In resource-constrained Internet of Things (IoT) environments, lightweight deep learning is crucial for Radio Frequency Fingerprint Identification (RFFI). However, existing lightweight designs primarily rely on group convolution with a “hard split" topology, which strictly isolates channels and blocks inter-group information sharing, impairing feature extraction. To address this, we propose overlap convolution, a novel operator employing a “soft coverage" mechanism to facilitate inter-group interaction. By enabling tunable channel overlapping, this method unifies and generalizes standard and group convolutions, restoring inter-group interaction without requiring additional mixing. We then analyze the approach by introducing structural constraint entropy as an interpretive framework to investigate the information flow capacity. Theoretical analysis demonstrates that overlap convolution offers expanded structural flexibility to achieve enhanced learning ability. Furthermore, we establish the OverlapConv framework for systematic integration of the operator into networks. Within this framework, we develop an automatic parameter acquisition strategy based on a differentiable-to-discrete transition mechanism to efficiently narrow down the search space for optimal settings. Extensive evaluations across diverse datasets (LoRa and UAV RFFI) and multiple backbones (MobileNet, ShuffleNet, and EfficientNet) confirm the method’s effectiveness as a universal plug-and-play module. Notably, our approach achieves an accuracy gain of 29.22% on the Fire block, and improves the accuracy (averaging 2.1% and 2.47% on the two datasets) of FasterNet, EfficientNet, and LMSCNet with reduced FLOPs.

In this paper, we introduce cognitive contour, a novel image attribute that encapsulates the global shape perceived from sparsely distributed, identical or similar objects-such as drone swarms or flocks of geese-collectively termed sparse-structured objects. Unlike traditional contour analysis that delineates the boundaries of individual objects, cognitive contours reflect a gestalt-inspired perception of the overall structure formed by the ensemble, capturing higher-level visual organization. Detecting cognitive contours is challenging due to the sparsity and multiplicity of constituent elements. To tackle this, we propose a scale-space method that integrates alpha shapes into a scale-space framework. An alpha-shape scale space is constructed for the sparse-structured object, and the optimal scale is adaptively selected to extract cognitively meaningful contours with appropriate structural detail. Extensive experiments validate the effectiveness and robustness of the proposed method, enhancing visual inference and offering flexibility across diverse image-based applications. Code and data are available at: https://github.com/CookiC/Sparse.

Software defect prediction can identify potential defective modules in advance and then provide guidances for software testers to allocate more testing resources on these modules. During the gathering process for defect prediction datasets, if multiple metrics are used to measure the program modules, it will result in curse of dimensionality. Feature selection is one of effective methods to alleviate this problem. However, designing effective feature selection methods is a great challenge. Motivated by the idea of search based software engineering, we formalize this problem as a multi-objective optimization problem, and then propose novel method MOFES. To verify the effectiveness of our proposed method, we choose PROMISE dataset gathered from real projects, and compare MOFES with some classical baseline methods. Final results show that our method has the advantages of selecting less features and achieving better prediction performance in most projects while its computational cost is acceptable.

Image resolution in modern video processing and display systems are rocketing up in recent years. With the main stream video quality evolving from standard definition to high-definition, and further towards the emerging super high-definition, the bandwidth and power consumption of external memory are becoming serious bottlenecks. In this paper, frequency domain analysis is made on image down-sampling, which gives birth to the optimal sampling strategy for high-frequency energy protection. On that basis, we develop a new embedded compression (EC) technique, which encodes image frames through content-adaptive down-sampling and decodes them using side-information aided up-sampling. Apart from the low encoding complexity and even lower decoding complexity, the proposed EC algorithm also features high fidelity for images with sharp edges. Comparisons with some existing EC algorithms show the advantage of the new technique over its counterparts on a wide class of testing images.

