In the present study, a new algorithm for automatic target detection (ATR) in synthetic aperture radar (SAR) images has been proposed. First, moving and stationary target acquisition and recognition image chips have been segmented and then passed to a number of preprocessing stages such as histogram equalisation, position and size normalisation. Second, the feature extraction based on Zernike moments (ZMs) having linear transformation invariance properties and robustness in the presence of the noise has been introduced for the first time. Third, a genetic algorithm-based feature selection and a support vector machine classifier have been presented to select the optimal feature subset of ZMs for decreasing the computational complexity. Experimental results demonstrate the efficiency of the proposed approach in target recognition of SAR imagery. The authors obtained results show that just a small amount of ZMs features is sufficient to achieve the recognition rates that rival other established methods, and so ZMs features can be regarded as a powerful discriminatory feature for automatic target recognition applications relevant to SAR imagery. Furthermore, it can be observed that the classifier performs fairly well until the signal-to-noise ratio falls beneath 5 dB for noisy images.

In this study, the authors address the problem of tracking a single target in a calibrated multi-camera surveillance system with information on its location in the first frame of each view. Recently, tracking with online multiple instance learning (OMIL) has been shown to give promising tracking results. However, it may fail in a real surveillance system because of problems arising from target orientation, scale or illumination changes. In this study, the authors show that fusing target information from multiple views can avoid these problems and lead to a more robust tracker. At each camera node, an efficient OMIL algorithm is used to model target appearance. To update the OMIL-based classifier in one view, a co-training strategy is applied to generate a representative set of training bags from all views. Bags extracted from each view hold a unique weight depending on similarity of target appearance between the current view and the view which contains the classifier that needs to be updated. In addition, target motion on a camera's image plane is modelled by a modified particle filter guided by the corresponding object two-dimensional (2D) location and fused 3D location. Experimental results demonstrate that the proposed algorithm is robust for human tracking in challenging scenes.

In this study, the authors propose a framework for stereo–motion integration for dense depth estimation. They formulate the stereo–motion depth reconstruction problem into a constrained minimisation one. A sequential unconstrained minimisation technique, namely, the augmented Lagrange multiplier (ALM) method has been implemented to address the resulting constrained optimisation problem. ALM has been chosen because of its relative insensitivity to whether the initial design points for a pseudo-objective function are feasible or not. The development of the method and results from solving the stereo–motion integration problem are presented. Although the authors work is not the only one adopting the ALMs framework in the computer vision context, to thier knowledge the presented algorithm is the first to use this mathematical framework in a context of stereo–motion integration. This study describes how the stereo–motion integration problem was cast in a mathematical context and solved using the presented ALM method. Results on benchmark and real visual input data show the validity of the approach.

Recognition of visual attributes in images allows an image's information content to be expressed textually. This has benefits for web search and image archiving, especially since visual attributes transcend language barriers. Classifiers are traditionally trained using manually segmented images, which are expensive and time consuming to produce. The authors propose a method which uses raw, noisy and unsegmented results of web image searches, to learn semantic colour terms. They use probabilistic graphical models on continuous domain, both for weakly supervised learning, and for segmentation of novel images. Experiments show that the authors methods give better results than the current state of the art in colour naming using noisy, weakly labelled training data.

*Note: Colour figures are available in the online version of this paper.

Multiple instance learning (MIL) tracker becomes recently very popular because of their great success in complex scenes. Dynamically reflecting the appearance changes of the tracked object, the appearance updating plays an important role on tracking. In the original MIL tracker, the appearance model is assumed to obey normal distribution and its updating rule consists of a simple linearly weighted sum of the original and the current target distributions in the current frame. However, this updating method is not proved theoretically. In this work, the authors deduce a novel appearance updating method by estimating the mean and the variance of the sum of two normal distributions being merged in maximum likelihood estimation. The method can be naturally extended to multivariable distributions, useful to track colour object. Experimental results on some benchmark video sequences show that the method achieve higher precision and reliability than the three state-of-art trackers.

As a challenging problem, image haze removal plays an important role in computer vision applications. The dark channel prior has been widely studied for haze removal since it is simple and effective; however, it still suffers from over-saturation, artefacts and dark-look. To resolve these problems, this study proposes a method of single image haze removal using content-adaptive dark channel and post enhancement. The main contributions of this work are as follows: first, an associative filter, which can transfer the structures of a reference image and the grey levels of a coarse image to the filtering output, is employed to compute the dark channel efficiently and effectively. Secondly, the dark channel confidence is utilised to restrict the dark channel based on the content of the image. Finally, a post enhancement method is devised to map the luminance of the restored haze-free image with the preservation of local contrast. Experimental results demonstrate that the proposed method significantly improves the visibility of the hazy image.

This study deals with the problem of similarity matching in region-based image retrieval (RBIR). A novel visual similarity measurement called adaptive region matching (ARM) has been developed. For decreasing negative influence of interference regions and important information loss simultaneously, a region importance index is constructed and semantic meaningful region (SMR) is introduced. Moreover, ARM automatically performs SMR-to-image matching or image-to-image matching. Extensive experiments on Corel-1000, Caltech-256 and University of Washington (UW) databases demonstrate the authors proposed ARM is more flexible and more efficient than the existing visual similarity measurements that were originally developed for RBIR.

This study proposes a system to estimate the depth order of regions belonging to a monocular image sequence. For each frame, the regions are ordered according to their relative depth using information from the previous and following frames. The algorithm estimates occlusions relying on a hierarchical region-based representation of the image by means of a binary tree. This representation is used to define the final depth order partition which is obtained through an energy minimisation process. Finally, to achieve a global and consistent depth ordering, a depth order graph is constructed and used to eliminate contradictory local cues. The system is evaluated and compared with the state-of-the-art figure/ground labelling systems showing very good results.