检索结果-内蒙古大学图书馆

11th ACM Multimedia Systems Online Conference (MMSys)

作者： Schindler, Alexander Lindley, Andrew Jalali, Anahid Boyer, Martin Gordea, Sergiu King, Ross Austrian Inst Technol Ctr Digital Safety & Secur Vienna Austria

ISBN: (纸本)9781450368452

The forensic investigation of a terrorist attack poses a significant challenge to the investigative authorities, as often several thousand hours of video footage must be viewed. Large scale Video Analytic Platforms (VAP) assist law enforcement agencies (LEA) in identifying suspects and securing evidence. Current platforms focus primarily on the integration of different computer vision methods and thus are restricted to a single modality. We present a video analytic platform that integrates visual and audio analytic modules and fuses information from surveillance cameras and video uploads from eyewitnesses. Videos are analyzed according their acoustic and visual content. Specifically, Audio Event detection is applied to index the content according to attack-specific acoustic concepts. Audio similarity search is utilized to identify similar video sequences recorded from different perspectives. visual object detection and tracking are used to index the content according to relevant concepts. Innovative user-interface concepts are introduced to harness the full potential of the heterogeneous results of the analytical modules, allowing investigators to more quickly follow-up on leads and eyewitness reports.

关键词： Audio Event detection Audio Similarity visual object detection Large Scale Computing Multi-Modal Systems

来源：评论

学校读者我要写书评

暂无评论

Integrated Artificial Intelligence for Making Digital Human II 24

Integrated Artificial Intelligence for Making Digital Human ...

引用

16th International Conference on Machine Learning and Computing (ICMLC)

作者： Yoshiyuki, Usami Moro, Shota Kanagawa Univ Dept Appl Phys Kanagawa Ku Yokohama Kanagawa Japan Kanagawa Univ Coordinated Engn Program Kanagawa Ku Yokohama Kanagawa Japan

ISBN: (纸本)9798400709234

This paper presents the second report on making an integrated AI. Regarding visual processing, YOLOv8 and image2-text are employed to recognize surrounding visional scenes, which output meaningful text to the AI's text processing unit. In text processing, our previous work employed a question-answering system for questions from humans to the AI. However, in this study we use GPT2 for the convesation between humans and AI. This is because GPT2 has been found to be an excellent natural language processor that can provide appropriate responses to human questions and casual conversations. AI's response is shown in the form of a 3D avatar animation by using the MakeItTalk routine. In this work we devised a system in which AI can autonomously learn by itself when it does not respond to humans. Namely, about eight news items are obtained from web news. From there, AI generates sentences using GPT2. The repeating process of text generation is accomplished by cutting out several leading words from sentences. As a result, AI's attention theme is changing to a different topic. In addition, the AI creates a picture of the content by text2image routine. It makes AI's association in a form that is easy to understand for humans. In this work, the system accomplishes fine-tuning so that these associations could be stored in the AI circuits as distributed weights. In such a way, we have created an integrated system of AI, that behaves like a human being. As described in the text, we may say that our system is superior to human beings in two points. The first is computation speed. We recognize that the association process of AI is far faster than that of humans. The second point is that AI avatars created using diffusion model may be more attractive than real humans. Of course, the present system has problems that need to be improved. However, we can surely say that those problems will be solved with the current technology. In creating an integrated AI, this study shows that it is po

关键词： image2text text generation question and answering visual object recognition visual object detection

来源：评论

学校读者我要写书评

暂无评论

Optimized Custom Dataset for Efficient detection of Underwater Trash 24th

Optimized Custom Dataset for Efficient Detection of Underwat...

引用

24th Annual Conference on Towards Autonomous Robotic Systems (TAROS)

作者： Walia, Jaskaran Singh Seemakurthy, Karthik Vellore Inst Technol Chennai India Univ Lincoln Lincoln England

ISBN: (纸本)9783031433597;9783031433603

Accurately quantifying and removing submerged underwater waste plays a crucial role in safeguarding marine life and preserving the environment. While detecting floating and surface debris is relatively straightforward, quantifying submerged waste presents significant challenges due to factors like light refraction, absorption, suspended particles, and color distortion. This paper addresses these challenges by proposing the development of a custom dataset and an efficient detection approach for submerged marine debris. The dataset encompasses diverse underwater environments and incorporates annotations for precise labeling of debris instances. Ultimately, the primary objective of this custom dataset is to enhance the diversity of litter instances and improve their detection accuracy in deep submerged environments by leveraging state-of-the-art deep learning architectures. The source code to replicate the results in this paper can be found at GitHub.

