| 1. |
- Ahlberg, Jörgen, 1971-, et al.
(författare)
-
An information measure of sensor performance and its relation to the ROC curve
- 2010
-
Ingår i: Proc. SPIE 7695, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI. - : SPIE - International Society for Optical Engineering. ; , s. Art.nr. 7695-72-
-
Konferensbidrag (refereegranskat)abstract
- The ROC curve is the most frequently used performance measure for detection methods and the underlying sensor configuration. Common problems are that the ROC curve does not present a single number that can be compared to other systems and that no discrimination between sensor performance and algorithm performance is done. To address the first problem, a number of measures are used in practice, like detection rate at a specific false alarm rate, or area-under-curve. For the second problem, we proposed in a previous paper1 an information theoretic method for measuring sensor performance. We now relate the method to the ROC curve, show that it is equivalent to selecting a certain point on the ROC curve, and that this point is easily determined. Our scope is hyperspectral data, studying discrimination between single pixels.
|
|
| 2. |
- Felsberg, Michael, 1974-, et al.
(författare)
-
Online Learning of Correspondences between Images
- 2013
-
Ingår i: IEEE Transactions on Pattern Analysis and Machine Intelligence. - : IEEE Computer Society. - 0162-8828 .- 1939-3539. ; 35:1, s. 118-129
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a point in either view, the considered problem is to determine the corresponding location in the other view. The geometry and distortions of the projections are unknown as is the shape of the surface. Given several pairs of point-sets but no access to the 3D scene, correspondence mappings can be found by excessive global optimization or by the fundamental matrix if a perspective projective model is assumed. However, an iterative solution on sequences of point-set pairs with general imaging geometry is preferable. We derive such a method that optimizes the mapping based on Neyman's chi-square divergence between the densities representing the uncertainties of the estimated and the actual locations. The densities are represented as channel vectors computed with a basis function approach. The mapping between these vectors is updated with each new pair of images such that fast convergence and high accuracy are achieved. The resulting algorithm runs in real-time and is superior to state-of-the-art methods in terms of convergence and accuracy in a number of experiments.
|
|
| 3. |
- Larsson, Jan-Åke, et al.
(författare)
-
Modelling cell lineage using a meta-Boolean tree model with a relation to gene regulatory networks
- 2011
-
Ingår i: Journal of Theoretical Biology. - Amsterdam : Elsevier. - 0022-5193 .- 1095-8541. ; 268:1, s. 62-76
-
Tidskriftsartikel (refereegranskat)abstract
- A cell lineage is the ancestral relationship between a group of cells that originate from a single founder cell. For example, in the embryo of the nematode Caenorhabditis elegans an invariant cell lineage has been traced, and with this information at hand it is possible to theoretically model the emergence of different cell types in the lineage, starting from the single fertilized egg. In this report we outline a modelling technique for cell lineage trees, which can be used for the C. elegans embryonic cell lineage but also extended to other lineages. The model takes into account both cell-intrinsic (transcription factor-based) and -extrinsic (extracellular) factors as well as synergies within and between these two types of factors. The model can faithfully recapitulate the entire C. elegans cell lineage, but is also general, i.e., it can be applied to describe any cell lineage. We show that synergy between factors, as well as the use of extrinsic factors, drastically reduce the number of regulatory factors needed for recapitulating the lineage. The model gives indications regarding co-variation of factors, number of involved genes and where in the cell lineage tree that asymmetry might be controlled by external influence. Furthermore, the model is able to emulate other (Boolean, discrete and differential-equation-based) models. As an example, we show that the model can be translated to the language of a previous linear sigmoid-limited concentration-based model (Geard and Wiles, 2005). This means that this latter model also can exhibit synergy effects, and also that the cumbersome iterative technique for parameter estimation previously used is no longer needed. In conclusion, the proposed model is general and simple to use, can be mapped onto other models to extend and simplify their use, and can also be used to indicate where synergy and external influence would reduce the complexity of the regulatory process.
|
|
| 4. |
- Linderhed, Anna, et al.
