In order to achieve multiple targets in real-time or near real-time orientation, a multi-target selfdetermination orientation system based on airborne photoelectric imaging platform is established and a precise multi-target self-determination orientation model based on line-of-sight vector of pixel is proposed for the system.Using target detection algorithms to obtain the precise pixel coordinates of each target, the line-of-sight vectors of each target are constructed based on image forming principles for single-plane array charge coupled device(CCD) sensors, and the view angles of pixel between the main target at image center and other targets are calculated.Combining with the azimuth angle, elevation angle and the distance between the main target and the photoelectric platform, the distance and angle relations between other targets and the photoelectric platform are calculated. Based on the position and attitude information of aircraft, which is obtained by the global positioning system (GPS)heading and attitude measuring system, the homogeneous coordinate transformation method is applied to calculate the geodetic coordinates of multiple targets in a single image. For the orientation error caused by the lens distortion,a method based on the lens distortion ratio is presented to correct it. When flying at an altitude of 1100 m, the circular error probable (CEP) of multi-target self-determination orientation system is approximately 28.74 m, and the height error is about 18 m. It can geolocate 50 targets in a single image in real-time. When the lens distortion ratio is 2%, the CEP of multiple targets position data is reduced by 7% after correcting the lens distortion. The multitarget self-determination orientation method has high efficiency and is convenient for engineering application.