Chengbo Ai

Mobile Cross-Slope Measurement Method Using Lidar Technology

An effective cross slope facilitates drainage on highways and prevents hydroplaning. There is a need for transportation agencies to identify and measure road sections that have noneffective cross slopes so that timely corrective maintenance can be performed. However, the traditional manual methods used by transportation agencies to measure cross slopes with a digital level are time-consuming and labor intensive; these methods are not feasible for conducting a network-level cross-slope measurement. A proposed mobile cross-slope measurement method uses emerging mobile lidar technology that can accurately and effectively conduct network-level cross-slope measurement at highway speeds. The proposed mobile cross-slope measurement method uses emerging lidar technology (lidar calibration, data acquisition, region of interest extraction, and cross-slope computation). A sensitivity study was conducted to determine the key parameter (i.e., the region of interest interval) for the proposed method. The accuracy and the repeatability of the proposed method were critically validated through testing in a controlled environment. A case study demonstrated the capability of the proposed method. The results from the controlled test show that the proposed method can achieve desirable accuracy with an average measurement difference of 0.088 from the digital-level measurements and a desirable level of repeatability with a standard deviation of less than 0.038 in three runs. The results of the case study show that the proposed method can be operated at highway speed and is promising for the assessment of network-level cross-slope adequacy.

Geometry Preserving Active Polygon-Incorporated Sign Detection Algorithm

AbstractA generalized traffic sign detection algorithm incorporating a hybrid active contour (HAC) model has been previously developed to automatically detect all types of traffic signs. Although the HAC model has shown some promising results, there are still some false negatives remaining due to the over-evolution of the HAC model. Therefore, further improvement is needed to reduce the number of these false negatives. This paper is aimed at developing a new geometry-preserving active polygon (GPAP) model to address the over-evolution issue in the HAC model for improving the computation speed. The contributions of this paper include (1) proposing a new geometry-preserving evolution that ensures that the “contour” only evolves at its vertices instead of at every point along the edges; (2) tailoring a new energy function that enables a polygon to effectively converge to traffic sign regions without losing its geometry integrity by using both local color contrast feature and global elongation and rectangular...

Automated Superelevation Measurement Method Using a Low-Cost Mobile Device

The horizontal curve is one of the focal points of roadway safety because this curve plays a critical role in transitioning vehicles between tangent roadway sections; moreover, car crashes are frequently concentrated on horizontal curves despite their disproportionate length in the road network. As a critical safety property of horizontal curves, superelevation is crucial to vehicle safety because it counteracts the lateral acceleration produced in vehicles when they travel the curves. Despite the emergence of several sensing-based methods in recent years, labor-intensive and time-consuming manual superelevation evaluation is often carried out by transportation agencies because the newer methods usually demand expensive equipment and complicated operations. Transportation agencies are in urgent need of low-cost, reliable alternatives to improve their data collection practices. This paper proposes an automated superelevation measurement method using inexpensive mobile devices. The proposed method integrates and processes sensing data from a mobile device and derives superelevation by using fundamental vehicle kinematics at a horizontal curve. Kalman filtering–based noise reduction, regression-based radius computation, and complementary-filtering-based rolling angle computation methods are introduced to achieve accurate results despite low-frequency, noisy signals from the inexpensive devices. An experimental test on SR-2 in Georgia demonstrates that the proposed method delivers results with accuracies comparable to those of a lidar-based method. A case study of high friction surface treatment site selection using a ball bank indicator shows that the proposed method is a promising alternative for transportation agencies to achieve low-cost yet reliable data collection for safety analysis and improvement.

