Jintao Liu

Jintao Liu

Auto-generated profile, based on publicly available information

Jintao Liu

School of Engineering, University of Almeria, 04120 Almeria, Spain

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
27 April 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZZZhenxi Zhao
Zhenxi Zhao
YLYang Liu
Yang Liu
XSXudong Sun
Xudong Sun
JLJintao Liu
Jintao Liu
XYXinting Yang
Xinting Yang
CZChao ZHou
Chao ZHou
The automatic detection and identification of fish from underwater videos is of great significance for fishery resource assessment and ecological environment monitoring. However, due to the poor quality of underwater images and unconstrained fish movement, traditional hand-designed feature extraction methods or convolutional neural network (CNN)-based object detection algorithms cannot meet the detection requirements in real underwater scenes. Therefore, to realize fish recognition and localization in a complex underwater environment, this paper proposes a novel composite fish detection framework based on a composite backbone and an enhanced path aggregation network called Composited FishNet. By improving the residual network (ResNet), a new composite backbone network (CBresnet) is designed to learn the scene change information (source domain style), which is caused by the differences in the image brightness, fish orientation, seabed structure, aquatic plant movement, fish species shape and texture differences. Thus, the interference of underwater environmental information on the object characteristics is reduced, and the output of the main network to the object information is strengthened. In addition, to better integrate the high and low feature information output from CBresnet, the enhanced path aggregation network (EPANet) is also designed to solve the insufficient utilization of semantic information caused by linear upsampling. The experimental results show that the average precision (AP) 0.5:0.95 , AP 50 and average recall (AR) max=10 of the proposed Composited FishNet are 75.2%, 92.8% and 81.1%, respectively. The composite backbone network enhances the characteristic information output of the detected object and improves the utilization of characteristic information. This method can be used for fish detection and identification in complex underwater environments such as oceans and aquaculture.

24 February 2020 in Animals
Verified
Journal Article
Open access
PDF file
SZSong Zhang
Song Zhang
XYXinting Yang
Xinting Yang
YWYizhong Wang
Yizhong Wang
ZZZhenxi Zhao
Zhenxi Zhao
JLJintao Liu
Jintao Liu
CZChao ZHou
Chao ZHou
In intensive aquaculture, the number of fish in a shoal can provide valuable input for the development of intelligent production management systems. However, the traditional artificial sampling method is not only time consuming and laborious, but also may put pressure on the fish. To solve the above problems, this paper proposes an automatic fish counting method based on a hybrid neural network model to realize the real-time, accurate, objective, and lossless counting of fish population in far offshore salmon mariculture. A multi-column convolution neural network (MCNN) is used as the front end to capture the feature information of different receptive fields. Convolution kernels of different sizes are used to adapt to the changes in angle, shape, and size caused by the motion of fish. Simultaneously, a wider and deeper dilated convolution neural network (DCNN) is used as the back end to reduce the loss of spatial structure information during network transmission. Finally, a hybrid neural network model is constructed. The experimental results show that the counting accuracy of the proposed hybrid neural network model is up to 95.06%, and the Pearson correlation coefficient between the estimation and the ground truth is 0.99. Compared with CNN- and MCNN-based methods, the accuracy and other evaluation indices are also improved. Therefore, the proposed method can provide an essential reference for feeding and other breeding operations.

16 March 2022 in Aquaculture Research
Verified
Journal Article
Closed access
JLJintao Liu
Jintao Liu
FBFernando Bienvenido
Fernando Bienvenido
XYXinting Yang
Xinting Yang
ZZZhenxi Zhao
Zhenxi Zhao
SFShuangxing Feng
Shuangxing Feng
CZChao ZHou
Chao ZHou

