Target detection method based on deep learning

The invention discloses a target detection method based on deep learning. The method comprises the following steps: determining a target area to be detected; inputting the target area into a detection network pre-trained based on deep learning, and carrying out forward propagation to obtain the first qualified probability; carrying out cutting operation on the target area to obtain a plurality of point locations. After a target area to be detected is determined, the target area can be input into a detection network based on deep learning pre-detection to carry out front-position transmission, obtain a first qualified probability, determine a key area of a target picture, and input the key target area into the detection network based on deep learning pre-detection to carry out front-position transmission, the second qualification probability is obtained, whether the target detection area is qualified or not is determined according to the first qualification probability and the second qualification probability,