The invention belongs to the technical field of bridge structure defects, and particularly discloses an
underwater bridge structure defect identification method based on
machine vision, and the method comprises the steps: firstly, employing a water surface monitoring camera to detect water surface moving objects around a
pier, and carrying out the recognition of the
underwater bridge structure defects based on the types, distribution density and motion trails of the objects; constructing a static distribution
interference factor and a
dynamic motion interference factor, and performing weighted fusion to generate a
water body detection interference coefficient. Meanwhile, the water
turbidity and the real-time flow velocity are obtained by means of an
underwater sensor, and the light supplementing distance, the
red light proportion and the
shutter speed are dynamically adjusted in combination with the water detection interference coefficient. Then, the ROV is controlled to descend with the axis of the
pier as the spiral center, visible light and
ray transmission images are synchronously collected according to the adjusted parameters, a panoramic image is formed through
fusion splicing, finally, defect danger indexes are output through image recognition and fed back, efficient detection and accurate evaluation of the state of the
pier are achieved, and reliability and effectiveness of defect recognition are enhanced.