Xiaotao Shao

Xiaotao Shao

Auto-generated profile, based on publicly available information

Xiaotao Shao

School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
22 December 2020 in IEEE Access
Verified
Journal Article
Open access
XSXiaotao Shao
Xiaotao Shao
CWCaike Wei
Caike Wei
YSYan Shen
Yan Shen
ZWZhong-Li Wang
Zhong-Li Wang
Existing night vehicle detection methods mainly detect vehicles by detecting headlights or taillights. However, these features are adversely affected by the complex road lighting environment. In this paper, a cascade detection network framework FteGanOd is proposed with a feature translate-enhancement (FTE) module and the object detection (OD) module. First, the FTE module is built based on CycleGAN and multi-scale feature fusion is proposed to enhance the detection of vehicle features at night. The features of night and day are combined by fusing different convolutional layers to produce enhanced feature (EF) maps. Second, the OD module, based on the existing object detection network, is improved by cascading with the FTE module to detect vehicles on the EF maps. The proposed FteGanOd method recognizes vehicles at night with greater accuracy by improving the contrast between vehicles and the background and by suppressing interference from ambient light. The proposed FteGanOd is validated on the Berkeley Deep Drive (BDD) dataset and our private dataset. The experimental results show that our proposed method can effectively enhance vehicle features and improve the accuracy of vehicle detection at night.

5 March 2021 in Sensors
Verified
Journal Article
Open access
PDF file
XSXiaotao Shao
Xiaotao Shao
Q WangQ Wang
Q Wang
WWei Yang
Wei Yang
YCYun Chen
Yun Chen
YXYi Xie
Yi Xie
ZWZhong-Li Wang
Zhong-Li Wang
The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method.

20 September 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
TLTengfei Lu
Tengfei Lu
ZWZhong-Li Wang
Zhong-Li Wang
YSYan Shen
Yan Shen
XSXiaotao Shao
Xiaotao Shao
YTYonglin Tang
Yonglin Tang
Catenary is one of the most crucial parts of electrified railway system. How to detect the part defects of catenary in time and keep it in a stable and safe operation conditions are the main tasks for maintainance. The existing data-driven vision-based defect detection methods will face a big challenge that, there are many catenary parts and each part has several types of defects, but there are few defect sample images for each type of defect, which limits them in real applications. To alleviate this problem, a semantic label-enhanced variational autoencoder (VAE) method for catenary part defect detection, termed Defect VAE (DefVAE), is presented. The proposed method is based on a label-enhanced VAE network that determines the distribution boundary in latent feature space of defect sample for additional defect generation. The addition of semantic label information to the VAE improves the inter-class distance in latent space, clarifying the boundary and further boosting the capabilities of the defect detection method, which is demonstrated in our experiments. Additionally, the defect type is classified by combining the outputs of the classifier confidence and the pixel-level reconstruction error which is based on a sliding label mode of the variational autoencoder. Extensive experiments with the open benchmark dataset MVTec and the catenary dataset collected by ourselves demonstrate that the presented DefVAE outperforms the baseline methods across the majority of indicators.

27 August 2015 in Sensors
Verified
Journal Article
Open access
PDF file
JXJingjing Xu
Jingjing Xu
WWei Yang
Wei Yang
LZLinyuan Zhang
Linyuan Zhang
RHRuisong Han
Ruisong Han
XSXiaotao Shao
Xiaotao Shao
In this paper, a wireless sensor network (WSN) technology adapted to underground channel conditions is developed, which has important theoretical and practical value for safety monitoring in underground coal mines. According to the characteristics that the space, time and frequency resources of underground tunnel are open, it is proposed to constitute wireless sensor nodes based on multicarrier code division multiple access (MC-CDMA) to make full use of these resources. To improve the wireless transmission performance of source sensor nodes, it is also proposed to utilize cooperative sensors with good channel conditions from the sink node to assist source sensors with poor channel conditions. Moreover, the total power of the source sensor and its cooperative sensors is allocated on the basis of their channel conditions to increase the energy efficiency of the WSN. To solve the problem that multiple access interference (MAI) arises when multiple source sensors transmit monitoring information simultaneously, a kind of multi-sensor detection (MSD) algorithm with particle swarm optimization (PSO), namely D-PSO, is proposed for the time-frequency coded cooperative MC-CDMA WSN. Simulation results show that the average bit error rate (BER) performance of the proposed WSN in an underground coal mine is improved significantly by using wireless sensor nodes based on MC-CDMA, adopting time-frequency coded cooperative transmission and D-PSO algorithm with particle swarm optimization.

4 July 2025 in Computer Vision and Image Understanding
Verified
Journal Article
Closed access
XSXiaotao Shao
Xiaotao Shao
GZGuipeng Zhang
Guipeng Zhang
YSYan Shen
Yan Shen
BZBoyu Zhang
Boyu Zhang
ZWZhong-Li Wang
Zhong-Li Wang
YSYanlong Sun
Yanlong Sun

18 January 2021 in IEEE Access
Verified
Journal Article
Open access
YSYan Shen
Yan Shen
MLMeng Luo
Meng Luo
YCYun Chen
Yun Chen
XSXiaotao Shao
Xiaotao Shao
ZWZhong-Li Wang
Zhong-Li Wang
YHYa-Li Hou
Ya-Li Hou
The cross-view image translation task is aimed at generating scene images from arbitrary views. However, due to the great differences in the shapes and contents of the various views, the quality of the generated images is degraded. Small objects, such as vehicles’ shapes and details, are not clear, which causes them to be structurally inconsistent with the semantic map used to guide the generation process. To solve this problem, we propose a novel generative adversarial network based on a local and global information processing module (LAGGAN) to recover the image’s details and structures. The network will further combine the input viewpoint image and the target semantic segmentation map to guide the generation of the target image from another viewpoint. The proposed LAGGAN includes a two-stage generator and a parameter-sharing discriminator. LAGGAN uses a new local and global information processing module (LAG) to generate high-quality images from various views. Moreover, we integrate dilated convolutions into the discriminator to capture the global context, which can enhance the discriminative ability and further adjust the LAG module. Therefore, most semantic information can be preserved, and the details of the target viewpoint images can be translated more sharply. Quantitative and qualitative evaluation on both CVUSA and Dayton datasets attest to the fact that our method, LAGGAN, presents satisfactory perceptual results and is comparable to state-of-the-art methods on the cross-view image translation task.