检索结果-内蒙古大学图书馆

Robust long-term correlation tracking using convolutional features and detection proposals

NEUROCOMPUTING 2018年 317卷 137-148页

作者： Lin, Bin Li, Ying Xue, Xizhe Chan, Jonathan Cheung-Wai Northwestern Polytech Univ Sch Comp Sci Xian 710072 Shaanxi Peoples R China Vrije Univ Brussel Dept Elect & Informat B-1050 Brussels Belgium

Correlation filter based trackers have achieved appealing performance and high efficiency in recent years. However, for long-term tracking where target objects undergo dramatic appearance variation due to heavy occlusion or out-of-view, conventional correlation filter based tracking algorithms would be distracted by irrelevant objects. Once the trained tracker loses its way, it is impossible to recover the information for the following frames as the model has drifted. In this paper, we decompose the long-term tracking task into tracking and detection. Tracker learns separate correlation filters for explicit translation and scale estimation. Specifically, in order to improve tracking accuracy, the convolutional features for translation filter are extracted, and the scale filter is learned using the target appearance sampled at different scales. Detector trains an online long-term filter and applies it to the entire frame to generate detection proposals. By exploiting these detection proposals, it helps the tracker to recover from problems such as temporary or persistent occlusions. In this way, the proposed approach could handle the model drifting problem effectively for long-term tracking with more accurate estimation of object scale and location. Extensive experimental results on large-scale benchmark sequences have shown the robustness of the proposed method. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Long-term tracking Correlation filter Convolutional features detection proposals

来源：评论

学校读者我要写书评

暂无评论

What Makes for Effective detection proposals?

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2016年第4期38卷 814-830页

作者： Hosang, Jan Benenson, Rodrigo Dollar, Piotr Schiele, Bernt Max Planck Inst Informat D2 Saarbrucken Saarland Germany Facebook AI Res FAIR Menlo Pk CA USA

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.

关键词： Computer vision object detection detection proposals

来源：评论

学校读者我要写书评

暂无评论

Objectness Scoring and detection proposals in Forward-Looking Sonar Images with Convolutional Neural Networks 7th

Objectness Scoring and Detection Proposals in Forward-Lookin...

引用

7th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR)

作者： Valdenegro-Toro, Matias Heriot Watt Univ Sch Engn & Phys Sci Ocean Syst Lab Edinburgh EH14 4AS Midlothian Scotland

ISBN: (纸本)9783319461823;9783319461816

Forward-looking sonar can capture high resolution images of underwater scenes, but their interpretation is complex. Generic object detection in such images has not been solved, specially in cases of small and unknown objects. In comparison, detection proposal algorithms have produced top performing object detectors in real-world color images. In this work we develop a Convolutional Neural Network that can reliably score objectness of image windows in forward-looking sonar images and by thresholding objectness, we generate detection proposals. In our dataset of marine garbage objects, we obtain 94% recall, generating around 60 proposals per image. The biggest strength of our method is that it can generalize to previously unseen objects. We show this by detecting chain links, walls and a wrench without previous training in such objects. We strongly believe our method can be used for class-independent object detection, with many real-world applications such as chain following and mine detection.

关键词： Object detection detection proposals Sonar image processing Forward-looking sonar

来源：评论

学校读者我要写书评

暂无评论

A Pedestrian detection System Accelerated by Kernelized proposals

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2020年第3期21卷 1216-1228页

作者： Baek, Jeonghyun Hyun, Junhyuk Kim, Euntai Yonsei Univ Sch Elect & Elect Engn Seoul 120749 South Korea

When pedestrian detection (PD) is implemented on a central processing unit (CPU), performing real-time processing using a classical sliding window is difficult. Therefore, an efficient proposal generation method is required. A new generation method, named additive kernel binarized normed gradient (AKBING), is proposed herein, and this method is applied to the PD for real-time implementation on a CPU. The AKBING is based on an additive kernel support vector machine (AKSVM) and is implemented using the binarized normed gradient. The proposed PD can operate in real time because all AKSVM computations are approximated via simple atomic operations. In the suggested kernelized proposal method, the popular features and a classifier are combined, and the method is tested on a Caltech Pedestrian dataset and KITTI dataset. The experimental results show that the detection system with the proposed method improved the speed with minor degradation in detection accuracy.

