检索结果-南通市图书馆

object detection based on combination of local and spatial information

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2011年第4期22卷 715-720页

作者： Qinkun Xiao Nan Zhang Fei Li Yue Gao School of Electronics and Information Engineering Xi'an Technological University Xi'an 710032 E R. China Fujitsu Research & Development Center Co. LTD. Beijing 100025 E R. China Department of Automation Tsinghua University Beijing 100084 P. R. China

A method of object detection based on combination of local and spatial information is proposed. Firstly, the categorygiven representative images are chosen through clustering to be templates, and the local and spatial information of template are ex- tracted and generalized as the template feature. At the same time, the codebook dictionary of local contour is also built up. Secondly, based on the codebook dictionary, sliding-window mechanism and the vote algorithm are used to select initial candidate object win- dows. Lastly, the final object windows are got from initial candidate windows based on local and spatial structure feature matching. Experimental results demonstrate that the proposed approach is able to consistently identify and accurately detect the objects with better performance than the existing methods.

关键词： object detection codebook dictionary spatial matching local contour matching.

object detection and Tracking Method of AUV Based on Acoustic Vision

在线全文

学校读者我要写书评

暂无评论

China Ocean Engineering 2012年第4期26卷 623-636页

作者：张铁栋万磊曾文静徐玉如 National Key Laboratory of Science and Technology on Autonomous Underwater Vehicle Harbin Engineering University

This paper describes a new framework for object detection and tracking of AUV including underwater acoustic data interpolation, underwater acoustic images segmentation and underwater objects tracking. This framework is applied to the design of vision-based method for AUV based on the forward looking sonar sensor. First, the real-time data flow （underwater acoustic images） is pre-processed to form the whole underwater acoustic image, and the relevant position information of objects is extracted and determined. An improved method of double threshold segmentation is proposed to resolve the problem that the threshold cannot be adjusted adaptively in the traditional method. Second, a representation of region information is created in light of the Gaussian particle filter. The weighted integration strategy combining the area and invariant moment is proposed to perfect the weight of particles and to enhance the tracking robustness. Results obtained on the real acoustic vision platform of AUV during sea trials are displayed and discussed. They show that the proposed method can detect and track the moving objects underwater online, and it is effective and robust.

关键词： AUV acoustic image object detection Gaussian particle filter object tracking

object detection in Remote Sensing Images Using Picture Fuzzy Clustering and MapReduce

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第12期43卷 1241-1253页

作者： Tran Manh Tuan Tran Thi Ngan Nguyen Tu Trung Faculty of Computer Science and Engineering Thuyloi University175 Tay SonDong DaHanoi010000Vietnam

In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_*** formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.

关键词： Remote sensing images picture fuzzy clustering image segmentation object detection MapReduce

Variational Bayesian Inference for Finite Inverted Dirichlet Mixture Model and Its Application to object detection

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2018年第3期27卷 603-610页

作者： LAI Yuping PING Yuan HE Wenda WANG Baocheng WANG Jingzhong ZHANG Xiufeng Department of Information Security North China University of Technology School of Information Engineering Xuchang University National Research Center for Rehabilitation Technical Aids

As a variant of Finite mixture model(FMM), finite Inverted Dirichlet mixture model(IDMM)can not avoid the conventional challenges, such as how to select the appropriate number of mixture components based on the observed data. Towards easing these issues,we propose a variational inference framework for learning IDMM which has been proved to be an efficient tool for modeling vectors with positive elements. Compared with the conventional Expectation maximization(EM) algorithm commonly used for learning FMM, the proposed approach prevents over-fitting well. Furthermore, it is able to do automatic determination of the number of mixture components and parameters estimation, *** results on both synthetic and real data of object detection confirm significant improvements on flexibility and efficiency being achieved.

关键词： Bayesian estimation Mixture models Inverted Dirichlet distribution Variational inference object detection

Vision-based aerial image mosaicking algorithm with object detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2022年第2期33卷 259-268页

作者： HAN Jun LI Weixing FENG Kai PAN Feng School of Automation Beijing Institute of TechnologyBeijing 100081China

Aerial image sequence mosaicking is one of the chal-lenging research fields in computer *** obtain large-scale orthophoto maps with object detection information,we propose a vision-based image mosaicking algorithm without any extra location *** to object detection results,we define a complexity factor to describe the importance of each input ima-ge and dynamically optimize the feature extraction *** feature points extraction and matching processes are mainly guided by the speeded-up robust features(SURF)and the grid motion statistic(GMS)algorithm respectively.A robust refer-ence frame selection method is proposed to eliminate the trans-formation distortion by searching for the center area based on ***,the sparse Levenberg-Marquardt(LM)al-gorithm and the heavy occluded frames removal method are ap-plied to reduce accumulated errors and further improve the mo-saicking *** proposed algorithm is performed by using multithreading and graphics processing unit(GPU)accel-eration on several aerial image *** experiment results demonstrate that our algorithm outperforms most of the existing aerial image mosaicking methods in visual quality while guaranteeing a high calculation speed.

