复杂光照条件下的交通标志检测与识别 下载: 1018次
Traffic Sign Detection and Recognition Under Complicated Lighting Conditions
图 & 表
图 1. MCT计算过程示意图
Fig. 1. Schematic of MCT calculation process
下载图片 查看原文
图 2. 部分样本效果。(a)原图像;(b)变换后图像
Fig. 2. Partial sample effects. (a) Original images; (b) transformed images
下载图片 查看原文
图 3. 本文算法整体流程图
Fig. 3. Overall flow chart of proposed algorithm
下载图片 查看原文
图 4. 多尺度卷积神经网络结构
Fig. 4. Structure of multi-scale convolutional neural network
下载图片 查看原文
图 5. GTSDB部分样本示意图
Fig. 5. Partial sample pictures in GTSDB dataset
下载图片 查看原文
图 6. 自建数据集部分样本示意图
Fig. 6. Partial sample pictures in self-built dataset
下载图片 查看原文
图 7. 本文算法检测效果图。(a) GTSDB数据集检测结果;(b) CQD数据集检测结果;(c) CQN数据集检测结果
Fig. 7. Detection results of proposed algorithm. (a) Detection results of GTSDB dataset; (b) detection results of CQD dataset; (c) detection results of CQN dataset
下载图片 查看原文
表 1各算法检测性能
Table1. Detection performance of each algorithm
Dataset | Algorithm | TP | FN | FP | Precision /% | Recall rate /% |
---|
| Proposed algorithm | 354 | 5 | 6 | 98.33 | 98.61 | GTSDB | MCT-Adaboost | 318 | 38 | 42 | 88.33 | 89.33 | | HOG+SVM | 349 | 5 | 7 | 98.03 | 98.58 | | Proposed algorithm | 583 | 14 | 10 | 98.31 | 97.65 | CQD | MCT-Adaboost | 519 | 71 | 85 | 85.93 | 87.97 | | HOG+SVM | 568 | 38 | 19 | 96.76 | 93.73 | | Proposed algorithm | 245 | 18 | 13 | 94.96 | 93.16 | CQN | MCT-Adaboost | 174 | 35 | 44 | 79.82 | 83.25 | | HOG+SVM | 206 | 24 | 33 | 86.19 | 89.57 |
|
查看原文
表 2各算法识别准确率
Table2. Recognition accuracy of each algorithm%
Dataset | Accuracy |
---|
Proposed algorithm | Multi-scale CNN[15] | Random forests[16] | LDA on HOG[17] |
---|
GTSRB | 98.94 | 98.31 | 97.20 | 95.68 | CQD | 98.37 | 97.88 | 95.24 | 93.07 | CQN | 96.61 | 91.75 | 84.37 | 67.33 |
|
查看原文
表 3各算法运行的时间成本
Table3. Running time cost of each algorithmms
Algorithm | Time cost |
---|
Proposed algorithm | 81 | MCT-Adaboost | 394 | HOG+SVM | 267 | Faster-RCNN | 102 |
|
查看原文
屈治华, 邵毅明, 邓天民, 朱杰, 宋晓华. 复杂光照条件下的交通标志检测与识别[J]. 激光与光电子学进展, 2019, 56(23): 231009. Zhihua Qu, Yiming Shao, Tianmin Deng, Jie Zhu, Xiaohua Song. Traffic Sign Detection and Recognition Under Complicated Lighting Conditions[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231009.