隨著虛實互動展演的發展，以人體姿態估計取代穿戴式設備，讓使用者直接以動 作與設施互動，逐漸成為重要的應用需求。這類場域多為多人互動且容易產生遮擋，須以多台固定攝影機從多視角同時拍攝，並維持自影像擷取至 3D 姿態輸出全程的即時性。然而，現有多視角 3D 人體姿態估計研究多採循序式架構，難以滿足多視角處理的低延遲需求；且在即時性較佳的三角測量方法中，2D 偵測誤差會直接導致 3D 骨架變形。 針對上述動機，本研究設計並實作一套無須專用硬體的多視角多人 3D 姿態估計端 到端系統，具體貢獻包含：設計影像擷取、2D 推論、多視角資料處理、人物姿態重建與輸出五層分散式架構，以並行處理降低系統整體延遲；整合時間同步、時間差過濾與補幀機制，在視角延遲下維持運算所需的有效視角數量；並導入骨長修正方法，改善 2D 偵測誤差造成的骨架異常。 實驗結果顯示，本系統能連續七天穩定運作，於有人活動時段內 99.986% 的時間 維持 30 FPS 以上，且端到端延遲低於 60 毫秒。在 CMU Panoptic 資料集上，骨長修正機制將骨架長度誤差（Bone Length Error， BLE）由 26.28 mm 降至 22.11 mm；在模擬視角延遲情境下，時間同步與補幀機制將 BLE 由 22.28 mm 降至 21.34 mm。驗證了本系統在維持低延遲的同時，能有效維持 3D 骨架品質。;With the development of virtual-real interactive exhibitions， replacing wearable devices with human pose estimation (HPE) allows users to interact directly through body motion. Such scenarios involve multi-person interaction and frequent occlusion， requiring multiple fixed cameras to capture the scene from multi-view while maintaining real-time performance from image capture to 3D pose output. However， existing multi-view 3D HPE studies mostly adopt sequential architectures， struggling to meet low-latency demands. Furthermore， while triangulation offers low latency， 2D detection errors directly cause 3D skeleton deformation. To address these issues， this study designs and implements an end-to-end multi-view multiperson 3D pose estimation system without specialized hardware. The main contributions include: designing a five-layer distributed architecture (image capture， 2D inference， multi-view data processing， pose reconstruction， output) to reduce latency via parallel processing; integrating time synchronization， time-difference filtering， and frame fill-in mechanisms to maintain sufficient views under delays; and adopting bone length correction to fix 2D-induced skeletal anomalies. Experimental results show that the system operates stably for seven days. During human activity periods， it maintains 30 FPS or above and an end-to-end latency below 60 ms for 99.986% of the time. On the CMU Panoptic dataset， bone length correction reduces the bone length error (BLE) from 26.28 mm to 22.11 mm， while time synchronization and fill-in mechanisms reduce it from 22.28 mm to 21.34 mm under simulated delays， verifying both real-time performance and skeleton quality.
