| 1. |
- Li, Bo, 1982-, et al.
(author)
-
Distinctive curve features
- 2016
-
In: Electronics Letters. - : John Wiley & Sons. - 0013-5194 .- 1350-911X. ; 52:3, s. 197-198
-
Journal article (peer-reviewed)abstract
- Curves and lines are geometrical, abstract features of an image. Whereas interest points are more limited, curves and lines provide much more information of the image structure. However, the research done in curve and line detection is very fragmented. The concept of scale space is not yet fused very well into curve and line detection. Keypoint (e.g. SIFT, SURF, ORB) is a successful concept which represent features (e.g. blob, corner etc.) in scale space. Stimulated by the keypoint concept, a method which extracts distinctive curves (DICU) in scale space, including lines as a special form of curve features is proposed. A curve feature can be represented by three keypoints (two end points, and one middle point). A good way to test the quality of detected curves is to analyse the repeatability under various image transformations. DICU using the standard Oxford benchmark is evaluated. The overlap error is calculated by averaging the overlap error of three keypoints on the curve. Experiment results show that DICU achieves good repeatability comparing with other state-of-the-art methods. To match curve features, a relatively uncomplicated way is to combine local descriptors of three keypoints on each curve.
|
|
| 2. |
- Mårell-Olsson, Eva, 1966-, et al.
(author)
-
Opportunities and challenges of using socially intelligent agents : increasing interaction and school participation for children suffering from a long-term illness
- 2021
-
In: The international journal of information and learning technology. - : Emerald Group Publishing Limited. - 2056-4880 .- 2056-4899. ; 38:4, s. 393-411
-
Journal article (peer-reviewed)abstract
- Purpose – Children suffering from cancer or cardiovascular disease, who need extended periods of treatment in hospitals, are subjected to multiple hardships apart from the physical implications, for example, experienced isolation and disrupted social and academic development. This has negative effects long after the child’s recovery from the illness. The purpose of this paper is to examine the non-medical needs of children suffering from a long-term illness, as well as research the field of artificial intelligence (AI) – more specifically, the use of socially intelligent agents (SIAs) – in order to study how technology can enhance children’s interaction, participation and quality of life. Design/methodology/approach – Interviews were performed with experts in three fields: housing manager for hospitalized children, a professor in computing science and researcher in AI, and an engineer and developer at a tech company.Findings – It is important for children to be able to take control of the narrative by using an SIA to support the documentation of their period of illness, for example. This could serve as a way of processing emotions, documenting educational development or keeping a reference for later in life. The findings also show that the societal benefits of AI include automating mundane tasks and recognizing patterns. Originality/value – The originality of this study concerns the holistic approach of increasing the knowledge and understanding of these children’s specific needs and challenges, particularly regarding their participation and interaction with teachers and friends at school, using an SIA.
|
|
| 3. |
- Söderström, Ulrik, 1978-, et al.
(author)
-
Asymmetrical principal component analysis for video coding
- 2008
-
In: Electronics Letters. - : Institution of Engineering and Technology (IET). - 0013-5194 .- 1350-911X. ; 44:4, s. 276-277
-
Journal article (peer-reviewed)abstract
- Principal component analysis (PCA) can be used to encode video sequences at extremely low bit rates, e.g. 34.6 dB (PSNR) at 4.2 kbit/s. The same eigenvectors are used for encoding and decoding for this coding. Introduced is a coding scheme where eigenvectors for only part of the video frames are used for encoding but the eigenvectors for the entire frame are used for decoding. This is called asymmetric PCA coding. This reduces the complexity of encoding by ap5 times and at the same time increases the reconstruction quality for the facial part of the video with 0.4 dB (PSNR).
|
|
