检索结果-内蒙古大学图书馆

On Onboard LiDAR-Based Flying object detection

IEEE TRANSACTIONS ON ROBOTICS 2025年 41卷 593-611页

作者： Vrba, Matous Walter, Viktor Pritzl, Vaclav Pliska, Michal Baca, Tomas Spurny, Vojtech Hert, Daniel Saska, Martin Czech Tech Univ Fac Elect Engn Prague 16627 Czech Republic

A new robust and accurate approach for the detection and localization of flying objects with the purpose of highly dynamic aerial interception and agile multirobot interaction is presented in this article. The approach is proposed for use on board of autonomous aerial vehicles equipped with a 3-D LiDAR sensor. It relies on a novel 3-D occupancy voxel mapping method for the target detection that provides high localization accuracy and robustness with respect to varying environments and appearance changes of the target. In combination with a proposed cluster-based multitarget tracker, sporadic false positives are suppressed, state estimation of the target is provided, and the detection latency is negligible. This makes the system suitable for tasks of agile multirobot interaction, such as autonomous aerial interception or formation control where fast, precise, and robust relative localization of other robots is crucial. We evaluate the viability and performance of the system in simulated and real-world experiments which demonstrate that at a range of 20 m, our system is capable of reliably detecting a microscale UAV with an almost 100% recall, 0.2 m accuracy, and 20 ms delay.

关键词： Autonomous aerial vehicles Robot sensing systems Location awareness Robots Point cloud compression Accuracy Detectors Laser radar Three-dimensional displays Target tracking Aerial systems autonomous aerial interception multirobot systems object detection perception and autonomy segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient object detection

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第3期47卷 1958-1974页

作者： Tang, Hao Li, Zechao Zhang, Dong He, Shengfeng Tang, Jinhui Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Singapore Management Univ Sch Comp & Informat Syst Singapore 188065 Singapore

RGB-Thermal Salient object detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately considered the robustness against noise originating from defective modalities, thereby leading to suboptimal performance in complex scenarios. Inspired by hierarchical human visual systems, we propose the ConTriNet, a robust Confluent Triple-Flow Network employing a "Divide-and-Conquer" strategy. This framework utilizes a unified encoder with specialized decoders, each addressing different subtasks of exploring modality-specific and modality-complementary information for RGB-T SOD, thereby enhancing the final saliency map prediction. Specifically, ConTriNet comprises three flows: two modality-specific flows explore cues from RGB and Thermal modalities, and a third modality-complementary flow integrates cues from both modalities. ConTriNet presents several notable advantages. It incorporates a Modality-induced Feature Modulator (MFM) in the modality-shared union encoder to minimize inter-modality discrepancies and mitigate the impact of defective samples. Additionally, a foundational Residual Atrous Spatial Pyramid Module (RASPM) in the separated flows enlarges the receptive field, allowing for the capture of multi-scale contextual information. Furthermore, a Modality-aware Dynamic Aggregation Module (MDAM) in the modality-complementary flow dynamically aggregates saliency-related cues from both modality-specific flows. Leveraging the proposed parallel triple-flow framework, we further refine saliency maps derived from different flows through a flow-cooperative fusion strategy, yielding a high-quality, full-resolution saliency map for the final prediction. To evaluate the ro

关键词： Decoding Robustness Benchmark testing object detection Noise Lighting Accuracy Visualization Thermal noise Modulation Encoder-Decoder multi-modal fusion RGB- thermal salient object detection

来源：评论

学校读者我要写书评

暂无评论

DA-Net: Density-Aware 3D object detection Network for Point Clouds

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 665-678页

作者： Wang, Shuhua Lu, Ke Xue, Jian Zhao, Yang Univ Chinese Acad Sci Sch Engn Sci Beijing 100049 Peoples R China China Three Gorges Univ Coll Comp & Informat Technol Yichang 443002 Peoples R China

3D object detection is an important but demanding task, which has become an active research topic in the field of multimedia. Much recent research has been devoted to exploiting end-to-end trainable object detection networks with point clouds. However, most state-of-the-art methods have bottlenecks in detecting occluded objects and small objects, because the sparseness of point clouds is exacerbated on these objects. In this paper, a Density-Aware 3D object detection network (DA-Net) is proposed to improve the perception performance for detecting occluded and small objects, which contains four components: a backbone module with an inverse density scoring module (IDM) and a point-wise attention module (PAM), a 3D intersection over union Estimation Module (3DEM), a Consistent Label Assignment (CLA) method and an Adaptive-Soft-NMS method. The proposed backbone module makes the network concentrate on low-density points of occluded objects, and suppresses outliers and background points. Then, the 3DEM is introduced to evaluate the localization quality of the prediction boxes. Furthermore, the proposed CLA method can more accurately select positive and negative samples for small objects. Finally, Adaptive-Soft-NMS is proposed in our method to reduce the number of false detections during inference and thereby improve detection performance substantially. Extensive experiments demonstrated that the proposed method achieves state-of-the-art performance on two large-scale datasets, SUN RGB-D (62.1% in terms of mAP@0.25) and ScanNetV2 (67.1% in terms of mAP@0.25), and in particular, the detection accuracy of small objects and occluded objects are extremely improved.

