Current Issue

2025, Volume 51,  Issue 7

Display Method:
Volume 7 Issue E-journal
Volume 51 Issue72025
iconDownload (96974) 174 iconPreview
Image super-resolution reconstruction network based on multi-scale spatial attention guidance
CHENG Deqiang, WANG Peijie, DONG Yanqiang, KOU Qiqi, JIANG He
2025, 51(7): 2185-2195. doi: 10.13700/j.bh.1001-5965.2023.0547
Abstract:

Aiming at the problem that the attention-mechanism-based image super-resolution reconstruction network ignores the heterogeneity of attentional features and treats features at different levels uniformly by directly incorporating the attention mechanism into the network model. This study designs a no...

Fuzzy logic and adaptive strategy for infrared and visible light image fusion
YANG Yong, LIU Jiaxiang, HUANG Shuying, WANG Xiaozheng, XIA Yukun
2025, 51(7): 2196-2208. doi: 10.13700/j.bh.1001-5965.2023.0383
Abstract:

Due to different imaging mechanisms, infrared imaging can capture target information under special conditions where the targetis obstructed, while visible light imaging can capture the texture details of the scenarios. Therefore, to obtain a fusion image containing both target information and textur...

Spatial information-enhanced indoor multi-task RGB-D scene understanding
SUN Guodong, XIONG Chenyun, LIU Junjie, ZHANG Yang
2025, 51(7): 2209-2217. doi: 10.13700/j.bh.1001-5965.2023.0391
Abstract:

To explore 3D space, mobile robots need to obtain a large amount of scene information, which includes semantic, instance objects, and positional relationships. The accuracy and computational complexity of scene analysis are the two focuses of mobile terminals. Therefore, a spatial information-enhanc...

Coordinate-aware attention-based multi-frame self-supervised monocular depth estimation
CHENG Deqiang, FAN Shuming, QIAN Jiansheng, JIANG He, KOU Qiqi
2025, 51(7): 2218-2228. doi: 10.13700/j.bh.1001-5965.2023.0417
Abstract:

A novel multi-frame self-supervised single-image depth estimation technique based on coordinate-aware attention has been presented to tackle the issue of hazy depth prediction near object edges in single-image depth estimation methods. Firstly, a coordinate-aware attention module is proposed to enha...

Railway panoramic segmentation based on recursive gating enhancement and pyramid prediction
CHEN Yong, ZHOU Fangchun, ZHANG Jiaojiao
2025, 51(7): 2229-2239. doi: 10.13700/j.bh.1001-5965.2023.0492
Abstract:

A recursive gated enhancement and pyramid prediction railway panoramic segmentation network is proposed to address the issues of insufficient target feature extraction and blurred edge contour segmentation in high-speed railway scene panoramic segmentation. On the basis of the DETR panoramic segment...

Cascaded object drift determination network for long-term visual tracking
HOU Zhiqiang, ZHAO Jiaxin, CHEN Yu, MA Sugang, YU Wangsheng, FAN Jiulun
2025, 51(7): 2240-2252. doi: 10.13700/j.bh.1001-5965.2023.0504
Abstract:

Aiming at the problems of artificially selecting the threshold and poor determination performance in the existing object drift determination criteria, this paper proposes a cascaded object drift determination network with adaptive threshold selection. Firstly, through the cascade design of the two s...

Robust semi-supervised video object segmentation based on dynamic embedding feature
CHEN Yadang, ZHAO Yibing, WU Enhua
2025, 51(7): 2253-2261. doi: 10.13700/j.bh.1001-5965.2023.0354
Abstract:

A semi-supervised video object segmentation (VOS) method was proposed to address the issues of increasing memory consumption during inference and the difficulty of training relying solely on low-level pixel features. The method is based on dynamic embedding features and an auxiliary loss function. F...

Analysis of image and text sentiment method based on joint and interactive attention
HU Huijun, DING Ziyi, ZHANG Yaofeng, LIU Maofu
2025, 51(7): 2262-2270. doi: 10.13700/j.bh.1001-5965.2023.0365
Abstract:

The image and text sentiment in social media is an important factor affecting public opinion and is receiving increasing attention in the field of natural language processing (NLP). Currently, the analysis of image and text sentiment in social media has mainly focused on single image and text pairs,...

Semantic information-guided multi-label image classification
HUANG Jun, FAN Haodong, HONG Xudong, LI Xue
2025, 51(7): 2271-2281. doi: 10.13700/j.bh.1001-5965.2023.0382
Abstract:

Multi-label image classification aims to predict a set of labels for a given input image. Existing studies based on semantic information either use the correlation between semantic and visual space to guide the feature extraction process to generate effective feature representations or use the corre...