(författare)
-
Compression of Hyperspectral data for Automated Analysis
- 2009
-
Ingår i: SPIE Europe Remote Sensing 2009. - : SPIE. - 9780819477828
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- State of the art and coming hyperspectral optical sensors generate large amounts of data and automatic analysis is necessary. One example is Automatic Target Recognition (ATR), frequently used in military applications and a coming technique for civilian surveillance applications. When sensors communicate in networks, the capacity of the communication channel defines the limit of data transferred without compression. Automated analysis may have different demands on data quality than a human observer, and thus standard compression methods may not be optimal. This paper presents results from testing how the performance of detection methods are affected by compressing input data with COTS coders. A standard video coder has been used to compress hyperspectral data. A video is a sequence of still images, a hybrid video coder use the correlation in time by doing block based motion compensated prediction between images. In principle only the differences are transmitted. This method of coding can be used on hyperspectral data if we consider one of the three dimensions as the time axis. Spectral anomaly detection is used as detection method on mine data. This method finds every pixel in the image that is abnormal, an anomaly compared to the surroundings. The purpose of anomaly detection is to identify objects (samples, pixels) that differ significantly from the background, without any a priori explicit knowledge about the signature of the sought-after targets. Thus the role of the anomaly detector is to identify “hot spots” on which subsequent analysis can be performed. We have used data from Imspec, a hyperspectral sensor. The hyperspectral image, or the spectral cube, consists of consecutive frames of spatial-spectral images. Each pixel contains a spectrum with 240 measure points. Hyperspectral sensor data was coded with hybrid coding using a variant of MPEG2. Only I- and P- frames was used. Every 10th frame was coded as P frame. 14 hyperspectral images was coded in 3 different directions using x, y, or z direction as time. 4 different quantization steps were used. Coding was done with and without initial quantization of data to 8 bbp. Results are presented from applying spectral anomaly detection on the coded data set.
|
|
| 5. |
- Lundmark, A., et al.
(författare)
-
Hierarchical subsampling giving fractal regions
- 2001
-
Ingår i: IEEE Transactions on Image Processing. - : Institute of Electrical and Electronics Engineers (IEEE). - 1057-7149 .- 1941-0042. ; 10:1, s. 167-173
-
Tidskriftsartikel (refereegranskat)abstract
- Recursive image subsampling which yields support areas approaching fractals is described and analyzed using iterated function systems. The subsampling scheme is suitable in, e.g., hierarchical image processing and image coding schemes. For hexagonally sampled images a hierarchical subsampling structure is given which yields hexagon-like regions with fractal borders.
|
|
| 6. |
- Ringaby, Erik, et al.
(författare)
-
Co-aligning Aerial Hyperspectral Push-broom Strips for Change Detection
- 2010
-
Ingår i: Proc. SPIE 7835, Electro-Optical Remote Sensing, Photonic Technologies, and Applications IV. - : SPIE - International Society for Optical Engineering. - 9780819483539 ; , s. Art.nr. 7835B-36-
-
Konferensbidrag (refereegranskat)abstract
- We have performed a field trial with an airborne push-broom hyperspectral sensor, making several flights over the same area and with known changes (e.g., moved vehicles) between the flights. Each flight results in a sequence of scan lines forming an image strip, and in order to detect changes between two flights, the two resulting image strips must be geometrically aligned and radiometrically corrected. The focus of this paper is the geometrical alignment, and we propose an image- and gyro-based method for geometric co-alignment (registration) of two image strips. The method is particularly useful when the sensor is not stabilized, thus reducing the need for expensive mechanical stabilization. The method works in several steps, including gyro-based rectification, global alignment using SIFT matching, and a local alignment using KLT tracking. Experimental results are shown but not quantified, as ground truth is, by the nature of the trial, lacking.
|
|
| 7. |
- Ringaby, Erik, et al.
(författare)
-
Co-alignmnent of Aerial Push-broom Strips using Trajectory Smoothness Constraints
- 2010
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- We study the problem of registering a sequence of scan lines (a strip) from an airborne push-broom imager to another sequence partly covering the same area. Such a registration has to compensate for deformations caused by attitude and speed changes in the aircraft. The registration is challenging, as both strips contain such deformations. Our algorithm estimates the 3D rotation of the camera for each scan line, by parametrising it as a linear spline with a number of knots evenly distributed in one of the strips. The rotations are estimated from correspondences between strips of the same area. Once the rotations are known, they can be compensated for, and each line of pixels can be transformed such that ground trace of the two strips are registered with respect to each other.
|
|
| 8. |
- Robinson, Yohan, 1977, et al.