Verified
Journal Article
Open access
PDF file
JLJintao Liu
Jintao Liu
ABAlfredo Tolón Becerra
Alfredo Tolón Becerra
JBJosé Fernando Bienvenido-Barcena
José Fernando Bienvenido-Barcena
XYXinting Yang
Xinting Yang
ZZZhenxi Zhao
Zhenxi Zhao
CZChao ZHou
Chao ZHou
The real-time classification of fish feeding behavior plays a crucial role in aquaculture, which is closely related to feeding cost and environmental preservation. In this paper, a Fish Feeding Intensity classification model based on the improved Vision Transformer (CFFI-Vit) is proposed, which is capable of quantifying the feeding behaviors of rainbow trout (Oncorhynchus mykiss) into three intensities: strong, moderate, and weak. The process is outlined as follows: firstly, we obtained 2685 raw feeding images of rainbow trout from recorded videos and classified them into three categories: strong, moderate, and weak. Secondly, the number of transformer encoder blocks in the internal structure of the ViT was reduced from 12 to 4, which can greatly reduce the computational load of the model, facilitating its deployment on mobile devices. And finally, a residual module was added to the head of the ViT, enhancing the model’s ability to extract features. The proposed CFFI-Vit has a computational load of 5.81 G (Giga) Floating Point Operations per Second (FLOPs). Compared to the original ViT model, it reduces computational demands by 65.54% and improves classification accuracy on the validation set by 5.4 percentage points. On the test set, the model achieves precision, recall, and F1 score of 93.47%, 93.44%, and 93.42%, respectively. Additionally, compared to state-of-the-art models such as ResNet34, MobileNetv2, VGG16, and GoogLeNet, the CFFI-Vit model’s classification accuracy is higher by 6.87, 8.43, 7.03, and 5.65 percentage points, respectively. Therefore, the proposed CFFI-Vit can achieve higher classification accuracy while significantly reducing computational demands. This provides a foundation for deploying lightweight deep network models on edge devices with limited hardware capabilities.

19 June 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
ZZZhenxi Zhao
Zhenxi Zhao
XYXinting Yang
Xinting Yang
JLJintao Liu
Jintao Liu
CZChao ZHou
Chao ZHou
CZChunjiang Zhao
Chunjiang Zhao
Only a few key fish individuals can play a dominant role in actual fish group, therefore, it is reasonable to infer group activities from the relationship between individual actions. However, the complex underwater environment, rapid and similar fish individual movements are likely to cause the indistinct action characteristics, as well as adhesion of data distribution, and it is difficult to infer the relationship between individual actions directly by using graph convolutional network (GCN). Therefore, this paper proposes a graph convolution vector calibration (GCVC) network for fish group activity recognition through individual action relationship reasoning. By improving reasoning ability of GCN, an activity feature vector calibration module is designed to solve the data adhesion and mismatch between the estimated and true distribution. The idea is to first count the distribution of the original data, and make each dimension of its active feature vector follow the Gaussian distribution, so as to generate a better similar category distribution. In addition, we also produced a fish activity dataset to verify the performance of the proposed algorithm. The experimental results show that the GCVC achieves a group activity recognition accuracy of 93.33 $\%$ , and the Macro-F1 is 93.25 $\%$ , which is 19.21 $\%$ and 24.2 $\%$ higher than before, respectively. By using GCVC, the corrected activity feature vector distribution is more consistent, and the data adhesion is reduced, the model can achieve more fully supervised learning. The fish group activity dataset is available on Github: https://github.com/crazysboy/GCVC/tree/master .

18 February 2020 in IEEE Access
Verified
Journal Article
Open access
XSXudong Sun
Xudong Sun
ZZZhenxi Zhao
Zhenxi Zhao
SZSong Zhang
Song Zhang
JLJintao Liu
Jintao Liu
XYXinting Yang
Xinting Yang
CZChao ZHou
Chao ZHou
In recent years, residual learning has shown excellent performance on convolutional neural network (CNN)-based single-image super-resolution (SISR) tasks. However, CNN-based SISR approaches have focused mainly on the design of deep architectures, and the rectified linear units (ReLUs) used in these networks hinder shallow-to-deep information transfer. As a result, these methods are unable to utilize some shallow information, and improving model performance is difficult. To solve the above issues, this paper proposes an image SR reconstruction method based on a generative adversarial network with a residual dense architecture. First, before ReLU activation, the number of feature channels is expanded by a factor of 6~9 using a 1 × 1 convolutional layer, which improves the utilization of shallow information. Next, the original discriminator is replaced with a relativistic average discriminator, thereby improving the authenticity of the discriminative network. Finally, preactivation features are used to improve the perceptual loss, thus providing stronger monitoring for brightness consistency and texture restoration. Experimental results show that the proposed algorithm improves the utilization of shallow information in a deep network. Structural similarity (SSIM) index evaluations show that the overall utilization of shallow information is increased by 105.52%. In addition, the average runtime is 0.42 sec/frame, nearly 3.6 times faster than those of traditional methods. Moreover, the recovered images have an average natural image quality evaluator value of 3.4 and high perceptual quality, showing that the proposed method is suitable for image reconstruction applications in fields such as agriculture and medicine.