关键词： Deep Learning Computer Vision visual object detection Artificial Intelligence Robotics Marine Debris Trash detection Dataset Generation Data Pre-processing

来源：评论

学校读者我要写书评

暂无评论

Exploring Residual and Spatial Consistency for object detection

Exploring Residual and Spatial Consistency for Object Detect...

引用

9th International Conference on Computer Vision Theory and Applications (VISAPP)

作者： Wang, Hao Zhang, Ya Xu, Zhe Shanghai Jiao Tong Univ Inst Image Commun & Informat Proc Shanghai Peoples R China

ISBN: (纸本)9789897581335

Local image features show a high degree of repeatability, while their local appearance usually does not bring enough discriminative pattern to obtain a reliable matching. In this paper, we present a new object matching algorithm based on a novel robust estimation of residual consensus and flexible spatial consistency filter. We evaluate the similarity between different homography model via two-parameter integrated Weibull distribution and inlier probabilities estimates, which can select uncontaminated model to help eliminating outliers. Spatial consistency test was encoded by the geometric relationships of domain knowledge in two directions, which is invariant to scale, rotation, and translation especially robust to the flipped image. Experiment results on nature images with clutter background demonstrate our method effectiveness and robustness.

关键词： visual object detection Wide Baseline Matching Local Image Feature Spatial Consistency

来源：评论

学校读者我要写书评

暂无评论

Edge-based Realtime Image object detection for UAV Missions 30

Edge-based Realtime Image Object Detection for UAV Missions

引用

30th Wireless and Optical Communications Conference (WOCC)

作者： Wu, Meng-Shou Li, Chi-Yu Natl Yang Ming Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan

ISBN: (纸本)9781665427722

Unmanned Aerial Vehicle (UAV) has limited computing power, but requires high accuracy and low latency in the visual object detection for critical UAV missions, such as infrastructure inspection. It may need highly complex machine learning algorithms with the demand of extensive computing power. With the rising edge computing technology, the heavily-loaded object detection tasks can be offloaded to edge computing systems. To enable such edge-based object detection with low overhead, we discover that it is critical to minimize the response time of the detection while maximizing the frequency of detected image frames. In this paper, we identify three key research challenges, conduct an experimental case study to show that current edge-based naive solutions cannot achieve the above goal, and finally point out major ideas for potential solutions.

关键词： UAV edge computing visual object detection

来源：评论

学校读者我要写书评

暂无评论

Vehicle detection framework for challenging lighting driving environment based on feature fusion method using adaptive neuro-fuzzy inference system

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2018年第2期15卷

作者： Pae, Dong Sung Choi, In Hwan Kang, Tae Koo Lim, Myo Taeg Korea Univ Sch Elect Engn Seoul South Korea Sangmyung Univ Dept Human Intelligence & Robot Engn Cheonan South Korea

This article proposes a new preceding vehicle detection framework for challenging lighting environments using a novel feature fusion technique based on an adaptive neuro-fuzzy inference system. A combination of two feature descriptors, the histogram of oriented gradients and local binary patterns, is adopted to improve the vehicle detection accuracy of the proposed framework, and the performance of the combination in image transformations is evaluated. Furthermore, we tested the detection performance of the proposed framework in three challenging driving conditions and filmed the test image sequences for each categorized environment of the experiments. The experimental results demonstrate that the proposed framework outperforms the conventional framework under specific driving environments with harsh lighting conditions.

