Calorie detection in dishes based on deep learning and 3D reconstruction

被引：1

作者：

Shi, Yongqiang ^{[1
]}

Gao, Wenjian ^{[1
]}

Shen, Tingting ^{[1
]}

Li, Wenting ^{[2
]}

Li, Zhihua ^{[1
]}

Huang, Xiaowei ^{[1
,3
]}

Li, Chuang ^{[1
]}

Chen, Hongzhou ^{[1
]}

Zou, Xiaobo ^{[1
,3
]}

Shi, Jiyong ^{[1
,3
]}

机构：

[1] Jiangsu Univ, Sch Food & Biol Engn, Sch Agr Engn, Zhenjiang 212013, Peoples R China

[2] Jiangsu Univ Sci & Technol, Sch Grain Sci & Technol, Zhenjiang 212100, Peoples R China

[3] Nanjing Univ Finance & Econ, Coll Food Sci & Engn, Collaborat Innovat Ctr Modern Grain Circulat & Saf, 128 North Railway St, Nanjing 210023, Peoples R China

来源：

COMPUTERS AND ELECTRONICS IN AGRICULTURE | 2025年 / 229卷

基金：

中国国家自然科学基金; 中国博士后科学基金;

关键词：

Calorie calculation; Deep learning; Deep camera; 3D reconstruction;

D O I：

10.1016/j.compag.2024.109832

中图分类号：

S [农业科学];

学科分类号：

09 ;

摘要：

Caloric intake is a crucial factor in maintaining overall health. This work addresses the challenge of automating detection of calories in vegetables and dishes by utilizing an Intel Realsense depth camera and implementing deep learning techniques in image classification combined with 3D reconstruction to the field of food. By incorporating a CBAM mechanism before and after the DenseNet264 convolutional layer, the accuracy rate is improved to 83.74%. Furthermore, a calorie detection model with a maximum average error of 0.0429 is developed through the integration of 3D reconstruction, principal component analysis and the Monte Carlo volume algorithm. Specifically, the average errors for individual dishes range from 0.049 to 0.102, while set meal samples have errors between 0.017 and 0.075. The errors observed in this study are maintained within acceptable limits, suggesting potential applicability for robot-assisted intelligent catering services in the future.

引用

页数：12

共 38 条

[21] Mobile Multi-Food Recognition Using Deep Learning [J].

Pouladzadeh, Parisa ;

Shirmohammadi, Shervin .

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2017, 13 (03)

[22]

Rahman M.F., 2020, Food Calorie Estimation Based on Food Recognition

[23] Vision-based food nutrition estimation via RGB-D fusion network [J].

Shao, Wenjing ;

Min, Weiqing ;

Hou, Sujuan ;

Luo, Mengjiang ;

Li, Tianhao ;

Zheng, Yuanjie ;

Jiang, Shuqiang .

FOOD CHEMISTRY, 2023, 424

[24]

Simonyan K, 2015, Arxiv, DOI arXiv:1409.1556

[25]

Szegedy C, 2014, Arxiv, DOI [arXiv:1409.4842, 10.48550/arXiv.1409.4842, DOI 10.48550/ARXIV.1409.4842]

[26] Rethinking the Inception Architecture for Computer Vision [J].

Szegedy, Christian ;

Vanhoucke, Vincent ;

Ioffe, Sergey ;

Shlens, Jon ;

Wojna, Zbigniew .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2818-2826

[27]

Szegedy C, 2015, PROC CVPR IEEE, P1, DOI 10.1109/CVPR.2015.7298594

[28]

VijayaKumari G., 2022, GLOB TRANSIT PROC, V3, P225, DOI [10.1016/j.gltp.2022.03.027, DOI 10.1016/J.GLTP.2022.03.027]

[29] Imbalance knowledge-driven multi-modal network for land-cover semantic segmentation using aerial images and LiDAR point clouds [J].

Wang, Yameng ;

Wan, Yi ;

Zhang, Yongjun ;

Zhang, Bin ;

Gao, Zhi .

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2023, 202 :385-404

[30] CBAM: Convolutional Block Attention Module [J].

Woo, Sanghyun ;

Park, Jongchan ;

Lee, Joon-Young ;

Kweon, In So .

COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :3-19

← 1 2 3 4 →