检索结果-内蒙古大学图书馆

Study on efficient recognition and accurate localization method of waste plastic bottles based on deep learning

ECOLOGICAL INFORMATICS 2025年 86卷

作者： Xie, Shilong Wu, Hu Mao, Wenjie Chu, Xianlong Meng, Yixing Yang, Xianhai Shandong Univ Technol Sch Mech Engn Zibo 255000 Peoples R China

As a vital component of ecologically sustainable development, the effective recovery and reuse of waste plastic bottles is essential for environmental protection and resource recycling. Given the varying recycling values of plastic bottles based on their colors, precise sorting and recycling are particularly important. Traditional manual sorting methods face challenges such as low efficiency and high costs. In contrast, machine vision-based image recognition technology offers a more efficient solution for classifying and recovering waste plastic bottles, with classification recognition and target positioning being critical technologies for the optimal use of ecological resources. This study introduces a deep learning approach for identifying and locating waste plastic bottles, utilizing the reversible column network (RevCol) as the backbone to prevent information loss. A lightweight combined decoupling head is designed to minimize computational load while enhancing accuracy. The Weighted Intersection over Union version 3 (WIoU v3) loss function is incorporated to improve detection performance. By leveraging depth information from an infrared camera alongside RGB image mapping, the method achieves recognition and three-dimensional positioning. Experimental results indicate that the proposed model outperforms traditional models, with a 36.39 % reduction in parameters and a 50.62 % decrease in computational requirements, while accuracy and recall rates improve by 4.56 % and 12.14 %, respectively. Additionally, mAP50 and mAP50-95 values increase by 5.86 % and 3.89 %, and the recognition speed reaches 62 FPS, a 51.22 % improvement, meeting real-time detection needs. Experiments conducted on a deep learning-UR5 robot platform demonstrate high recognition accuracy and sorting success rates in actual waste plastic bottle sorting scenarios. The promotion and implementation of this method will significantly enhance the recycling of waste plastic resources and contribute to th

关键词： Recycling of waste plastic bottles Machine vision Deep learning target recognition classification detection Three-dimensional positioning

来源：评论

学校读者我要写书评

暂无评论

Small infrared target detection by data-driven proposal and deep learning-based classification 44

Small infrared target detection by data-driven proposal and ...

引用

Conference on infrared technology and Applications XLIV

作者： Ryu, Junhwan Kim, Sungho Yeungnam Univ Dept Elect Engn 280 Daehak Ro Gyongsan 38541 Gyeongsangbuk D South Korea

ISBN: (纸本)9781510617605

In this paper, we propose a data-driven proposal and deep-learning based classification scheme for small target detection. Previous studies have shown feasible performance using conventional computer vision techniques such as spatial and temporal filters. However, those are handcrafted approaches and are not optimized due to the nature of the application fields. Recently, deep learning has shown excellent performance for many computer vision problems, which motivates the deep learning-based small target detection. The proposed data-driven proposal and convolutional neural network (DDP-CNN) can generate possible target locations through the data-driven proposal and final targets are recognized through the classification network. According to the experimental results using drone database, the DDP-CNN shows 91% of train accuracy and 0.85 of average precision (AP) of the target detection.

关键词： Small target detection infrared small target detection Deep learning classification Region proposal Convolution Neural Network

来源：评论

学校读者我要写书评

暂无评论

Integrating hyperspectrograms with class modeling techniques for the construction of an effective expert system: Quality control of pharmaceutical tablets based on near-infrared hyperspectral imaging

引用

JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS 2025年 256卷 116697页

作者： Pieszczek, Lukasz Daszykowski, Michal Univ Siles Katowice Inst Chem 9 Szkolna St PL-40006 Katowice Poland Univ Siles Katowice Ctr Microscop Studies Matter SPIN Lab 75 Pulku Piechoty St 1 PL-41500 Chorzow Poland

Near-infrared hyperspectral imaging (NIR-HSI) integrated with expert systems can support the monitoring of active pharmaceutical ingredients (APIs) and provide effective quality control of tablet formulations. However, existing quality control methods usually test a limited number of variability sources affecting the final product. This study examines the potential of NIR-HSI (in the spectral range of 935.61-1720.2 nm) as an advanced and high-throughput detector to identify different manufacturing factors and their fluctuations that impact tablet properties. These are, for instance, particle sizes of powdered excipients, their mixing, compression force used to form a tablet, origin of ingredients, storage conditions, and concentration of API. During the study, the novel expert system approach was developed to support NIR-HSI, enabling the detection of subtle, diverse substandard anomalies in tablets. The system combines (i) hyperspectrograms, which characterize and simplify tablet spatial heterogeneity through principal component analysis scores distribution, and (ii) a one-class classifier (OCC), trained exclusively on target class samples, without the need for substandard tablets. The system was trained to recognize known sources of variation and validated using tablets with cellulose, magnesium stearate, and ascorbic acid as API. It outperformed the alternative approach based on averaged spectra, achieving 100.00% sensitivity and 98.77% specificity.

