This paper introduces a Convolutional Neural Network (CNN) model for Arabic Sign Language (AASL) recognition, using the AASL dataset. Recognizing the fundamental importance of communication for the hearing-impaired, e...This paper introduces a Convolutional Neural Network (CNN) model for Arabic Sign Language (AASL) recognition, using the AASL dataset. Recognizing the fundamental importance of communication for the hearing-impaired, especially within the Arabic-speaking deaf community, the study emphasizes the critical role of sign language recognition systems. The proposed methodology achieves outstanding accuracy, with the CNN model reaching 99.9% accuracy on the training set and a validation accuracy of 97.4%. This study not only establishes a high-accuracy AASL recognition model but also provides insights into effective dropout strategies. The achieved high accuracy rates position the proposed model as a significant advancement in the field, holding promise for improved communication accessibility for the Arabic-speaking deaf community.展开更多
针对遮挡场景下车辆跟踪精度下降的问题,提出了一种基于卷积核优选的遮挡车辆跟踪(Convolutional Kernel Optimization for Occluded Vehicle Tracking,CKO-OVT)算法。CKO-OVT算法通过卷积核优选策略自适应挑选出对车辆目标更为敏感的...针对遮挡场景下车辆跟踪精度下降的问题,提出了一种基于卷积核优选的遮挡车辆跟踪(Convolutional Kernel Optimization for Occluded Vehicle Tracking,CKO-OVT)算法。CKO-OVT算法通过卷积核优选策略自适应挑选出对车辆目标更为敏感的卷积算子进行特征提取,通过判别式孪生网络对跟踪结果进行评估并在跟踪失效的情况下重定位目标,进一步提升跟踪的鲁棒性和准确性。实验部分,构建了遮挡车辆跟踪(Occluded Vehicle Tracking,OVT)数据集,分别在目标跟踪基准(Object Tracking Benchmark,OTB)数据集、TColor-128公开数据集和自建OVT数据集上同高效卷积跟踪(Efficient Convolution Operators for Tracking,ECO)算法、ECO轻量化版本(Efficient Convolution Operators for Tracking Using HOG and CN,ECOHC)、相关滤波(Kernelized Correlation Filters Tracker,KCF)算法、判别式尺度空间跟踪(Discriminative Scale Space Tracker,DSST)算法、循环结构核跟踪(Circulant Structure Kernel Tracker,CSK)算法、层次相关滤波跟踪(Hierarchical Convolutional Features for Visual Tracking,HCFT)算法、基于分层卷积特征的鲁棒视觉跟踪(Robust Visual Tracking via Hierarchical Convolutional Features,HCFTstar)算法、全卷积孪生网络跟踪(Fully-Convolutional Siamese Networks for Object Tracking,SiameseFC)算法和抗干扰感知孪生网络跟踪(Distractor-Aware Siamese Networks for Object Tracking,DaSiam)算法9种主流算法进行实验对比,实验结果表明CKO-OVT算法在OTB数据集上距离精确率提升了2.2%,重叠成功率提升了1.8%;在TColor-128数据集上距离精确率提升了0.4%,重叠成功率提升了0.9%;在OVT数据集上距离精确率提升了1.7%,重叠成功率提升了1.2%。CKO-OVT算法通过自适应卷积核优选和判别式孪生网络,显著提升了遮挡场景下车辆跟踪的鲁棒性和准确性,在OTB、TColor-128和自建OVT数据集上的实验结果表明,CKO-OVT算法在距离精确率和重叠成功率上优于主流跟踪算法,为智能交通和自动驾驶领域的车辆跟踪提供了有效的解决方案。展开更多
文摘This paper introduces a Convolutional Neural Network (CNN) model for Arabic Sign Language (AASL) recognition, using the AASL dataset. Recognizing the fundamental importance of communication for the hearing-impaired, especially within the Arabic-speaking deaf community, the study emphasizes the critical role of sign language recognition systems. The proposed methodology achieves outstanding accuracy, with the CNN model reaching 99.9% accuracy on the training set and a validation accuracy of 97.4%. This study not only establishes a high-accuracy AASL recognition model but also provides insights into effective dropout strategies. The achieved high accuracy rates position the proposed model as a significant advancement in the field, holding promise for improved communication accessibility for the Arabic-speaking deaf community.
文摘针对遮挡场景下车辆跟踪精度下降的问题,提出了一种基于卷积核优选的遮挡车辆跟踪(Convolutional Kernel Optimization for Occluded Vehicle Tracking,CKO-OVT)算法。CKO-OVT算法通过卷积核优选策略自适应挑选出对车辆目标更为敏感的卷积算子进行特征提取,通过判别式孪生网络对跟踪结果进行评估并在跟踪失效的情况下重定位目标,进一步提升跟踪的鲁棒性和准确性。实验部分,构建了遮挡车辆跟踪(Occluded Vehicle Tracking,OVT)数据集,分别在目标跟踪基准(Object Tracking Benchmark,OTB)数据集、TColor-128公开数据集和自建OVT数据集上同高效卷积跟踪(Efficient Convolution Operators for Tracking,ECO)算法、ECO轻量化版本(Efficient Convolution Operators for Tracking Using HOG and CN,ECOHC)、相关滤波(Kernelized Correlation Filters Tracker,KCF)算法、判别式尺度空间跟踪(Discriminative Scale Space Tracker,DSST)算法、循环结构核跟踪(Circulant Structure Kernel Tracker,CSK)算法、层次相关滤波跟踪(Hierarchical Convolutional Features for Visual Tracking,HCFT)算法、基于分层卷积特征的鲁棒视觉跟踪(Robust Visual Tracking via Hierarchical Convolutional Features,HCFTstar)算法、全卷积孪生网络跟踪(Fully-Convolutional Siamese Networks for Object Tracking,SiameseFC)算法和抗干扰感知孪生网络跟踪(Distractor-Aware Siamese Networks for Object Tracking,DaSiam)算法9种主流算法进行实验对比,实验结果表明CKO-OVT算法在OTB数据集上距离精确率提升了2.2%,重叠成功率提升了1.8%;在TColor-128数据集上距离精确率提升了0.4%,重叠成功率提升了0.9%;在OVT数据集上距离精确率提升了1.7%,重叠成功率提升了1.2%。CKO-OVT算法通过自适应卷积核优选和判别式孪生网络,显著提升了遮挡场景下车辆跟踪的鲁棒性和准确性,在OTB、TColor-128和自建OVT数据集上的实验结果表明,CKO-OVT算法在距离精确率和重叠成功率上优于主流跟踪算法,为智能交通和自动驾驶领域的车辆跟踪提供了有效的解决方案。
