In order to study the characteristics and risks of lane-changing behaviors of large vehicles, trajectory data of large vehicles in the expressway merging area was collected based on drone shooting and image recognition technology, and lane-changing characteristics and spatiotemporal risks of large vehicles were analyzed. The results indicate that the average value of the lane change duration of large vehicles is 5.28 s, the average value of the first half time is 2.60 s, the average value of the last half time is 2.68 s, and the average value of longitudinal lane change travel distance is 78.12 meters. They all obey Weibull Distribution, and are significantly related to lane-changing speed. The lane change duration and the first half time are significantly related to the distance between the large vehicle and the vehicle in front in the original lane and the distance between the large vehicle and the vehicle in front in the target lane. The first half time is also significantly related to the distance along the lane line. 75.40% of large vehicles start to change lanes within 100 meters before the bottleneck section of the merging area, and the occurrence of lane-changing behavior spreads from the outer lane to the inner lane in turn. The ave-rage distance and relative speed between the large vehicle and the vehicle in front in the original lane are the smallest, which are 22.91 meters and-0.90 m/s, respectively. If the lane change gap is small, the driver will be more inclined to change lane when the lane change gap shrinks slowly or continuously expands. The large vehicle has the highest risk of collision with the vehicle in front in the original lane, and approximately 15.32% of large vehicles change lanes when they are in an unsafe state with the vehicles in front.

In order to improve the safety level of non-motor vehicle traffic at signalized intersections, based on the survey data of signalized intersections with overlapping phase control in Guangzhou, this study analyzed the influencing factors of non-motor vehicle crossing behavior based on the C5.0 decision tree algorithm. Considering the influence of different periods on the crossing behavior of non-motor vehicles in the signal cycle, the study divided a complete signal cycle into four risk periods according to the risk conflict of non-motorized vehicles crossing the street, namely, the opposite green light risk period, the same direction green light safety period, the same direction green light risk period and the vertical direction risk period. And it divided the crossing behavior into three categories according to the waiting selection of non-motor vehicles at the intersection and whether or not to run red-light, namely, risky, opportunistic and law-abiding. It studied the influencing factors of the three types of crossing behavior by constructing a C5.0 decision tree model and analyzed and evaluated the classification effect of the model. The results show that the overall accuracy of the model classification results is greater than 83.04%, the AUC is greater than 0.880, and the model prediction accuracy is good. The crossing behavior of non-motorized vehicles at signalized intersections with overlapping phase control is mainly significantly related to the traffic environment, while the factors related to the rider’s behavior are less significant. The arrival risk period, non-motor vehicle signal light facilities, conflicting motor traffic flow, number of lanes and crossing risk have significant impacts on the occurrence of risk-taking crossing behavior, among which the arrival risk period is the most important influencing factor. The number of lanes, red-light time and arrival risk period have significant impacts on the occurrence of opportunistic crossing behavior, among which the number of lanes is the most important influencing factor. The conflicting motor traffic flow flow, signal period, number of lanes, crossing area and crossing risk have significant impacts on the occurrence of law-obeying crossing behavior, among which the conflicting motor traffic flow is the most important influencing factor.