In foggy weather, images of outdoor scene are usually characterized with poor visibility as well as faint color saturation. The degraded hazy images may have substantial negative impact on most computer vision systems...In foggy weather, images of outdoor scene are usually characterized with poor visibility as well as faint color saturation. The degraded hazy images may have substantial negative impact on most computer vision systems. Thus image haze removal is of the practical significance in engineering. This paper proposes a fast and effective single image haze removal algorithm on the basis of the physics imaging model. To extract the global atmospheric light accurately, we exploit multiple prior rules underlying hazy images, and put forward a novel measurement to judge the likelihood that a pixel is regarded as the global atmospheric light. In addition, the rough transmission map is estimated through a multiscale fusion process based on the Laplace pyramid transform, and refined by a total variation model. Experimental results demonstrate the proposed method outperforms most of the state-of-the-art algorithms in terms of the dehazing quality, and achieves a trade-off between the computational efficiency and haze removal capability.展开更多
复杂交通环境下目标检测中存在很多外界干扰因素,导致通用的目标检测算法效果较差。针对目标检测方法中全局特征信息利用不充分,小目标、遮挡目标检测精度低,以及模型计算量大等问题,提出一种基于改进YOLOv5s的融合全局特征目标检测方...复杂交通环境下目标检测中存在很多外界干扰因素,导致通用的目标检测算法效果较差。针对目标检测方法中全局特征信息利用不充分,小目标、遮挡目标检测精度低,以及模型计算量大等问题,提出一种基于改进YOLOv5s的融合全局特征目标检测方法。首先,对YOLOv5s的主干网络进行扩展,得到更深层的特征图以增强较大目标的语义信息;其次,在此基础上引入全局信息融合模块代替原模型中的Neck部分,以3D卷积的方式融合各尺度信息;然后,设计了一种基于位置的先验框匹配方法,在原图尺度上搜索与真实框匹配的先验框;最后,使用Copy-Paste数据增强方法增大小目标样本数量并使用DIoUNMS作为后处理方法进行非极大值抑制。该模型在BDD100K数据集中平均精确率(mean Average Precision,mAP)为54.55%,检测速度为63.72帧每秒(Frames Per Second,FPS)。与原始YOLOv5s算法相比,该方法在检测速度及精度方面均有明显优势。展开更多
基金supported by the National Natural Science Foundation of China(61571241)the Industry-University-research Prospective Joint Project of Jiangsu Province(BY2014014)+2 种基金the Major Projects of Jiangsu Province University Natural Science Research(15KJA510002)the Jiangsu Province Graduate Research and Innovation Project(CXZZ130476)the Science Research Fund of NUPT(NY215169)
文摘In foggy weather, images of outdoor scene are usually characterized with poor visibility as well as faint color saturation. The degraded hazy images may have substantial negative impact on most computer vision systems. Thus image haze removal is of the practical significance in engineering. This paper proposes a fast and effective single image haze removal algorithm on the basis of the physics imaging model. To extract the global atmospheric light accurately, we exploit multiple prior rules underlying hazy images, and put forward a novel measurement to judge the likelihood that a pixel is regarded as the global atmospheric light. In addition, the rough transmission map is estimated through a multiscale fusion process based on the Laplace pyramid transform, and refined by a total variation model. Experimental results demonstrate the proposed method outperforms most of the state-of-the-art algorithms in terms of the dehazing quality, and achieves a trade-off between the computational efficiency and haze removal capability.
文摘复杂交通环境下目标检测中存在很多外界干扰因素,导致通用的目标检测算法效果较差。针对目标检测方法中全局特征信息利用不充分,小目标、遮挡目标检测精度低,以及模型计算量大等问题,提出一种基于改进YOLOv5s的融合全局特征目标检测方法。首先,对YOLOv5s的主干网络进行扩展,得到更深层的特征图以增强较大目标的语义信息;其次,在此基础上引入全局信息融合模块代替原模型中的Neck部分,以3D卷积的方式融合各尺度信息;然后,设计了一种基于位置的先验框匹配方法,在原图尺度上搜索与真实框匹配的先验框;最后,使用Copy-Paste数据增强方法增大小目标样本数量并使用DIoUNMS作为后处理方法进行非极大值抑制。该模型在BDD100K数据集中平均精确率(mean Average Precision,mAP)为54.55%,检测速度为63.72帧每秒(Frames Per Second,FPS)。与原始YOLOv5s算法相比,该方法在检测速度及精度方面均有明显优势。
