全部
图书
期刊
学位论文
会议论文
报纸
图片
视频
新闻
按文献类别分组
按栏目分组
关键词
- EGMT-CD: Edge-Guided Multimodal Transformers Change Detection from Satellite and Aerial Images
- 作者： Yunfan Xiang Xiangyu Tian Yue Xu Xiaokun Guan Zhengchao Chen 来源： Remote Sensing 年份： 2023 文献类型 ： 期刊 关键词： sensing detection images edge Transformer feature change remote alignment heterogeneous
- 描述： Change detection from heterogeneous satellite and aerial images plays a progressively important role in many fields, including disaster assessment, urban construction, and land use monitoring. Currently, researchers have mainly devoted their attention to change detection using homologous image pairs and achieved many remarkable results. It is sometimes necessary to use heterogeneous images for change detection in practical scenarios due to missing images, emergency situations, and cloud and fog occlusion. However, heterogeneous change detection still faces great challenges, especially using satellite and aerial images. The main challenges in satellite and aerial image change detection are related to the resolution gap and blurred edge. Previous studies used interpolation or shallow feature alignment before traditional homologous change detection methods, which ignored the high-level feature interaction and edge information. Therefore, we propose a new heterogeneous change detection model based on multimodal transformers combined with edge guidance. In order to alleviate the resolution gap between satellite and aerial images, we design an improved spatially aligned transformer (SP-T) with a sub-pixel module to align the satellite features to the same size of the aerial ones supervised by a token loss. Moreover, we introduce an edge detection branch to guide change features using the object edge with an auxiliary edge-change loss. Finally, we conduct considerable experiments to verify the effectiveness and superiority of our proposed model (EGMT-CD) on a new satellite–aerial heterogeneous change dataset, named SACD. The experiments show that our method (EGMT-CD) outperforms many previously superior change detection methods and fully demonstrates its potential in heterogeneous change detection from satellite–aerial images.
- CNN with New Spatial Pyramid Pooling and Advanced Filter-Based Techniques: Revolutionizing Traffic Monitoring via Aerial Images
- 作者： Irfan Javid Rozaida Ghazali Waddah Saeed Tuba Batool Ebrahim Al Wajih 来源： Sustainability 年份： 2023 文献类型 ： 期刊 关键词： semantic Kalman categorization recognition extended vehicle filter pooling U and pyramid segmentation spatial Net
- 描述： The escalation in vehicular traffic, in conjunction with global population growth, has precipitated heightened road congestion, augmented air pollution, and a rise in vehicular accidents. Over the past decade, the global vehicular count has witnessed a substantial surge. In this context, traffic monitoring emerges as a paramount challenge, especially within developing nations. This research introduces an innovative system for vehicle detection and categorization aimed at intelligent traffic monitoring. The system utilizes a convolutional neural network-based U-Net model for the segmentation of aerial images. After segmentation, the outputs are further analyzed for vehicle identification. This vehicle detection utilizes an advanced spatial pyramid pooling (ASPP) mechanism which refines the spatial partitions of the image and captures intricate details, enhancing the accuracy and precision of the detection process. Detected vehicles are then categorized into distinct subcategories. For the effective management and control of high-density traffic flow, the extended Kalman filter (EKF) technique is employed, thereby reducing the reliance on human oversight. In experimental evaluations, our proposed model exhibits exemplary vehicle detection capabilities across the German Aerospace Center (DLR3K) and the Vehicle Detection in Aerial Imagery (VEDAI) datasets. Potential applications of the system encompass vehicle identification in traffic streams, traffic congestion assessment, intersection traffic density analysis, differentiation of vehicle types, and pedestrian pathway determination.
- CNN with New Spatial Pyramid Pooling and Advanced Filter-Based Techniques: Revolutionizing Traffic Monitoring via Aerial Images
- 作者： Irfan Javid Rozaida Ghazali Waddah Saeed Tuba Batool Ebrahim Al Wajih 来源： Sustainability 年份： 2023 文献类型 ： 期刊 关键词： semantic Kalman categorization recognition extended vehicle filter pooling U and pyramid segmentation spatial Net
- 描述： The escalation in vehicular traffic, in conjunction with global population growth, has precipitated heightened road congestion, augmented air pollution, and a rise in vehicular accidents. Over the past decade, the global vehicular count has witnessed a substantial surge. In this context, traffic monitoring emerges as a paramount challenge, especially within developing nations. This research introduces an innovative system for vehicle detection and categorization aimed at intelligent traffic monitoring. The system utilizes a convolutional neural network-based U-Net model for the segmentation of aerial images. After segmentation, the outputs are further analyzed for vehicle identification. This vehicle detection utilizes an advanced spatial pyramid pooling (ASPP) mechanism which refines the spatial partitions of the image and captures intricate details, enhancing the accuracy and precision of the detection process. Detected vehicles are then categorized into distinct subcategories. For the effective management and control of high-density traffic flow, the extended Kalman filter (EKF) technique is employed, thereby reducing the reliance on human oversight. In experimental evaluations, our proposed model exhibits exemplary vehicle detection capabilities across the German Aerospace Center (DLR3K) and the Vehicle Detection in Aerial Imagery (VEDAI) datasets. Potential applications of the system encompass vehicle identification in traffic streams, traffic congestion assessment, intersection traffic density analysis, differentiation of vehicle types, and pedestrian pathway determination.