Object boundary extraction has long been a fundamental research topic, as well as an essential component in many visual computing and communication algorithms, such as computer vision, robotics, pattern recognition and video compression. Under this topic, human head-and-shoulder segmentation is of particular meaning, given the ubiquity of head-and-shoulder type of videos in social media, teleconferencing, and entertainment. Although human visual system can easily detect and recognize the head and upper body of a person, this seemingly simple task still poses a challenge to computers. In this paper, an effective and efficient segmentation method is proposed. This method consists of a novel human body descriptor in polar coordinates and a Markov chain based boundary model, which work together to generate precise boundary results. Moreover, dynamic programming is employed in this work, so as to accelerate the segmentation process. Comparisons with other algorithms are made in the experimental part, which clearly exhibits the advantage of our proposed method over some of its precedents.

With Massive MIMO installed on High Altitude Platforms (HAPs), capacity analysis is conducted for both sparse users and hotspot users. Sparse users are assumed to follow the Poisson Point Process and their capacities are obtained via the random geometry theorem. For hotspot users, Massive MIMO combined with HAP-based communication is shown to be able to achieve the multiplexing gain thus increase the hotspot capacity. The channel correlation model of UPA under LOS propagations is obtained for users within the hotspot. An upper bound of the correlation function is further derived to show that the correlation between hotspot users can be sufficiently low, resulting in hotspot capacity improvement. The hotspot capacity is affected by location distributions of the scheduled users. Four user location distribution models are considered, which leads to the capacity upper bound, the practical schemes to implement and the capacity estimation method respectively.

Single image haze removal is an underdetermined inverse problem whose solution hinges on valid image priors or models. In this work, robust priors drawn from outdoor scene statistics are explored. Specifically, a Gaussian mixture model of chrominance distribution is proposed toward transmittance estimation and its physical validity is justified. In addition, a new sparsity-based optimization approach for transmittance image super-resolution/restoration is proposed, which makes a solid assumption that most outdoor object surfaces are piece-wise linear and thus the corresponding depth image is sparse in Laplacian space. Experimental results are given in proof of the remarkably improved visual quality of our new haze removal technique over its predecessors.

In solving the inverse problem of haze removal, the most commonly used prior in the literature is perhaps that of dark channel, which assumes that at least one pixel in a small patch has a zero or near zero intensity level in one of the RGB color channels. However, this assumption is not physically based; it can be significantly off from the reality because most colors in outdoor natural scenes are unsaturated (e.g., the sky). Chances are that none of the R, G, B values in a patch of the latent image is close to zero. This paper offers detailed analysis on the effects of invalid dark channel assumption on dehazed images; in particular, it reveals the causes and behavior of spectral distortions that are inherent to the dark channel type of dehazing methods.

With rapid increase of image resolution in modern video processing and display systems, the bandwidth and power consumption of external memory are becoming serious bottlenecks. This problem can be alleviated by high-fidelity embedded compression (EC) techniques for video frame buffers. Classic lossless or near-lossless coding methods like CALIC are ill suited for embedded systems due to their high complexity. In this work, a new, simple infra-frame EC technique based on downsampling and side-information aided upsampling is developed. Through a study of a family of downsampling schemes, an optimal one is found and analyzed for EC. This downsampling scheme gives birth to the new EC technique. The main idea is to first split an image into blocks, and then adaptively choose different down sampling patterns and upsampling methods to code/decode these blocks. For a memory bandwidth reduction of 60%, the proposed EC system can achieve PSNR above 40dB, while allowing very simple, low-cost real-time hardware realization. A noteworthy novelty of this work is compression without entropy coding. The resulting code stream is of fixed-rate, supporting random access to pixel blocks.

Super resolution is a process to generate high-resolution images from their low-resolution versions. In many applications such as super-HD (4K) TV, super resolution has to be performed in real time. In this paper we propose a real-time image/video super-resolution algorithm, which achieves good performance at low computational cost via off-line learning of interpolation errors in different pixel contexts. The proposed algorithm consists of three stages: fast edge-guided interpolation to generate an initial HR estimation, GPU-aided de-convolution, and error feedback compensation. All three stages can be implemented with GPU to support real-time applications. Experiments demonstrate the competitive performance of the new real-time super-resolution algorithm in both PSNR and visual quality.