Multi-object tracking algorithm based on dual-branch feature enhancement and multi-level trajectory association
MA Sugang, DUAN Shuaipeng, HOU Zhiqiang, YU Wangsheng, PU Lei, YANG Xiaobao
2025, 51(7): 2282-2289. doi: 10.13700/j.bh.1001-5965.2023.0472
Abstract:

Insufficient target feature extraction and target occlusion situations frequently occur in single-stage multipal object tracking(MOT) algorithms, resulting in a large number of identity switches and degraded tracking performance. A multi-target tracking algorithm based on dual-branch feature enhance...

Fast multi-slice MRI reconstruction algorithm based on transform learning
DUAN Jizhong, LIU Huan
2025, 51(7): 2290-2303. doi: 10.13700/j.bh.1001-5965.2023.0561
Abstract:

Due to the significant correlation between neighboring slices in two-dimensional (2D) multi-slice magnetic resonance data, higher quality slice pictures can be reconstructed by taking use of the redundancy between slices. However, 2D multi-slice magnetic resonance imaging requires an amount of time....

Image sentiment analysis by combining contextual correlation
LUO Gaifang, ZHANG Hao, XU Dan
2025, 51(7): 2304-2313. doi: 10.13700/j.bh.1001-5965.2023.0345
Abstract:

Image sentiment analysis aims to analyze the emotions conveyed by visual content. A key challenge in this field is to bridge the affective gap between latent visual features and abstract emotions. Existing deep learning models attempt to address this issue by directly learning discriminative high-le...

Edge-intelligent transmission optimization of emergency surveillance video based on IcD-FDRL
LI Yan, WAN Zheng, DENG Chengzhi, WANG Shengqian
2025, 51(7): 2314-2329. doi: 10.13700/j.bh.1001-5965.2023.0378
Abstract:

Emergency surveillance video transmission is a key technical means to improve emergency handling capability under circumstances such as emergency monitoring, public security incident handling, and post-disaster reconstruction. It has gradually become a key focus of research and development in the co...

Path planning for agents based on adaptive polymorphic ant colony optimization
XING Na, DI Haotian, YIN Wenjie, HAN Yajun, ZHOU Yang
2025, 51(7): 2330-2337. doi: 10.13700/j.bh.1001-5965.2023.0432
Abstract:

In the realm of intelligent agent path planning, the ant colony algorithm stands as a prominent path-solving strategy that has garnered extensive adoption. However, conventional ant colony algorithms exhibit issues pertaining to local optima and excessive inflection points. The adaptive polymorphic ...

Few-shot object detection of aerial image based on language guidance vision
ZHANG Zhi, YI Huahui, ZHENG Jin
2025, 51(7): 2338-2348. doi: 10.13700/j.bh.1001-5965.2023.0491
Abstract:

This paper presents a few-shot object detection of aerial images based on language guidance vision in response to the problem of decreased detection accuracy in existing aerial image object detection brought on by a lack of training data and changes in the aerial image dataset, such as changes in sh...

An object detection algorithm based on feature enhancement and adaptive threshold non-maximum suppression
MENG Weijun, AN Wen, MA Sugang, YANG Xiaobao
2025, 51(7): 2349-2359. doi: 10.13700/j.bh.1001-5965.2023.0534
Abstract:

To further solve the problems of object omission and repeated detection and improve the accuracy of object detection, this paper proposes an object detection algorithm based on feature enhancement and adaptive threshold non-maximum suppression(NMS). The attention-guided multi-scale context module(AM...

Learning Harris Hawks optimization algorithm with signal-to-noise ratio
ZHANG Lin, SHEN Jiaying, HU Chuanlu, ZHU Donglin
2025, 51(7): 2360-2373. doi: 10.13700/j.bh.1001-5965.2023.0433
Abstract:

Aiming at the problem of insufficient population learning and adaptability of the Harris hawks optimization (HHO) algorithm, this paper proposes a learning Harris hawks optimization based on the signal-to-noise ratio(SLHHO)algorithm. By using the signal-to-noise ratio as a metric to assess individua...

