Real-time and accurate model of instance segmentation of foods

IF 2.9 4区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Yuhe Fan, Lixun Zhang, Canxing Zheng, Yunqin Zu, Keyi Wang, Xingyuan Wang
{"title":"Real-time and accurate model of instance segmentation of foods","authors":"Yuhe Fan, Lixun Zhang, Canxing Zheng, Yunqin Zu, Keyi Wang, Xingyuan Wang","doi":"10.1007/s11554-024-01459-z","DOIUrl":null,"url":null,"abstract":"<p>Instance segmentation of foods is an important technology to ensure the food success rate of meal-assisting robotics. However, due to foods have strong intraclass variability, interclass similarity, and complex physical properties, which leads to more challenges in recognition, localization, and contour acquisition of foods. To address the above issues, this paper proposed a novel method for instance segmentation of foods. Specifically, in backbone network, deformable convolution was introduced to enhance the ability of YOLOv8 architecture to capture finer-grained spatial information, and efficient multiscale attention based on cross-spatial learning was introduced to improve sensitivity and expressiveness of multiscale inputs. In neck network, classical convolution and C2f modules were replaced by lightweight convolution GSConv and improved VoV-GSCSP aggregation module, respectively, to improve inference speed of models. We abbreviated it as the DEG-YOLOv8n-seg model. The proposed method was compared with baseline model and several state-of-the-art (SOTA) segmentation models on datasets, respectively. The results show that the DEG-YOLOv8n-seg model has higher accuracy, faster speed, and stronger robustness. Specifically, the DEG-YOLOv8n-seg model can achieve 84.6% Box_mAP@0.5 and 84.1% Mask_mAP@0.5 accuracy at 55.2 FPS and 11.1 GFLOPs. The importance of adopting data augmentation and the effectiveness of introducing deformable convolution, EMA, and VoV-GSCSP were verified by ablation experiments. Finally, the DEG-YOLOv8n-seg model was applied to experiments of food instance segmentation for meal-assisting robots. The results show that the DEG-YOLOv8n-seg can achieve better instance segmentation of foods. This work can promote the development of intelligent meal-assisting robotics technology and can provide theoretical foundations for other tasks of the computer vision field with some reference value.</p>","PeriodicalId":51224,"journal":{"name":"Journal of Real-Time Image Processing","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Real-Time Image Processing","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11554-024-01459-z","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Instance segmentation of foods is an important technology to ensure the food success rate of meal-assisting robotics. However, due to foods have strong intraclass variability, interclass similarity, and complex physical properties, which leads to more challenges in recognition, localization, and contour acquisition of foods. To address the above issues, this paper proposed a novel method for instance segmentation of foods. Specifically, in backbone network, deformable convolution was introduced to enhance the ability of YOLOv8 architecture to capture finer-grained spatial information, and efficient multiscale attention based on cross-spatial learning was introduced to improve sensitivity and expressiveness of multiscale inputs. In neck network, classical convolution and C2f modules were replaced by lightweight convolution GSConv and improved VoV-GSCSP aggregation module, respectively, to improve inference speed of models. We abbreviated it as the DEG-YOLOv8n-seg model. The proposed method was compared with baseline model and several state-of-the-art (SOTA) segmentation models on datasets, respectively. The results show that the DEG-YOLOv8n-seg model has higher accuracy, faster speed, and stronger robustness. Specifically, the DEG-YOLOv8n-seg model can achieve 84.6% Box_mAP@0.5 and 84.1% Mask_mAP@0.5 accuracy at 55.2 FPS and 11.1 GFLOPs. The importance of adopting data augmentation and the effectiveness of introducing deformable convolution, EMA, and VoV-GSCSP were verified by ablation experiments. Finally, the DEG-YOLOv8n-seg model was applied to experiments of food instance segmentation for meal-assisting robots. The results show that the DEG-YOLOv8n-seg can achieve better instance segmentation of foods. This work can promote the development of intelligent meal-assisting robotics technology and can provide theoretical foundations for other tasks of the computer vision field with some reference value.

Abstract Image

实时准确的食品实例分割模型
食品的实例分割是确保助餐机器人食品成功率的一项重要技术。然而,由于食物具有较强的类内差异性、类间相似性和复杂的物理特性,这给食物的识别、定位和轮廓获取带来了更多挑战。针对上述问题,本文提出了一种新颖的食品实例分割方法。具体来说,在骨干网络中,引入了可变形卷积,以增强 YOLOv8 架构捕捉更细粒度空间信息的能力;引入了基于跨空间学习的高效多尺度注意力,以提高多尺度输入的灵敏度和表现力。在颈部网络中,经典的卷积和 C2f 模块分别被轻量级卷积 GSConv 和改进的 VoV-GSCSP 聚合模块取代,以提高模型的推理速度。我们将其简称为 DEG-YOLOv8n-seg 模型。我们分别在数据集上将所提出的方法与基线模型和几种最先进的(SOTA)分割模型进行了比较。结果表明,DEG-YOLOv8n-seg 模型具有更高的准确性、更快的速度和更强的鲁棒性。具体来说,DEG-YOLOv8n-seg 模型能在 55.2 FPS 和 11.1 GFLOPs 的条件下实现 84.6% 的 Box_mAP@0.5 和 84.1% 的 Mask_mAP@0.5 准确率。烧蚀实验验证了采用数据增强的重要性以及引入可变形卷积、EMA 和 VoV-GSCSP 的有效性。最后,DEG-YOLOv8n-seg 模型被应用于助餐机器人的食物实例分割实验。结果表明,DEG-YOLOv8n-seg 可以实现更好的食物实例分割。这项工作能促进智能助餐机器人技术的发展,并能为计算机视觉领域的其他任务提供理论基础,具有一定的参考价值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Real-Time Image Processing
Journal of Real-Time Image Processing COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-ENGINEERING, ELECTRICAL & ELECTRONIC
CiteScore
6.80
自引率
6.70%
发文量
68
审稿时长
6 months
期刊介绍: Due to rapid advancements in integrated circuit technology, the rich theoretical results that have been developed by the image and video processing research community are now being increasingly applied in practical systems to solve real-world image and video processing problems. Such systems involve constraints placed not only on their size, cost, and power consumption, but also on the timeliness of the image data processed. Examples of such systems are mobile phones, digital still/video/cell-phone cameras, portable media players, personal digital assistants, high-definition television, video surveillance systems, industrial visual inspection systems, medical imaging devices, vision-guided autonomous robots, spectral imaging systems, and many other real-time embedded systems. In these real-time systems, strict timing requirements demand that results are available within a certain interval of time as imposed by the application. It is often the case that an image processing algorithm is developed and proven theoretically sound, presumably with a specific application in mind, but its practical applications and the detailed steps, methodology, and trade-off analysis required to achieve its real-time performance are not fully explored, leaving these critical and usually non-trivial issues for those wishing to employ the algorithm in a real-time system. The Journal of Real-Time Image Processing is intended to bridge the gap between the theory and practice of image processing, serving the greater community of researchers, practicing engineers, and industrial professionals who deal with designing, implementing or utilizing image processing systems which must satisfy real-time design constraints.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信