摘要
随着科技的不断进步,无人零售成为了未来社会的发展趋势;然而传统的无人售货超市存在成本高昂和水果蔬菜等生鲜产品售卖方式单一,效率低下,需要大量劳动力等缺陷;为了解决此问题,文章提出一种基于深度学习的智能无人果蔬售卖系统;该系统能够识别未打电子标签的果蔬生鲜,基于改进的目标检测算法精准识别果蔬的类别和位置,进而进行称重并计算商品的价格;通过实验验证,该系统具有综合化、智能化和专业化的优点,在自制果蔬数据集上,算法平均精度(mAP)提升了7.37%,实验证明本系统对果蔬的目标检测具有较强的鲁棒性。
With the continuous progress of science and technology,unmanned retail has become the development trend for the future society.However,traditional unmanned supermarkets have the defects of high cost,single selling method of fresh products such as fruits and vegetables,low efficiency,and large labor force.In order to solve above problems,an intelligent unmanned fruit and vegetable selling system based on deep learning is proposed.The system can identify fresh fruits and vegetables without electronic labels.Based on the improved target detection algorithm,the category and location of the fruits and vegetables are accurately identified,and then the goods are weighed,and the price of the goods is calculated.Through the experimental verification,the system has the advantages of synthesis,intelligence and specialization.The average accuracy(mAP)of the algorithm is improved by 7.37%on the self-made fruit and vegetable data set,and the experimental results show that this system has a strong robustness for the target detection of fruits and vegetables.
作者
吴晓凤
秦菁
刘子翔
徐浩然
WU Xiaofeng;QIN Jing;LIU Zixiang;XU Haoran(Xi'an Railway Vocational&Technical Institute,Xi'an 710026,China;Chang'an University,Xi'an 710064,China)
出处
《计算机测量与控制》
2023年第7期298-304,312,共8页
Computer Measurement &Control
基金
国家自然科学基金项目(52172379)。
关键词
无人售货
目标检测
实时通信
AI果蔬生鲜秤
嵌入式平台
深度学习
图像识别
unmanned sales
object detection
real-time communication
AI fruits and vegetables scale
embedded platform
deep learning
image indentification
