The task of crowd counting and localization is to predict the count and position of people in a crowd, which is a practical and essential subtask in crowd analysis and smart city systems. However, the inherent problems of scale variation and background disturbance restrain their performance. While recent research focus on studying counting and localization independently, a few works are capable of executing both tasks simultaneously. To this end, we propose a scale-context perceptive network (SCPNet) to jointly tackle the crowd counting and localization tasks in a unified framework. Specifically, a scale perceptive (SP) module with a local–global branch schema is designed to capture multiscale information. Meanwhile, a context perceptive (CP) module, by the channel-spatial self-attention mechanism, is derived to suppress the background disturbance. Furthermore, a novel hierarchical scale loss function that combines the Euclidean loss function and structural similarity loss function is designed to prompt the proposed model to fulfill the counting and localization simultaneously. Extensive experiments on challenging crowd data sets prove the superiority of the proposed SCPNet compared with the state-of-the-art competitors in both objective and subjective evaluations.
25 July 2023 in IEEE Transactions on Intelligent Transportation Systems
Self-driving technology and safety monitoring devices in intelligent transportation systems require superb capacity for context awareness. Accurately inferring the counts of crowds and vehicles are the two practical and fundamental tasks in the transportation system. However, the scale variation and background interference in the traffic image hinder the counting performance. To solve the aforementioned problems, a scale region recognition network (SRRNet) is proposed in this paper. It has two key components, termed scale level awareness (SLA) module and object region recognition (ORR) module. The SLA module aims to encode the representations at multiple scales, which are beneficial to address the scale variation. The ORR module is designed to suppress background interference through the visual attention mechanism. Extensive experimental results on four crowd counting datasets and five vehicle counting datasets have demonstrated the superiority of the proposed SRRNet in both counting accuracy and robustness compared with the mainstream competitors. Meanwhile, substantial ablation studies have proved the effectiveness of the proposed SLA and ORS modules.
Object counting is a fundamental task in remote sensing analysis. Nevertheless, it has been barely studied compared with object counting in natural images due to the challenging factors, e.g., background clutter and scale variation. This paper proposes a triple attention and scale-aware network (TASNet). Specifically, a triple view attention (TVA) module is adopted to remedy the background clutter, which executes three-dimension attention operations on the input tensor. In this case, it can capture the interaction dependencies between three dimensions to distinguish the object region. Meanwhile, a pyramid feature aggregation (PFA) module is employed to relieve the scale variation. The PFA module is built in a four-branch architecture, and each branch has a similar structure composed of dilated convolution layers to enlarge the receptive field. Furthermore, a scale transmit connection is introduced to enable the lower branch to acquire the upper branch’s scale, increasing the output’s scale diversity. Experimental results on remote sensing datasets prove that the proposed model can address the issues of background clutter and scale variation. Moreover, it outperforms the state-of-the-art (SOTA) competitors subjectively and objectively.
19 February 2024 in IEEE Transactions on Consumer Electronics
In the domain of infrared and visible image fusion, the majority of existing methods are designed for infrared and visible images with normal illumination conditions. However, these methods may not effectively address the challenges presented by long-haul transmission scenarios in the Tactile Internet. To meet the requirements of nighttime infrared and visible image fusion in long-haul network architectures for the tactile internet, an illumination component adjusting network (ICANet) is built. Firstly, an illumination adjustment denoising subnetwork (IADSubNet) is designed to enhance the illumination component of nighttime visible images and simultaneously eliminate noise. Secondly, a local-global perception fusion subnetwork (LGPFSubNet) is built to dynamically extract and fuse both global and local information of the source images. Furthermore, we leverage a mutual consistency loss to generate fused images that are both visually appealing and rich in information. This ensures the fidelity and consistency of the fused images during long-distance transmission. Comprehensive experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) methods quantitatively and qualitatively, and prove that it has potential for high performance in the long-haul transmission scenarios of tactile Internet. Meanwhile, the fused images generated by the ICANet significantly enhance object detection tasks. It is a critical aspect for many tactile internet applications dependent on real-time and accurate object recognition.
Computer vision plays a pivotal role in modern society, which transforms fields such as healthcare, transportation, entertainment, and manufacturing by enabling machines to interpret and understand visual information, revolutionizing industries, and enhancing daily life
21 November 2023 in Software: Practice and Experience