Changhui Hu

Changhui Hu

Auto-generated profile, based on publicly available information

Changhui Hu

Nanjing University of Posts and Telecommunications

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
19 December 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
CHChanghui Hu
Changhui Hu
YHYin Hu
Yin Hu
LXLintao Xu
Lintao Xu
YGYanyong Guo
Yanyong Guo
ZCZiyun Cai
Ziyun Cai
PLPan Liu
Pan Liu
We observe that the low-light RGB images, as well as night traffic monitoring (NTM) images, contain lots of color pixels with zeros caused by the low-light, which means that the low-light images suffer both information weakness and information loss of zero-element pixels. In this paper, we propose a novel flow-based generative method JTE-CFlow for low-light image enhancement, which consists of a joint-attention transformer based conditional encoder (JTE) and a map-wise cross affine coupling flow (CFlow). Specifically, JTE executes short-range and long-range operations by RRDBs (i.e., residual-in-residual dense blocks) and JATs (i.e., joint-attention transformer blocks) in series connection. JAT achieves weak information amplification and information loss restoration of zero-element pixels by the integration of self-attention and specific-attention with sharing the same value vectors, where the query and key vectors of specific-attention are from the zero-map feature of the low-light image. On the other hand, CFlow develops a map-wise cross affine coupling (MCAC) layer to perform cross learning for the flow feature, and a multiplication coupling network (MCN) to learn the transformation parameters of MCAC. JTE-CFlow learns to map the subtraction of outputs of CFlow and JTE (i.e., the residual code) into a standard normal distribution, and the inverse network of CFlow takes the latent feature of the low-light image as its input to infer the enhanced image. Experiments show that JTE-CFlow outperforms most SOTA methods on 7 mainstream low-light datasets with the same architecture, and can be applied to enhance NTM images. The source code and pre-trained models are available at https://github.com/NJUPT-IPR-HuYin/JTE-CFlow.

1 December 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
CHChanghui Hu
Changhui Hu
LXLintao Xu
Lintao Xu
YGYanyong Guo
Yanyong Guo
XJXiaoyuan Jing
Xiaoyuan Jing
XLXiaobo Lu
Xiaobo Lu
PLPan Liu
Pan Liu

1 March 2021 in Pattern Recognition
Verified
Journal Article
Closed access
CHChang-Hui Hu
Chang-Hui Hu
JYJian Yu
Jian Yu
Fei WuFei Wu
Fei Wu
YZYang Zhang
Yang Zhang
XJXiaoyuan Jing
Xiaoyuan Jing
PLPan Liu
Pan Liu

14 October 2019 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
CHChang-Hui Hu
Chang-Hui Hu
YZYang Zhang
Yang Zhang
Fei WuFei Wu
Fei Wu
XLXiaobo Lu
Xiaobo Lu
PLPan Liu
Pan Liu
XJXiaoyuan Jing
Xiaoyuan Jing
This paper models the driver face recognition problem under the intelligent traffic monitoring systems as severe illumination variation face recognition with single sample problem. Firstly, in the point of view of numerical value sign, the current illumination invariant unit is derived from the subtraction of two pixels in the face local region, which may be positive or negative, we propose a generalized illumination robust (GIR) model based on positive and negative illumination invariant units to tackle severe illumination variations. Then, the GIR model can be used to generate several GIR images based on the local edge-region or the local block-region, which results in the edge-region based GIR (EGIR) image or the block-region based GIR (BGIR) image. For single GIR image based classification, the GIR image utilizes the saturation function and the nearest neighbor classifier, which can develop EGIR-face and BGIR-face. For multi GIR images based classification, the GIR images employ the extended sparse representation classification (ESRC) as the classifier that can form the EGIR image based classification (GIRC) and the BGIR image based classification (BGIRC). Further, the GIR model is integrated with the pre-trained deep learning (PDL) model to construct the GIR-PDL model. Finally, the performances of the proposed methods are verified on the Extended Yale B, CMU PIE, AR, self-built Driver and VGGFace2 face databases. The experimental results indicate that the proposed methods are efficient to tackle severe illumination variations.

1 September 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
LXLintao Xu
Lintao Xu
CHChanghui Hu
Changhui Hu
BZBo Zhang
Bo Zhang
Fei WuFei Wu
Fei Wu
ZCZiyun Cai
Ziyun Cai

17 January 2025 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
CHChanghui Hu
Changhui Hu
TCTiesheng Chen
Tiesheng Chen
DJDonghang Jing
Donghang Jing
KHKerui Hu
Kerui Hu
YGYanyong Guo
Yanyong Guo
PLPan Liu
Pan Liu
This paper proposes a novel normalizing flow learning based method IIAG-CoFlow for low-light image enhancement (LLIE), which consists of an inter-and intra-channel attention Transformer based conditional generator (IIAG) and a complete flow (CoFlow). On the one hand, IIAG is designed as a U-shape network, whose down-sampling and up-sampling layers are constructed by IIZAT (i.e., inter-and intra-channel and zero-map attention Transformer) and IIAT (i.e., inter-and intra-channel attention Transformer) respectively. IIAT is designed to calculate inter-channel attention and intra-channel attention independently. Based on IIAT, IIZAT is designed to perform parallel fusion of zero-map attention and intra-channel attention. On the other hand, based on existing normalizing flow, we bring in unconditional affine coupling layer and design 3 invertible linear transformation layers, to develop CoFlow. The height and width axes based cross attention network (HWCAN) is proposed to learn affine/linear transformation parameters for conditional feature-driven layers of CoFlow. Experiments show that IIAG-CoFlow outperforms existing SOTA LLIE methods on several benchmark low-light datasets, and real NTM images. The source codes and pre-trained models are available at https://github.com/NJUPT-IPR-ChenTS/IIAG-CoFlow.