Object detection is a crucial task with numerous applications. The ability to detect changes in an object requires monitoring its behavior over time to recognize any alterations. This task is crucial in various domains, ranging from basic image analysis to remote sensing applications, where understanding geographic changes is of utmost importance. For example, in the production of printed circuit boards and integrated circuits, detecting component errors is essential. Similarly, in astronomy, tracking the movement of astronomical objects and changes in land cover due to tectonic plate deviations are of great interest. Change detection and tracking models are therefore in high demand. However, current models that use Earth Mover’ Distance (EMD) for binary classification of object changes have limited applications. Therefore, an alternate position change identification model that can function as a substitute for deep learning methods is required. In this study, we propose a model that utilizes Mean Square Error (MSE)in place of EMD and considers the variation in image intensity from pixel to pixel to improve accuracy. Moreover, to overcome the limitations of binary classification our model categorizes images into multiple groups based on their chronological position. This enables us to identify the differences between various time periods more accurately. To train and evaluate our model, we use synthetic images, allowing us to create a model that can function with less data compared to current methods. Overall, our proposed model can significantly improve object change detection in various domains, making it a valuable addition to the field.