The invention discloses a Bayesian optimization exposure control method based on entropy weight image gradient, and relates to the technical field of vehicle-mounted cameras. According to the Bayesian optimization exposure control method based on the entropy weight image gradient, the entropy weight gradient is added on the basis of the gradient information of the original image, so that on one hand, gradient noise in the original image can be minimized, and on the other hand, a saturated mask can be established; therefore, the information loss of the original image is reduced to the maximum extent by reducing the overexposure or underexposure area, and the detail features of the original image are reserved; meanwhile, in order to avoid overlong exposure stabilization time of the camera, a Bayesian optimization algorithm is added in the exposure control method, and the optimal shutter time is obtained. The Bayesian optimization exposure control method is suitable for many computer vision target detection fields, such as scenes of lane detection, vehicle detection, pedestrian detection and the like.