Automatic Truck Processing Time Extraction at Marine Container Terminal Gates Using Low-Frame-Rate Images

Truck processing time, including the processing time per lane and per truck at a specific timestamp, at marine container terminal gates is crucial for measuring the performance of terminals. Truck processing time has traditionally been collected for short periods of time (e.g., a few hours) through field observation. From the surveillance cameras widely available at terminal gates, researchers have attempted to collect truck processing time data by manually reviewing camera images frame by frame. However, this manual review process is labor-intensive and time-consuming. This study is motivated by the need for effectively collecting truck processing times over a long period of time. An image-processing algorithm to automatically extract truck processing time data using the low-frame-rate images (less than 1 frame per second, fps) is first proposed. The proposed algorithm includes three steps: (1) design of two region of interest (ROIs) per lane to capture truck trajectories, (2) a frame-differencing change-detection algorithm addressing the low frame rate and cast shadow issue, and (3) a unique state transition model with a set of decision rules, considering perspective occlusion and other potential sources of false positive detections, to reliably detect truck departures. An experimental test using one days actual images in varying conditions was conducted to evaluate the performance of the proposed algorithm. Experimental tests have demonstrated the robustness of the proposed algorithms ability to meet the unique technical challenges at a terminal gate, including the following: day and night conditions, cast shadows, occlusion by work vehicles, people, and nearby trucks. An experimental test using 7,225 images (6,567 day and 658 night operation images) was conducted to evaluate the performance of the proposed algorithm. Experimental tests have also demonstrated the robustness of the proposed algorithm for successfully detecting truck departures under several challenging situations, including perspective occlusion, cast shadows, nighttime and various lighting conditions, and multiple-lane departures. The correct detection rate is 98.1% for daytime images and 90.8% for nighttime images, giving our data a correct detection rate of 97.6%.

Identification of Site Characteristics for Proactive High-Friction Surface Treatment Site Selection using Sensor-Based, Detailed, Location-Referenced Curve Characteristics Data

The Georgia Department of Transportation (GDOT) has developed a proactive high-friction surface treatment (HFST) program for curve sites prone to run-off-road (ROR) crashes. Using crash data and a single-criterion, ball bank indicator (BBI) value, GDOT seeks to maximize the return on its HFST investment. GDOT has partnered with Georgia Tech to identify additional factors for its HFST site-selection (HFST-SS) decision-making process by leveraging high-resolution, full-coverage sensor data (e.g., GPS and LiDAR). This paper proposes a methodology to identify site characteristics that can be used in GDOT’s HFST-SS process by leveraging the sensor data and automatically extracting roadway curve features as follows: (a) roadway data collection using state-of-the-art sensing technologies, (b) automatic extraction of detailed site characteristics data and curve information, (c) curved-based roadway segmentation using the extracted curve information; (d) spatial integration of curve-site characteristics data (CSCD); (e) analysis of CSCD and ROR crashes to identify additional factors for HFST site selection. A case study using CSCD extracted from Georgia State Route 2 demonstrates the proposed methodology. Results show that on sharp curves having comparable site characteristics, vertical grades greater than 3% play an important role in ROR crashes. Therefore, a vertical grade greater than 3% could be considered as an additional HFST-SS factor along with the current BBI criterion.

Automated Sidewalk Assessment Method for Americans with Disabilities Act Compliance Using Three-Dimensional Mobile Lidar

The sidewalk is an indispensable infrastructure for pedestrians, especially wheelchair users. Wheelchair users rely on quality sidewalks to facilitate safe and uninterrupted trips in their everyday lives. Transportation agencies are required to evaluate regulatory compliance with the Americans with Disabilities Act (ADA) and are responsible for the timely maintenance of inadequate sidewalks. However, these timely evaluation and maintenance activities are usually lacking because of the labor-intensive and cost-prohibitive data collection process in the current practice. There is an urgent need for an efficient and reliable method for assessment of sidewalk compliance with the ADA. This paper aims to address such a need by proposing an automated sidewalk assessment method using three-dimensional mobile light detection and ranging (lidar) and image processing. The presence of sidewalks and curb ramps is first extracted by use of a video log image and a lidar point cloud. Then, the corresponding key features regulated by the ADA, including the sidewalk width, cross slope, and grade and the curb ramp slope, are automatically measured. By comparison with the manual ground truth from a field survey, the experimental tests conducted on the Georgia Institute of Technology campus at Atlanta, Georgia, showed accurate measurement results for the key features of the sidewalk and curb ramps. A case study was then conducted to demonstrate that the proposed method could provide transportation agencies a convenient and cost-effective means of assessment of compliance with the ADA by integration of accurately extracted sidewalk location and measurement information.