关键词： Three-dimensional displays object detection Point cloud compression Estimation Location awareness Sun Feature extraction 3D object detection point clouds inverse density deep learning

来源：评论

学校读者我要写书评

暂无评论

Feature pyramid fully convolutional network for small and medium object detection in high-resolution remote sensing images

引用

JOURNAL OF ELECTRONIC IMAGING 2025年第1期34卷

作者： Zhu, Yaoxuan Yang, Hua Zhu, Bin Xie, Bo Natl Univ Def Technol State Key Lab Pulsed Power Laser Technol Hefei Peoples R China

In recent years, deep neural networks have demonstrated significant success in object detection. However, detecting small and medium-sized objects in large-scale, high-resolution remote sensing images (HRSI) remains a challenging task with important military and civilian applications. To address this challenge, we propose an end-to-end feature pyramid fully convolutional network (FP-FCN). Our approach is informed by a detailed analysis of the differences between HRSI and natural images, particularly in terms of color, texture, shape, and spatial layout characteristics. This analysis guided the design of the FP-FCN framework. First, to accommodate objects at varying scales, we employ a feature pyramid network (FPN) to generate multi-level feature maps. Second, considering the high speed and precision of the region-based fully convolutional network (R-FCN) in object detection tasks, we adopted it as the base structure and implemented two parallel operations of location-sensitive pooling on the generated feature maps. Classification results are extracted from multi-level feature maps, whereas regression results are obtained from large-scale feature maps. Third, to mitigate the potential reduction in detection efficiency introduced by multi-level feature maps, we adjusted the number of channels in the feature map according to the number of object types relevant to the HRSI detection task. Finally, experimental results on the PASCAL VOC dataset demonstrate the effectiveness of our proposed method. For the most difficult-to-detect small objects, FP-FCN improves the mean average precision (mAP) by 3.2%, 6.6%, and 5.2% compared with Faster R-CNN + FPN, YOLOF, and R-FCN, respectively. In the HRSI experiment, we developed a small dataset targeting the core components of nuclear power plants as detection objects. When compared with existing object detection networks, our method exhibits clear advantages. (c) 2025 SPIE and IS&T [DOI:10.1117/***.34.1.013033]

关键词： remote sensing image object detection fully convolutional networks feature pyramid

来源：评论

学校读者我要写书评

暂无评论

SA-LfV: self-annotated labeling from videos for object detection

引用

MACHINE LEARNING 2025年第1期114卷 1-24页

作者： Sivapuram, Arun Kumar Komuravelli, Prashanth Gorthi, Rama Krishna Sai Indian Inst Technol Tirupati Dept Elect Engn Tirupati Andhra Pradesh India Indian Inst Technol Tirupati Dept Comp Sci & Engn Tirupati Andhra Pradesh India

In the realm of object detection, the remarkable strides made by deep neural networks over the past decade have been hampered by challenges such as data labeling and the need to capture natural variations in training samples. Existing benchmark datasets are confined with limited set of classes, and natural variations. This paper presents "SA-LfV", a novel framework designed to streamline object detection from videos with minimal human input. By utilizing basic computer vision tasks, such as image classification and tracking single objects, our method generates pseudo-labels for object detection efficiently. To ensure a rich variety of training samples, we introduce two innovative sampling strategies. The first applies density-based clustering, choosing samples that represent a wide range of scenarios. The second analyzes object movements and their mutual information, capturing diverse behaviors and appearances. The proposed object detection data labeling procedure is demonstrated on object-tracking datasets and custom-downloaded videos. Through these methods, our framework has produced a dataset with 70,000 pseudo-labeled bounding boxes across 13 object classes, significantly diversifying the available data for object detection tasks. Our experiments show that the proposed framework can effectively adapt to unlabelled ImageNet classes, indicating its potential to broaden the capabilities of object detection models. Moreover, integrating our self-annotated dataset with standard benchmark datasets leads to a notable improvement in object detection performance. This new approach not only simplifies the traditionally labor-intensive process of manual labeling but also paves the way for expanding object detection to a wider range of classes and applications.

