Video indexing by spatial representation

Recent approaches to video indexing and retrieval are either pixel-oriented or object-oriented. While the former approaches focus on motion and changes thereto, the latter focus on spatial relations among objects in the scene. In this paper, a spatial knowledge representation technique combining both approaches is proposed. This representation supplements the spatial knowledge of visual objects with information about their pixel positions in the video frame. It provides a practical way to construct video indices, enabling searching for and retrieval of video sequences that contain motion as well as sparsely disjoint objects

Dynamic threshold determination by local and global edge evaluation

In this paper we consider two methods for automatically determining values for thresholding edge maps. Rather than use statistical methods they are based on the figural properties of the edges. Two approaches are taken. We investigate applying an edge evaluation measure based on edge continuity and edge thinness to determine the threshold on edge strength. However, the technique is not valid when applied to edge detector outputs that are one-pixel wide. In this case, we use a measure based on work by Lowe for assessing edges. This measure is based on length and average strength of complete linked edge lists.

An empirical analysis of colour image segmentation using fuzzy c-means clustering

In this paper, an empirical analysis to examine the effects of image segmentation with different colour models using the fuzzy c-means (FCM) clustering algorithm is conducted. A qualitative evaluation method based on human perceptual judgement is used. Two sets of complex images, i.e., outdoor scenes and satellite imagery, are used for demonstration. These images are employed to examine the characteristics of image segmentation using FCM with eight different colour models. The results obtained from the experimental study are compared and analysed. It is found that the CIELAB colour model yields the best outcomes in colour image segmentation with FCM.

Performance evaluation of multi-frame super-resolution algorithms

Multi-frame super-resolution algorithms aim to increase spatial resolution by fusing information from several low-resolution perspectives of a scene. While a wide array of super-resolution algorithms now exist, the comparative capability of these techniques in practical scenarios has not been adequately explored. In addition, a standard quantitative method for assessing the relative merit of super-resolution algorithms is required. This paper presents a comprehensive practical comparison of existing super-resolution techniques using a shared platform and 4 common greyscale reference images. In total, 13 different super-resolution algorithms are evaluated, and as accurate alignment is critical to the super-resolution process, 6 registration algorithms are also included in the analysis. Pixel-based visual information fidelity (VIFP) is selected from the 12 image quality metrics reviewed as the measure most suited to the appraisal of super-resolved images. Experimental results show that Bayesian super-resolution methods utilizing the simultaneous autoregressive (SAR) prior produce the highest quality images when combined with generalized stochastic Lucas-Kanade optical flow registration.

Riviere

'Riviere' (2012) was created in response to the painting 'Man in a Green Coat' (1998) by Kylie Wren, held in the Deakin University Art Collection. This artistic response was produced for the Face to Face Exhibition held at Deakin University Art Gallery.

Quantitative experimental comparison of single-beam, sidescan, and multibeam benthic habitat maps

Map comparison is a relatively uncommon practice in acoustic seabed classification to date, contrary to the field of land remote sensing, where it has been developed extensively over recent decades. The aim here is to illustrate the benefits of map comparison in the underwater realm with a case study of three maps independently describing the seabed habitats of the Te Matuku Marine Reserve (Hauraki Gulf, New Zealand). The maps are obtained from a QTC View classification of a single-beam echosounder (SBES) dataset, manual segmentation of a sidescan sonar (SSS) mosaic, and automatic classification of a backscatter dataset from a multibeam echosounder (MBES). The maps are compared using pixel-to-pixel similarity measures derived from the literature in land remote sensing. All measures agree in presenting the MBES and SSS maps as the most similar, and the SBES and SSS maps as the least similar. The results are discussed with reference to the potential of MBES backscatter as an alternative to SSS mosaic for imagery segmentation and to the potential of joint SBES–SSS survey for improved habitat mapping. Other applications of map-similarity measures in acoustic classification of the seabed are suggested.

A modified moment-based image watermarking method robust to cropping attack

Developing a watermarking method that is robust to cropping attack is a challenging task in image watermarking. The moment-based watermarking schemes show good robustness to common signal processing attacks and some geometric attacks but are sensitive to cropping attack. In this paper, we modify the moment-based approach to deal with cropping attack. Firstly, we find the probability density function (pdf) of the pixel value distribution from the original image. Secondly, we reshape and normalize the pdf of the pixel value distribution (PPVD) to form a two dimensional image. Then, the moment invariants are calculated from the PPVD image. Since PPVD is insensitive to cropping, the proposed method is robust to cropping attack. Besides, it also has high robustness against other common attacks. Experimental results demonstrate the effectiveness of the proposed method.

Image reduction operators based on non-monotonic averaging functions

Image reduction is a crucial task in image processing, underpinning many practical applications. This work proposes novel image reduction operators based on non-monotonic averaging aggregation functions. The technique of penalty function minimisation is used to derive a novel mode-like estimator capable of identifying the most appropriate pixel value for representing a subset of the original image. Performance of this aggregation function and several traditional robust estimators of location are objectively assessed by applying image reduction within a facial recognition task. The FERET evaluation protocol is applied to confirm that these non-monotonic functions are able to sustain task performance compared to recognition using nonreduced images, as well as significantly improve performance on query images corrupted by noise. These results extend the state of the art in image reduction based on aggregation functions and provide a basis for efficiency and accuracy improvements in practical computer vision applications.

