Microcirculation plays a crucial role in delivering oxygen and nutrients to living tissues and in removing metabolic wastes from the human body. Monitoring the velocity of blood flow in microcirculation is essential for assessing various diseases, such as diabetes, cancer, and critical illnesses. Because of the complex morphological pattern of the capillaries, both in-vivo capillary identification and blood flow velocity measurement by conventional optical capillaroscopy are challenging. Thus, we focused on developing an in-vivo optical microscope for capillary imaging, and we propose an in-vivo full-field flow velocity measurement method based on intelligent object identification. The proposed method realizes full-field blood flow velocity measurements in microcirculation by employing a deep neural network to automatically identify and distinguish capillaries from images. In addition, a spatiotemporal diagram analysis is used for flow velocity calculation. In-vivo experiments were conducted, and the images and videos of capillaries were collected for analysis. We demonstrated that the proposed method is highly accurate in performing full-field blood flow velocity measurements in microcirculation. Further, because this method is simple and inexpensive, it can be effectively employed in clinics.