The invention discloses a bridge area ship navigation situation analysis method based on image recognition, which comprises the following steps: acquiring the navigation situation characteristics in the historical navigation of the ship; according to the navigation situation characteristics in the historical navigation of the ship, constructing the navigation situation database of the ship; according to the navigation situation characteristics in the historical navigation of the ship, constructing the navigation situation database of the ship; For ships to be inspected, use Viola-Jones frame detects the position of the ship in the channel surveillance video image. The AAM feature point location model based on multi-feature fusion is established to identify the navigation situation featuresof the ships to be detected in the channel surveillance video image by AAM feature point location model. A multi-feature fusion model based on support vector machine is established to match the shipposture features to be detected with the ship navigation posture database by using the multi-feature fusion model. According to the matching results, the real-time detection and alarm are carried outto detect the navigation situation of the ship during the voyage. The invention reduces the risk of ships navigating in the bridge area, and provides reference basis and safety guarantee for ships navigating and maneuvering.