(författare)
-
AI och framtidens försvarsmedicin
- 2020
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Medicinskt legitimerad personal är, och kommer med stor sannolikhet fortsattatt vara, en knapp resurs inom Försvarsmaktens sjukvårdsorganisation. I denna rapport ges en översikt över pågående och planerade ansatser baserade påartificiell intelligens (AI) inom akutsjukvård med särskild tonvikt på omhändertagandet av traumapatienter, där lösningarna skulle kunna bidra till att Försvarsmakten kan bibehålla sin sjukvårdskapacitet i kritiska lägen. Rapporten är ett resultat av samarbetet mellan FM, FOI, FMV, FHS och KI, och vänder sig i första hand till Försvarsmaktens strategiska ledning.Användningen av AI-teknik i framtida beslutsstöd kan skapa nya möjligheter till avlastning av personal och resurseffektivisering. Tekniken ger möjligheter att i realtid samla in, bearbeta och analysera stora mängder blandadinformation om förbands hälsoläge och fysiska stridsvärde. Bedömning av skadade kan t.ex. göras av triagedrönare och den efterföljande evakueringen kanunderlättas av intelligenta autonoma plattformar. Införandet av AI-system ställer dock vårdgivaren inför svåra etiska och medikolegala överväganden.Försvarsmedicin har en central roll i Försvarsmaktens krigföringsförmåga och för samhällets uthållighet. För att nyttja hela AI-teknikens framfart till Försvarsmaktens nytta måste dess innebörd och konsekvens för försvarsmedicinen förstås. Därför rekommenderar denna studie att Försvarsmaktens framtida satsningar inom AI och autonomi inkluderar den försvarsmedicinska teknikutveckling som är beskriven i denna rapport.
|
|
| 9. |
- Wadströmer, Niclas, et al.
(författare)
-
A new hyperspectral dataset and some challenges
- 2010
-
Ingår i: Proc. SPIE 7695, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XVI. - : SPIE - International Society for Optical Engineering. ; , s. Art.nr. 7695-22-
-
Konferensbidrag (refereegranskat)abstract
- We present a new hyperspectral data set that FOI will keep publicly available. The hyperspectral data set was collected in an airborne measurement over the countryside. The spectral resolution was about 10 nm which allowed registrations in 60 spectral bands in the visual and near infrared range (390-960 nm). Objects with various signature properties were placed in three areas: the edge of a wood, an open field and a rough open terrain. Several overflights were performed over the areas. Between the overflights some of the objects were moved, representing different scenarios. Our interest is primarily in anomaly detection of man-made objects placed in nature where no such objects are expected. The objects in the trial were military and civilian vehicles, boards of different size and a camouflage net. The size of the boards range from multipixel to subpixel size. Due to wind and cloud conditions the stability and the flight height of the airplane vary between the overflights, which makes the analysis extra challenging.
|
|
| 10. |
- Wadströmer, Niclas, 1964-
(författare)
-
Coding of fractal binary images with contractive set mappings composed of affine transformations
- 2001
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- There are several efficient algorithms by which one can generate approximations of binaryattractors induced from contractive set mappings which are composed of affine mappings.There are also complex attractors resembling natural-looking images where the attractors areinduced from only a few affine mappings which can be represented with a few bits. Thus it ismore efficient to store and transmit the affine mappings than the image itself. For set mappingsto be useful for image coding, it is also necessary to have an algorithm which can finda set mapping that defines an attractor image which is close to the given image.In the present thesis, we will describe and analyse two algorithms for this problem, usuallycalled an inverse problem. One algorithm is based on a full search through the parameterspace of the affine mappings. The other is based on a gradient search in the parameter spaceof the affine mappings where the gradient is obtained by the Kantorovich metric. Wedescribe some variants of these attractor coding methods and compare them with non-fractalcoding methods for binary images.We have found that the gradient search algorithm can be used to improve a good initialsolution. A disadvantage of this algorithm is that the number of mappings must be given.Thus, it is less suitable for encoding images. The full search algorithm with its variants canbe used to encode binary images. It also has an inverse property regarding the number of affinemappings, which means that if the given image was generated by a set mapping, thenunder some conditions the algorithm can recover the mappings that generated the givenimage.The Kantorovich distance has a high computational complexity and takes considerabletime to compute even for small images. We have implemented two algorithms with somevariants for the computation of the distance and compared them. We found that they can beused to compute the distance between images.The underlying notion behind the attractor-based techniques described here is that usinga larger parameter space for the affine mappings in the spatial domain should give a betterimage coding in a rate distortion sense. We have also made some experiments on grey scaleimages along this line of thought.
|
|
