IET Computer Vision
Volume 11, Issue 5, August 2017
Volumes & issues:
Volume 11, Issue 5
August 2017
-
- Author(s): Guo Niu and Zhengming Ma
- Source: IET Computer Vision, Volume 11, Issue 5, p. 331 –341
- DOI: 10.1049/iet-cvi.2015.0441
- Type: Article
- + Show details - Hide details
-
p.
331
–341
(11)
In manifold learning, alignment is performed with the objective of deriving the global low-dimensional coordinates of input data from their local coordinates. In virtually all alignment processes, the relation between the local and global coordinates is designed intuitively, without mathematical deduction and detailed analysis. In this study, the authors propose a local non-linear alignment manifold learning algorithm (LNA) for non-linear dimensionality reduction, based on the concept of local pullback and the mathematical characteristics of a manifold. According to mathematical manifold theory, a function defined on a manifold cannot be differentiated directly on the manifold directly. Instead, it has to be pulled back to Euclidean space with the help of local homeomorphism between the manifold and Euclidean space, where it is then differentiated. In the authors’ proposed algorithm, the component functions of global homeomorphism are regarded as the functions defined on the manifold and pulled back to the Euclidean space. Then, Taylor expansion is utilised up to the second order to establish the relation between the global and local coordinates. The objective function in LNA is based on the alignment error and can be solved with an eigenvalue problem. The experimental results conducted on various datasets verify the validity of the authors’ method.
- Author(s): Qi Xia ; Naiming Qi ; Dong Ye ; Yubo Guo ; Tianye Wang
- Source: IET Computer Vision, Volume 11, Issue 5, p. 342 –349
- DOI: 10.1049/iet-cvi.2016.0145
- Type: Article
- + Show details - Hide details
-
p.
342
–349
(8)
Compared with fixed focus cameras, zoom cameras can be used to provide more precise measurements in space tasks. However, the calibration of zoom cameras in this case is a difficulty, as it is not convenient to set up a calibration device on the spacecraft. To solve this problem, the authors present a real-time zoom camera calibration algorithm based on fixed stars. With the star images captured by the zoom camera, they firstly use a star identification method to recognise the identity of stars. By means a series of coordinate transformation, they are able to build the one-to-one mapping between the pixel coordinates and epoch celestial coordinates of the stars. Finally, the internal and external parameters of the zoom camera are obtained based on the thick lens zoom camera model. Simulation and experiment results show that the internal parameters of zoom cameras are rarely affected by the noise of latitude, longitude and time. Furthermore, the calibration precision and robustness of focal length reaches a satisfactory level.
- Author(s): Muhammad Bilal
- Source: IET Computer Vision, Volume 11, Issue 5, p. 350 –357
- DOI: 10.1049/iet-cvi.2016.0403
- Type: Article
- + Show details - Hide details
-
p.
350
–357
(8)
Histogram intersection kernel support vector machine (SVM) is accepted as a better discriminator than its linear counterpart when used for pedestrian detection in images and video frames. Its computational complexity has, however, limited its use in practical real-time detectors. To circumvent this problem, prior work proposed a low complexity detection framework based on integer-only histograms of oriented gradient features which allow a look-up table-based implementation of kernel SVM leading to further simplification without compromising detection performance. This work describes several important enhancements made in the original framework related to the pre-processing steps, feature calculation and training setup. Resultantly, the augmented framework, proposed in this study, stands out in terms of the detection accuracy and computational complexity compared to contemporary detectors. The best detector described in this study achieves 8 and 2% lesser miss rates (MRs) on ETH and INRIA pedestrian datasets, respectively, compared to the well-known boosting cascades-based aggregate channel feature detector despite avoiding complex floating point operations. Moreover, the proposed detector performs exceptionally better in scenarios where less than 10−2 false positives per image are desired as demonstrated through the MR versus false positive curves.
- Author(s): Wei-Yu Lee ; Chi-Ying Li ; Jia-Yush Yen
- Source: IET Computer Vision, Volume 11, Issue 5, p. 358 –367
- DOI: 10.1049/iet-cvi.2016.0151
- Type: Article
- + Show details - Hide details
-
p.
358
–367
(10)
This study addresses the problem of recovering the three-dimensional depth data from the images taken by a light-field camera. Unlike the conventional approach to extract the depth information from the spatial and the angular gradients in the epipolar plane images (EPIs), this study proposes to check the similarity between the pixels for the estimation of EPI slopes and use a wavelet transformation augmented multi-scale analysis to perform smart segmentations. The Markov random field is then applied for surface reconstruction. The proposed algorithm offers significant improvement to the depth estimation, especially for noise contaminated images. Application of the method on the light-field images and on synthesised data show that the proposed method is robust against the noise and achieves better estimation results compared with the available literature.
- Author(s): Yawar Rehman ; Irfan Riaz ; Xue Fan ; Hyunchul Shin
- Source: IET Computer Vision, Volume 11, Issue 5, p. 368 –377
- DOI: 10.1049/iet-cvi.2016.0303
- Type: Article
- + Show details - Hide details
-
p.
368
–377
(10)
In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d-patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D-patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant-detections around a true-positive is different from that around a false-positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true-positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well-known methods (under partially occluded settings), on KTSD dataset.
Local non-linear alignment for non-linear dimensionality reduction
Real-time calibration of space zoom cameras based on fixed stars
Algorithmic optimisation of histogram intersection kernel support vector machine-based pedestrian detection using low complexity features
Integrating wavelet transformation with Markov random field analysis for the depth estimation of light-field images
D-patches: effective traffic sign detection with occlusion handling
Most viewed content
Most cited content for this Journal
-
Brain tumour classification using two-tier classifier with adaptive segmentation technique
- Author(s): V. Anitha and S. Murugavalli
- Type: Article
-
Driving posture recognition by convolutional neural networks
- Author(s): Chao Yan ; Frans Coenen ; Bailing Zhang
- Type: Article
-
Local directional mask maximum edge patterns for image retrieval and face recognition
- Author(s): Santosh Kumar Vipparthi ; Subrahmanyam Murala ; Anil Balaji Gonde ; Q.M. Jonathan Wu
- Type: Article
-
Fast and accurate algorithm for eye localisation for gaze tracking in low-resolution images
- Author(s): Anjith George and Aurobinda Routray
- Type: Article
-
‘Owl’ and ‘Lizard’: patterns of head pose and eye pose in driver gaze classification
- Author(s): Lex Fridman ; Joonbum Lee ; Bryan Reimer ; Trent Victor
- Type: Article