In this paper we present a new method for object tracking initialization using background subtraction. We propose an effective scheme for updating a background model adaptively in dynamic scenes. Unlike the traditional methods that use the same “learning rate” for the entire frame or sequence, our method assigns a learning rate for each pixel according to two parameters. The first parameter dep...

The Kepler mission monitors > 100, 000 stellar targets using 42 2200×1024 pixel CCDs. Bandwidth constraints prevent the downlink of all 96 million pixels per 30-minute cadence, so the Kepler spacecraft downlinks a specified collection of pixels for each target. These pixels are selected by considering the object brightness, background and the signal-to-noise of each pixel, and are optimized to ...

The availability of high-resolution remote sensing (HRRS) data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN) can be applied to multispectral orthoimagery and a digital surface model (DSM) of a small city for a full, fast and accurate per-pixel cla...

We describe a nonparametric pixel appearance probability model to represent local image information. It allows an optimal image analysis framework that integrates lowand high-level stages to substantially improve overall accuracy of object reconstruction. In this framework, feature detection would be an overall consequence rather than an intermediate result. The pixel appearance probability mod...

The successful launch of the Chinese high spatial resolution hyperspectral satellite TianGong-1 (TG-1) opens up new possibilities for applications of remotely-sensed satellite imagery. One of the main goals of the TG-1 mission is to provide observations of surface attributes at local and landscape spatial scales to map urban land cover accurately using the hyperspectral technique. This study at...

Large receptive field and dense prediction are both important for achieving high accuracy in pixel labeling tasks such as semantic segmentation. These two properties, however, contradict with each other. A pooling layer (with stride 2) quadruples the receptive field size but reduces the number of predictions to 25%. Some existing methods lead to dense predictions using computations that are not...

Image segmentation using graph cuts have become very popular in the last years. These methods are computationally expensive, even with hard constraints (seed pixels). We present a solution that runs in time proportional to the number of pixels. Our method computes an ordered region growing from a set of seeds inside the object, where the propagation order of each pixel is proportional to the co...

Speed and accuracy are important factors when dealing with time-constraint events for disaster, risk, and crisis-management support. Object-based image analysis can be a time consuming task in extracting information from large images because most of the segmentation algorithms use the pixel-grid for the initial object representation. It would be more natural and efficient to work with perceptua...

The authors analyze in this paper whether the introduction of the uncertainty associated to the classification of surface elements in the classification of landscape units can improve the results accuracy. To this end, a hybrid classification method is developed, incorporating uncertainty information in the automatic classification of very high spatial resolution multispectral satellite images ...

true and HYPR LR profiles Figure 4. Artery waveforms of HYPR LR at edge pixel (left) and at center pixel (right). Figure 2. True waveforms of 3 objects (left) and HYPR LR images (right) reconstructed with kernels of widths: 3, 5, 12 at time point 5 (indicated by a black dashed line on the left. Figure 1. 1D object model and convolution kernel with wa shown as red area, wv as blue area Analytica...