This section surveys the datasets most commonly used for training and testing semantic segmentation models based on deep learning. According to whether the datasets take into account the changes of lighting conditions, weather and seasonal, this paper divides these datasets into two categories: no cros...
Semantic segmentation can distinguish objects in remote sensing images at the pixel level. However, traditional semantic segmentation algorithms are more and more difficult to meet people's needs. With the rapid development of deep learning, especially its application in remote sensing images has greatly...
Visual semantic segmentation aims at separating a visual sample into diverse blocks with specific semantic attributes and identifying the category for each block, and it plays a crucial role in environmental perception. Conventional learning-based visual
This component involves various techniques, such as 3D semantic segmentation, 3D object detection and recognition, 3D instance segmentation, 3D pose estimation, and 3D reconstruction. Among them, the performance of 3D reconstruction greatly depends on the semantic representation of output data, which ...
In this article, a deep learning algorithm for the semantic segmentation of high-resolution remote-sensing images using the U-net convolutional network was proposed to map the damage rapidly. The algorithm was implemented within a ... Y Bai,E Mas,S Koshimura - 《Remote Sensing》 被引量: 0...
Few-shot semantic segmentation aims at training a model that can segment novel classes in a query image with only a few densely annotated support exemplars. It remains a challenge because of large intra-class variations between the support and query imag
(2022) found a correlation of 0.96. Subsequently, Lu (2018) used automatic image identification AI to calculate the GVI. This AI uses a deep learning algorithm called “semantic segmentation,” which associates labels or categories such as “sky,”“vegetation,”“building,” and “road” with...
Our frame- work, which we term "Splice", does not involve adversar- ial training, nor does it require any additional input infor- mation such as semantic segmentation or correspondences, and can generate high resolution results, e.g., work in HD. We demonstrate high quality ...
By virtue of a million intensively collected panoramic street view images in Shenzhen, China, the image-segmentation technique SegNet automatically extracts pixelwise semantical information and classifies visual elements. The throughput of the eye-level perception of the street canyon is formed by five ...
In the subsequent UCD iterations, for each iteration, we analyzed the feedback collected from either usability testing focus groups or online surveys from the previous iteration and updated user needs and requirements accordingly. 2.1.3. Design In the first UCD iteration, we reviewed existing ...