Object detection from still images has been among the most active and challenging area in computer vision recently. In contrast, fully supervised object detection from video has rarely been investigated. In this paper, we propose an algorithm to improve the performance of object detection from video. Our proposed method is based on an empirical property that the trajectory of an object is important for detection in videos. We use object trajectory to filter outliers, determine probable location of object and correct detection errors. We compare our method with baseline method which regard video frames as still images directly. Experiments show that our method outperform the compared baseline in terms of average precision while inducing moderate computation overhead.