The Belt and Road (B&R) initiative is proposed to promote common development among countries along the B&R. In recent years, although the B&R has contributed to the regions along the route, it is always a controversial topic in the international community. A number of scholars have done a set of research works to analyze the effects of the B&R projects based on traditional economic methods. However, the drawbacks of subjectivity and delay reduce the conviction of the analysis results. In this paper, we leverage the objectivity and real-time features of remote sensing (RS) images to analyze the effects of the B&R project. Our research takes Voi town along the Mongolia-Nairobi Railway as the representative city. In addition, in order to prove the causal relationship between the B&R and economic development, we select the Taveta town as the comparison city. The semantic segmentation based on deep learning is applied to the multi-temporal RS images, to retrieve the economic development by automatically recognizing houses. On this basis, the construction and development of both the studied region and the comparison are quantitatively analyzed by meshing analysis and standard deviation elliptic methods. For overcoming the shortages of the conventional algorithms, a novel segmentation network based on the attention mechanism is proposed. The evaluation proves the semantic segmentation results can fully support the follow-up data analysis. In addition, the analysis results show that our work is a convincing initiative to reveal the values of the B&R projects for economic developments in the B&R-related regions.