目的 传统视觉场景识别(visual place recognition,VPR)算法的性能依赖光学图像的成像质量,因此高速和高动态范围场景导致的图像质量下降会进一步影响视觉场景识别算法的性能。针对此问题,提出一种融合事件相机的视觉场景识别算法,利用...目的 传统视觉场景识别(visual place recognition,VPR)算法的性能依赖光学图像的成像质量,因此高速和高动态范围场景导致的图像质量下降会进一步影响视觉场景识别算法的性能。针对此问题,提出一种融合事件相机的视觉场景识别算法,利用事件相机的低延时和高动态范围的特性,提升视觉场景识别算法在高速和高动态范围等极端场景下的识别性能。方法 本文提出的方法首先使用图像特征提取模块提取质量良好的参考图像的特征,然后使用多模态特征融合模块提取查询图像及其曝光区间事件信息的多模态融合特征,最后通过特征匹配查找与查询图像最相似的参考图像。结果 在MVSEC(multi-vehicle stereo event camera dataset)和RobotCar两个数据集上的实验表明,本文方法对比现有视觉场景识别算法在高速和高动态范围场景下具有明显优势。在高速高动态范围场景下,本文方法在MVSEC数据集上相较对比算法最优值在召回率与精度上分别提升5.39%和8.55%,在RobotCar数据集上相较对比算法最优值在召回率与精度上分别提升3.36%与4.41%。结论 本文提出了融合事件相机的视觉场景识别算法,利用了事件相机在高速和高动态范围场景的成像优势,有效提升了视觉场景识别算法在高速和高动态范围场景下的场景识别性能。展开更多
Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof ...Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.展开更多
目的可见光—红外跨模态行人再识别旨在匹配具有相同行人身份的可见光图像和红外图像。现有方法主要采用模态共享特征学习或模态转换来缩小模态间的差异,前者通常只关注全局或局部特征表示,后者则存在生成模态不可靠的问题。事实上,轮...目的可见光—红外跨模态行人再识别旨在匹配具有相同行人身份的可见光图像和红外图像。现有方法主要采用模态共享特征学习或模态转换来缩小模态间的差异,前者通常只关注全局或局部特征表示,后者则存在生成模态不可靠的问题。事实上,轮廓具有一定的跨模态不变性,同时也是一种相对可靠的行人识别线索。为了有效利用轮廓信息减少模态间差异,本文将轮廓作为辅助模态,提出了一种轮廓引导的双粒度特征融合网络,用于跨模态行人再识别。方法在全局粒度上,通过行人图像到轮廓图像的融合,用于增强轮廓的全局特征表达,得到轮廓增广特征。在局部粒度上,通过轮廓增广特征和基于部件的局部特征的融合,用于联合全局特征和局部特征,得到融合后的图像表达。结果在可见光—红外跨模态行人再识别的两个公开数据集对模型进行评估,结果优于一些代表性方法。在SYSU-MM01(Sun Yat-sen University multiple modality 01)数据集上,本文方法rank-1准确率和平均精度均值(mean average precision,mAP)分别为62.42%和58.14%。在RegDB(Dongguk body-based person recognition database)数据集上,本文方法rank-1和mAP分别为84.42%和77.82%。结论本文将轮廓信息引入跨模态行人再识别,提出一种轮廓引导的双粒度特征融合网络,在全局粒度和局部粒度上进行特征融合,从而学习具有判别性的特征,性能超过了近年来一些具有代表性的方法,验证了轮廓线索及其使用方法的有效性。展开更多
文摘Zero-shot learning enables the recognition of new class samples by migrating models learned from semanticfeatures and existing sample features to things that have never been seen before. The problems of consistencyof different types of features and domain shift problems are two of the critical issues in zero-shot learning. Toaddress both of these issues, this paper proposes a new modeling structure. The traditional approach mappedsemantic features and visual features into the same feature space;based on this, a dual discriminator approachis used in the proposed model. This dual discriminator approach can further enhance the consistency betweensemantic and visual features. At the same time, this approach can also align unseen class semantic features andtraining set samples, providing a portion of information about the unseen classes. In addition, a new feature fusionmethod is proposed in the model. This method is equivalent to adding perturbation to the seen class features,which can reduce the degree to which the classification results in the model are biased towards the seen classes.At the same time, this feature fusion method can provide part of the information of the unseen classes, improvingits classification accuracy in generalized zero-shot learning and reducing domain bias. The proposed method isvalidated and compared with othermethods on four datasets, and fromthe experimental results, it can be seen thatthe method proposed in this paper achieves promising results.
文摘目的可见光—红外跨模态行人再识别旨在匹配具有相同行人身份的可见光图像和红外图像。现有方法主要采用模态共享特征学习或模态转换来缩小模态间的差异,前者通常只关注全局或局部特征表示,后者则存在生成模态不可靠的问题。事实上,轮廓具有一定的跨模态不变性,同时也是一种相对可靠的行人识别线索。为了有效利用轮廓信息减少模态间差异,本文将轮廓作为辅助模态,提出了一种轮廓引导的双粒度特征融合网络,用于跨模态行人再识别。方法在全局粒度上,通过行人图像到轮廓图像的融合,用于增强轮廓的全局特征表达,得到轮廓增广特征。在局部粒度上,通过轮廓增广特征和基于部件的局部特征的融合,用于联合全局特征和局部特征,得到融合后的图像表达。结果在可见光—红外跨模态行人再识别的两个公开数据集对模型进行评估,结果优于一些代表性方法。在SYSU-MM01(Sun Yat-sen University multiple modality 01)数据集上,本文方法rank-1准确率和平均精度均值(mean average precision,mAP)分别为62.42%和58.14%。在RegDB(Dongguk body-based person recognition database)数据集上,本文方法rank-1和mAP分别为84.42%和77.82%。结论本文将轮廓信息引入跨模态行人再识别,提出一种轮廓引导的双粒度特征融合网络,在全局粒度和局部粒度上进行特征融合,从而学习具有判别性的特征,性能超过了近年来一些具有代表性的方法,验证了轮廓线索及其使用方法的有效性。