关键词： visual object detection vehicle detection binary descriptor feature fusion adaptive neuro-fuzzy inference system

来源：评论

学校读者我要写书评

暂无评论

visual-Context Boosting for Eye detection

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 2010年第6期40卷 1460-1467页

作者： Song, Mingli Tao, Dacheng Sun, Zhuo Li, Xuelong Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Zhejiang Peoples R China Nanyang Technol Univ Sch Comp Engn Singapore 639798 Singapore Microsoft China R&D Grp Beijing 100083 Peoples R China Chinese Acad Sci State Key Lab Transient Opt & Photon Xian Inst Opt & Precis Mech Xian 710119 Peoples R China

Eye detection plays an important role in many practical applications. This paper presents a novel two-step scheme for eye detection. The first step models an eye by a newly defined visual-context pattern (VCP), and the second step applies semisupervised boosting for precise detection. VCP describes both the space and appearance relations between an eye region (region of eye) and a reference region (region of reference). The context feature of a VCP is extracted by using the integral image. Aiming to reduce the human labeling efforts, we apply semisupervised boosting, which integrates the context feature and the Haar-like features for precise eye detection. Experimental results on several standard face data sets demonstrate that the proposed approach is effective, robust, and efficient. We finally show that this approach is ready for practical applications.

关键词： Eye detection region of reference (ROR) visual object detection

来源：评论

学校读者我要写书评

暂无评论

Towards the Accurate Automatic detection of Mesoscale Convective Systems in Remote Sensing Data: From Data Mining to Deep Learning Models and Their Applications

引用

REMOTE SENSING 2023年第14期15卷 3493-3493页

作者： Krinitskiy, Mikhail Sprygin, Alexander Elizarov, Svyatoslav Narizhnaya, Alexandra Shikhov, Andrei Chernokulsky, Alexander Russian Acad Sci Shirshov Inst Oceanol Moscow 117997 Russia Moscow Inst Phys & Technol 9 Inst Skiy Per Dolgoprudnyi 141701 Russia Moscow Ctr Fundamental & Appl Math Leninskie Gory 1 Moscow 119991 Russia Russian Acad Sci AM Obukhov Inst Atmospher Phys Moscow 119017 Russia Sci & Prod Assoc Typhoon Obninsk 249038 Russia Perm State Univ Fac Geog Perm 614068 Russia Russian Acad Sci Inst Geog Moscow 119017 Russia

Mesoscale convective systems (MCSs) and associated hazardous meteorological phenomena cause considerable economic damage and even loss of lives in the mid-latitudes. The mechanisms behind the formation and intensification of MCSs are still not well understood due to limited observational data and inaccurate climate models. Improving the prediction and understanding of MCSs is a high-priority area in hydrometeorology. One may study MCSs either employing high-resolution atmospheric modeling or through the analysis of remote sensing images which are known to reflect some of the characteristics of MCSs, including high temperature gradients of cloud-top, specific spatial shapes of temperature patterns, etc. However, research on MCSs using remote sensing data is limited by inadequate (in size) databases of satellite-identified MCSs and poorly equipped automated tools for MCS identification and tracking. In this study, we present (a) the GeoAnnotateAssisted tool for fast and convenient visual identification of MCSs in satellite imagery, which is capable of providing AI-generated suggestions of MCS labels;(b) the Dataset of Mesoscale Convective Systems over the European Territory of Russia (DaMesCoS-ETR), which we created using this tool, and (c) the Deep Convolutional Neural Network for the Identification of Mesoscale Convective Systems (MesCoSNet), constructed following the RetinaNet architecture, which is capable of identifying MCSs in Meteosat MSG/SEVIRI data. We demonstrate that our neural network, optimized in terms of its hyperparameters, provides high MCS identification quality (mAP=0.75, true positive rate TPR=0.61) and a well-specified detection uncertainty (false alarm ratio FAR=0.36). Additionally, we demonstrate potential applications of the GeoAnnotateAssisted labelling tool, the DaMesCoS-ETR dataset, and the MesCoSNet neural network in addressing MCS research challenges. Specifically, we present the climatology of axisymmetric MCSs over the European territory

关键词： mesoscale convective systems visual object detection geospatial labeling Meteosat SEVIRI client-server application convolutional neural networks deep learning machine learning RetinaNet

来源：评论

学校读者我要写书评

暂无评论

Single-trial extraction of event-related potentials (ERPs) and classification of visual stimuli by ensemble use of discrete wavelet transform with Huffman coding and machine learning techniques

