关键词： 目标检测   卷积神经网络   多尺度目标检测   感受野   特征金字塔网络(FPN)  

摘要： 针对多尺度目标检测中主干网络实际感受野远远小于理论感受野,感受野分布稀疏,以及特征金字塔网络(feature pyramid network,FPN)在横向连接过程中统一通道数会丢失通道信息等影响模型性能的问题,提出一种扩增实际感受野和多特征融合改进FPN的多尺度目标检测算法ResFPN。针对主干网络实际感受野远远小于理论感受野的问题,设计了多分支膨胀卷积(multi-branch dilated convolutional,MBD)模块和多分支池化(multi-branch pooling,MBP)模块,通过学习不同尺度空间特征融合,扩增感受野。针对感受野分布稀疏问题,提出轻量级通道交互融合(channel interactive fusion,CIF)模块,通过双分支结构并在每一分支叠加不同数量深度可分离卷积学习像素间的依赖关系增强特征表示。针对FPN通过1×1卷积统一通道数会丢失通道信息的问题,尝试利用SubPixel卷积提取C5层输出特征,保留原始丰富语义信息的同时引出额外双向路径对FPN通道信息进行补充,但这可能会产生冗余信息。因此,在额外双向路径后引入全局上下文(global context,GC)模块,利用GC瓶颈转换模块进一步融合特征信息,减少信息冗余。实验表明,提出的ResFPN有效解决了感受野分布稀疏问题,并将主干网络感受野增大为原来的一倍,同时提出的改进FPN通道丢失问题的方法也在多尺度目标检测中获得了良好的性能。与典型的网络Faster R-CNN相比,大、中、小物体检测平均精度在具有挑战性的MS COCO数据集上分别提高了2.2、1.6、2.0个百分点,与其他检测器相比检测效果也有提升。

关键词： 复杂工业环境   工业机器人   视觉识别   图像处理  

摘要： 聚焦于面向复杂工业环境的工业机器人视觉识别与控制技术。负责解决复杂工业场景中光照变化、遮挡、多目标干扰等问题,包括对工业机器人视觉识别技术的组成、图像处理与特征提取方法进行分析,以及积极探索深度学习算法在目标分类、检测与分割中的应用。还针对其控制系统如何构建和运作,以及掌握控制算法原理进行说明,并重点追踪了运动学求解、路径规划及视觉伺服控制技术。

关键词： 多尺度交叉注意力   边缘感知   伪装目标检测   特征金字塔结构  

摘要： 针对当前伪装目标检测算法无法准确、完整地检测出目标对象和其边缘的问题,提出了一种融合多尺度交叉注意力和边缘感知的伪装目标检测网络(multi-scale cross attention and edge perception network,MAEP-Net)。利用Res2Net-50提取图像的原始特征,并采用融合了多尺度交叉注意力的特征金字塔结构从通道、空间两个维度挖掘目标位置信息和凸显伪装目标区域特征;使用定位模块对目标的大致位置进行准确定位;边缘感知模块抑制低级特征中背景的噪声,融合边缘特征以获取更多的边缘细节信息;细化模块通过注意力机制分别从前景和背景两个方向关注目标线索,利用边缘先验、语义先验、领域先验、区域先验知识进一步细化目标结构和边缘轮廓。在3个公开数据集上的实验表明,所提算法相较于12种主流算法在4个客观评价指标上均取得了最优表现,尤其是在COD10K数据集上所提算法的加权平均值F-measure和平均绝对误差(mean absolute error,MAE)分别达到0.797和0.031。由此可见,所提算法在COD任务上具有较好的检测效果。

关键词： 人体姿态估计   计算机视觉   深度神经网络   评价指标  

摘要： 人体姿态估计是计算机视觉领域的重要研究方向,在教育教学、临床诊断、人机交互等多场景均有重要应用。随着深度神经网络提出及发展,其以强大的特征学习能力、大规模并行处理等优势,广泛应用于人体姿态估计,并大幅提高了估计结果准确度和识别效率。以人体姿态估计为研究对象,梳理近5年相关领域100篇包含RNN、CNN、GAN、前沿网络模型等深度神经网络及其变体架构的代表性文献;此外,汇总梳理近5年常用数据集,并阐释了模型常用评估指标。最后,总结现阶段人体姿态估计领域面临的挑战,并展望未来研究,以进一步探讨深度神经网络在人体姿态估计中的应用潜力。

关键词： 计算机视觉技术   电力设备故障检测   诊断  

摘要： 随着电力系统规模的持续扩大,确保电力设备安全稳定运行显得尤为重要。与传统检测方式相比,基于计算机视觉技术的电力设备故障检测与诊断方法具有显著优势,在电力行业得到了广泛应用。文章深入探讨了计算机视觉技术在电力设备故障检测与诊断中的具体应用,旨在通过这一先进技术为电力系统的可靠运行提供有效保障,同时为相关领域的研究人员和技术人员提供有价值的参考。

关键词： 计算机视觉   NSGA-II   施工场地布置   动态优化  

摘要： 针对当前施工场地布置依赖经验、资源浪费及安全隐患等问题,本文提出一种基于计算机视觉与非支配排序遗传算法(NSGA-II)的施工场地动态布置优化方法。通过计算机视觉技术获取实时的施工场地数据,构建场地布置的场景感知模型,并基于此实现对施工过程中各临时设施的空间位置与状态的动态跟踪。在此基础上,结合施工阶段划分和资源流通特性,采用NSGA-II算法进行多目标优化,以减少施工过程中的运输成本和二次搬运,提高施工效率和安全性。最后,结合某大型综合体项目验证所提出方法的有效性。