关键词： proposals Feature extraction Support vector machines Microsoft Windows Real-time systems Additives Kernel Additive kernel binarized normed gradient Caltech Pedestrian dataset KITTI dataset detection proposals pedestrian detection LDCF

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Real-Time Correlation Tracking Framework for UAV Videos

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第4期52卷 2418-2429页

作者： Xue, Xizhe Li, Ying Yin, Xiaoyue Shang, Changjing Peng, Taoxin Shen, Qiang Northwestern Polytech Univ Sch Comp Sci & Engn Natl Engn Lab Integrated AeroSp Ground Ocean Big Shaanxi Prov Key Lab Speech & Image Informat Proc Xian 710072 Peoples R China Aberystwyth Univ Fac Business & Phys Sci Dept Comp Sci Aberystwyth SY23 3DB Dyfed Wales Edinburgh Napier Univ Sch Comp Edinburgh EH10 5DT Midlothian Scotland

Discriminative correlation filter (DCF) has contributed tremendously to address the problem of object tracking benefitting from its high computational efficiency. However, it has suffered from performance degradation in unmanned aerial vehicle (UAV) tracking. This article presents a novel semantic-aware real-time correlation tracking framework (SARCT) for UAV videos to enhance the performance of DCF trackers without incurring excessive computing cost. Specifically, SARCT first constructs an additional detection module to generate ROI proposals and to filter any response regarding the target irrelevant area. Then, a novel semantic segmentation module based on semantic template generation and semantic coefficient prediction is further introduced to capture semantic information, which can provide precise ROI mask, thereby effectively suppressing background interference in the ROI proposals. By sharing features and specific network layers for object detection and semantic segmentation, SARCT reduces parameter redundancy to attain sufficient speed for real-time applications. Systematic experiments are conducted on three typical aerial datasets in order to evaluate the performance of the proposed SARCT. The results demonstrate that SARCT is able to improve the accuracy of conventional DCF-based trackers significantly, outperforming state-of-the-art deep trackers.

关键词： Target tracking Semantics Videos Correlation Real-time systems proposals Unmanned aerial vehicles detection proposals discriminative correlation filter (DCF) semantic information unmanned aerial vehicle (UAV) tracking

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm for detection of Vacant Spaces in Delimited and Non-Delimited Parking Lots

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2020年第10期21卷 4052-4062页

作者： Varghese, Arun Sreelekha, G. Natl Inst Technol Calicut Kozhikode 673601 India Natl Inst Technol Calicut Dept Elect & Commun Engn Kozhikode 673601 India

Smart parking management systems that provide drivers with real-time information about availability and location of parking spaces are high among the wish list of urban dwellers. This paper proposes a machine learning approach for automatic detection of vacant lots in delimited parking spaces where the boundaries of the individual parking lots are predefined, which is then extended to a more general scenario of non-delimited parking spaces. A bag of features (bof) representation for the lots is used with a single svm classifier to discriminate between occupied and vacant lots. For non-delimited spaces, a customized background subtraction algorithm is used to generate proposal regions where vehicles can possibly be found, which are then verified using a bof plus svm approach. When tested on public datasets with images of real parking spaces, the proposed method shows robustness against large intra-class variabilities of vehicles and wide variations in vehicle pose and scale in each parking lot. Compared to state-of-the-art methods, the major advantages of the proposed approach are that it requires fewer images to train the classifier, accepts non-rectangular, variable sized images as input and can also be applied to non-delimited parking spaces, making it suitable for practical deployment.

关键词： Feature extraction Visualization Cameras Space vehicles Automobiles Histograms Vacant parking space detection bag of features image classification detection proposals background subtraction

来源：评论

学校读者我要写书评

暂无评论

CORRELATION FILTER TRACKING WITH ADAPTIVE PROPOSAL SELECTION FOR ACCURATE SCALE ESTIMATION

CORRELATION FILTER TRACKING WITH ADAPTIVE PROPOSAL SELECTION...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiong, Luo Liang, Yanjie Yan, Yan Wang, Hanzi Xiamen Univ Sch Informat Sci & Engn Fujian Key Lab Sensing & Comp Smart City Xiamen Fujian Peoples R China

