IET Comput. Vis.最新文献_第2页

TRC-YOLO: A real-time detection method for lightweight targets based on mobile devices TRC-YOLO:一种基于移动设备的轻型目标实时检测方法

IET Comput. Vis. Pub Date : 2021-10-09 DOI: 10.1049/cvi2.12072

Guanbo Wang, H. Ding, Zhijun Yang, Bo Li, Yihao Wang, Liyong Bao

引用次数: 19

BDC: Bounding-Box Deep Calibration for High Performance Face Detection BDC:高性能人脸检测的边界盒深度校准

IET Comput. Vis. Pub Date : 2021-10-08 DOI: 10.1049/cvi2.12122

Shi Luo, Xiong-fei Li, Xiaoli Zhang

{"title":"BDC: Bounding-Box Deep Calibration for High Performance Face Detection","authors":"Shi Luo, Xiong-fei Li, Xiaoli Zhang","doi":"10.1049/cvi2.12122","DOIUrl":"https://doi.org/10.1049/cvi2.12122","url":null,"abstract":"The Fundamental Research Funds for the Central Universities, JLU; The Graduate Innovation Fund of Jilin University; The ‘Thirteenth Five‐Year Pla’ Scientific Research Planning Project of Education Department of Jilin Province, Grant/Award Numbers: JKH20200678KJ, JJKH20200997KJ; The National Key Research and Development Project of China, Grant/Award Number: 2019YFC0409105; The National Natural Science Foundation of China, Grant/Award Number: 61801190; The Industrial Technology Research and Development Funds of Jilin Province, Grant/Award Number: 2019C054‐3 Abstract Modern convolutional neural networks (CNNs)‐based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive discussion is given for the replacement rationality between predicted and annotated bounding‐boxes. Finally, the authors propose a novel Bounding‐Box Deep Calibration (BDC) method to reasonably replace misaligned annotations with model predicted bounding‐boxes and offer calibrated annotations for the training set. Extensive experiments on multiple detectors and two popular benchmark datasets show the effectiveness of BDC on improving models' precision and recall rate, without adding extra inference time and memory consumption. Our simple and effective method provides a general strategy for improving face detection, especially for light‐weight detectors in real‐time situations.","PeriodicalId":301341,"journal":{"name":"IET Comput. Vis.","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114144104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-scale feature fusion connection for a YOLO detector 用于YOLO探测器的跨尺度特征融合连接

IET Comput. Vis. Pub Date : 2021-10-06 DOI: 10.1049/cvi2.12069

Zhongling Ruan, Hao Wang, Jianzhong Cao, Hongbo Zhang

引用次数: 2

End-to-end global to local convolutional neural network learning for hand pose recovery in depth data 端到端全局到局部卷积神经网络学习深度数据手部姿态恢复

IET Comput. Vis. Pub Date : 2021-08-12 DOI: 10.1049/cvi2.12064

Meysam Madadi, Sergio Escalera, Xavier Baró, Jordi Gonzàlez

引用次数: 3

Contour Loss for Instance Segmentation via k-step Distance Transformation Image 基于k步距离变换图像的轮廓损失分割

IET Comput. Vis. Pub Date : 2021-02-22 DOI: 10.1049/cvi2.12114

Xiaolong Guo, Xiaosong Lan, Kunfeng Wang, Shuxiao Li

{"title":"Contour Loss for Instance Segmentation via k-step Distance Transformation Image","authors":"Xiaolong Guo, Xiaosong Lan, Kunfeng Wang, Shuxiao Li","doi":"10.1049/cvi2.12114","DOIUrl":"https://doi.org/10.1049/cvi2.12114","url":null,"abstract":"Instance segmentation aims to locate targets in the image and segment each target area at pixel level, which is one of the most important tasks in computer vision. Mask R-CNN is a classic method of instance segmentation, but we find that its predicted masks are unclear and inaccurate near contours. To cope with this problem, we draw on the idea of contour matching based on distance transformation image and propose a novel loss function, called contour loss. Contour loss is designed to specifically optimize the contour parts of the predicted masks, thus can assure more accurate instance segmentation. In order to make the proposed contour loss to be jointly trained under modern neural network frameworks, we design a differentiable k-step distance transformation image calculation module, which can approximately compute truncated distance transformation images of the predicted mask and corresponding ground-truth mask online. The proposed contour loss can be integrated into existing instance segmentation methods such as Mask R-CNN, and combined with their original loss functions without modification of the inference network structures, thus has strong versatility. Experimental results on COCO show that contour loss is effective, which can further improve instance segmentation performances.","PeriodicalId":301341,"journal":{"name":"IET Comput. Vis.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124964834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Robustness of ToF and stereo fusion for high-accuracy depth map 高精度深度图中ToF和立体融合的鲁棒性

IET Comput. Vis. Pub Date : 2019-01-22 DOI: 10.12783/dtcse/ammms2018/27315

Zhenshan Bao, Bowen Li, Wen-bo Zhang

引用次数: 2