Jingwen Wang

Ms. Jingwen Wang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
30 April 2022 in Micromachines
Verified
Journal Article
Open access
PDF file
Yan LiuYan Liu
Yan Liu
JWJingwen Wang
Jingwen Wang
YLYujie Li
Yujie Li
CLCanlin Li
Canlin Li
WZWeizheng Zhang
Weizheng Zhang
Lane detection is an important and challenging part of autonomous driver assistance systems and other advanced assistance systems. The presence of road potholes and obstacles, complex road environments (illumination, occlusion, etc.) are ubiquitous, will cause the blur of images, which is captured by the vision perception system in the lane detection task. To improve the lane detection accuracy of blurred images, a network (Lane-GAN) for lane line detection is proposed in the paper, which is robust to blurred images. First, real and complex blur kernels are simulated to construct a blurred image dataset, and the improved GAN network is used to reinforce the lane features of the blurred image, and finally the feature information is further enriched with a recurrent feature transfer aggregator. Extensive experimental results demonstrate that the proposed network can get robust detection results in complex environments, especially for blurred lane lines. Compared with the SOTA detector, the proposed detector achieves a larger gain. The proposed method can enhance the lane detail features of the blurred image, improving the detection accuracy of the blurred lane effectively, in the driver assistance system in high speed and complex road conditions.

11 November 2021 in Entropy
Verified
Journal Article
Open access
PDF file
Yan LiuYan Liu
Yan Liu
tiantian qiutiantian qiu
tiantian qiu
JWJingwen Wang
Jingwen Wang
WQWenting Qi
Wenting Qi
Vehicle detection plays a vital role in the design of Automatic Driving System (ADS), which has achieved remarkable improvements in recent years. However, vehicle detection in night scenes still has considerable challenges for the reason that the vehicle features are not obvious and are easily affected by complex road lighting or lights from vehicles. In this paper, a high-accuracy vehicle detection algorithm is proposed to detect vehicles in night scenes. Firstly, an improved Generative Adversarial Network (GAN), named Attentive GAN, is used to enhance the vehicle features of nighttime images. Then, with the purpose of achieving a higher detection accuracy, a multiple local regression is employed in the regression branch, which predicts multiple bounding box offsets. An improved Region of Interest (RoI) pooling method is used to get distinguishing features in a classification branch based on Faster Region-based Convolutional Neural Network (R-CNN). Cross entropy loss is introduced to improve the accuracy of classification branch. The proposed method is examined with the proposed dataset, which is composed of the selected nighttime images from BDD-100k dataset (Berkeley Diverse Driving Database, including 100,000 images). Compared with a series of state-of-the-art detectors, the experiments demonstrate that the proposed algorithm can effectively contribute to vehicle detection accuracy in nighttime.

18 October 2021 in Entropy
Verified
Journal Article
Open access
PDF file
Yan LiuYan Liu
Yan Liu
JWJingwen Wang
Jingwen Wang
tiantian qiutiantian qiu
tiantian qiu
WQWenting Qi
Wenting Qi
Vehicle detection is an essential part of an intelligent traffic system, which is an important research field in drone application. Because unmanned aerial vehicles (UAVs) are rarely configured with stable camera platforms, aerial images are easily blurred. There is a challenge for detectors to accurately locate vehicles in blurred images in the target detection process. To improve the detection performance of blurred images, an end-to-end adaptive vehicle detection algorithm (DCNet) for drones is proposed in this article. First, the clarity evaluation module is used to determine adaptively whether the input image is a blurred image using improved information entropy. An improved GAN called Drone-GAN is proposed to enhance the vehicle features of blurred images. Extensive experiments were performed, the results of which show that the proposed method can detect both blurred and clear images well in poor environments (complex illumination and occlusion). The detector proposed achieves larger gains compared with SOTA detectors. The proposed method can enhance the vehicle feature details in blurred images effectively and improve the detection accuracy of blurred aerial images, which shows good performance with regard to resistance to shake.

31 May 2021 in KSII Transactions on Internet and Information Systems
Verified
Journal Article
Closed access
YLYan Liu
Yan Liu
BLBingxue Lv
Bingxue Lv
JWJingwen Wang
Jingwen Wang
WHWei Huang
Wei Huang
TQTiantian Qiu
Tiantian Qiu
YCYunzhong Chen
Yunzhong Chen
KSII Transactions on Internet and Information Systems TIIS Paper Details

12 December 2024 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
YLYan Liu
Yan Liu
WQWenting Qi
Wenting Qi
JWJingwen Wang
Jingwen Wang
YXYanqiu Xiao
Yanqiu Xiao
GCGuangzhen Cui
Guangzhen Cui
LHLi Han
Li Han

1 March 2022 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
Yan LiuYan Liu
Yan Liu
JWJingwen Wang
Jingwen Wang
YLYujie Li
Yujie Li
GLGuangwei Li
Guangwei Li
GTGaopeng Tang
Gaopeng Tang
Pose estimation is the detection of human action poses, which is an important task of computer vision. The requirements of tasks such as unmanned driving and intelligent surveillance have also contributed to the development of human pose estimation. In this context, deep learning (DL) has a remarkable impact on human pose estimation. In this study, we investigate a pose estimation algorithm called convolutional pose machines (CPM) and implement it on a mobile platform (i.e., Android). By combining the classical CPM and the mobile deep learning framework Mobile AI Compute Engine (MACE), the model is deployed to the mobile platform to estimate the human pose directly and locally on the mobile phone without relying on the Internet. Thus, the proposed method can achieve effective performance while protecting users’ personal data. Experimental results on real-world data validate that this system has achieved the expected results of accurate recognition of common actions with a simple interface.