This research aims to develop an object detection model capable of distinguishing the gait of normal and disabled people with high accuracy. Object detection is currently being developed to detect people and is being implemented in normal and gender-based gait recognition. Gait recognition, if further observed, includes recognizing both normal people and people with disabilities. Normal people walk like most people, but people with disabilities have different gaits from normal people. Some use walking aids, while others walk without them. Yolov8 is a platform for detecting people. This research proposes an object detection for normal people and people with disabilities, both those who use assistive devices and those who do not. The dataset used is Disabled gait, comprising 6500 images, and will be split into 3 data splits: 70% for training, 20% for validation, and 10% for testing. Model evaluation uses precision, recall, mAP50, and mAP50-90. The test results for 3 classifications, namely assistive, non-assistive, and normal, show the highest value in the assistive class with an mAP50 value of 0.98 and an mAP50-95 value of 0.996. This research provides a reliable gait-based object detection model that can accurately distinguish normal individuals from people with disabilities, including those using assistive devices. The findings support the development of more inclusive surveillance, healthcare, and mobility-assessment systems through high-performance detection validated by strong mAP scores.