AbstractTraffic signs are important roadway assets that provide critical guidance, including regulations and safety-related information, to road users. Traffic signs need to be inventoried by transportation agencies. However, the traditional manual methods carried out in the field are dangerous, labor-intensive, and time-consuming. There is a need to develop alternative methods to cost-effectively inventory traffic signs. The research reported in this paper, sponsored by the U.S. DOT Research and Innovative Technology Administration Program, is to critically assess an alternative traffic sign inventory method using mobile light detection and ranging (LiDAR), and inertial navigation system (INS), technologies. The contribution of this paper is three-fold, as follows: (1) an alternative traffic sign inventory method is proposed using mobile LiDAR and INS technologies, (2) a key LiDAR parameter calibration procedure (including a sensitivity study of the key parameters) is proposed to achieve a desirable traffic sign detection rate, and (3) the reliability and productivity of the proposed method is critically assessed (by quantitatively measuring the detection rate and processing time of the proposed method). Actual data, collected on an interstate highway (I-95) and a local urban road (37th Street in Savannah, Georgia), were used to critically assess the performance. Results show that the proposed method can correctly detect 94.0 and 91.4% of the traffic signs on interstate highways and local urban roads with less than seven false-positive cases. Results also show that when compared to the in-field manual survey test conducted by Georgia DOT, the proposed method can potentially reduce the processing time for sign inventory by approximately 76%. The results demonstrate that the proposed method is promising for establishing a cost-effective traffic sign inventory method for transportation agencies. Future research directions are also recommended.
Critical Assessment of an Enhanced Traffic Sign Detection Method Using Mobile LiDAR and INS Technologies
Journal of transportation engineering ; 141 , 5
2015
Article (Journal)
English
British Library Online Contents | 2015
|Automated traffic sign and light pole detection in mobile LiDAR scanning data
Wiley | 2019
|