Robust Alzheimer’s Patient Detection and Tracking for Room Entry Monitoring Using YOLOv8 and Cross Product Analysis

Recent advances in computer vision and artificial intelligence (AI) have made real-time people counting systems extremely reliable, with experts in crowd control, occupancy supervision, and security. To improve the accuracy of people counting at entry and exit points, the current study proposes a deep learning model that combines You Only Look Once (YOLOv8) for object detection, ByteTrack for multi-object tracking, and a unique method for vector-based movement analysis. The system determines if a person has entered or exited by analyzing their movement concerning a predetermined boundary line. Two different logical strategies are used to record entry and exit points. By leveraging object tracking, cross-product analysis, and current frame state updates, the system effectively tracks human flow in and out of a room and maintains an accurate count of the occupants. The present approach is supervised on Alzheimer’s patients or residents in the hospital or nursing home environment where the highest level of monitoring is essential. A comparison of the two strategy frameworks reveals that robust tracking combined with deep learning detection yields 97.2% and 98.5% accuracy in both controlled and dynamic settings, respectively. The model’s effectiveness and applicability for real-time occupancy and human management tasks are demonstrated by performance measures in terms of accuracy, computing time, and robustness in various scenarios. This integrated technique has a wide range of applications in public safety systems and smart buildings, and it shows considerable gains in counting reliability.