关键词： Near-infrared hyperspectral imaging (NIR-HSI) Process analytical technology (PAT) Pharmaceutical quality control Hyperspectrogram One-class classification

来源：评论

学校读者我要写书评

暂无评论

Single frame IR point target detection based on a Gaussian mixture model classification

Single frame IR point target detection based on a Gaussian m...

引用

Conference on Electro-Optical and infrared Systems - technology and Applications IX

作者： Genin, Laure Champagnat, Frederic Le Besnerais, Guy Astrium Satellites F-31402 Toulouse 4 France Onera French Aerosp Lab F-91761 Palaiseau France

ISBN: (纸本)9780819492821

This paper deals with point target detection in non-stationary background such as cloud scenes in aerial or satellite imaging. We propose a new method to estimate second order background statistics within a spatial detection method by Matched Filter (MF). Our approach consists in classifying the pixels of the image by gathering the pixels of similar covariance matrices and in estimating one covariance matrix for each class. We use a classification Expectation-Maximization (CEM) algorithm based on a zero mean Gaussian mixture model. A key issue is the robustness of the classification with regard to target presence. This problem is efficiently tackled in a very simple manner. The resulting Gaussian Mixture Matched Filter (GMMF) has the advantage to adapt itself to second order non-stationary backgrounds and requires only the tuning of the window size used to build the observation vector associated with each pixel. Efficiency of the proposed GMMF approach is demonstrated on a large variety of cloudy sky backgrounds.

关键词： Point target detection Gaussian Mixture Model Image Segmentation Matched Filter

来源：评论

学校读者我要写书评

暂无评论

ASSK-Net: Automatic Spatial Selection Kernel Network for Faster Oriented Object detection

引用

JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING 2025年 1-14页

作者： Hu, Yong Jing, Zhengbiao Su, Yun Zhang, Fang Jing, Donglin Chengdu Vocat & Tech Coll Ind Sch Informat Engn Chengdu Peoples R China Chengdu Vocat & Tech Coll Ind Sch Intelligent Mfg & Automot Chengdu Peoples R China Shanghai Aerosp Control Technol Inst Shanghai 201109 Peoples R China China Aerosp Sci & Technol Corp Res & Dev Ctr Infrared Detect Technol Shanghai 201109 Peoples R China

The improvement in existing remote sensing detectors often relies on complex structures and deeper convolutional layers, leading to a significant increase in computational complexity. While previous works have designed various novel lightweight convolutions to improve target feature representation, these structures often overlook the unique prior knowledge of remote sensing scenes when applied to aerial detection tasks, resulting in decreased detection performance. Specifically, this prior knowledge includes: (1) Accurate detection of aerial objects often requires extensive contextual information. (2) The range of contextual information needed for different categories varies greatly. To address this, our paper fully considers this prior knowledge and proposes the Adaptive Spatial Selection Kernel Network (ASSK-Net). We first use large kernel convolution decomposition operations to decouple a series of convolutions with smaller sizes and rapidly expanding dilation rates, constructing diverse receptive fields with different spatial coverage ranges while significantly reducing computation. Based on this, a spatial selection mechanism is used to effectively weight feature maps with different levels of information richness, enhancing the feature differences between targets and backgrounds. Finally, we design an adaptive class equilibrium loss function, increasing the loss weight with rare categories and other easily confused categories with similar classification scores, thus improving the discriminative capability for rare categories. Comprehensive experiments on datasets (such as DOTA, UCAS-AOD, and HRSC2016) indicate that our ASSK-Net achieves optimal performance, effectively balancing computational complexity and detection accuracy.

关键词： Lightweight network Oriented object detection Convolution decomposition Sample balance

来源：评论

学校读者我要写书评

暂无评论

Real-time multi-sensor data fusion for target detection, classification, tracking, counting, and range estimates

Real-time multi-sensor data fusion for target detection, cla...

引用

Conference on detection and Remediation Technologies for Mines and Minelike targets IX

作者： Tsui, EK Thomas, R U.S. Army Tank-Automotive and Armaments Command/Armament Research Development and Engineering Ctr. (United States) McQ Associates Inc. (United States)

ISBN: (纸本)0819453382

As part of the Commanding General of Army Material Command's Research, Development & Engineering Command (RDECOM), the U.S. Army Research Development and Engineering Center (ARDEC), Picatinny funded a joint development effort with McQ Associates, Inc. to develop an Advanced Minefield Sensor (AMS) as a technology evaluation prototype for the Anti-Personnel Landmine Alternatives (APLA) Track III program. This effort laid the fundamental groundwork of smart sensors for detection and classification of targets, identification of combatant or noncombatant, target location and tracking at and between sensors, fusion of information across targets and sensors, and automatic situation awareness to the 1(st) responder. The efforts have culminated in developing a performance oriented architecture meeting the requirements of size, weight, and power (SWAP). The integrated digital signal processor (DSP) paradigm is capable of computing signals from sensor modalities to extract needed information within either a 360degrees or fixed field of view with acceptable false alarm rate. This paper discusses the challenges in the developments of such a sensor, focusing on achieving reasonable operating ranges, achieving low power, small size and low cost, and applications for extensions of this technology.

