Muhammad Zaheer Aziz

Fast and Robust Generation of Feature Maps for Region-Based Visual Attention

Visual attention is one of the important phenomena in biological vision which can be followed to achieve more efficiency, intelligence, and robustness in artificial vision systems. This paper investigates a region-based approach that performs pixel clustering prior to the processes of attention in contrast to late clustering as done by contemporary methods. The foundation steps of feature map construction for the region-based attention model are proposed here. The color contrast map is generated based upon the extended findings from the color theory, the symmetry map is constructed using a novel scanning-based method, and a new algorithm is proposed to compute a size contrast map as a formal feature channel. Eccentricity and orientation are computed using the moments of obtained regions and then saliency is evaluated using the rarity criteria. The efficient design of the proposed algorithms allows incorporating five feature channels while maintaining a processing rate of multiple frames per second. Another salient advantage over the existing techniques is the reusability of the salient regions in the high-level machine vision procedures due to preservation of their shapes and precise locations. The results indicate that the proposed model has the potential to efficiently integrate the phenomenon of attention into the main stream of machine vision and systems with restricted computing resources such as mobile robots can benefit from its advantages.

Evaluation of Visual Attention Models for Robots

This paper presents a new approach for providing visual attention on robot vision systems. Compared to other approaches our method is very fast as it processes regions rather than individual pixels. The proposed method first builds a list of regions by applying a shade and shadow tolerant segmentation step. The features of these regions are computed using their convex hulls in order to simplify and accelerate the processing. Feature values are stored within the records of respective regions instead of constructing a master map of attention. Then an algorithmic method is applied for finding the focus of attention in contrast to mathematical approaches used by existing models. Experiments conducted on simulated and real image data have not only demonstrated the validity of the proposed approach but have also led to the establishment of a comprehensive robotic vision system.

Visual search in static and dynamic scenes using fine-grain top-down visual attention

Artificial visual attention is one of the key methodologies inspired from nature that can lead to robust and efficient visual search by machine vision systems. A novel approach is proposed for modeling of top-down visual attention in which separate saliency maps for the two attention pathways are suggested. The maps for the bottom-up pathway are built using unbiased rarity criteria while the top-down maps are created using fine-grain feature similarity with the search target as suggested by the literature on natural vision. The model has shown robustness and efficiency during experiments on visual search using natural and artificial visual input under static as well as dynamic scenarios.

Color Saliency and Inhibition Using Static and Dynamic Scenes in Region Based Visual Attention

This paper proposes a novel approach to construct saliency map of color contrast and an enhanced technique for inhibition of return on this map for artificial visual attention. The ability to handle dynamic scenes is also included in the model by introducing a memory based mechanism. For the process of color map construction the traditionally followed concept of double-opponent colors is extended by implementing the concepts of contrast from the subject of color theory. In context of inhibition of return, the color based inhibition is also modeled according to recent research in human vision apart from the commonly implemented spatial inhibition. The proposed methods have produced results compatible with the existing models of visual attention whereas the region-based nature of the proposed technique renders advantages of precise localization of the foci of attention, proper representation of the shapes of the attended objects, and accelerated computation time.

An attentional approach for perceptual grouping of spatially distributed patterns

A natural (human) eye can easily detect large visual patterns or objects emerging from spatially distributed discrete entities. This aspect of pattern analysis has been barely addressed in literature. We propose a biologically inspired approach derived from the concept of visual attention to associate together the distributed pieces of macro level patterns. In contrast to the usual approach practiced by the existing models of visual attention, this paper introduces a short-term excitation on the features and locations related to the current focus of attention in parallel to the spatial inhibition of return. This causes the attention system to fixate on analogous units in the scene that may formulate a meaningful global pattern. It is evident from the results of experiments that the outcome of this process can help in widening the scope of intelligent machine vision.

Fast Depth Saliency from Stereo for Region-Based Artificial Visual Attention

Depth is an important feature channel for natural vision organisms that helps in focusing attention on important locations of the viewed scene. Artificial visual attention systems require a fast estimation of depth to construct a saliency map based upon distance from the vision system. Recent studies on depth perception in biological vision indicate that disparity is computed using object detection in the brain. The proposed method exploits these studies and determines the shift that objects go through in the stereo frames using data regarding their borders. This enables efficient creation of depth saliency map for artificial visual attention. Results of the proposed model have shown success in selecting those locations from stereo scenes that are salient for human perception in terms of depth.

Towards Standardization of Evaluation Metrics and Methods for Visual Attention Models

Every field of science requires standardization of metrics and measurement methods for detecting true advancement in research. Efforts on computational models of visual attention models have increased in the recent years and now it is important to have standard measuring techniques in this area in order to avoid undue deceleration in its progress. This paper performs a review of the evaluation techniques used by different researchers in the field and brings them in an organized structure. Further methods and metrics are also proposed that would lead to more objective and quantitative evaluation of the attention models.

Classification using scale and rotation tolerant shape signatures from convex hulls

A novel real-time approach for classification or identification of objects is presented here that is suitable for visual attention system of mobile robots. The proposed method constructs convex hulls for regions found in an image using a new external scanning technique. Then a cleaning step produces refined polygons that are in turn used for extracting shape signatures for the regions. In the training phase, shape signatures are collected from test data to find a mean signature for a particular object. A small database is created for all objects related to a specific context in which classification is to be performed. In classifying phase, signatures obtained from objects found in a given image are compared with those present in the database for identification. Nearest signature from the database to a given one is taken as identity of the later. Results have proved efficiency and accuracy of this method.

Early clustering approach towards modeling of bottom-up visual attention

A region-based approach towards modelling of bottom-up visual attention is proposed with an objective to accelerate the internal processes of attention and make its output usable by the high-level vision procedures to facilitate intelligent decision making during pattern analysis and vision-based learning. A memory-based inhibition of return is introduced in order to handle the dynamic scenarios of mobile vision systems. Performance of the proposed model is evaluated on different categories of visual input and compared with human attention response and other existing models of attention. Results show success of the proposed model and its advantages over existing techniques in certain aspects.