The invention relates to a target object ranging method based on deep learning under a truck environment. The target object ranging method comprises the following steps of S1: obtaining target objectimage data; S2: preprocessing the obtained target object image data; S3: inputting the preprocessed target object image data into an SSD (Steady-State Distribution) model, and processing by the SSD model to obtain the pixel position coordinate of a target object in an image; S4: according to the identified pixel position coordinate of the target object in the image, through the image ranging method, calculating a distance between the target object and an image collection device, thus obtaining the distance between the target object and the image collection device, wherein the SSD model is a compressed and improved model, and the target object image data is target object image data obtained under an overlooking condition. For the target object which needs to be identified by a mine area truck, the ranging method provided by the invention has the advantages of high identification speed, high identification efficiency, high ranging speed since a monocular ranging method is used and the like.