关键词： Sensors Cameras target detection Imaging systems infrared cameras Image processing infrared imaging Image compression Digital signal processing Image resolution

来源：评论

学校读者我要写书评

暂无评论

infrared aircraft few-shot classification method based on cross-correlation network

引用

红外与毫米波学报 2025年第1期44卷 103-111页

作者： HUANG Zhen ZHANG Yong GONG Jin-Fu Key Laboratory of Infrared System Detection and Imaging Technology Chinese Academy of SciencesShanghai 200083China University of Chinese Academy of Sciences Beijing 100049China Shanghai Institute of Technical Physics Chinese Academy of SciencesShanghai 200083China

In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is *** method combines two core modules:a simple parameter-free self-attention and *** analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot *** proposed cross-correlation network integrates these two modules and is trained in an end-to-end *** simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between *** with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target *** results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.

关键词： infrared imaging aircraft classification few-shot learning parameter-free attention cross attention

来源：评论

学校读者我要写书评

暂无评论

detection and classification of target formations in infrared image sequences

Detection and classification of target formations in infrare...

引用

Imaging infrared: Scene Simulation, Modeling, and Real Image Tracking

作者： Bronskill, John F. Hepburn, John S.A. Au, Wing K. Advanced Technology Cent Canada

This paper describes a knowledge-based approach to the detection and classification of ground-based military target formations in infrared (IR) image sequences at long range from an airborne platform. The motivation for this approach is that at long range military vehicle targets in IR imagery typically consists of only a few pixels, have low contrast and exist in a high clutter environment making reliable detection, classification or identification of individual targets extremely difficult. Thus, the system detailed here detects targets based on their membership in a military target formation or convoy, relying on the structure or spatial organization of the formation and not individual target signatures. The system consists of two major components;Point target detection and Tracking (PTD);and Knowledge-Based Constraint Hierarchical target Formation detection and classification (TFD). The first component detects and tracks both stationary and moving point targets which are passed on as candidates for clustering into target formations by a rule-based matching process in the second component.

关键词： infrared Imaging

来源：评论

学校读者我要写书评

暂无评论

Multisensor information fusion for target detection and classification

Multisensor information fusion for target detection and clas...

引用

Sensor Fusion 1988

作者： Roggemann, Michael C. Mills, James P. Rogers, Steven K. Kabrisky, Matthew Air Force Institute of Technology Departments of Engineering Physics and Electrical Engineering Wright-Patterson AFBOH45433 United States

Merging information available from multisensor views of a scene is a useful approach to target detection and classification. Development of multisensor information fusion techniques using a data base of real imagery from an absolute range laser radar and a corresponding forward looking infrared (FLIR) sensor is underway. Our conceptual approach to multisensor target detection and classification uses sensor-dependent segmentation and feature extraction. Information is fused first at the detection level and then within the classifier. We hypothesize that an approach to information fusion based on the mathematical theory of evidence (i.e., evidential reasoning) is a useful method for multisensor object classification. In this paper we summarize an approach to a multisensor object classification system, discuss results of multisensor segmentation algorithm, and present an evidential reasoning-based approach to a multisensor classifier. © 1988 Proceedings of SPIE - The International Society for Optical Engineering. All rights reserved.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Radar Based target detection and classification

Radar Based Target Detection and Classification

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Santhanamari, G. Muni Jyothi Prakash, S. Dharshini, B. Kousalya, S. Akash, R. PSG Institute of Technology and Applied Research Department of ECE Coimbatore India Associate Engineer Qualcomm India Pvt. Ltd Bengaluru India System Engineer Societe Generale Global Solution Centre Bengaluru India

ISBN: (纸本)9798350335835

In recent years, RADARs have begun to replace more sensors like cameras, ultrasonic devices, and infrared sensors used in common places in everyday life. As integrated circuit technology has advanced, the environmental robustness of radar technology has enabled small, inexpensive, short-range radars operating at frequencies ranging from a few GHz to hundreds of GHz (millimeter waves). As a result, RADAR has become a popular choice for many new applications, including patient monitoring, adaptive control of self-driving cars and drones, structure monitoring, airport security, and gesture recognition. Another recent area of interest is RADAR-based wildlife anti-poaching activities. The model's performance is assessed using the spectrogram obtained from a radar signature database of moving targets in a typical setting. The goal of this work is to discriminate between moving human and animal targets based on variation in range of red cells in the spectrogram. Observed results indicate that the model's classification accuracy depends on the length of continuous on target observation. The radar-based target detection and classification system used for border security measures and wildlife anti-poaching operations for animals like rhinos or elephants are both potential activities. © 2023 IEEE.

关键词： Animals

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：