Adaptive search window reconstruction for low-delay video compressive sensing
SUN Renhui, LIU Hao, DENG Kailian, YAN Shuai
2025, 51(7): 2374-2383. doi: 10.13700/j.bh.1001-5965.2023.0333
Abstract:

For distributed video compressive sensing, the inter-frame multi-hypothesis prediction offers low computational complexity at the encoding end and good restoration quality for non-key frames at the decoding end. In recent years, many optimization algorithms related to it have been proposed. However,...

Efficient weakly-supervised video moment retrieval algorithm without multimodal fusion
JIANG Xun, XU Xing, SHEN Fumin, WANG Guoqing, YANG Yang
2025, 51(7): 2384-2393. doi: 10.13700/j.bh.1001-5965.2023.0379
Abstract:

The weakly-supervised video moment retrieval (WSVMR) task retrieves in and out points of specific events from untrimmed videos based on natural language query text, using a deep learning algorithm model trained through video and natural language text matching relationships. Most existing WSVMR algor...

Lightweight neural network design for infrared small ship detection
TANG Wenting, LI Bo, JI Mengqi
2025, 51(7): 2394-2403. doi: 10.13700/j.bh.1001-5965.2024.0747
Abstract:

A lightweight neural network design method is proposed to efficiently represent small ships in infrared remote sensing images. To improve the representation effect of infrared dim and small targets, a method for simulating the visual receptive field adjustment mechanism that incorporates multi-scale...

Omnidirectional image quality assessment based on adaptive multi-viewport fusion
FENG Chenxi, ZHANG Di, LIN Gan, YE Long
2025, 51(7): 2404-2414. doi: 10.13700/j.bh.1001-5965.2023.0381
Abstract:

Existing omnidirectional image quality assessment (OIQA) models extract local features from each viewport independently, increasing computational complexity and making it difficult to describe the correlations between viewports using an end-to-end fusion model. To solve these issues, a quality asses...

Multi-source remote sensing image classification based on wavelet transform and parallel attention
WANG Jiayi, GAO Feng, ZHANG Tiange, GAN Yanhai
2025, 51(7): 2415-2422. doi: 10.13700/j.bh.1001-5965.2023.0329
Abstract:

Exploring the dependency relationships of multi-source remote sensing image data features to leverage the complementary advantages between different modalities has become a prominent research direction in the field of remote sensing. Existing joint classification tasks of hyperspectral and synthetic...

Saliency-aware triple-regularized correlation filter algorithm for UAV object tracking
HE Bing, WANG Fasheng, WANG Xing, SUN Fuming
2025, 51(7): 2423-2436. doi: 10.13700/j.bh.1001-5965.2023.0362
Abstract:

Object tracking in unmanned aerial vehicle (UAV) scenarios has been widely applied in many real-world tasks. Different from general object tracking, UAV object tracking is more easily affected by complex environmental interferences and computational limitations. In this paper, a saliency-aware tripl...

Aerial image stitching algorithm based on unsupervised deep learning
LIANG Zhenfeng, XIA Haiying, TAN Yumei, SONG Shuxiang
2025, 51(7): 2437-2449. doi: 10.13700/j.bh.1001-5965.2023.0366
Abstract:

Traditional image stitching approaches predominantly depend on accurate feature localization and distribution, which leads to suboptimal robustness in intricate aerial photography contexts. Consequently, a comprehensive unsupervised deep learning framework for aerial image stitching was devised, enc...

An adaptive automatic construction algorithm for sentiment dictionaries based on semantic rules
WEI Qinglan, HE Yu, SONG Jinbao
2025, 51(7): 2450-2459. doi: 10.13700/j.bh.1001-5965.2023.0367
Abstract:

Although text sentiment analyses using dictionaries are efficient and unsupervised, their accuracy relies heavily on the dictionary quality. The quality of existing Chinese sentiment dictionaries in cross-domain applications needs to be improved, as the manually constructed Chinese dictionaries fail...

Continual learning method based on differential feature distillation for multimodal network
HE Chiyuan, CHENG Shaoxu, XU Linfeng, MENG Fanman, WU Qingbo
2025, 51(7): 2460-2467. doi: 10.13700/j.bh.1001-5965.2023.0369
Abstract:

Continual learning has become a new research hotspot in recent years. However, in the continual learning of multimodal architecture, the data are generally not fully utilized, resulting in catastrophic forgetting and learning obstruction. To address these issues, a multimodal continual learning meth...

Cover selection method for batch image steganography based on multivariate optimization
WANG Yangguang, YAO Yuanzhi, YU Nenghai
2025, 51(7): 2468-2477. doi: 10.13700/j.bh.1001-5965.2023.0380
Abstract:

Batch image steganography provides an effective means for covert communication on social networks by embedding secret messages into multiple cover images through cover selection. Compared with traditional image steganography, a key challenge of batch image steganography lies in designing an effectiv...

