The field of vision of deep-sea submersible is usually limited, and it is difficult to observe the surrounding seabed through the video image of a single field of vision, which increases the difficulty for researchers to understand the overall distribution of seabed sediment. To solve the above problems, this paper proposes a fast stitching method of seabed sediment image based on deep-sea submersible image. Firstly, the red channel of the video frame is corrected based on the image enhancement method of channel compensation, and the brightness enhancement and CLAHE processing are carried out. Then, CUDA accelerated surf algorithm is used to extract feature points and descriptors, and KD tree algorithm is used to initially match the feature points of the front and back frames. Secondly, the KNN classification algorithm is used to eliminate the mismatching, and the inter frame motion estimation is carried out for the screened matching points. The base map is generated through the transformation matrix and the front and rear frames are spliced. Finally, the feature point coordinates and inter frame motion information are fused, and the above process is repeated to generate a continuous mosaic image. In this paper, the video images obtained by Jiaolong in a certain voyage are used for mosaic processing experiment. The results show that this method has good mosaic effect, and its feasibility is verified.