『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: 基於深度學習之即時物件偵測與辨識技術

技術簡介

基於深度學習之物件辨識技術,其可在DrivePX2上達到30FPS

Abstract

deep learning-based multi-class object detection which could achieve 30 FPS on NVIDIA DrivePX2

技術規格

辨識距離18m 車速<30km/h 系統更新率<30FPS

Technical Specification

"detection range:18m speed limitation: 30 km/h FPS:>30"

技術特色

本物件偵測模型使用了GoogLenet做為卷積神經網路之基底,其架構可使用NVIDIA之特製軟體(TensorRT)最佳化,使得基於卷積神經網路之行車即時物件偵測變得可能 特色: 1. 單一CNN, 2. 解讀CNN最後一層即可完成物件偵測辨識 3. CNN架構為眾深度學習框架所支援

應用範圍

各式車輛

接受技術者具備基礎建議(設備)

NVIDIA DrivePX2, Caffe, Driveworks, TensorRT

接受技術者具備基礎建議(專業)

資訊/電機

技術分類 汽機車與自行車

聯絡資訊

聯絡人:陳斌勇 智慧車輛技術組

電話:+886-3-5915817 或 Email:kelvin_chen@itri.org.tw

客服專線:+886-800-45-8899

傳真:+886-3-5820452

[{"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}]