Graph neural networks (GNNs) encounter challenges in establishing deep structures and managing a large number of parameters effectively to learn node features comprehensively. Consequently, in vision tasks, GNNs often struggle to achieve high classification accuracy compared to convolutional neural networks. Nonetheless, GNNs retain crucial advantages and potential, particularly in lightweight network scale and efficient, reliable decision-making. Thus, improving GNN performance in vision tasks remains a significant research endeavor, with numerous important works exploring the application of GNN models in such contexts, where the graph representation of images poses a key challenge. Existing methods often fall short in adaptively generating blocks of different sizes and their corresponding edges to form graph representations according to graph semantics. To address this issue, we propose a novel method to convert images into graphical forms using granular-ball computing. Our approach does not rely on manual annotation or other learning methods, yet it can dynamically generate block nodes of varying sizes and corresponding edges. Compared to other state-of-the-art methods, our approach better captures semantic information within the graph. Despite having fewer parameters, our method significantly enhances accuracy. Overall, our work holds substantial implications for improving the performance of graph neural networks in vision tasks.

An emerging Internet of Video Things (IoVT) application, crowd counting is a computer vision task where the number of heads in a crowded scene is estimated. In recent years, it has attracted increasing attention from academia and industry because of its great potential value in public safety and urban planning. However, it has become a challenge to cross the gap between the increasingly heavy and complex network architecture widely used for the pursuit of counting with high accuracy and the constrained computing and storage resources in the edge computing environment. To address this issue, an effective lightweight crowd counting method based on an encoder–decoder network, named lightweight crowd counting network (LEDCrowdNet), is proposed to achieve an optimal tradeoff between counting performance and running speed for edge applications of IoVT. In particular, an improved MobileViT module as an encoder is designed to extract global-local crowd features of various scales. The decoder is composed of the adaptive multiscale large kernel attention module (AMLKA) and the lightweight counting atrous spatial pyramid pooling process module (LC-ASPP), which can perform end-to-end training to obtain the final density map. The proposed LEDCrowdNet is suitable for deployment on two edge computing platforms (NVIDIA Jetson Xavier NX and Coral Edge TPU) to reduce the number of floating point operations (FLOPs) without a significant drop in accuracy. Extensive experiments on five mainstream benchmarks (ShanghaiTech Part_A/B, UCF_CC_50, UCF-QNRF, WorldExpo’10, and RSOC data sets) verify the correctness and efficiency of our method.

In recent decades, remote sensing object counting has attracted increasing attention from academia and industry due to its potential benefits in urban traffic, public safety, and road planning. However, this issue is becoming a challenge for computer vision because of various technical barriers, such as large-scale variation, complex background interference, and nonuniform density distribution. Recent results show hopeful prospects for object counting using convolutional neural networks (CNNs), but most existing CNN-based methods draw on larger and more complex architectures, which leads to a huge computational and storage burdens, severely limiting their application in real-world scenarios. In this article, a lightweight multiscale feature fusion network for remote sensing object counting, named LMSFFNet, is presented to achieve a better balance between the running speed of the network and the counting accuracy. Specifically, in the encoding process, we select a MobileViT module as the backbone of the network to reduce the numbers of network parameters and computing cost. In return, a cascade structure of the channel–spatial attention mechanisms compensates for the weaker feature extraction ability of the lightweight network. In the decoding process, a lightweight multiscale context fusion module (LMCFM) as a multiscale feature fusion module is developed to solve the problem that the number of parameters increases with the expansion of the object scale when extracting multiscale features. In addition, a lightweight counting scale pooling module (LCSPM) is used to mine the subtle features of the target object. Two kinds of typical object counting experiments, namely, experiments on remote sensing benchmarks (RSOC dataset) and crowd benchmarks (ShanghaiTech, UCF-QNRF, and UCF_CC_50 datasets), show the effectiveness of the proposed method.