计算机科学
人工智能
姿势
稳健性(进化)
卷积神经网络
计算机视觉
RGB颜色模型
目标检测
方向(向量空间)
过程(计算)
机器视觉
分割
模式识别(心理学)
数学
生物化学
基因
操作系统
化学
几何学
作者
Yadan Zeng,Yee Seng Teoh,Guoniu Zhu,Elvin Toh,I‐Ming Chen
出处
期刊:Robotica
[Cambridge University Press]
日期:2024-02-21
卷期号:42 (7): 2108-2124
被引量:7
标识
DOI:10.1017/s0263574724000122
摘要
Abstract The rise in the number of automated robotic kitchens accelerated the need for advanced food handling system, emphasizing food analysis including ingredient classification pose recognition and assembling strategy. Selecting the optimal piece from a pile of similarly shaped food items is a challenge to automated meal assembling system. To address this, we present a constructive assembling algorithm, introducing a unique approach for food pose detection–Fast Image to Pose Detection (FI2PD), and a closed-loop packing strategy. Powered by a convolutional neural network (CNN) and a pose retrieval model, FI2PD is adept at constructing a 6D pose from only RGB images. The method employs a coarse-to-fine approach, leveraging the CNN to pinpoint object orientation and position, alongside a pose retrieval process for target selection and 6D pose derivation. Our closed-loop packing strategy, aided by the Item Arrangement Verifier, ensures precise arrangement and system robustness. Additionally, we introduce our FdIngred328 dataset of nine food categories ranging from fake foods to real foods, and the automatically generated data based on synthetic techniques. The performance of our method for object recognition and pose detection has been demonstrated to achieve a success rate of 97.9%. Impressively, the integration of a closed-loop strategy into our meal-assembly process resulted in a notable success rate of 90%, outperforming the results of systems lacking the closed-loop mechanism.
科研通智能强力驱动
Strongly Powered by AbleSci AI