Gait analysis has become recently a popular research field and been widely applied to clinical diagnosis of neurodegenerative diseases. Various low-cost sensor-based and vision-based systems are developed for capturing the hip and knee joint angles. However, the performances of these systems have not been validated and compared between each other. The purpose of this study is to set up an experiment and compare the performances of a sensor-based system with multiple inertial measurement units (IMUs), a vison-based gait analysis system with marker detection, and a markerless vision-based system on capturing the hip and knee joint angles during normal walking. The obtained measurements were validated with the data acquired from goniometers as ground truth measurement. The results indicate that the IMUs-based sensor system gives excellent performance with small errors, while vision systems produce acceptable results with slightly larger errors.