关键词： Image segmentation  

摘要： To address challenges such as time consumption, interference from dynamic objects, insufficient feature points leading to low real-time performance, reduced mapping accuracy, and inaccurate pose estimation in indoor dynamic environment mapping of visual SLAM (simultaneous localization and mapping) systems, this study proposes a visual SLAM algorithm based on object detection and point-line feature association, referred to as LDF-SLAM. To mitigate time consumption and dynamic object interference, MobileNetV3 is introduced to replace the YOLOv8 backbone network, thereby reducing the number of network parameters. A parameter-free attention-enhanced ResAM module is designed and integrated with the MobileNetV3 network to create a lightweight detection network to enhance detection capability and efficiently identify dynamic objects. Subsequently, the multi-view geometry method is introduced to compensate, filter and reject potential dynamic feature points together with the improved lightweight network, and the remaining static feature points are used to construct a dense point cloud map, thereby improving the mapping accuracy of the SLAM system. In addition, to resolve inaccuracies in pose estimation due to insufficient static feature points, a fusion FLD line feature extraction method is proposed to enhance pose estimation accuracy. A line segment length suppression mechanism is also designed to ensure the system’s real-time performance and improve its robustness. Experiments conducted on the TUM and Bonn data sets demonstrate that the root-mean-square-error (RMSE) of absolute trajectory error of LDF-SLAM is reduced and outperforms other mainstream SLAM algorithms, significantly enhancing the robustness and accuracy of the SLAM system in dynamic environments. © 2025 Universitat zu Koln. All rights reserved.

关键词： Feature extraction  

摘要： Aiming to address the issue of overlapping occlusion caused by the varying sizes and large quantities of dragon fruit, a multi-scale weighted feature fusion network (MBS — YOLO v8) was proposed based on the YOLO v8 model. Firstly, the squeeze-and-excitation attention (SEAttention) mechanism was incorporated into the feature extraction module to enhance the network's ability to capture critical details, thereby addressing the ehallenge of small object detection. Secondly, a multi-scale weighted fusion network (MWConv) was introdueed to generate feature maps with varying receptive fields, improving the capture of global features within images. Finally, experimental results demonstrated that MBS — YOLO v8 achieved an accuracy of 92. 5%, a recall rate of 90. 1%, and a mean average precision (mAP50) of 94. 7%. Compared with the YOLO v8n algorithm, MBS — YOLO v8 showed improvements of 2. 1 percentage points, 5.9 percentage points, and 2 percentage points in accuracy, recall, and mAP50, respectively. The proposed MBS — YOLO v8 model exhibited high robustness, effectively integrating global feature Information with low-dimensional local features to enhance the model's understanding of image content. This approach effectively addressed challenges related to overlapping oeelusion and small object detection, providing an improved methodology for detecting dragon fruit and other similar targets. © 2025 Chinese Society of Agricultural Machinery. All rights reserved.

关键词： Data reduction  

摘要： Infrared detection serves as a crucial tool for remote search and surveillance, and it plays a significant role in many applications. To enhance the infrared detection accuracy of small targets in complex backgrounds, a Trans-YOLO detection framework based on an improved YOLOv8 model with RT-DETR is proposed. First, to avoid the issue of non-maximum suppression (NMS) in YOLOv8 erroneously suppressing true targets, the Head component of YOLOv8 is replaced with the Decoder & Head from RT-DETR. Furthermore, to address the challenges of weak signal strength and small size of infrared small targets, an RGCSPELAN module is designed to enable the detection network to perform more fine-grained processing of the input features. Finally, to reduce the semantic disparity between deep and shallow features, a new feature fusion strategy, called CAFM-based fusion (CAFMFusion) mechanism, is designed to facilitate the flow of different types of feature information within the network, thereby enhancing the model’s ability to detect targets of varying sizes. Experimental results show that the proposed Trans-YOLO model achieves 86. 1% and 99. 5% mean average precision at IoU= 0. 5 (intersection over union) on two public datasets with complex scenarios, representing improvements of 7. 7 percentage points and 3. 0 percentage points over the original YOLOv8 model, respectively. Additionally, the model achieves the processing speed of 371. 9 frame/s and 369. 4 frame/s on the two datasets, respectively, effectively balancing accuracy and speed. © 2025 Universitat zu Koln. All rights reserved.

关键词： Drones  

摘要： To address the challenges of insufficient feature information in small targets within unmanned aerial vehicle (UAV) aerial images and significant variation in target scales, a small target detection algorithm based on an improved YOLOv8n is proposed. The improvements focus on the following aspects: i) design of a multi-scale feature fusion layer in the detection layer tailored for feature extraction and processing of small targets to improve the ability to collect detailed information of small targets;ii) concerning the neck network, a triple-feature fusion module and a scale sequence feature fusion module are introduced to effectively fuse the detailed information from low-level feature maps with the semantic information from high-level feature maps. This enhances detection capabilities across targets of varying scales. In the backbone network, ConvNeXt v2 is used to replace the backbone network, thereby enhancing the localization and feature extraction capabilities of small targets against complex backgrounds. To optimize the deployment of the model in embedded systems, a layer adaptive amplitude pruning algorithm is adopted to balance the computational complexity and detection accuracy of the model. The algorithm performance is tested using the VisDrone2019 dataset and compared with several mainstream models. The experimental results indicate that the improved algorithm attains a detection accuracy (mAP50) of 30. 2%, which is 3. 8 percent point higher than that of the benchmark model, YOLOv8n, while reducing the parameter count by 1. 63×106 © 2025 Universitat zu Koln. All rights reserved.