2011-01-012024-05-18https://scholars.lib.ntu.edu.tw/handle/123456789/699501摘要：即時多維全域感測(multi-dimensional full-field sensing)為智慧型機器人對核能電廠危險急難救援行動之一項核心關鍵技術發展重點，即時多維視覺資訊提供災變中救災行動能力極為重要之首要救災環境中空間與物件訊息，藉由即時多維全域感測資料(2D影像+3D形貌+輻射強度)之整合成為關鍵之救災資訊，對多機器人協同在危險環境中對特定物件之偵測與辨識與危急程度評估，提供不可或缺之核心資訊。因此，本計劃提出以三年計劃之多年期發展，研發重點將包括危險環境中多維感測影像之偵測與重建能力、多機器人協同對特定物件(如受傷人員)之偵測與辨識與危急程度評估，以進一步發展出在危險環境中救災之精確動作導引與事件發展之監控能力。 計畫之第一年將著重於單機器人即時多維影像偵測系統與環境重建之研發，發展高速影像(含光譜資訊)處理、多視角全域影像校正以及多維資料疊合技術，以達成即時全域多維影像光學偵測與重建系統。以第一年之發展成果為基礎，第二年將發展多機器人協同對即時多維影像偵測系統與環境重建技術，將發展具有避免偵測死角之即時多維感測能力，多機器人之即時多維感測影像之疊合技術，對欲偵測之危險急難環境，快速重建完整即時多維影像資訊。以第二年之發展為基礎，第三年將發展自動化即時多維影像之特徵擷取技術，以利獲得危險急難環境中物件(如救難人員目標)之形貌與影像特徵，達成多維影像之有效資料減容與關鍵特徵萃取之目標，建立以物件形貌與影像色譜特徵為基礎之智慧型物件偵測(detection)與辨識(recognition)技術，配合多機器人之協同資訊整合能力，發展一套對救難情況之自動化精確定位與監控能力。<br> Abstract: Applications of high-speed machine vision to be equipped with intelligent robots for accurate 3-D model reconstruction and object recognition are extremely critical for winning success in today’s globally competitive world. New generation machine vision systems having complicated optical image algorithms, electro-optic hardware and intelligent software systems are now capable of delivering on the simultaneous promises of high-speed and high-reliability 3-D object detection, especially for an intelligent robot operation in fields. The optical machine vision technology has thus become an essential method and expertise for developing intelligent robots. The main objective of this project is to develop an innovative real-time 3-D machine vision system and methodology using optical interferometry and to develop object recognition capability using reconstructed 3-D information. It also aims to develop a miniaturized optical vision system for intelligent robot operation. The system to be developed integrates an innovative spontaneous optical interferometric principle and a novel optical detection method to become capable of measuring dynamic 3-D surface characteristics with a measurement bandwidth up to few hundreds Hz level bandwidth. In addition, to satisfy spontaneous operation demands of an in-field robot operation, the project also includes the development of an innovative 3-D reconstruction and shape recognition method, to speed up fast object searching and accurate identification. Therefore, the objectives of this three-year project have been targeted to achieve the following development: (1/3)：Development of an innovative real time 3-D image detection system for robot vision. (2/3): Miniaturization and optimization of the real time 3-D image detection system for robot vision. (3/3): Development of innovative 3-D object shape reconstruction and recognition for robot vision.非破壞檢測 (NDT)影像重建線上監控技術機器視覺NDTimage imaging and reconstructionin-line monitoringmachine vision