In recent years, the engineering application value of hybrid aquatic-aerial robots (HAARs) has been increasingly validated. However, during the hydrofoil planing process, time-varying environmental disturbances can lead to significant model uncertainties in the system. To address this challenge, this paper proposes an error-oriented active disturbance rejection control (ADRC) approach. The method employs an extended state observer (ESO) to uniformly estimate and compensate for both internal and external disturbances based on real-time error signals. On this foundation, We propose an innovative time-series compensation mechanism, which uses historical characteristic information of the system to enhance suppression of time-varying uncertain interferences. Simulation results demonstrate that the proposed control strategy outperforms conventional methods in terms of anti-interference performance and robustness.

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 article 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 task of few-shot classification (FSC) is to build a model to discriminate novel categories that do not present in training categories with limited labeled samples. However, in many applications, the training categories and novel categories are assumed to come from the same domain. Existing few-shot classification algorithms achieve promising performance in a single domain, but often fail to generalize to unseen domains because of the different feature distribution across domains. The main goal of this work is to propose an effective recognition model that can work on various image domains with domain shift. Specifically, we propose to construct a new domain-attention mechanism with some adapters based on the squeeze-and-excitation network architectures . The proposed network processes multiple domains simultaneously and all parameters are shared across domains. In addition, because of the large discrepancy in feature distributions among different domains, similarity transformation layers are used to reduce the differences in the feature distributions in the training stage. Extensive experiments were conducted to validate the domain generalization capability (GC) of this model on four FSC datasets: mini-ImageNet, Cars, CUB-200-2011, and Simpsons Characters Data. The results show that the presented method has excellent performances on various datasets across diverse domains.

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, AP50and average recall (AR)max=10of 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.