Search

Homography estimation is regarded as one of the key challenges in image alignment, where the goal is to estimate the projective transformation between two images on the same plane. Unsupervised learning methods are gradually becoming popular due to their excellent performance and lack of need for labeled data. However, in regional scenes with repeated textures, there may be ambiguity in the correspondence between local features, affecting homography estimation accuracy. This paper proposes a new unsupervised deep homography method RTHEN to solve such problems. In order to effectively obtain repeated texture features, a multi-scale Feature pyramid Siamese network (FPSN) is designed. Specifically, we dynamically allocate the weights of recited texture features through a dynamic attention module and introduce a channel attention module to provide rich contextual information for repeated texture areas. We propose a hard triplet loss function based on overlap constraints to optimize the matching results. At the same time, we collected a repetitive texture image dataset (RTID) for homography estimation training and evaluation. Experimental results show that our method outperforms existing learning methods in repetitive texture scenes and offers competitive performance with state-of-the-art traditional methods. • An unsupervised method is employed for homography estimation. • The issue of mismatching in repetitive textures is effectively addressed. • Formulated a loss function with overlap constraints to enhance estimation results. • Curated a dataset of repeated texture images for training and model evaluation. [ABSTRACT FROM AUTHOR]

• A method for single-object tracking of fish was proposed. • The problems of similar interference, occlusion and image blur are solved. • The model has good performance in aquaculture environment. • Tracking of fish will improve fish welfare. In aquaculture, tracking fish helps to obtain information about their growth, behavior, location and health, etc. However, there are some problems in the process of fish tracking. Firstly, to solve the noise problem of underwater images, we use the contrast limited adaptive histogram equalization (CLAHE) to carry out local histogram equalization in each small block, which increases the image contrast while retaining more details. This operation enhances the contrast of the image while suppressing noise to solve the problem of noisy images. Then, to solve the problems of similarity interference, occlusion and scale variation among fish, we propose a new method for fish single object tracking in aquaculture environments, called SiamFCA, by combining the coordinated attention mechanism (CA). The method is based on the siamese network framework and uses a modified AlexNet to extract the depth features of image pairs. And through the coordinate attention mechanism, the model can learn the relationship between different objects more accurately, which can improve the accuracy and robustness of the model when dealing with complex image scenes. Finally, the correlation operation between classification and regression is performed based on the region proposal network (RPN). By classifying, region suggestions can be labeled as positive or negative samples, and regression can calibrate the position and size of the region proposal to match targets more accurately. The experimental results show that the precision and success rate of the algorithm are 84.2 % and 62.4 %, respectively, which are better than the tracking methods such as SiamRPN and DaSiamRPN, etc. The SiamFCA runs at 83 fps, which meets the demand of real-time fish tracking in aquaculture. [ABSTRACT FROM AUTHOR]

• A survey of machine vision for fish tracking in aquaculture. • A taxonomy of the techniques and classify the papers based on the taxonomy. • An analysis of fish detection and tracking methods. • A review of the application of fish tracking technology in fish research. • Summarized the datasets that can be used for fish tracking. In aquaculture, Behavioral monitoring of fish contributes to scientific management and reduces the threat of loss from disease and stress. Fish tracking technology plays an important role in behavior monitoring. It can pay attention to the movement of fish at any time and discover various abnormal behaviors in time. As a non-invasive method, computer vision is a powerful tool for fish tracking.. Its tracking principle is to establish the relationship between fish positions in a continuous video sequence and get the complete movement trajectory of the fish. Nevertheless, computer vision modeling used for fish tracking is riddled with many challenges, such as fish deformation, frequent occlusion, scale change, etc. Around these difficult issues, many scholars have carried out the research. In this paper, we review the progress of tracking algorithms in fish research. Then, methods for fish tracking before deep learning are introduced. Further, a detailed discussion of fish tracking methods employing deep learning such as tracking-by-detection, deep features combined with correlation filtering methods, Siamese networks, etc. Furthermore, we summarize datasets that can be used as fish tracking and give evaluation metrics in target tracking algorithms. In addition, experimental data of several mainstream tracking algorithms on a public tracking dataset are given. Finally, we discuss the outstanding findings and look forward to the fish tracking method combined with Transformer, aiming to provide a reference for accelerating the promotion of smart fishery and precision farming. [ABSTRACT FROM AUTHOR]

• Using ERPs to study the impact of empathy with nature on green purchase behavior. • Empathy with nature could effectively promote consumers' green purchase behavior. • Empathy with nature could reduce the decision conflict when buying green products. • Empathy with nature could affect consumers' product preferences. Due to the attitude-behavior gap in green consumption, it is necessary to conduct more research on consumers' actual purchase behavior. At present, few studies have been conducted on the impact of empathy with nature on green purchase behavior. This research explored the underlying neural mechanism of empathy with nature on consumers' green purchase decisions by applying the event-related potentials (ERPs) approach. Behaviorally, compared with the control group, the experimental group had a higher purchase rate of green products and spent less time when buying green products. For the experimental group, buying green products required less time than buying traditional products. At the neural level, when buying green products, the N2 and N400 amplitudes of the experimental group were smaller than those of the control group. For the experimental group, buying green products elicited a smaller N2 amplitude than buying traditional products. These findings suggested that empathy with nature could reduce consumers' decision conflict when buying green products, thereby promoting consumers' green purchase behavior. [ABSTRACT FROM AUTHOR]

• The time course of ERPs responses to the expertise congruency effect in ads was examined. • The cognitive process comprises an early conflicted perception and later memory recollection stage. • Stimulating pairs of athlete star and sport brand triggered a more negative N2 and positive LPP compared to the other pairs. • The N2 mainly reflects the conflict process of celebrity-brand, and the LPP refers to the recollection process of the expertise association. Celebrity/brand endorsement is omnipresent and has great influence on consumers. In the current study, the event-related potentials (ERPs) were utilized to explore the neural process underlying how expertise congruency effect matters in ads. Twenty-five participants (two excluded) were recruited to accept or refuse the brands (stimulus 2) endorsed by celebrities (stimulus 1) during a S1–S2 paradigm. Behavioral results indicated significant differences in the acceptance rates and reaction time, while ERPs component provided further insight into the cognitive processing: early conflicted perception and later memory recollection process. The results of ERPs showed that, when the celebrity is an athlete star, presenting a sport brand (AS, expertise congruity) triggered a less negative N2 and a larger LPP component compared to a leisure brand (AL, expertise incongruity) but not different with singer star (SS and SL, expertise neutrality). We suggested the N2 may reflect the conflict process of celebrity-brand, while the LPP may demonstrate the recollection process of expertise association in memory. Such findings implied that a more fluent processing (smaller N2 and larger LPP) and prominent performances could be obtained in an expertise congruity scenario, which deepened our understanding of expertise congruency effect in advertising. [ABSTRACT FROM AUTHOR]