The invention provides an improved convolutional neural network-based object detection method. The method comprises the following steps of: acquiring a mark image of a marked object; preliminarily training an improved convolutional neural network by adoption of a random sampling method, obtaining preliminarily classified positive samples and negative samples and corresponding classification probability values, and selecting a certain proportion of positive samples and negative samples according to the classification probability values to train the improved convolutional neural network so as toobtain a trained object detection model; inputting a to-be-detected image; and carrying out object detection on the to-be-detected image by adoption of the object detection model and outputting a detection result. Compared with the prior art, the method is capable of rapidly and correctly realizing object detection in images.