关键词： object detection Tracking Labeling Clustering Data augmentation

来源：评论

学校读者我要写书评

暂无评论

One point is all you need for weakly supervised object detection

引用

PATTERN RECOGNITION 2025年 159卷

作者： Zhang, Shiwei Wang, Zhengzheng Ke, Wei Xi An Jiao Tong Univ Sch Software Engn Xian 710049 Shaanxi Peoples R China Pengcheng Lab Shenzhen 518057 Guangdong Peoples R China

object detection with weak annotations has attracted much attention recently. Weakly supervised object detection(WSOD) methods which only use image-level labels to train a detector encounter some severe problems that it cannot cover the whole object and the region proposal methods waste a large amount of time. Meanwhile, point supervised object detection(PSOD) leverages point annotations that remarkably improves the performance. However, point annotation is still complex and increase the costs of annotation. To overcome these issues, we propose a novel method which only requires one point per category fora training image. Compared to point annotation, our method significantly reduces the annotation cost as the number of point annotations is largely reduced. We design a framework to train a detector with one point per category annotation. Firstly, a pseudo box generation module is introduced to generate the corresponding pseudo boxes of the annotated points. Then, inspired by the observation that the features of objects with the same class in an image are very similar, a dense instances mining module is proposed to make use of the similarity between the features of objects with the same class to discover unlabeled instances and generate pseudo category heatmaps. Finally, the pseudo boxes and pseudo category heatmaps are leveraged to train a detector. Experiments conducted on popular open-source datasets verify the effectiveness of our annotation method and framework. Our proposed method outperforms previous WSOD methods and achieves comparable performance with some PSOD methods in amore efficient way.

关键词： object detection Weak annotation Similarity-based learning

来源：评论

学校读者我要写书评

暂无评论

MAFF-Net: Enhancing 3D object detection With 4D Radar via Multi-Assist Feature Fusion

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第5期10卷 4284-4291页

作者： Bi, Xin Weng, Caien Tong, Panpan Fan, Baojie Eichberge, Arno Tongji Univ Sch Automot Studies Shanghai 201804 Peoples R China Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China Graz Univ Technol Inst Automot Engn A-8010 Graz Austria

Perception systems are crucial for the safe operation of autonomous vehicles, particularly for 3D object detection. While LiDAR-based methods are limited by adverse weather conditions, 4D radars offer promising all-weather capabilities. However, 4D radars introduce challenges such as extreme sparsity, noise, and limited geometric information in point clouds. To address these issues, we propose MAFF-Net, a novel multi-assist feature fusion network specifically designed for 3D object detection using a single 4D radar. We introduce a sparsity pillar attention (SPA) module to mitigate the effects of sparsity while ensuring a sufficient receptive field. Additionally, we design the cluster query cross-attention (CQCA) module, which uses velocity-based clustered features as queries in the cross-attention fusion process. This helps the network enrich feature representations of potential objects while reducing measurement errors caused by angular resolution and multipath effects. Furthermore, we develop a cylindrical denoising assist (CDA) module to reduce noise interference, improving the accuracy of 3D bounding box predictions. Experiments on the VoD and TJ4DRadSet datasets demonstrate that MAFF-Net achieves state-of-the-art performance, outperforming 16-layer LiDAR systems and operating at over 17.9 FPS, making it suitable for real-time detection in autonomous vehicles.

关键词： object detection autonomous vehicle navigation autonomous vehicle navigation 4D radar 4D radar point cloud point cloud deep learning methods deep learning methods

来源：评论

学校读者我要写书评

暂无评论

Advancing object detection performance: random replacement one-one optimized convolutional LeNet algorithm with novel strategies for improved efficiency

引用

EVOLVING SYSTEMS 2025年第2期16卷 1-26页

作者： Alsowail, Rakan A. Al-Shehari, Taher King Saud Univ Self Dev Skills Dept Comp Skills Riyadh 11362 Saudi Arabia

In recent years, computer vision has become indispensable, particularly in advancing object detection and recognition capabilities. Identifying specific objects amidst a complex scene remains a critical challenge. To address this, computer vision methodologies must optimize detection and recognition while managing trade-offs effectively. This study introduces the random replacement one-one optimized convolutional LeNet algorithm (ConvLeNet-RROO) to improve the efficiency and overall performance of object detection systems. ConvLeNet-RROO innovatively incorporates a random replacement strategy during training, selectively replacing weights or neurons to mitigate local minima and accelerate convergence. Moreover, the algorithm integrates one-to-one optimized convolutional layers, which significantly reduce computational complexity without compromising accuracy. Extensive experiments conducted on diverse object detection datasets, including the Indian vehicle dataset, cars detection dataset, vehicle detection dataset, BIT-vehicle dataset, and urban vehicle dataset, illustrate that ConvLeNet-RROO surpasses traditional LeNet and other existing models in detection performance. The integration of optimal curves and a novel random substitution strategy improves performance in object detection by enhancing the ability of a model to accurately detect objects in various conditions. Performance evaluation of ConvLeNet-RROO involves comprehensive analysis using several major performance metrics including accuracy, precision, false positive rate, and false negative rate, demonstrating its superior performance compared to all other existing methods. Experimental results validate the model's exceptional accuracy (99.5%), recall (96.9%), precision (98.4%), F1-measure (97.7%), low false positive rate (0.147), and false negative rate (0.028), highlighting its efficacy in advancing object detection capabilities.

