Hongfeng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hongfeng Wang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Jianzhong Wang
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China
4 shared publications - Kemeng Bai
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
3 shared publications - Yong Sun
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China
2 shared publications - Haonan Xu
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
1 shared publication - Xinlin Chen
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
1 shared publication - Zibo Yu
School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China
1 shared publication
Latest Publications
- Open Access
DRSNFuse: Deep Residual Shrinkage Network for Infrared and Visible Image Fusion
Infrared images are robust against illumination variation and disguises, containing the sharp edge contours of objects. Visible images are enriched with texture details. Infrared and visible image fusion seeks to obtain high-quality images, keeping the advantages of source images. This paper proposes an object-aware image fusion method based on a deep residual shrinkage network, termed as DRSNFuse. DRSNFuse exploits residual shrinkage blocks for image fusion and introduces a deeper network in infrared and visible image fusion tasks than existing methods based on fully convolutional networks. The deeper network can effectively extract semantic information, while the residual shrinkage blocks maintain the texture information throughout the whole network. The residual shrinkage blocks adapt a channel-wise attention mechanism to the fusion task, enabling feature map channels to focus on objects and backgrounds separately. A novel image fusion loss function is proposed to obtain better fusion performance and suppress artifacts. DRSNFuse trained with the proposed loss function can generate fused images with fewer artifacts and more original textures, which also satisfy the human visual system. Experiments show that our method has better fusion results than mainstream methods through quantitative comparison and obtains fused images with brighter targets, sharper edge contours, richer details, and fewer artifacts.
Open AccessDRSNFuse: Deep Residual Shrinkage Network for Infrared and Visible Image Fusion
Infrared images are robust against illumination variation and disguises, containing the sharp edge contours of objects. Visible images are enriched with texture details. Infrared and visible image fusion seeks to obtain high-quality images, keeping the advantages of source images. This paper proposes an object-aware image fusion method based on a deep residual shrinkage network, termed as DRSNFuse. DRSNFuse exploits residual shrinkage blocks for image fusion and introduces a deeper network in infrared and visible image fusion tasks than existing methods based on fully convolutional networks. The deeper network can effectively extract semantic information, while the residual shrinkage blocks maintain the texture information throughout the whole network. The residual shrinkage blocks adapt a channel-wise attention mechanism to the fusion task, enabling feature map channels to focus on objects and backgrounds separately. A novel image fusion loss function is proposed to obtain better fusion performance and suppress artifacts. DRSNFuse trained with the proposed loss function can generate fused images with fewer artifacts and more original textures, which also satisfy the human visual system. Experiments show that our method has better fusion results than mainstream methods through quantitative comparison and obtains fused images with brighter targets, sharper edge contours, richer details, and fewer artifacts.
- Open Access
- 25 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (13) , 6462
A Study of Eye-Tracking Gaze Point Classification and Application Based on Conditional Random Field
The head-mounted eye-tracking technology is often used to manipulate the motion of servo platform in remote tasks, so as to achieve visual aiming of servo platform, which is a highly integrated human-computer interaction effect. However, it is difficult to achieve accurate manipulation for the uncertain meanings of gaze points in eye-tracking. To solve this problem, a method of classifying gaze points based on a conditional random field is proposed. It first describes the features of gaze points and gaze images, according to the eye visual characteristic. An LSTM model is then introduced to merge these two features. Afterwards, the merge features are learned by CRF model to obtain the classified gaze points. Finally, the meaning of gaze point is classified for target, in order to accurately manipulate the servo platform. The experimental results show that the proposed method can classify more accurate target gaze points for 100 images, the average evaluation values Precision = 86.81%, Recall = 86.79%, We = 86.79%, these are better than relevant methods. In addition, the isolated gaze points can be eliminated, and the meanings of gaze points can be classified to achieve the accuracy of servo platform visual aiming.
- 25 June 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (13) , 6462
Open AccessA Study of Eye-Tracking Gaze Point Classification and Application Based on Conditional Random Field
The head-mounted eye-tracking technology is often used to manipulate the motion of servo platform in remote tasks, so as to achieve visual aiming of servo platform, which is a highly integrated human-computer interaction effect. However, it is difficult to achieve accurate manipulation for the uncertain meanings of gaze points in eye-tracking. To solve this problem, a method of classifying gaze points based on a conditional random field is proposed. It first describes the features of gaze points and gaze images, according to the eye visual characteristic. An LSTM model is then introduced to merge these two features. Afterwards, the merge features are learned by CRF model to obtain the classified gaze points. Finally, the meaning of gaze point is classified for target, in order to accurately manipulate the servo platform. The experimental results show that the proposed method can classify more accurate target gaze points for 100 images, the average evaluation values Precision = 86.81%, Recall = 86.79%, We = 86.79%, these are better than relevant methods. In addition, the isolated gaze points can be eliminated, and the meanings of gaze points can be classified to achieve the accuracy of servo platform visual aiming.
