Chao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chao Liu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jialin Tang
Key Laboratory of Intelligent Detection in Complex Environment of Aerospace Land and Sea, Beijing Institute of Technology, China
2 shared publications - Binghua Su
Beijing Institute of Technology, Beijing, China and Beijing Institute of Technology, Zhuhai, Zhuhai, China
1 shared publication - Jinghui Yan
Zhuhai College, Beijing Institute of Technology, China
1 shared publication - Lili Wang
Beijing Institute of Technology, China
1 shared publication - Tenghui Wang
Beijing Institute of Technology, Zhuhai, China
1 shared publication - Yufei He
Beijing Institute of Technology, China
1 shared publication
Latest Publications
- Open Access
- 16 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 302-307
Research on underwater object detection of improved YOLOv7 model based on attention mechanism
Due to the complex content and blurry image of the images obtained in the underwater environment, which affect the detection results, resulting in the problems of false detection of objects and difficulty in feature extraction in conventional object detection models, this paper proposes an improved YOLOv7 model to improve the accuracy and real-time performance of underwater object detection models. Based on the YOLOv7 model, this model integrates the CBAM to enhance the weight of the feature information of the detection object in the spatial dimension and channel dimension, so that the feature information of the model object can be captured more easily and the detection accuracy is improved. The SPPFCSPC module is used to reduce the calculation amount of the model and improve the operation speed of the model while maintaining the receptive field. Through comparative ablation experiments, it is proved that the proposed method has higher detection accuracy in object detection in complex underwater environment than several detection models and YOLOv7 models.
- 16 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 302-307
Open AccessResearch on underwater object detection of improved YOLOv7 model based on attention mechanism
Due to the complex content and blurry image of the images obtained in the underwater environment, which affect the detection results, resulting in the problems of false detection of objects and difficulty in feature extraction in conventional object detection models, this paper proposes an improved YOLOv7 model to improve the accuracy and real-time performance of underwater object detection models. Based on the YOLOv7 model, this model integrates the CBAM to enhance the weight of the feature information of the detection object in the spatial dimension and channel dimension, so that the feature information of the model object can be captured more easily and the detection accuracy is improved. The SPPFCSPC module is used to reduce the calculation amount of the model and improve the operation speed of the model while maintaining the receptive field. Through comparative ablation experiments, it is proved that the proposed method has higher detection accuracy in object detection in complex underwater environment than several detection models and YOLOv7 models.
- Open Access
- 16 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 564-570
Underwater Image Enhancement Based on Color Different Attenuation
Underwater images play a very important role in projects related to the underwater environment. But in the underwater environment, the R channel attenuation of the RGB image and other reasons make the quality of the image significantly different from that on land in terms of color and clarity. In order to correct the chromatic aberration of the underwater image and improve the clarity, we propose a DAC method based on the compensation of difference. First, we perform contrast stretching and image denoising on the image. Then extract the details layer and the base layer of the RGB channel of the image respectively, and use the detail layer of the G, B channels with more information to compensate for the detail layer of the R channel. Finally, we optimize the details of the picture through the grayscale world algorithm to obtain the true color of the picture. We compared with various methods in the public underwater dataset UIEB, and it turns out that our method can well solve the problems of chromatic aberration and blur.
- 16 December 2022
- Published by Association for Computing Machinery (ACM)
- p. 564-570
Open AccessUnderwater Image Enhancement Based on Color Different Attenuation
Underwater images play a very important role in projects related to the underwater environment. But in the underwater environment, the R channel attenuation of the RGB image and other reasons make the quality of the image significantly different from that on land in terms of color and clarity. In order to correct the chromatic aberration of the underwater image and improve the clarity, we propose a DAC method based on the compensation of difference. First, we perform contrast stretching and image denoising on the image. Then extract the details layer and the base layer of the RGB channel of the image respectively, and use the detail layer of the G, B channels with more information to compensate for the detail layer of the R channel. Finally, we optimize the details of the picture through the grayscale world algorithm to obtain the true color of the picture. We compared with various methods in the public underwater dataset UIEB, and it turns out that our method can well solve the problems of chromatic aberration and blur.