22 skills found
cxdzyq1110 / Posture Recognition CNNTo help machines learn what we human beings are doing via a camera is important. Once it comes true, machines can make different responses to all kinds of human's postures. But the process is very difficult as well, because usually it is very slow and power-consuming, and requires a very large memory space. Here we focus on real-time posture recognition, and try to make the machine "know" what posture we make. The posture recognition system is consisted of DE10-Nano SoC FPGA Kit, a camera, and an HDMI monitor. SoC FPGA captures video streams from the camera, recognizes human postures with a CNN model, and finally shows the original video and classification result (standing, walking, waving, etc.) via HDMI interface.
Health-Devices-Research-Group / Posture And Fall Detection System Using 3D Motion SensorsThis work presents a supervised learning approach for training a posture detection classifier, and implementing a fall detection system using the posture classification results as inputs with a Microsoft Kinect v2 sensor. The Kinect v2 skeleton tracking provides 3D depth coordinates for 25 body parts. We use these depth coordinates to extract seven features consisting of the height of the subject and six angles between certain body parts. These features are then fed into a fully connected neural network that outputs one of three considered postures for the subject: standing, sitting, or lying down. An average classification rate of over 99.30% for all three postures was achieved on test data consisting of multiple subjects where the subjects were not even facing the Kinect depth camera most of the time and were located in different locations. These results show the feasibility to classify human postures with the proposed setup independently of the location of the subject in the room and orientation to the 3D sensor.
adaline-ankit / Fitness Trainer ApplicationAn AI-Driven fitness mobile application that provides real-time feedback. Works on the Meidapipe Pose Estimation Model and Tensorflow Pose Classification Models. The main Functionality of the application is to provide correct real-time feedback to the user about the Correct Posture for more than 7 exercises and Yoga Poses and also keep a Repetition count.
husencd / DriverPostureClassificationPyTorch-based Driver Posture Classification
ZhenchaoTang / Fine GrainedImageClassificationWeakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification
lukaszkepka / PostureGuardRealtime detection of incorrect sitting posture
AlifSrSE / RealTimeSurveillanceSystemAI-powered multi-camera surveillance with posture classification, fall/inactivity detection, heatmaps, and real-time alerts. Built using OpenCV, MediaPipe, Streamlit & Flask.
Fustincho / UD Private In Bed Posture ClassificationProject entry for the Secure and Private AI Challenge, hosted by Udacity and sponsored by Facebook (May - August, 2019)
Geniets / Posture Classification Deep LearningA project comparing a custom CNN and an EfficientNetB0 transfer learning model for classifying sitting posture into "Good" and "Bad" categories using TensorFlow
elizanyambu / Posture AnalysisIn this work, we presented how vision-based systems of artificial intelligence can be designed in order to gain insight into human posture and precisely classify postural abnormalities. For this, OpenPose and machine learning algorithms to analyze walking patterns of participants in order to observe anomalies during the gait cycle are investigated. The results indicate that the best re-sult classification of normal or abnormal gait can be achieved by combining the lateral and frontal perspective, by using angles features and by classifying the data with a linear SVM. Fur-thermore, our work is independent of the OpenPose framework, which means that our results can be used by any approach that can provide 2D coordinate data. In summary, this study pro-vides valuable insight into the human posture data and provides a reliable system for detecting abnormal gait.
msai-cereal / AI Fitness Trainer V1real-time exercise posture classification and assessment system implemented as an OpenCV library utilizing Ultralytics' YOLOv8 and LSTM
askmuhsin / Human Posture Helper CodeHelper-code base for human posture recognition/classification
TUI-NICR / Multi Task Person PerceptionContains the code and weights to our paper "Multi-Task Deep Learning for Depth-based Person Perception in Mobile Robotics" that was published on IROS 2020.
SohamPrajapati / Posture Detection Pose Classification Project"Welcome to our posture detection and pose classification web application repository! Utilizing Python, Flask, and libraries like Mediapipe, we empower users to monitor and classify human poses in real-time through webcam interactions. Perfect for fitness monitoring and gesture-based interfaces."
deepesh0203 / Sleep Posture ClassificationBuild ML model to analyze sleep posture from pressure mat readings. Further extend the project to analyze sleep patterns.
CodeSage4 / Classification Of Hand Postures Using Machine Learning ModelsNo description available
ostadabbas / Infant Posture EstimationAppearance-Independent Pose-Based Posture Classification in Infants (ICPRW2022)
rbr7 / Practical Machine Learning CourseraHuman Activity Recognition(HAR) - Case Study : Wearable Computing: Accelerometers’ Data Classification of Body Postures and Movements, using Random forests classifier to quantify and predict best way to do exercise.
Quhaoh233 / Human Posture ClassificationAn integrated network enables GCN+LSTM+TransfermorEncoderLayer for Human Posture Classification, which achieves an average of 80% accuracy.
HTAnh2003 / Classification Of Human Postures Sitting Standing LyingThis repository contains the source code for a real-time human pose classification system. It utilizes Mediapipe for pose estimation and a Support Vector Machine (SVM) for classifying poses into categories like sitting, standing, and lying down.
