<![CDATA[Egg counting is an important stage in the laying hen farming industry because it directly affects productivity and the efficiency of production management. Manual counting methods still have several limitations, including relatively long processing time, the need for a large workforce, and a fairly high error rate due to human factors. These conditions indicate the need for the implementation of automated technology capable of improving speed, accuracy, and consistency in the egg counting process. This study aims to develop an automatic egg counting system based on computer vision by integrating YOLO11 as the object detection method and ByteTrack as the object tracking method. The egg dataset was collected through image acquisition under various conditions, followed by annotation and data augmentation processes before being used in the model training stage using Google Colab.The test results show that the developed system is capable of detecting and counting eggs with a high level of accuracy, where precision and recall values exceed 0.90, and the average counting accuracy reaches 94.4% under various testing conditions. The main factors affecting system errors are high conveyor speed, which causes motion blur, and lighting variations that can lead to false positives and false negatives. The main contribution of this research is the development of a camera-based counting system design, thereby reducing errors in counting the number of eggs. The results of this study indicate that the integration of YOLO11 and ByteTrack has the potential to improve the efficiency of automated egg counting processes and contribute to the advancement of computer vision technology in the modern poultry industry.]]>
