The rapid advancements in autonomous driving technology necessitate the extensive deployment of automotive radars operating within the 77-81 GHz millimeter-wave band in the forthcoming years. In contrast to earlier Fr...
详细信息
Video description aims to translate the visual content in a video with appropriate natural language. Most of current works only focus on the description of factual content, paying insufficient attention to the emotion...
详细信息
There are some shortcomings in existing salient object detection methods of remote sensing images. For example, the extracting features are insufficient and they are always seriously interfered by complex background i...
详细信息
There are some shortcomings in existing salient object detection methods of remote sensing images. For example, the extracting features are insufficient and they are always seriously interfered by complex background i...
详细信息
ISBN:
(数字)9798350368284
ISBN:
(纸本)9798350368291
There are some shortcomings in existing salient object detection methods of remote sensing images. For example, the extracting features are insufficient and they are always seriously interfered by complex background information. To solve these problems, a visual attention model based on Gestalt theory is proposed. First, a pyramid anisotropic scale space model is built, followed by the extraction of multi-scale, multi-directional low-and high-frequency visual features to construct multi-space saliency maps. Then each spatial saliency map can be adaptively fused based on the similarity principle of Gestalt theory. Comparison and analysis are implemented among our proposed method and some existing methods on the public natural image dateset ECSSD and remote sensing image dateset ORSSD. The experimental results show that the proposed method has higher detection accuracy than existing saliency detection methods, especially in the detection of remote sensing images. It is greatly demonstrated that the effectiveness and feasibility of the proposed method.
暂无评论