Action recognition is one of computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes. Human Action Recognition (HAR) is a challenging task that has various applications, such as intelligent video surveillance and human-computer interaction. In this paper we describe a method of HAR for outdoor monitoring system. For detection a person we utilize YOLO v.8. then from the sequential frames we extract a motion feature. We use pre-trained VGG-16 model for spatial feature extraction. Then, this feature vector is fed to action classifier.