引用

JOURNAL OF NEUROENGINEERING AND REHABILITATION 2023年第1期20卷 70-70页

作者： Amin, Hafeez Ullah Ullah, Rafi Reza, Mohammed Faruque Malik, Aamir Saeed Univ Nottingham Sch Comp Sci Fac Sci & Engn Jalan Broga Semenyih 43500 Malaysia Univ Teknol PETRONAS Dept Comp & Informat Sci Seri Iskandar 32610 Perak Malaysia Hosp Univ Sains Malaysia Sch Med Sci Dept Neurosci Kota Baharu 16150 Kelantan Malaysia Brno Univ Technol Fac Informat Technol Brno Czech Republic

Background Presentation of visual stimuli can induce changes in EEG signals that are typically detectable by averaging together data from multiple trials for individual participant analysis as well as for groups or conditions analysis of multiple participants. This study proposes a new method based on the discrete wavelet transform with Huffman coding and machine learning for single-trial analysis of evenal (ERPs) and classification of different visual events in the visual object detection task. Methods EEG single trials are decomposed with discrete wavelet transform (DWT) up to the 4th level of decomposition using a biorthogonal B-spline wavelet. The coefficients of DWT in each trial are thresholded to discard sparse wavelet coefficients, while the quality of the signal is well maintained. The remaining optimum coefficients in each trial are encoded into bitstreams using Huffman coding, and the codewords are represented as a feature of the ERP signal. The performance of this method is tested with real visual ERPs of sixty-eight subjects. Results The proposed method significantly discards the spontaneous EEG activity, extracts the single-trial visual ERPs, represents the ERP waveform into a compact bitstream as a feature, and achieves promising results in classifying the visual objects with classification performance metrics: accuracies 93.60 +/- 6.5, sensitivities 93.55 +/- 4.5, specificities 94.85 +/- 4.2, precisions 92.50 +/- 5.5, and area under the curve (AUC) 0.93 +/- 0.3 using SVM and k-NN machine learning classifiers. Conclusion The proposed method suggests that the joint use of discrete wavelet transform (DWT) with Huffman coding has the potential to efficiently extract ERPs from background EEG for studying evoked responses in singletrial ERPs and classifying visual stimuli. The proposed approach has O(N) time complexity and could be implemented in real-time systems, such as the brain-computer interface (BCI), where fast detection of mental events is desired

关键词： Single trials analysis (ERPs) visual object detection Discrete wavelet transform Huffman coding Machine learning classifiers

来源：评论

学校读者我要写书评

暂无评论

"Seeing" electroencephalogram through the skull: imaging prefrontal cortex with fast optical signal

引用

JOURNAL OF BIOMEDICAL OPTICS 2010年第6期15卷 061702-061702页

作者： Medvedev, Andrei V. Kainerstorfer, Jana M. Borisov, Sergey V. Gandjbakhche, Amir H. VanMeter, John GUMC CFMI Washington DC 20057 USA Univ Vienna Dept Phys Vienna Austria Eunice Kennedy Shriver Natl Inst Child Hlth & Hum NIH Sect Analyt & Funct Biophoton Program Pediat Imaging & Tissue Sci Bethesda MD 20892 USA

Near-infrared spectroscopy is a novel imaging technique potentially sensitive to both brain hemodynamics (slow signal) and neuronal activity (fast optical signal, FOS). The big challenge of measuring FOS noninvasively lies in the presumably low signal-to-noise ratio. Thus, detectability of the FOS has been controversially discussed. We present reliable detection of FOS from 11 individuals concurrently with electroencephalogram (EEG) during a Go-NoGo task. Probes were placed bilaterally over prefrontal cortex. Independent component analysis (ICA) was used for artifact removal. Correlation coefficient in the best correlated FOS EEG ICA pairs was highly significant (p < 10(-8)), and event-related optical signal (EROS) was found in all subjects. Several EROS components were similar to the event-related potential (ERP) components. The most robust "optical N200" at t = 225 ms coincided with the N200 ERP;both signals showed significant difference between targets and nontargets, and their timing correlated with subject's reaction time. Correlation between FOS and EEG even in single trials provides further evidence that at least some FOS components "reflect" electrical brain processes directly. The data provide evidence for the early involvement of prefrontal cortex in rapid object recognition. EROS is highly localized and can provide cost-effective imaging tools for cortical mapping of cognitive processes. (C) 2010 Society of Photo-Optical Instrumentation Engineers, [DO: 10.1117/1.3505007]

关键词： near-infrared spectroscopy fast optical signal event-related signal electroencephalogram independent component anaysis visual object detection

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：