ISBN: (纸本)9781538695524

Recently, some correlation filter based trackers with detection proposals have achieved state-of-the-art tracking results. However, a large number of redundant proposals given by the proposal generator may degrade the performance and speed of these trackers. In this paper, we propose an adaptive proposal selection algorithm which can generate a small number of high-quality proposals to handle the problem of scale variations for visual object tracking. Specifically, we firstly utilize the color histograms in the HSV color space to represent the instances (i.e., the initial target in the first frame and the predicted target in the previous frame) and proposals. Then, an adaptive strategy based on the color similarity is formulated to select high-quality proposals. We further integrate the proposed adaptive proposal selection algorithm with coarse-to-fine deep features to validate the generalization and efficiency of the proposed tracker. Experiments on two benchmark datasets demonstrate that the proposed algorithm performs favorably against several state-of-the-art trackers.

关键词： Visual Tracking Correlation Filters detection proposals Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Personness estimation for real-time human detection on mobile devices

引用

EXPERT SYSTEMS WITH APPLICATIONS 2017年 72卷 130-138页

作者： Kim, Kyuwon Oh, Changjae Sohn, Kwanghoon Yonsei Univ Sch Elect & Elect Engn Seoul 03722 South Korea Samsung Elect Mobile Div Suwon 16677 South Korea

One aim of detection proposal methods is to reduce the computational overhead of object detection. However, most of the existing methods have significant computational overhead for real-time detection on mobile devices. A fast and accurate proposal method of human detection called personness estimation is proposed, which facilitates real-time human detection on mobile devices and can be effectively integrated into part-based detection, achieving high detection performance at a low computational cost. Our work is based on two observations: (i) normed gradients, which are designed for generic object-ness estimation, effectively generate high-quality detection proposals for the person category;(ii) fusing the normed gradients with color attributes improves the performance of proposal generation for human detection. Thus, the candidate windows generated by the personness estimation will very likely contain human subjects. The human detection is then guided by the candidate windows, offering high detection performance even when the detection task terminates prior to completion. This interruptible detection scheme, called anytime detection, enables real-time human detection on mobile devices. Furthermore, we introduce a new evaluation methodology called time-recall curves to practically evaluate our approach. The applicability of our proposed method is demonstrated in extensive experiments on a publicly available dataset and a real mobile device, facilitating acquisition and enhancement of portrait photographs (e.g. selfie) on widespread mobile platforms. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Human detection detection proposals Normed gradients Color attributes Deformable part-based model

来源：评论

学校读者我要写书评

暂无评论

Improved Edge Boxes with Object Saliency and Location Awards

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2016年第2期E99D卷 488-495页

作者： Kuang, Peijiang Zhou, Zhiheng Wu, Dongcheng S China Univ Technol Elect Informat Engn Inst 381 Wushan Rd Guangzhou 510641 Guangdong Peoples R China Huiding Technol Co Ltd Shenzhen Peoples R China

Recently, object-proposal methods have attracted more and more attention of scholars and researchers for its utility in avoiding exhaustive sliding window search in an image. Object-proposal method is inspired by a concept that objects share a common feature. There exist many object-proposal methods which are either in segmentation fashion or engineering categories depending on low-level feature. Among those object-proposal methods, Edge Boxes, which is based on the number of contours that a bounding box wholly contains, has the state of art performance. Since Edge Boxes sometimes misses proposing some obvious objects in some images, we propose an appropriate version of it based on our two observations. We call the appropriate version as Improved Edge Boxes. The first of our observations is that objects have a property which can help us distinguish them from the background. It is called object saliency. An appropriate way we employ to calculate object saliency can help to retrieve some objects. The second of our observations is that objects 'prefer' to appear at the center part of images. For this reason, a bounding box that appears at the center part of the image is likely to contain an object. These two observations are going to help us retrieve more objects while promoting the recall performance. Finally, our results show that given just 5000 proposals we achieve over 89% object recall but 87% in Edge Boxes at the challenging overlap threshold of 0.7. Further, we compare our approach to some state-of-the-art approaches to show that our results are more accurate and faster than those approaches. In the end, some comparative pictures are shown to indicate intuitively that our approach can find more objects and more accurate objects than Edge Boxes.

关键词： detection proposals saliency object location Edge Boxes

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：