Fall events are important health issues in elderly living environments like homes. Hence, a confident and real-time video surveillance device that pays attention could better their everyday lives. We proposed an optical flow feedback convolutional neural network according to the video stream in a home environment. Our proposed model uses rule-based filters before an input convolutional layer and the recorded optical flow for supervising the optical flow of variation. Detecting human posture is a key factor while fall events are like a falling posture. By sequencing frames of action it is possible to recognize a fall. Our system can clearly detect the normal lying posture and lying after falling. Our proposed method can efficiently detect action motion and recognize the action posture. We compared the performance with other standard benchmark datasets and deployed our model to simulate a real home situation, and the correct ratio achieved 82.7% and 98% separately.

Under the vigorous development of global anticipatory computing in recent years, there have been numerous applications of artificial intelligence (AI) in people’s daily lives. Learning analytics of big data can assist students, teachers, and school administrators to gain new knowledge and estimate learning information; in turn, the enhanced education contributes to the rapid development of science and technology. Education is sustainable life learning, as well as the most important promoter of science and technology worldwide. In recent years, a large number of anticipatory computing applications based on AI have promoted the training professional AI talent. As a result, this study aims to design a set of interactive robot-assisted teaching for classroom setting to help students overcoming academic difficulties. Teachers, students, and robots in the classroom can interact with each other through the ARCS motivation model in programming. The proposed method can help students to develop the motivation, relevance, and confidence in learning, thus enhancing their learning effectiveness. The robot, like a teaching assistant, can help students solving problems in the classroom by answering questions and evaluating students’ answers in natural and responsive interactions. The natural interactive responses of the robot are achieved through the use of a database of emotional big data (Google facial expression comparison dataset). The robot is loaded with an emotion recognition system to assess the moods of the students through their expressions and sounds, and then offer corresponding emotional responses. The robot is able to communicate naturally with the students, thereby attracting their attention, triggering their learning motivation, and improving their learning effectiveness.

Automatic learning feedback monitoring and analysis are becoming essential in modern education. We present a video analytic system capable of monitoring in-class student’s learning behaviors and providing feedback to the instructor. It is a common practice nowadays for students to take electronic notes or browse online using laptops and cellphones in class. However the use of technology can also impact student concentration and affect learning behaviors, which can seriously hinder their learning progress if not controlled properly. In this pioneering study, we propose a non-intrusive deep-learning based computer vision system to monitor student concentration by extracting and inferring high-level visual behavior cues, including their facial expressions, gestures and activities. Our system can automatically assist instructors with situational awareness in real time. We assume only RGB color images as input and runable system on edge devices for easy deployment. We propose two video analytic components for student behavior analysis: (1) The facial analysis component operates based on Dlib face detection and facial landmark tracking to localize each student and analyze their face orientations, eye blinking, gazes, and facial expressions. (2) The activity detection and recognition component operates based on OpenPose and COCO object detection can identify eight types of in-class gestures and behaviors including raising-hand, typing, phone-answering, crooked-head, desk napping, etc. Experiments are performed on a newly collected real-world In-Class Student Activity Dataset (ICSAD), where we achieved nearly 80% activity detection rate. Our system is view-independent in handling facial and pose orientations with average angular error < 10°. The source code of this work is at: https://github.com/YiZengHsieh/ICSAD .

This study presents a stereo vision robotic arm assistance system, in which five degrees of catching can be performed by the robot arm in a single instance. The algorithm of the control system is built for population-based optimization and specifically aimed to assist people with disabilities. The proposed stereo vision-based robot arm system enables users to manipulate objects based on the robot’s ability to aim at objects by using computer vision. The stereo vision system counts the parameters by focusing on the real-word position of the instance in the coordinate system. A trained deep fully connected network is then adopted to compensate the location measurement errors incurred by the inaccurate parameters measured from the deep learning procedure. Subsequently, the proposed Q-learning-based swarm optimization algorithm is adopted to solve the forward kinematics problem and count the angles of each servo. The performance of the robot arm is compared with several real-life experiments to test its ability to grip a target object in different positions.

In recent years, the breakthrough of neural networks and the rise of deep learning have led to the advancement of machine vision, which has been commonly used in the practical application of image recognition. Automobiles, drones, portable devices, behavior recognition, indoor positioning and many other industries also rely on the integrated application, and require the support of deep learning and machine vision. As for these technologies, there is a high demand for the accuracy related to the recognition of portraits or objects. The recognition of human figures is also a research goal that has drawn great attention in various fields. However, the portrait will be affected by various factors such as height, weight, posture, angle and whether it is covered or not, which affects the accuracy of recognition. This paper applies the application of deep learning to portraits with different poses and angles, especially the actual distance of a single lens for the shadowed portrait (depth estimation), so that it can be used for automatic control of drones in the future. Traditional methods for calculating depth using images are mainly divided into three types: one—single-lens estimation, two—lens estimation, and three—optical band estimation. In view of the fact that both the second and third categories require relatively large and expensive equipment to effectively perform distance calculations, numerous methods for calculating distance using a single lens have recently been produced. However, whether it is the use of traditional “units of distance measurement calibration”, “defocus distance measurement”, or the “three-dimensional grid space messages distance measurement method”, all of these face corresponding difficulties and problems. Additionally, they have to deal with outside disturbances and process the shadowed image. Therefore, under the new research method, OpenPose, which is proposed by Carnegie Mellon University, this paper intends to propose a depth algorithm for a single-lens occluded portrait to estimate the actual portrait distance for different poses, angles of view and obscuration.