; Multimodal Sensing; RTAB-Map; SLAM Construction; Behavioral Trajectory Analysis.

Abstract

With the rapid development of artificial intelligence and computer vision technology, this paper proposes a multi-modal perception method based on object tracking for continuous monitoring and security detection of children's activities in family environment. YOLOv8 and DeepSORT were used for multi-target detection and tracking, and RTAB-Map was introduced to complete real-time positioning and map construction of three-dimensional family environment through closed-loop detection and memory management, combined with vision and lidar sensors, so as to realize real-time detection and behavioral trajectory analysis of children at home and ensure the safety of children at home. The experimental results show that the accuracy of multi-target tracking (MOTA) is 87.5% compared with the baseline method. Reasoning speed maintained at 25FPS; The root mean square error (RMSE) of trajectory tracking is controlled within 0.15m, which provides a reliable solution for real-time safety detection of children at home.

Downloads

Download data is not yet available.

References

[1] Lou H ,Duan X ,Guo J , et al.DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor[J].Electronics,2023,12(10):2323.

[2] Kaur H, Sahambi J S. Vehicle tracking in video using fractional feedback Kalman filter[J]. IEEE Transactions on Computational Imaging, 2016, 2(4): 550-561.

[3] Khan S, Naseer M, Hayat M, et al. Transformers in vision: A survey[J]. ACM computing surveys (CSUR), 2022, 54(10s): 1-41.

[4] Taketomi T, Uchiyama H, Ikeda S. Visual SLAM algorithms: A survey from 2010 to 2016[J]. IPSJ transactions on computer vision and applications, 2017, 9(1): 16.

[5] Fuentes-Pacheco J, Ruiz-Ascencio J, Rendón-Mancha J M. Visual simultaneous localization and mapping: a survey[J]. Artificial intelligence review, 2015, 43: 55-81.

[6] Mur-Artal R, Tardós J D. Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras[J]. IEEE transactions on robotics, 2017, 33(5): 1255-1262.

[7] Campos C, Elvira R, Rodríguez J J G, et al. Orb-slam3: An accurate open-source library for visual, visual–inertial, and multimap slam[J]. IEEE transactions on robotics, 2021, 37(6): 1874-1890.

[8] Endo Y, Sato K, Yamashita A, et al. Indoor positioning and obstacle detection for visually impaired navigation system based on LSD-SLAM[C]//2017 International Conference on Biometrics and Kansei Engineering (ICBAKE). IEEE, 2017: 158-162.

[9] Wen Z. SLAM based vision self-navigation robot with RTAB-MAP algorithm[J]. Applied and Computational Engineering, 2023, 6: 1-5.

[10] Muharom S, Sardjono T A, Mardiyanto R. Real-Time 3D Modeling and Visualization Based on RGB-D Camera using RTAB-Map through Loop Closure[C]//2023 International Seminar on Intelligent Technology and Its Applications (ISITIA). IEEE, 2023: 228-233.

[11] Zhou S, Li Z, Lv Z, et al. Research on positioning accuracy of mobile robot in indoor environment based on improved RTABMAP algorithm[J]. Sensors, 2023, 23(23): 9468.