Detecting neuropsychiatric symptoms (NPS) such as anxiety, agitation, or depression is essential because it enables the early identification and more tailored treatment of mental health conditions. Currently, NPS is detected using patient- or caregiver-reported outcomes, which can be inherently subjective and prone to various biases. The goal of this project is to develop an automated system based on novel ambient intelligence and computer vision technologies that objectively detect NPS. We aim to design a clinician-facing dashboard to provide healthcare professionals with better insights into a patient's activities of daily living and their behavioral context. By recognizing these signs early, individuals can receive the necessary support to effectively manage their symptoms, slow the progress of mental or neurodegenerative disorders, and lead healthier, more fulfilling lives.