基於影像處理之人體姿態辨識

Abstract

本論文之主要目的在於藉由攝影機擷取到的影像資訊，得以在環境中尋找人員的存在，並且完成六種人體姿態的辨識。本系統使用膚色與髮色資訊，以及連通標記法(Connected component labeling)完成人頭的偵測，再用橢圓模型與人體模型來辨識影像中存在的人體。利用所找到的人體資訊與相關特徵，本論文完成一套可用來判斷人體姿態的影像處理系統。此外，本論文使用類神經網路融合影像辨識資訊與實驗室之基於三軸加速規之人體姿態估測資訊，實驗結果發現，融合前的影像平均辨識率為79.23%，人體姿態估測模組為88%，融合後之平均辨識率可達93.5%。

Real-time body pose information is very useful for many human-robot interaction applications. However, due to the motion of both human and the robot, robust body pose recognition poses a challenge in such a system design. This thesis aims to locate a human body in the image plane and then recognize six body poses through image recognition. The color-space techniques and the method of connected component are used to detect a human. Ellipse models and body shape patterns are used to locate human body in the video stream. Furthermore, a neutral network has been designed to fuse data from image recognition and inertial sensors to improve the recognition rate under various environmental variations. Experimental results show that the average recognition rate of six body poses is 93.5%, an improvement from 79.23% and 90.67% of using only image recognition and inertial sensor respectively.