Human posture estimation (HPE) was an attractive concept that includes the prognosis of articulated joint position of the human body from the sequences of images of a specific person. Human postures estimation through computer interactions was a key factor that involves the human movements and positions during sitting, standing, walking, running, jumping, throwing, catching, and even talking. Different body dimensions (2D/3D) and landmarks were investigated through the proper channel using computer learning models. There are numerous learning programs to understand human posture estimation in computer programming. Commonly used machine learning techniques for posture recognition are deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), etc. Computer interaction learning was prominent areas of analysis and evaluation. The artificial intelligence (AI) helps to analyse human body through segmental domain of interest using various computer applications. Such types of studies require a huge database depending upon the type of evaluation and testing. The human body had a great bipod interactions for erect posture and also an advantage of the abundance of movement patterns involved. In this concept, both human posture analysis and human movement estimations have a significant role to evaluate the state of health, fitness, and skill perfections. This review will provide an overlook to the insight of different models under different use and response of computerized interactions. Here, the published materials in different journals have been put forward to see and compare different types of interventions made so far.