Xunxun Zhang

Dr. Xunxun Zhang


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
XZXunxun Zhang
Xunxun Zhang
XZXu Zhu
Xu Zhu
Vehicle detection in aerial images has attracted great attention as an approach to providing the necessary information for transportation road network planning and traffic management. However, because of the low resolution, complex scene, occlusion, shadows, and high requirement for detection efficiency, implementing vehicle detection in aerial images is challenging. Therefore, we propose an efficient and scene-adaptive algorithm for vehicle detection in aerial images using an improved YOLOv3 framework, and it is applied to not only aerial still images but also videos composed of consecutive frame images. First, rather than directly using the traditional YOLOv3 network, we construct a new structure with fewer layers to improve the detection efficiency. Then, since complex scenes in aerial images can cause the partial occlusion of vehicles, we construct a context-aware-based feature map fusion to make full use of the information in the adjacent frames and accurately detect partially occluded vehicles. The traditional YOLOv3 network adopts a horizontal bounding box, which can attain the expected detection effects only for vehicles with small length–width ratio. Moreover, vehicles that are close to each other are liable to cause lower accuracy and a higher detection error rate. Hence, we design a sloping bounding box attached to the angle of the target vehicles. This modification is conducive to predicting not only the position but also the angle. Finally, two data sets were used to perform extensive experiments and comparisons. The results show that the proposed algorithm generates the desired and excellent performance.

2 January 2022 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
XZXunxun Zhang
Xunxun Zhang
XLXiao Yu Lu
Xiao Yu Lu
LPLang Peng
Lang Peng
Owing to the strong complementarity between visible and infra-red thermal (RGB-T) images, the two types of images receive the increased application of vehicle detection in traffic monitoring. Now, how to take full advantage of the two kinds of images for vehicle fusion detection has drawn wide publicity. Nevertheless, due to the requirement of high quality and high precision on vehicle fusion detection, and insufficiency of the infra-red thermal dataset, it is extremely hard to realize the vehicle fusion detection in RGB-T images. In our work, a complementary and precise vehicle fusion detection approach in RGB-T images is put forward, which combines the detection results of both visible and infra-red thermal images based on a decision-level fusion strategy. For vehicle detection in visible images, an effective and shallow network is constructed. For vehicle detection in infra-red thermal images, we do not directly train an effective network because of the insufficiency of the infra-red thermal vehicle samples. Instead, semi-supervised transfer learning is applied to combine the trained visible network for vehicle detection in infra-red thermal images. Next, for the decision-level fusion, we propose a novel fusion algorithm. It not only retains the vehicle results detected only in the visible images or only the infra-red thermal images but also fuses the detection results of the same vehicle in both visible and infra-red thermal images. Finally, VOT2019 and RGBT234 data sets are introduced to evaluate the proposed vehicle fusion detection approach. Compared with the main trend of current, it is indicated that the proposed approach can obtain competitive and superior vehicle fusion detection results in RGB-T images.

1 September 2024 in Journal of Highway and Transportation Research and Development (English Edition)
Verified
Journal Article
Open access
PDF file
XZXunxun Zhang
Xunxun Zhang
XZXu Zhu
Xu Zhu
Vehicle detection in aerial imagery is of paramount importance for various intelligent transportation applications, including vehicle tracking, traffic control, and traffic behavior analysis. However, this task presents significant challenges due to factors such as scale variance, the presence of small vehicles, and complex scenes conditions. The demand for high-quality and precise vehicle detection exacerbates these challenges, particularly in complex environments characterized by low light and occlusion. To address these issues, we propose a balanced feature fusion and attention mechanism-based vehicle detection network, termed BaAM-YOLO, specifically designed for aerial images. Firstly, to improve the vehicle detection accuracy, we didn't directly fuse deep and shallow features. Instead, we focused on achieving a balanced contribution from different feature layers. Secondly, to enhance the feature extraction capabilities of our model, we incorporated a simple parameter-free attention mechanism (SimAM), which aims to improve detection accuracy. Additionally, to effectively model the target confidence loss and classification loss, we emplogyed focal loss to derive a loss function that facilitates dynamic adjustment for multi-class classification. The proposed vehicle detection method was evaluated using the VisDrone2019 dataset. Comparative analyses with state-of-the-art research indicate that the proposed method can obtain superior and competitive results in vehicle detection.