Name
Abstract | ||
|---|---|---|
A memory-based method is proposed for accurate object detection in surveillance scenes.Two models imitate the mechanism of memory and prediction in our brain respectively.Feature learning and sequence learning are integrated in a memory-based classification model.A memory-based prediction model is specially designed to output the mask indicating the potential object locations. 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. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.patcog.2017.01.030 | Pattern Recognition |
Keywords | Field | DocType |
Convolutional neural network,Long short-term memory,Object detection | Viola–Jones object detection framework,Computer science,Convolutional neural network,Artificial intelligence,Sequence learning,Memorization,Object detection,Computer vision,Object-class detection,Pattern recognition,Effective method,Machine learning,Feature learning | Journal |
Volume | Issue | ISSN |
67 | C | 0031-3203 |
Citations | PageRank | References |
11 | 0.52 | 29 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xudong Li | 1 | 56 | 4.11 |
| Mao Ye | 2 | 442 | 48.46 |
| Yiguang Liu | 3 | 338 | 37.15 |
| Feng Zhang | 4 | 32 | 11.36 |
| Dan Liu | 5 | 115 | 19.90 |
| Song Tang | 6 | 17 | 2.67 |