- Open Access
Centered Multi-Task Generative Adversarial Network for Small Object Detection
Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimation can significantly improve the performance of small object detection. This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation. To achieve this, we propose a generative adversarial network (GAN) capable of image super-resolution and two-stage small object detection. We exploit a generator in CMTGAN for image super-resolution and a discriminator for object detection. We introduce an artificial texture loss into the generator to retain the original feature of small objects. We also use a centered mask in the generator to make the network focus on the central part of images where small objects are more likely to appear in our method. We propose a discriminator with detection loss for two-stage small object detection, which can be adapted to other GANs for object detection. Compared with existing interpolation methods, the super-resolution images generated by CMTGAN are more explicit and contain more information. Experiments show that our method exhibits a better detection performance than mainstream methods.
Open AccessCentered Multi-Task Generative Adversarial Network for Small Object Detection
Despite the breakthroughs in accuracy and efficiency of object detection using deep neural networks, the performance of small object detection is far from satisfactory. Gaze estimation has developed significantly due to the development of visual sensors. Combining object detection with gaze estimation can significantly improve the performance of small object detection. This paper presents a centered multi-task generative adversarial network (CMTGAN), which combines small object detection and gaze estimation. To achieve this, we propose a generative adversarial network (GAN) capable of image super-resolution and two-stage small object detection. We exploit a generator in CMTGAN for image super-resolution and a discriminator for object detection. We introduce an artificial texture loss into the generator to retain the original feature of small objects. We also use a centered mask in the generator to make the network focus on the central part of images where small objects are more likely to appear in our method. We propose a discriminator with detection loss for two-stage small object detection, which can be adapted to other GANs for object detection. Compared with existing interpolation methods, the super-resolution images generated by CMTGAN are more explicit and contain more information. Experiments show that our method exhibits a better detection performance than mainstream methods.
- Open Access
A Pupil Segmentation Algorithm Based on Fuzzy Clustering of Distributed Information
Pupil segmentation is critical for line-of-sight estimation based on the pupil center method. Due to noise and individual differences in human eyes, the quality of eye images often varies, making pupil segmentation difficult. In this paper, we propose a pupil segmentation method based on fuzzy clustering of distributed information, which first preprocesses the original eye image to remove features such as eyebrows and shadows and highlight the pupil area; then the Gaussian model is introduced into global distribution information to enhance the classification fuzzy affiliation for the local neighborhood, and an adaptive local window filter that fuses local spatial and intensity information is proposed to suppress the noise in the image and preserve the edge information of the pupil details. Finally, the intensity histogram of the filtered image is used for fast clustering to obtain the clustering center of the pupil, and this binarization process is used to segment the pupil for the next pupil localization. Experimental results show that the method has high segmentation accuracy, sensitivity, and specificity. It can accurately segment the pupil when there are interference factors such as light spots, light reflection, and contrast difference at the edge of the pupil, which is an important contribution to improving the stability and accuracy of the line-of-sight tracking.
Open AccessA Pupil Segmentation Algorithm Based on Fuzzy Clustering of Distributed Information
Pupil segmentation is critical for line-of-sight estimation based on the pupil center method. Due to noise and individual differences in human eyes, the quality of eye images often varies, making pupil segmentation difficult. In this paper, we propose a pupil segmentation method based on fuzzy clustering of distributed information, which first preprocesses the original eye image to remove features such as eyebrows and shadows and highlight the pupil area; then the Gaussian model is introduced into global distribution information to enhance the classification fuzzy affiliation for the local neighborhood, and an adaptive local window filter that fuses local spatial and intensity information is proposed to suppress the noise in the image and preserve the edge information of the pupil details. Finally, the intensity histogram of the filtered image is used for fast clustering to obtain the clustering center of the pupil, and this binarization process is used to segment the pupil for the next pupil localization. Experimental results show that the method has high segmentation accuracy, sensitivity, and specificity. It can accurately segment the pupil when there are interference factors such as light spots, light reflection, and contrast difference at the edge of the pupil, which is an important contribution to improving the stability and accuracy of the line-of-sight tracking.