Redesigning learning through social media, Web 2.0 and F2F teaching : an action research study

The focus of this research was to explore how social and participatory media could be used to enhance the face-to-face teaching and learning process. Action research was used to design learning that valued the students’ own experiences and to encourage students to create, connect and form a partnership in the learning process: hence supporting students' strengths and abilities. To monitor and participate in the use of social media required an increase in the teacher's work time. As a partial counter-balance, it was found that the teacher/researcher successfully reduced her time spent on correction by implementing peer and self-assessment and by making more effective use of classroom observations. This led to a valuable triangulation of assessment data. Reviewing many of the screen clips collected in this study, one can see the diversity of roles and activities in which the students were engaged, and their development over time through the action research cycle. Combining Web 2.0, face-to-face teaching and social media, where students made online friends and used pseudonyms, provided students with more choices and flexibility when working, communicating and learning. This research may help curriculum developers interweave new technologies, new literacies and multimodal learning methods into day-to-day learning programs. The developed methods of learning and designs should also be transferable to other educational learning environments.

Histogram shape-based robust image watermarking method

Developing a watermarking method that is robust to cropping attack and random bending attacks (RBAs) is a challenging task in image watermarking. In this paper, we propose a histogram-based image watermarking method to tackle with both cropping attack and RBAs. In this method first the gray levels are divided into groups. Secondly the groups for watermark embedding are selected according to the number of pixels in them, which makes this method fully based on the histogram shape of the original image and adaptive to different images. Then the watermark bits are embedded by modifying the histogram of the selected groups. Since histogram shape is insensitive to cropping and independent from pixel positions, the proposed method is robust to cropping attack and RBAs. Besides, it also has high robustness against other common attacks. Experimental results demonstrate the effectiveness of the proposed method. © 2014 IEEE.

Efficacy comparison of clustering systems for limb detection

This paper presents a comparison of applying different clustering algorithms on a point cloud constructed from the depth maps captured by a RGBD camera such as Microsoft Kinect. The depth sensor is capable of returning images, where each pixel represents the distance to its corresponding point not the RGB data. This is considered as the real novelty of the RGBD camera in computer vision compared to the common video-based and stereo-based products. Depth sensors captures depth data without using markers, 2D to 3D-transition or determining feature points. The captured depth map then cluster the 3D depth points into different clusters to determine the different limbs of the human-body. The 3D points clustering is achieved by different clustering techniques. Our Experiments show good performance and results in using clustering to determine different human-body limbs.

Learning complementary saliency priors for foreground object segmentation in complex scenes

Object segmentation is widely recognized as one of the most challenging problems in computer vision. One major problem of existing methods is that most of them are vulnerable to the cluttered background. Moreover, human intervention is often required to specify foreground/background priors, which restricts the usage of object segmentation in real-world scenario. To address these problems, we propose a novel approach to learn complementary saliency priors for foreground object segmentation in complex scenes. Different from existing saliency-based segmentation approaches, we propose to learn two complementary saliency maps that reveal the most reliable foreground and background regions. Given such priors, foreground object segmentation is formulated as a binary pixel labelling problem that can be efficiently solved using graph cuts. As such, the confident saliency priors can be utilized to extract the most salient objects and reduce the distraction of cluttered background. Extensive experiments show that our approach outperforms 16 state-of-the-art methods remarkably on three public image benchmarks.

Peripheral injected cholecystokinin-8S modulates the concentration of serotonin in nerve fibers of the rat brainstem

Serotonin and cholecystokinin (CCK) play a role in the short-term inhibition of food intake. It is known that peripheral injection of CCK increases c-Fos-immunoreactivity (Fos-IR) in the nucleus of the solitary tract (NTS) in rats, and injection of the serotonin antagonist ondansetron decreases the number of c-Fos-IR cells in the NTS. This supports the idea of serotonin contributing to the effects of CCK. The aim of the present study was to elucidate whether peripherally injected CCK-8S modulates the concentration of serotonin in brain feeding-regulatory nuclei. Ad libitum fed male Sprague-Dawley rats received 5.2 and 8.7 nmol/kg CCK-8S (n = 3/group) or 0.15 M NaCl (n = 3-5/group) injected intraperitoneally (ip). The number of c-Fos-IR neurons, and the fluorescence intensity of serotonin in nerve fibers were assessed in the paraventricular nucleus (PVN), arcuate nucleus (ARC), NTS and dorsal motor nucleus of the vagus (DMV). CCK-8S increased the number of c-Fos-ir neurons in the NTS (mean ± SEM: 72 ± 4, and 112 ± 5 neurons/section, respectively) compared to vehicle-treated rats (7 ± 2 neurons/section, P < 0.05), but did not modulate c-Fos expression in the DMV or ARC. Additionally, CCK-8S dose-dependently increased the number of c-Fos-positive neurons in the PVN (218 ± 15 and 128 ± 14, respectively vs. 19 ± 5, P < 0.05). In the NTS and DMV we observed a decrease of serotonin-immunoreactivity 90 min after injection of CCK-8S (46 ± 2 and 49 ± 8 pixel/section, respectively) compared to vehicle (81 ± 8 pixel/section, P < 0.05). No changes of serotonin-immunoreactivity were observed in the PVN and ARC. Our results suggest that serotonin is involved in the mediation of CCK-8's effects in the brainstem. © 2014 Elsevier Inc.