<![CDATA[Object detection is very we often find in everyday life that facilitates every activities in the object recognition process, for example in the military field, intelligent transportation, face detection, robotics, and others. Detection target detection is one of the hotspots of research in the field of computer vision. The location and category of the target can be determined by using target detection. Currently, target detection has been applied in many fields, one of which includes image segmentation.You only look once (YOLO) is an algorithm that can perform object detection in realtime, YOLO itself always gets development and improvement from previous versions. YOLOv8 is a type of YOLO from the latest version. YOLOv8 is a new implementation of Deep Learning that connects the input (original image) with the output. This type of YOLOv8 algorithm uses A deep dive architecture, assisted by CNN and a new backbone which uses convolutional layers for pixels which when described will be shaped like a pyramid. YOLOv8 is a stable object detection processing method with 80% higher than the previous version of YOLO, which makes YOLOv8 a type of YOLO that is better at processing object data faster and more efficiently in Real-Time.The camera with omnidirectional system is able to detect spherical objects and other objects using the YOLOV8 model used. In performance testing with 320×320 and 416×416 frames, because it fits the grid structure of the YOLO architecture. YOLOv8 has a higher mAP value with a value of 95,5% compared to previous versions of YOLO. In the detection test, YOLOv8 has a better average object detection than the previous version of YOLO which is indicated by the number of objects detected more stable.]]>
