Publications by authors named "Chengjin Lyu"
Article Synopsis
- The paper presents a new cooperative method designed to enhance the accuracy of Turn Movement Count (TMC) in challenging traffic conditions by incorporating data from surrounding areas.
- It addresses limitations of existing vision-based TMC systems, particularly issues related to vehicle occlusions that hinder detection and tracking at intersections.
- By utilizing shared information from neighboring observation systems, the proposed method improves data assessment, leading to better vehicle movement identification and overall accuracy.
Dual cameras with visible-thermal multispectral pairs provide both visual and thermal appearance, thereby enabling detecting pedestrians around the clock in various conditions and applications, including autonomous driving and intelligent transportation systems. However, due to the greatly varying real-world scenarios, the performance of a detector trained on a source dataset might change dramatically when evaluated on another dataset. A large amount of training data is often necessary to guarantee the detection performance in a new scenario.
View Article and Find Full Text PDF