Vehicle detection in video frames has been treated the same way detecting vehicle for an isolated image. However, the models designed for the isolated image are blind to fast-moving vehicles and cannot localize the moving targets partially occluded in the scene. In this case, we figure out a way to combine the classic moving target detection method with the neural network method. In this work, first, we propose to add three-differential-frames into the neural network of Yolov3 as the second input which contains the motion information on the front and back frames to detect vehicles partially occluded; second, we reform the network by using Octave Convolution to reduce memory and computational cost while boosting accuracy. We experimentally show that by using the aforementioned methods together, compared with using original YOLOv3 on UA-DETRAC data set, AP is increased by 2.31%, recall is increased by 4.01%, and precision is increased by 3.10%. We demonstrate that the proposed method is indeed effective.