关键词： object detection Normalization Noise removal Convolutional neural network LeNet One-to-one-based optimizer Random replacement strategy

来源：评论

学校读者我要写书评

暂无评论

Optimization of algorithms for dim light enhancement and object detection in deep learning models for abandoned object recognition

引用

JOURNAL OF ELECTRONIC IMAGING 2025年第1期34卷

作者： Gong, Xiaoqiang Jiang, Dong Dai, Wei Cheng, Xiaojun Bozhou Univ Dept Elect & Informat Engn Bozhou Peoples R China Zhejiang Gongshang Univ Dept Elect & Elect Engn Hangzhou Peoples R China Zhejiang Gongshang Univ Dept Math & Stat Hangzhou Peoples R China Bozhou Univ Dept Econ & Management Bozhou Peoples R China

Littering garbage or abandoned object items could have a certain impact on people, and it is not only troublesome to recycle them but also difficult to find the person who threw them away in low light conditions. In recent years, deep learning-based dim light enhancement algorithms and object detection algorithms have gradually emerged as the core of object recognition in image recognition. Developing dim light enhancement algorithms and object detection algorithms is a challenging task due to various problems such as robustness, data limitation, reliability, and computational efficiency. We constructed a dataset of abandoned objects by capturing them from multiple angles and using LabelImg for image annotation. We propose an improved model, ZERO-DCE-CB, to address the issues of poor denoising performance and incomplete feature extraction in addressing the issue of dark light enhancement. For target recognition, the BiFormer with dynamic sparse attention mechanism and step-less convolution (SPD) Conv were combined with YOLOv7-BS to enhance the model's ability to extract image features. The proposed model has a flexible structure and can change at the training or inference phase to accommodate the amount of available information. The proposed model is evaluated on both the constructed abandoned object dataset and the original dataset. The results showed that ZERO-DCE-CB has a better brightening effect and less noise compared with the original model and other models, with an increase of 0.36 and 0.01 in peak signal-to-noise ratio and structural similarity, respectively. The accuracy of the improved YOLOv7-BS has been improved to 89.9%, and there almost have been no missed detections. Although the focus has been on abandoned objects, the proposed design methodology can be generalized to recognize object patterns in images. 2025 SPIE and IS&T

关键词： deep learning dim light enhancement object detection abandoned object

来源：评论

学校读者我要写书评

暂无评论

A small object detection model for drone images based on multi-attention fusion network

引用

IMAGE AND VISION COMPUTING 2025年 155卷

作者： Hu, Jie Pang, Ting Peng, Bo Shi, Yongguo Li, Tianrui Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Neijiang Normal Univ Data Recovery Key Lab Sichuan Prov Neijiang 641100 Sichuan Peoples R China Minist Educ Engn Res Ctr Sustainable Urban Intelligent Transpo Chengdu 611756 Peoples R China Southwest Jiaotong Univ Natl Engn Lab Integrated Transportat Big Data Appl Chengdu 611756 Peoples R China Southwest Jiaotong Univ Mfg Ind Chains Collaborat & Informat Support Techn Chengdu 611756 Peoples R China

object detection in aerial images is crucial for various applications, including precision agriculture, urban planning, disaster management, and military surveillance, as it enables the automated identification and localization of ground objects from high-altitude images. However, this field encounters several significant challenges: (1) The uneven distribution of objects;(2) High-resolution aerial images contain numerous small objects and complex backgrounds;(3) Significant variation in object sizes. To address these challenges, this paper proposes a new detection network architecture based on the fusion of multiple attention mechanisms named MAFDet. MAFDet comprises three main components: the multi-attention focusing sub-network, the multi-scale Swin transformer backbone, and the detection head. The multi-attention focusing sub-network generates attention maps to identify regions with dense small objects for precise detection. The multi-scale Swin transformer embeds the efficient multi-scale attention module into the Swin transformer block to extract better multi-layer features and mitigate background interference, thereby significantly enhancing the model's feature extraction capability. Finally, the detector processes regions with dense small objects and global images separately, subsequently fusing the detection results to produce the final output. Experimental results demonstrate that MAFDet outperforms existing methods on widely used aerial image datasets, VisDrone and UAVDT, achieving improvements in small object detection average precision (APs) of 1.21% and 1.98%, respectively.

关键词： object detection Aerial image Deep learning Attention mechanism Swin transformer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：