Accurate object detection using memory-based models in surveillance scenes

Object detection is a significant step of intelligent surveillance. The existing methods achieve the goals by technically designing or learning special features and detection models. Conversely, we propose an effective method for accurate object detection, which is inspired by the mechanism of memory and prediction in our brain. Firstly, a fix-sized window is slid on a static image to generate an image sequence. Then, a convolutional neural network extracts a feature sequence from the image sequence. Finally, a long short-term memory receives these sequential features in proper order to memorize and recognize the sequential patterns. Our contributions are 1) a memory-based classification model in which both of feature learning and sequence learning are integrated subtly, and 2) a memory-based prediction model which is specially designed to predict potential object locations in the surveillance scenes. Compared with some state-of-the-art methods, our method obtains the best performance in term of accuracy on three surveillance datasets. Our method may give some new insights on object detection researches.