『您的瀏覽器不支援JavaScript功能,若網頁功能無法正常使用時,請開啟瀏覽器JavaScript狀態』

跳到主要內容區塊

工業技術研究院

:::

技術名稱: 無人商店技術

技術簡介

融合多重感測與電腦視覺技術,進行即時顧客商品取放辨識及追蹤綁定,實現「拿了就走」的購物情境。

Abstract

Combining sensor fusion and computer vision technologies to identify exactly what a customer pick up or push back in real time, and realized "grab-and-go" purchasing scenario.

技術規格

本技術實現「拿了就走」無縫式購物流程,將實體商店完整數位化。技術主要包含商品取放與追蹤綁定,其中商品取放辨識用於結帳的自動化是智慧商店的基礎,RFID技術已推行多年但成本因素以及含有金屬、水分的包裝或商品會產生干擾的問題,一直無法廣泛實用。近年因影像辨識技術的進展,而有導入影像辨識的系統出現。相較於純影像的技術,本技術藉由其他多種sensors的輔助,可突破影像辨識的瓶頸,達到足夠的準確率,同時,建模成本與運算成本也比較低。Amazon Go 是第一個將 sensor fusion技術用於結帳自動化,現行版本在貨架內並無攝影機,而是藉由廣布於天花板的攝影機與高精度的重量感應器來判斷。本技術在貨架內配有攝影機與一般的重量感應器,也因此智慧貨架可獨立運作,不需仰賴環境攝影機。

Technical Specification

A realization of "grab and go" seamless shopping process and a totally digitalization for brick-and-motar retail. The technology mainly composed of 2 parts (1) item pick up/place back recognition (2) customer tracking and binding. Item pick up back/ place back recognition is the basis of intelligent store technology. It has been decades for introducing RFID into this application. Due to the cost problem and metal, water interference issues, it’s hard to be widely applied. Computer vision solutions appeared recently thanks to the advances on computer vision technology. Compare to the pure computer vision, our solution made a breakthrough to the accuracy bottleneck under the help of the sensors. We reached the high standard of accuracy with lower modeling and computing costs. Amazon Go is the first sensor-fusion based automatic checkout system in the world. Instead of using cameras on the smart shelves, the current version of Amazon go chooses high precision load cells on the smart shelves with the help of the large amount of roof-mounted cameras. Our system, by contrast, is with the setting of on-self cameras and normal load cells, which makes it possible for the smart shelves to operate independently.

技術特色

本技術可發展(1)拿了就走無人商店(2)智慧商品架等相關應用,並可搭配後端系統發展智慧補備、顧客定義商品陳列、倉庫物料管理以及自助取貨等延伸應用。

應用範圍

可應用於零售場域或特殊場域如辦公室、工廠、住宅社區等,或結合服務的一人店。此外,亦可應用於倉儲、物料管理如無人物料室等應用。

接受技術者具備基礎建議(設備)

可支援AIOT之運算、系統管理架構。

接受技術者具備基礎建議(專業)

商店系統整合之基礎建置能力。

技術分類 智慧商務技術及服務

聯絡資訊

聯絡人:李紀幸 執行長室

電話:03-5917062 或 Email:GraceCHLee@itri.org.tw

客服專線:+886-800-45-8899

傳真:03-5910257

[{"text":"企業網","weight":13.0},{"text":"材化所","weight":11.5},{"text":"機械所","weight":10.0},{"text":"綠能所","weight":9.4},{"text":"生醫所","weight":8.0},{"text":"半導體","weight":6.2},{"text":"南分院","weight":5.0},{"text":"太陽能","weight":5.0},{"text":"課程","weight":5.0},{"text":"遠紅外線","weight":5.0},{"text":"雷射","weight":4.0},{"text":"LED","weight":4.0},{"text":"LED可見光","weight":3.0},{"text":"5G","weight":3.0},{"text":"工研人","weight":3.0},{"text":"電光所","weight":3.0},{"text":"綠能與環境研究所","weight":3.0},{"text":"機械","weight":3.0},{"text":"資通所","weight":2.0},{"text":"面板","weight":2.0},{"text":"文字轉語音","weight":2.0},{"text":"實習","weight":2.0},{"text":"無人機","weight":2.0},{"text":"生醫","weight":2.0},{"text":"3D","weight":2.0},{"text":"v2x","weight":2.0},{"text":"員工","weight":2.0},{"text":"地圖","weight":2.0},{"text":"太陽光電","weight":2.0},{"text":"材料與化工研究所","weight":1.0}]