Pedestrian attribute recognition algorithm based on multi-label adversarial domain adaptation
HU Qiangliang, CHEN Lin, SHANG Mingsheng
2025, 51(7): 2478-2487. doi: 10.13700/j.bh.1001-5965.2023.0386
Abstract:

Current unsupervised domain adaption algorithms usually consider only single-label learning, failing to adapt to multi-label classification tasks in pedestrian attribute recognition. To address this issue, a multi-label adversarial domain adaptation algorithm was proposed for pedestrian attribute re...

Dual-channel vision Transformer-based image style transfer
JI Zongxing, BEI Jia, LIU Runze, REN Tongwei
2025, 51(7): 2488-2497. doi: 10.13700/j.bh.1001-5965.2023.0392
Abstract:

Image style transfer aims to adjust the visual properties of a content image based on a style reference image, preserving the original content while presenting specific styles to generate visually appealing stylized images. Most existing representative methods focus on extracting local image feature...

A rotated content-aware retina network for SAR ship detection
WANG Ziyi, YIN Jiahao, HUANG Bobin, GAO Feng
2025, 51(7): 2498-2505. doi: 10.13700/j.bh.1001-5965.2023.0394
Abstract:

Current synthetic aperture radar (SAR) ship detection methods primarily encounter two challenges: 1) the variability of target sizes and the abundance of interfering factors; 2) multiple orientations of targets and a limited quantity of training samples. To address these issues, this paper introduce...

Improved YOLOv7 method for aerial small target detection in aerial photography
LIU Yinuo, ZHANG Qi, WANG Rong, LI Chong
2025, 51(7): 2506-2512. doi: 10.13700/j.bh.1001-5965.2023.0411
Abstract:

This paper proposes an improved YOLOv7-based aerial small target detection method to address the high rates of missed and false detections in current detection technologies for aerial small target detection tasks. First, a CBAM fusion attention mechanism is incorporated into the backbone network, al...

A dense pedestrian tracking method based on fusion features under multi-vision
HUANG Yujie, CHEN Kai, WANG Ziyuan, WANG Ziteng
2025, 51(7): 2513-2525. doi: 10.13700/j.bh.1001-5965.2023.0416
Abstract:

Many multi-object pedestrian tracking algorithms have been proposed in computer vision, and great progress has been made in tracking efficiency and accuracy recently. Practical applications are severely hampered by the fact that the majority of tracking techniques now in use are still unable to addr...

Semi-supervised image retrieval based on triplet hash loss
SHAO Weizhi, XIONG Siyu, PAN Lili
2025, 51(7): 2526-2537. doi: 10.13700/j.bh.1001-5965.2023.0451
Abstract:

Currently, most of the image retrieval methods based on deep learning are supervised techniques, which require massive labeled data. However, it is very difficult and expensive to label so much data in real applications. Furthermore, the network learned picture similarity poorly since the triple los...

Identification of induced information for personalized recommendations based on knowledge graph
NI Wenkai, PENG Shufan, DU Yanhui
2025, 51(7): 2538-2552. doi: 10.13700/j.bh.1001-5965.2023.0475
Abstract:

In the age of intelligent information, managing the recommendations of Internet information service algorithms is a crucial step in creating a national Internet governance framework. Personalized recommendation algorithm is one of the important technologies for Internet information service algorithm...

Camouflaged object detection network based on human visual mechanisms
ZHANG Dongdong, WANG Chunping, FU Qiang
2025, 51(7): 2553-2561. doi: 10.13700/j.bh.1001-5965.2023.0511
Abstract:

Camouflaged object identification is a new visual detection job that has many applications in several fields. Its goal is to identify camouflaged targets that are completely disguised in their environment. To address the problem of current camouflaged object detection algorithms failing to accuratel...

A lightweight semantic VSLAM approach based on adaptive thresholding and speed optimization
QI Hao, FU Yuexin, HU Zhuhua, WU Jiaqi, ZHAO Yaochi
2025, 51(7): 2562-2572. doi: 10.13700/j.bh.1001-5965.2023.0552
Abstract:

Visual simultaneous localization and mapping (VSLAM) is a technology that utilizes visual and other sensory sensors to acquire information about unknown environments. It is widely applied in fields such as autonomous driving, robotics, augmented reality, and more. However, pixel-level semantic segme...