Abnormal plantar foot temperature changes are an early sign of diabetic foot (DF) ulcer, that can be detected using a thermal camera. This communication is composed of two main contributions. The first one concerns the segmentation of plantar foot thermal images. It consists of using the deep learning method U-Net to segment the thermal images. U-Net is trained by combining the two types of images (thermal and color) given by the thermal camera FLIR ONE Pro. Results show that this multimodal approach performs better than the one using only thermal images, especially for difficult cases. The second part is devoted to a transversal clinical study conducted within the Hospital National Dos de Mayo in Lima, Peru. 122 type II diabetic patients without ulcer were recruited. These individuals were classified into three risk groups of developing a foot ulcer. This classification is based on a medical examination: a low-risk group (R0), a medium-risk group (R1) and finally a high-risk group (R2). The study reveals that the average temperature of the plantar foot is 1°C higher in R1 than in R0 (p<0.1). The R1 group patients are characterized by a rapid recovery of their initial temperature after the cold stress test, compared to R0 and R2 (p<0.01). Finally, the mean absolute point-to-point temperature difference between left and right foot is lower in R1 than in R2 (p<0.1). These results demonstrate that thermal camera temperature assessment could help in the diagnosis of diabetic foot.