Contact measurements of the respiration rate using conventional electrocardiogram (ECG) equipment requires patients to wear chest straps that can cause skin irritation and discomfort. Therefore, a novel robust non-contact technique is developed for the evaluation of respiration rate variation. The periodic variation of optical flow can be observed from the changes of simple harmonic motion between inspirations and inspirations from the human’s upper body. Therefore, in order to characterize the motion, a salient region is automatically selected in the energy map resulted from Haar-Like features through consecutive frames. Furthermore, a median optical flow signal is used to acquire the primary respiration signal. The effective instantaneous frequencies from vertical variation decomposed by median optical flow signal are computed by the calculation of zero crossing points to evaluate respiration rates before the frequencies were rectified by an estimation of the noise elimination method. In addition, the proposed system can be conducted in real-time manner. Experimental results show that our proposed approach outperforms the current state-of-the-art approach with higher accuracy and smaller variance being achieved.使用傳統的心電圖(ECG)儀器計算呼吸率,接觸式量測需要患者穿戴胸帶,會引起皮膚刺激和不適。因此,一種新的非接觸式技術被開發用於呼吸率變化的計算。根據人上半身的區域去找尋區域要進行光流變化,Salient Area的能量圖是由Haar-Like特徵得到。此外,由上半身區域得到的Salient Area去計算中位數的光流訊號利用垂直的瞬時頻率變化獲取呼吸速率訊號,由中位數分解越零點計算評估的頻率是由濾波方法的估計之前。此外,還提出了使用照相機和非接觸式呼吸率即時監測系統。實驗結果表明,該方法比目前的先進設備提供更高的準確度。a~h‧‧‧步驟
