The present disclosure discloses an aircraft (e.g., unmanned aerial obstacle detection method and apparatus, to reduce aircraft obstacle detection errors, and improve aircraft obstacle detection precision. The apparatus performs image collection on a target obstacle by using a binocular camera, to obtain a first image and a second image. After determining a first pixel location obtained by projecting the target obstacle in the first image, and a second pixel location obtained by projecting the target obstacle in the second image, the apparatus calculates a disparity between the first pixel location and the second pixel location and a depth value between the binocular camera and the target obstacle according to the disparity and a preset disparity-to-depth mapping matrix, to detect whether a flight direction of the aircraft is blocked by an obstacle.