The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregula...The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.展开更多
To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level ...To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.展开更多
The localization of the blanket jamming is studied and a new method of solving the localization ambiguity is proposed. Radars only can acquire angle information without range information when encountering the blanket ...The localization of the blanket jamming is studied and a new method of solving the localization ambiguity is proposed. Radars only can acquire angle information without range information when encountering the blanket jamming. Netted radars could get position information of the blanket jamming by make use of radars' relative position and the angle information, when there is one blanket jamming. In the presence of error, the localization method and the accuracy analysis of one blanket jamming are given. However, if there are more than one blanket jamming, and the two blanket jamming and two radars are coplanar, the localization of jamming could be error due to localization ambiguity. To solve this confusion, the Kalman filter model is established for all intersections, and through the initiation and association algorithm of multi-target, the false intersection can be eliminated. Simulations show that the presented method is valid.展开更多
For existing indoor localization algorithm has low accuracy, high cost in deployment and maintenance, lack of robustness, and low sensor utilization, this paper proposes a particle filter algorithm based on multi-sens...For existing indoor localization algorithm has low accuracy, high cost in deployment and maintenance, lack of robustness, and low sensor utilization, this paper proposes a particle filter algorithm based on multi-sensor fusion. The pedestrian’s localization in indoor environment is described as dynamic system state estimation problem. The algorithm combines the smart mobile terminal with indoor localization, and filters the result of localization with the particle filter. In this paper, a dynamic interval particle filter algorithm based on pedestrian dead reckoning (PDR) information and RSSI localization information have been used to improve the filtering precision and the stability. Moreover, the localization results will be uploaded to the server in time, and the location fingerprint database will be built incrementally, which can adapt the dynamic changes of the indoor environment. Experimental results show that the algorithm based on multi-sensor improves the localization accuracy and robustness compared with the location algorithm based on Wi-Fi.展开更多
s-Lap is a new gene sequence from pig retinal pigment epithelial(RPE) cells, which was found and cloned in the early period of apoptosis of RPE cells damaged with visible light. We cloned the coding area sequence of t...s-Lap is a new gene sequence from pig retinal pigment epithelial(RPE) cells, which was found and cloned in the early period of apoptosis of RPE cells damaged with visible light. We cloned the coding area sequence of the novel gene of s-Lap and constructed its recombinant eukaryotic plasmid pcDNA3.1-GFP/s-lap with the recombinant DNA technique. The expression and localization of s-lap/GFP fusion protein in CHO and B_~16 cell lines were studied with the instantaneously transfected pcDNA3.1-GFP/s-lap recombinant plasmid. ~s-Lap/GFP fusion protein can be expressed in CHO and B_~16 cells with a high rate expression in the nuclei.展开更多
在图优化框架的基础上,设计多传感器融合方案和有效的优化方法,提出一套具有鲁棒性的定位与建图(Simultaneous Localization and Mapping,SLAM)方案,能够有效应对室内外复杂环境。进一步发展激光-视觉后端建图融合方法,构建具备全新地...在图优化框架的基础上,设计多传感器融合方案和有效的优化方法,提出一套具有鲁棒性的定位与建图(Simultaneous Localization and Mapping,SLAM)方案,能够有效应对室内外复杂环境。进一步发展激光-视觉后端建图融合方法,构建具备全新地图表达形式的点云网格化地图。同时使用低成本传感器,设计实现基于多传感器融合的高性能低成本背包扫描系统,整体完成在未知环境中的自我定位和稠密建图,且在低性能CPU设备上将长时间运动带来的每100 m的轨迹误差平均降低至厘米级。提出的基于多传感器融合方案,在精度、算力消耗上能够匹配现有主流方案,对获取各种环境条件下的系统准确定位结果和丰富的空间信息具有重要意义。展开更多
基金The support of this research was by Hubei Provincial Natural Science Foundation(2022CFB449)Science Research Foundation of Education Department of Hubei Province(B2020061),are gratefully acknowledged.
文摘The task of food image recognition,a nuanced subset of fine-grained image recognition,grapples with substantial intra-class variation and minimal inter-class differences.These challenges are compounded by the irregular and multi-scale nature of food images.Addressing these complexities,our study introduces an advanced model that leverages multiple attention mechanisms and multi-stage local fusion,grounded in the ConvNeXt architecture.Our model employs hybrid attention(HA)mechanisms to pinpoint critical discriminative regions within images,substantially mitigating the influence of background noise.Furthermore,it introduces a multi-stage local fusion(MSLF)module,fostering long-distance dependencies between feature maps at varying stages.This approach facilitates the assimilation of complementary features across scales,significantly bolstering the model’s capacity for feature extraction.Furthermore,we constructed a dataset named Roushi60,which consists of 60 different categories of common meat dishes.Empirical evaluation of the ETH Food-101,ChineseFoodNet,and Roushi60 datasets reveals that our model achieves recognition accuracies of 91.12%,82.86%,and 92.50%,respectively.These figures not only mark an improvement of 1.04%,3.42%,and 1.36%over the foundational ConvNeXt network but also surpass the performance of most contemporary food image recognition methods.Such advancements underscore the efficacy of our proposed model in navigating the intricate landscape of food image recognition,setting a new benchmark for the field.
