Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of three-dimensional Convolutional Neural Networks (3D ConvNet), a novel violent video detection scheme based on modified 3D ConvNet is proposed. In this work, the preprocessing method of data is improved, and a new sampling method by using key-frame as dividing nodes is designed. Then a random sampling method is adopted to produce the input frame sequence. With experimental evaluations on the Crowd violence dataset, the results demonstrate the effectiveness of the proposed new sampling method. For three public violent detection datasets, Hockey fight, Movies, and Crowd violence, individualized strategies are implemented to suit the varied clip length. For the short clips, the 3D ConvNet is constructed by using the uniform sampling method. For the longer clips, the new frame sampling strategy is adopted. The proposed scheme obtains competitive results: 99.62% on Hockey fight, 99.97% on Movies, 94.3% on Crowd violence. Experimental results show that our method is simple and effective.

Diffusion models (DMs) are a type of potential generative models, which have achieved better effects in many fields than traditional methods. DMs consist of two main processes: one is the forward process of gradually adding noise to the original data until pure Gaussian noise; the other is the reverse process of gradually removing noise to generate samples conforming to the target distribution. DMs optimize the application results through the iterative noise processing process. However, this greatly increases the computational and storage costs in the training and inference stages, limiting the wide application of DMs. Therefore, how to effectively reduce the resource consumption of using DMs while giving full play to their good performance has become a valuable and necessary research problem. At present, some research has been devoted to lightweight DMs to solve this problem, but there has been no survey in this area. This paper focuses on lightweight DMs methods in the field of image processing, classifies them according to their processing ideas. Finally, the development prospect of future work is analyzed and discussed. It is hoped that this paper can provide other researchers with strategic ideas to reduce the resource consumption of DMs, thereby promoting the further development of this research direction and providing available models for wider applications.

In recent years, the new physics of the Sun has been revealed using advanced data with high spatial and temporal resolutions. The Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamic Observatory has accumulated abundant observation data for the study of solar activity with sufficient cadence, but their spatial resolution (about 1″) is not enough to analyze the subarcsecond structure of the Sun. On the other hand, high-resolution observation from large-aperture ground-based telescopes, such as the 1.6 m Goode Solar Telescope (GST) at the Big Bear Solar Observatory, can achieve a much higher resolution on the order of 0.″1 (about 70 km). However, these high-resolution data only became available in the past 10 yr, with a limited time period during the day and with a very limited field of view. The Generative Adversarial Network (GAN) has greatly improved the perceptual quality of images in image translation tasks, and the self-attention mechanism can retrieve rich information from images. This paper uses HMI and GST images to construct a precisely aligned data set based on the scale-invariant feature transform algorithm and t0 reconstruct the HMI continuum images with four times better resolution. Neural networks based on the conditional GAN and self-attention mechanism are trained to restore the details of solar active regions and to predict the reconstruction error. The experimental results show that the reconstructed images are in good agreement with GST images, demonstrating the success of resolution improvement using machine learning.

Uneven lighting conditions often occur during real-life photography, such as images taken at night that may have both low-light dark areas and high-light overexposed areas. Traditional algorithms for enhancing low-light areas also increase the brightness of overexposed areas, affecting the overall visual effect of the image. Therefore, it is important to achieve differentiated enhancement of low-light and high-light areas. In this paper, we propose a network called correcting uneven illumination network (CUI-Net) with sparse attention transformer and convolutional neural network (CNN) to better extract low-light features by constraining high-light features. Specifically, CUI-Net consists of two main modules: a low-light enhancement module and an auxiliary module. The enhancement module is a hybrid network that combines the advantages of CNN and Transformer network, which can alleviate uneven lighting problems and enhance local details better. The auxiliary module is used to converge the enhancement results of multiple enhancement modules during the training phase, so that only one enhancement module is needed during the testing phase to speed up inference. Furthermore, zero-shot learning is used in this paper to adapt to complex uneven lighting environments without requiring paired or unpaired training data. Finally, to validate the effectiveness of the algorithm, we tested it on multiple datasets of different types, and the algorithm showed stable performance, demonstrating its good robustness. Additionally, by applying this algorithm to practical visual tasks such as object detection, face detection, and semantic segmentation, and comparing it with other state-of-the-art low-light image enhancement algorithms, we have demonstrated its practicality and advantages.

Autonomous underwater vehicle (AUV) has many intelligent optical system, which can collect underwater signal information to make the system decision. One of them is the intelligent vision system, and it can capture the images to analyze. The performance of the particle image segmentation plays an important role in the monitoring of underwater mineral resources. In order to improve the underwater mineral image segmentation performance, some novel segmentation algorithm architectures are proposed. In this paper, an improved mineral image segmentation is proposed based on the modified U-Net. The pyramid upsampling module and residual module are bring into the U-Net model, which are called JPU-Net, JPMU-Net and ResU-Net. These models combined the power of the residual block and the pyramid upsampling in the encoder part and in the decoder part respectively. The proposed models are tested on the Electron Microscopy images (EM) dataset and the underwater mineral image dataset. The experimental results show that JPU-Net has superior performance on the EM dataset, and JPMU-Net has a better segmentation result than existing convolutional neural network on the underwater mineral image dataset.