『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: 應用於自動駕駛之影像辨識技術

技術簡介

以Lidar點雲資料為分析對象,開發針對以下三種在道路上最常見到的類型進行辨識:交通標示牌、路樹、以及建築物角落。本技術依據型態學、群集理論、尺寸大小等限制來進行偵測演算法的開發。 完成行人分類器,其TPR為90.5%、FNR為2.8%。針對大人與小孩之分類方式,將整合Lidar點雲所提供之「距離」資訊,在距離資訊為可信之前提下,將影像中之像素轉換為尺寸,視為「身高」之判斷依據,再將行人精細分類成成人與小孩,其TPR可達85.2%,FNR為3.8%。

Abstract

This technical using the point cloud data which collected by Lidar sensor to develop the 3 kinds recognition methods, includes road signs, tree, and the building corner. This technical using the morphological theory, the cludtering theory, and the dimension condition to develop the detection method. This technical had developed the pedestrian classifier, which TPR is 90.5% and the FNR is 2.8%. Besides, it can combine the "distance" information from the Lidar sensor to detect the adult and child pedestrian, which TPR is 85.2% and FNR is 3.8%.

技術規格

. 將偵測到物件後到做出決策之間的系統反應時間控制<0.75sec,低於人類的平均反應時間 . 針對Lidar資料進行交通號誌、路樹、建築物角落等物件辨識正確率>90%以上。

Technical Specification

. Response time<0.75sec . Inspection TPR > 90% . TPR ?85% . FNR ?4%)

技術特色

本技術型態學、叢集理論、以及相關尺寸大小等理論基礎開發辨識演算法,針對Lidar資料進行辨識,可有效提升系統可靠度、辨識速度與準確率。 兩輪車及行人之辨識,針對台灣多雙輪車及行人之特色,可實際應用在自動駕駛感知次系統中。 開發以Yolo v.3為基礎之物件辨識機器學習模組,並針對台灣交通中,在都會區兩輪車與行人為大多數之特殊現象,進行辨識演算法最佳化之開發。此辨識模組可以全面強化自駕車針對台灣都會區兩輪車與行人之辨識率,提升國內產業競爭力。

應用範圍

車用電子檢測

接受技術者具備基礎建議(設備)

光學檢測設備

接受技術者具備基礎建議(專業)

廠商需具備機器學習演算法之基礎能力,並可自行架設取像光學模組,即可承接工研院開發技術,但為了提高辨識之準確性,針對不同環境、天候等因素則須蒐集大量當地實地影像進行訓練。

技術分類 智慧視覺系統技術

聯絡資訊

聯絡人:翁季萍(880141) 智慧視覺系統組

電話:+886-3-5915737 或 Email:cpweng@itri.org.tw

客服專線:+886-800-45-8899

傳真:+886-3-5917531

[{"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}]