文摘To overcome the shortcomings of 1 D and 2 D Otsu’s thresholding techniques, the 3 D Otsu method has been developed.Among all Otsu’s methods, 3 D Otsu technique provides the best threshold values for the multi-level thresholding processes. In this paper, to improve the quality of segmented images, a simple and effective multilevel thresholding method is introduced. The proposed approach focuses on preserving edge detail by computing the 3 D Otsu along the fusion phenomena. The advantages of the presented scheme include higher quality outcomes, better preservation of tiny details and boundaries and reduced execution time with rising threshold levels. The fusion approach depends upon the differences between pixel intensity values within a small local space of an image;it aims to improve localized information after the thresholding process. The fusion of images based on local contrast can improve image segmentation performance by minimizing the loss of local contrast, loss of details and gray-level distributions. Results show that the proposed method yields more promising segmentation results when compared to conventional1 D Otsu, 2 D Otsu and 3 D Otsu methods, as evident from the objective and subjective evaluations.
文摘The localization of the blanket jamming is studied and a new method of solving the localization ambiguity is proposed. Radars only can acquire angle information without range information when encountering the blanket jamming. Netted radars could get position information of the blanket jamming by make use of radars' relative position and the angle information, when there is one blanket jamming. In the presence of error, the localization method and the accuracy analysis of one blanket jamming are given. However, if there are more than one blanket jamming, and the two blanket jamming and two radars are coplanar, the localization of jamming could be error due to localization ambiguity. To solve this confusion, the Kalman filter model is established for all intersections, and through the initiation and association algorithm of multi-target, the false intersection can be eliminated. Simulations show that the presented method is valid.
文摘For existing indoor localization algorithm has low accuracy, high cost in deployment and maintenance, lack of robustness, and low sensor utilization, this paper proposes a particle filter algorithm based on multi-sensor fusion. The pedestrian’s localization in indoor environment is described as dynamic system state estimation problem. The algorithm combines the smart mobile terminal with indoor localization, and filters the result of localization with the particle filter. In this paper, a dynamic interval particle filter algorithm based on pedestrian dead reckoning (PDR) information and RSSI localization information have been used to improve the filtering precision and the stability. Moreover, the localization results will be uploaded to the server in time, and the location fingerprint database will be built incrementally, which can adapt the dynamic changes of the indoor environment. Experimental results show that the algorithm based on multi-sensor improves the localization accuracy and robustness compared with the location algorithm based on Wi-Fi.
文摘s-Lap is a new gene sequence from pig retinal pigment epithelial(RPE) cells, which was found and cloned in the early period of apoptosis of RPE cells damaged with visible light. We cloned the coding area sequence of the novel gene of s-Lap and constructed its recombinant eukaryotic plasmid pcDNA3.1-GFP/s-lap with the recombinant DNA technique. The expression and localization of s-lap/GFP fusion protein in CHO and B_~16 cell lines were studied with the instantaneously transfected pcDNA3.1-GFP/s-lap recombinant plasmid. ~s-Lap/GFP fusion protein can be expressed in CHO and B_~16 cells with a high rate expression in the nuclei.
文摘识别非驾驶行为是提高驾驶安全性的重要手段之一。目前基于骨架序列和图像的融合识别方法具有计算量大和特征融合困难的问题。针对上述问题,本文提出一种基于多尺度骨架图和局部视觉上下文融合的驾驶员行为识别模型(skeleton-image based behavior recognition network,SIBBR-Net)。SIBBR-Net通过基于多尺度图的图卷积网络和基于局部视觉及注意力机制的卷积神经网络,充分提取运动和外观特征,较好地平衡了模型表征能力和计算量间的关系。基于手部运动的特征双向引导学习策略、自适应特征融合模块和静态特征空间上的辅助损失,使运动和外观特征间互相引导更新并实现自适应融合。最终在Drive&Act数据集进行算法测试,SIBBR-Net在动态标签和静态标签条件下的平均正确率分别为61.78%和80.42%,每秒浮点运算次数为25.92G,较最优方法降低了76.96%。
文摘在图优化框架的基础上,设计多传感器融合方案和有效的优化方法,提出一套具有鲁棒性的定位与建图(Simultaneous Localization and Mapping,SLAM)方案,能够有效应对室内外复杂环境。进一步发展激光-视觉后端建图融合方法,构建具备全新地图表达形式的点云网格化地图。同时使用低成本传感器,设计实现基于多传感器融合的高性能低成本背包扫描系统,整体完成在未知环境中的自我定位和稠密建图,且在低性能CPU设备上将长时间运动带来的每100 m的轨迹误差平均降低至厘米级。提出的基于多传感器融合方案,在精度、算力消耗上能够匹配现有主流方案,对获取各种环境条件下的系统准确定位结果和丰富的空间信息具有重要意义。