关键词： image mosaicking object detection grid motion statistic(GMS) mapping

Lightweight object detection Networks for UAV Aerial Images Based on YOLO

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第4期33卷 997-1009页

作者： Yanshan LI Jiarong WANG Kunhua ZHANG Jiawei YI Miaomiao WEI Lirong ZHENG Weixin XIE ATR National Key Laboratory of Defense Technology Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

Existing high-precision object detection algorithms for UAV(unmanned aerial vehicle) aerial images often have a large number of parameters and heavy weight, which makes it difficult to be applied to mobile *** propose three YOLO-based lightweight object detection networks for UAVs, named YOLO-L, YOLO-S, and YOLO-M, respectively. In YOLO-L, we adopt a deconvolution approach to explore suitable upsampling rules during training to improve the detection accuracy. The convolution-batch normalization-Si LU activation function(CBS)structure is replaced with Ghost CBS to reduce the number of parameters and weight, meanwhile Maxpool maximum pooling operation is proposed to replace the CBS structure to avoid generating parameters and weight. YOLO-S greatly reduces the weight of the network by directly introducing CSPGhost Neck residual structures, so that the parameters and weight are respectively decreased by about 15% at the expense of 2.4% mAP. And YOLO-M adopts the CSPGhost Neck residual structure and deconvolution to reduce parameters by 5.6% and weight by 5.7%, while m AP only by 1.8%. The results show that the three lightweight detection networks proposed in this paper have good performance in UAV aerial image object detection task.

关键词： Training YOLO Deconvolution Accuracy object detection Autonomous aerial vehicles Feature extraction

Few-shot object detection based on positive-sample improvement

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2023年第10期28卷 74-86页

作者： Yan Ouyang Xin-qing Wang Rui-zhe Hu Hong-hui Xu Department of Mechanical Engineering College of Field EngineeringArmy Engineering University of PLANanjing210007China

Traditional object detectors based on deep learning rely on plenty of labeled samples,which are expensive to ***-shot object detection(FSOD)attempts to solve this problem,learning detection objects from a few labeled samples,but the performance is often unsatisfactory due to the scarcity of *** believe that the main reasons that restrict the performance of few-shot detectors are:(1)the positive samples is scarce,and(2)the quality of positive samples is ***,we put forward a novel few-shot object detector based on YOLOv4,starting from both improving the quantity and quality of positive ***,we design a hybrid multivariate positive sample augmentation(HMPSA)module to amplify the quantity of positive samples and increase positive sample diversity while suppressing negative ***,we design a selective non-local fusion attention(SNFA)module to help the detector better learn the target features and improve the feature quality of positive ***,we optimize the loss function to make it more suitable for the task of *** results on PASCAL VOC and MS COCO demonstrate that our designed few-shot object detector has competitive performance with other state-of-the-art detectors.

关键词： Few-shot learning object detection Sample augmentation Attention mechanism

Hierarchical-Based object detection with Improved Locality Sparse Coding

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第2期25卷 290-295页

作者： ZHU Suguo DU Junping REN Nan LIANG Meiyu Beijing Key Laboratory of Intelligent Telecommunication software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications

This paper proposes to extend the hierarchical method to be adapted to sequential frames, aiming at detecting the moving object in dynamic scenes. A novel two-layer model is proposed, in which dictionaries are learned through three different stages and the locality constrained sparse representation is improved. This leads more significant improvement for performance of both static image classification and moving object detection. The experimental results demonstrate that the proposed algorithm is efficient and robust compared with the state-of-the-art classification methods, and also able to detect moving object in the sequential frames accurately.

关键词： Hierarchical detection Sparse coding Classification object detection

EFECL:Feature encoding enhancement with contrastive learning for indoor 3D object detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 875-892页

作者： Yao Duan Renjiao Yi Yuanming Gao Kai Xu Chenyang Zhu School of Computing National University of Defense TechnologyChangsha 410000China

Good proposal initials are critical for 3D object detection ***,due to the significant geometry variation of indoor scenes,incomplete and noisy proposals are inevitable in most *** feature information among these“bad”proposals may mislead the *** learning provides a feasible way for representing proposals,which can align complete and incomplete/noisy proposals in feature *** aligned feature space can help us build robust 3D representation even if bad proposals are ***,we devise a new contrast learning framework for indoor 3D object detection,called EFECL,that learns robust 3D representations by contrastive learning of proposals on two different ***,we optimize both instance-level and category-level contrasts to align features by capturing instance-specific characteristics and semantic-aware common ***,we propose an enhanced feature aggregation module to extract more general and informative features for contrastive *** on ScanNet V2 and SUN RGB-D benchmarks demonstrate the generalizability and effectiveness of our method,and our method can achieve 12.3%and 7.3%improvements on both datasets over the benchmark *** code and models are publicly available at https://***/YaraDuan/EFECL.

关键词： indoor scene object detection contrastive learning feature enhancement