Extracting Traffic Signage by Combining Point Clouds and Images

Furao Zhang; Jianan Zhang; Zhihong Xu; Jie Tang; Peiyu Jiang; Ruofei Zhong

doi:10.3390/s23042262

Extracting Traffic Signage by Combining Point Clouds and Images

Sensors (Basel). 2023 Feb 17;23(4):2262. doi: 10.3390/s23042262.

Authors

Furao Zhang^{1

2

3}, Jianan Zhang^{1

2

3}, Zhihong Xu^{1

2

3}, Jie Tang^{1

2

3}, Peiyu Jiang⁴, Ruofei Zhong^{1

2

3}

Affiliations

¹ Key Laboratory of 3D Information Acquisition and Application, MOE, Capital Normal University, Beijing 100048, China.
² Base of the State Key Laboratory of Urban Environmental Process and Digital Modeling, Capital Normal University, Beijing 100048, China.
³ College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, China.
⁴ Department of Statistics, Uppsala University, 75120 Uppsala, Sweden.

Abstract

Recognizing traffic signs is key to achieving safe automatic driving. With the decreasing cost of LiDAR, the accurate extraction of traffic signs using point cloud data has received wide attention. In this study, we propose combining point cloud and image traffic sign extraction: firstly, we use the improved YoloV3 model to detect traffic signs in panoramic images. The specific improvement is that the convolution block attention module is added to the algorithm framework, the traditional K-means clustering algorithm is improved, and Focal Loss is introduced as the loss function. It shows higher accuracy on the TT100K dataset, with a 1.4% improvement in accuracy compared to the previous YoloV3. Then, the point cloud of the area where the traffic sign is located is extracted by combining the image detection results. On this basis, the outline of the traffic sign is accurately extracted using the reflection intensity, spatial geometry and other information. Compared with the traditional method, the proposed method can effectively reduce the missed detection rate, narrow the range of point cloud, and improve the detection accuracy by 10.2%.

Keywords: convolutional neural network; lidar point cloud; object detection; panoramic image; projection transformation.

Grants and funding

This work was supported in part by the National Key Technologies Research and Development Program of China under Grant 2022YFB3904101, in part by the National Natural Science Foundation of China under Grant U22A20568 and 42101444.