Name
Abstract | ||
|---|---|---|
Traffic sign detection (TSD) using convolutional neural networks (CNN) is promising and intriguing for autonomous driving. Especially, with sophisticated large-scale CNN models, TSD can be performed with high accuracy. However, the conventional CNN models suffer the drawbacks of being time-consuming and resource-hungry, which limit their application and deployments in various platforms of limited resources. In this paper, we propose a novel real-time traffic sign detection system with a lightweight backbone network named Depth Separable DetNet (DS-DetNet) and a lite fusion feature pyramid network (LFFPN) for efficient feature fusion. The new model can achieve a performance trade-off between speed and accuracy using a depthwise separable bottleneck block, a lite fusion module, and an improved SSD detection front-end. The testing results on the MS COCO and the GTSDB datasets reveal that 23.1% mAP with 6.39 M parameters and only 1.08B FLOPs on MSCOCO, 81.35% mAP with 5.78 M parameters on GTSDB. With our model, the run speed is 61 frames per second (fps) on GTX 1080ti, 12 fps on Nvidia Jetson Nano and 16 fps on Nvidia Jetson Xavier NX. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1007/s11554-021-01102-1 | JOURNAL OF REAL-TIME IMAGE PROCESSING |
Keywords | DocType | Volume |
Object detection, Traffic sign detection, Autonomous driving, Convolutional neural networks, Feature fusion | Journal | 18 |
Issue | ISSN | Citations |
6 | 1861-8200 | 1 |
PageRank | References | Authors |
0.37 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kun Ren | 1 | 1 | 0.37 |
| Long Huang | 2 | 1 | 0.37 |
| Chunqi Fan | 3 | 1 | 0.37 |
| Hong-Gui Han | 4 | 476 | 39.06 |
| Hai Deng | 5 | 21 | 1.39 |