Automatic ship detection by Unmanned Airborne Vehicles (UAVs) and satellites is one of the fundamental challenges in maritime research due to the variable appearances of ships and complex sea backgrounds. To address t...
详细信息
Automatic ship detection by Unmanned Airborne Vehicles (UAVs) and satellites is one of the fundamental challenges in maritime research due to the variable appearances of ships and complex sea backgrounds. To address this issue, in this paper, a novel multi-level ship detection algorithm is proposed to detect various types of offshore ships more precisely and quickly under all possible imaging variations. Our object detection system consists of two phases. First, in the category-independent region proposal phase, the steerable pyramid for multi-scale analysis is performed to generate a set of saliency maps in which the candidate region pixels are assigned to high salient values. Then, the set of saliency maps is used for constructing the graph-based segmentation, which can produce more accurate candidate regions compared with the threshold segmentation. More importantly, the proposed algorithm can produce a rather smaller set of candidates in comparison with the classical sliding window object detection paradigm or the other region proposal algorithms. Second, in the target identification phase, a rotation-invariant descriptor, which combines the histogram of oriented gradients (HOG) cells and the Fourier basis together, is investigated to distinguish between ships and non-ships. Meanwhile, the main direction of the ship can also be estimated in this phase. The overall algorithm can account for large variations in scale and rotation. Experiments on optical remote sensing (ORS) images demonstrate the effectiveness and robustness of our detection system.
Brain tumours and strokes are increasingly common, even from a young age. For this reason preliminary screenings, such as MRI scans, are crucial steps in detecting the abnormalities and finding a treatment. Given the ...
详细信息
Brain tumours and strokes are increasingly common, even from a young age. For this reason preliminary screenings, such as MRI scans, are crucial steps in detecting the abnormalities and finding a treatment. Given the increasing number of people developing different brain problems, there is a need in developing automated segmentation systems. Regardless the various methods presented in the literature, the lack of ground truth images determines the researchers to move towards unsupervised techniques. This paper presents an modified graph-based unsupervised brain segmentation method that uses a minimal spanning tree to segment brain from non-brain tissue. The original method uses human intervention for node selection. The aim is to eliminate human intervention and reduce the computational time required for brain segmentation. The presented method was compared with the original one in two ways: by resizing and scaling the images, and using images without any pre-processing step. Experimental results were obtained on the NFBS dataset and in both experiments the proposed approach delivers better results, both visually and numerically. Performance measures have improved, leading to better overall segmentation. The new method increased the precision and dice coefficient by 20%, resulting in a more accurate segmentation.
The paper presents the application of graph-based segmentation algorithm in image object detection. The input images are taken from thermal camera for night surveillance application. The graph-based algorithm was sele...
详细信息
ISBN:
(纸本)9781479987023
The paper presents the application of graph-based segmentation algorithm in image object detection. The input images are taken from thermal camera for night surveillance application. The graph-based algorithm was selected due to its low complexity, which allows us to process each image with the complexity of O(***(n)) where n is the number of pixels, and due to the fact that thermal images contains smaller number of regions of colors. With the detected regions, some additional measures are used to filter out the artifacts to correctly detect the object in the images. The numerical results have proved the high quality of the proposed solutions.
This paper investigates depth estimation using monocular cues. Human visual system uses monocular cues such as texture, focus and shading for depth perception. Our proposed algorithm is based on segmenting the image i...
详细信息
ISBN:
(纸本)9781457718823
This paper investigates depth estimation using monocular cues. Human visual system uses monocular cues such as texture, focus and shading for depth perception. Our proposed algorithm is based on segmenting the image into homogenous segments (superpixels), and then out of these segments we extract the ground segment and the sky segment. These two segments guide the depth estimation by providing region with maximum depth (sky) and region with minimum depth (ground). The reset of the segments will have a depth value between the sky and ground. This algorithm address image that contains sky and ground as a part of the image. The ground acts as a support for segments (eg. Trees, buildings) in the image, thus a vertical image segments tends to have similar depth as its ground support. On the other hand, some images are not supported by the ground but they are connected to it, therefore these segments will have depth value larger than its nearest ground pixels.
暂无评论