In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,th...In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.展开更多
A hierarchical particle filter（HPF） framework based on multi-feature fusion is proposed.The proposed HPF effectively uses different feature information to avoid the tracking failure based on the single feature in a ...A hierarchical particle filter（HPF） framework based on multi-feature fusion is proposed.The proposed HPF effectively uses different feature information to avoid the tracking failure based on the single feature in a complicated environment.In this approach,the Harris algorithm is introduced to detect the corner points of the object,and the corner matching algorithm based on singular value decomposition is used to compute the firstorder weights and make particles centralize in the high likelihood area.Then the local binary pattern（LBP） operator is used to build the observation model of the target based on the color and texture features,by which the second-order weights of particles and the accurate location of the target can be obtained.Moreover,a backstepping controller is proposed to complete the whole tracking system.Simulations and experiments are carried out,and the results show that the HPF algorithm with the backstepping controller achieves stable and accurate tracking with good robustness in complex environments.展开更多
煤矿井下弥漫着粉尘和雾气且多数区域为狭长巷道,仅依赖矿灯照明会导致视频监控图像出现细节模糊、局部过曝及目标尺寸多变等问题。这些因素增加了井下安全帽目标检测的难度,现有目标检测算法直接应用于煤矿井下场景时,通常面临精度不...煤矿井下弥漫着粉尘和雾气且多数区域为狭长巷道,仅依赖矿灯照明会导致视频监控图像出现细节模糊、局部过曝及目标尺寸多变等问题。这些因素增加了井下安全帽目标检测的难度,现有目标检测算法直接应用于煤矿井下场景时,通常面临精度不足的挑战。针对这些问题,研究提出一种基于YOLOv8n(You Only Look Once version 8n)的煤矿井下安全帽检测算法。首先,采用空间到深度机制将YOLOv8n主干网络中的Conv模块重新构建为空间到深度卷积(Space-to-Depth Convolutional,SPDConv)模块,以便从特征图中充分提取浅层细节信息,提高模型对细节模糊图像中小目标安全帽的检测精度;其次,引入基于注意力机制的尺度内特征交互模块,减少局部过曝对安全帽特征提取的干扰,增强模型对目标区域的关注能力;最后,借鉴高层次筛选特征融合金字塔对YOLOv8n的颈部网络进行重设计,改善模型对不同尺寸安全帽的检测能力,进一步提升检测精度。试验结果显示,该算法在CUMT-Helme T数据集上的平均精度均值达91.7%,相较于YOLOv8n提升了3.2百分点,同时模型参数量减少了1.9×10^(5)。与单次多边框检测(Single Shot MultiBox Detector,SSD)、快速区域卷积神经网络(Region-based Convolutional Neural Networks,Faster RCNN)、YOLOv5s、YOLOv6n、YOLOv7及YOLOv7-tiny等当前主流目标检测算法相比,该算法的平均精度均值最高,且参数量和浮点运算量较低,在实现较高检测精度的同时还具备一定的轻量化特性。展开更多
基金supported by the National Natural Science Foundation of China(62073036,62076031)Beijing Natural Science Foundation(4242049).
文摘In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.
基金supported by the National Natural Science Foundation of China(61304097)the Projects of Major International(Regional)Joint Research Program NSFC(61120106010)the Foundation for Innovation Research Groups of the National National Natural Science Foundation of China(61321002)
文摘A hierarchical particle filter（HPF） framework based on multi-feature fusion is proposed.The proposed HPF effectively uses different feature information to avoid the tracking failure based on the single feature in a complicated environment.In this approach,the Harris algorithm is introduced to detect the corner points of the object,and the corner matching algorithm based on singular value decomposition is used to compute the firstorder weights and make particles centralize in the high likelihood area.Then the local binary pattern（LBP） operator is used to build the observation model of the target based on the color and texture features,by which the second-order weights of particles and the accurate location of the target can be obtained.Moreover,a backstepping controller is proposed to complete the whole tracking system.Simulations and experiments are carried out,and the results show that the HPF algorithm with the backstepping controller achieves stable and accurate tracking with good robustness in complex environments.
文摘煤矿井下弥漫着粉尘和雾气且多数区域为狭长巷道,仅依赖矿灯照明会导致视频监控图像出现细节模糊、局部过曝及目标尺寸多变等问题。这些因素增加了井下安全帽目标检测的难度,现有目标检测算法直接应用于煤矿井下场景时,通常面临精度不足的挑战。针对这些问题,研究提出一种基于YOLOv8n(You Only Look Once version 8n)的煤矿井下安全帽检测算法。首先,采用空间到深度机制将YOLOv8n主干网络中的Conv模块重新构建为空间到深度卷积(Space-to-Depth Convolutional,SPDConv)模块,以便从特征图中充分提取浅层细节信息,提高模型对细节模糊图像中小目标安全帽的检测精度;其次,引入基于注意力机制的尺度内特征交互模块,减少局部过曝对安全帽特征提取的干扰,增强模型对目标区域的关注能力;最后,借鉴高层次筛选特征融合金字塔对YOLOv8n的颈部网络进行重设计,改善模型对不同尺寸安全帽的检测能力,进一步提升检测精度。试验结果显示,该算法在CUMT-Helme T数据集上的平均精度均值达91.7%,相较于YOLOv8n提升了3.2百分点,同时模型参数量减少了1.9×10^(5)。与单次多边框检测(Single Shot MultiBox Detector,SSD)、快速区域卷积神经网络(Region-based Convolutional Neural Networks,Faster RCNN)、YOLOv5s、YOLOv6n、YOLOv7及YOLOv7-tiny等当前主流目标检测算法相比,该算法的平均精度均值最高,且参数量和浮点运算量较低,在实现较高检测精度的同时还具备一定的轻量化特性。
