Integrating Object Affordances with Artificial Visual Attention
نویسندگان
چکیده
Affordances, as for example grasping possibilities, are known to play a role in the guidance of human attention but have not been considered in artificial attention systems so far. Extending our earlier work, we investigate the combination of affordance estimation and visual saliency in an artificial visual attention model. Different models based on saliency, affordance estimation, or their combination are suggested and evaluated via their predictions for a change detection task with human observers. Furthermore, we discuss the potential of Growing Neural Gases as a framework for consistently integrating bottom-up saliency, affordance-based and top-down attention mechanisms.
منابع مشابه
Learning Object Affordances for Tool Use and Problem Solving in Cognitive Robots
One of the hallmarks of human intelligence is the ability of predicting the consequences of actions and efficiently plan behaviors based on such predictions. This ability is supported by internal models that human babies acquire incrementally during development through sensorimotor experience: i.e. by interacting with objects in the environment while being exposed to sensori perception. An eleg...
متن کاملThe Role of Motor Affordances
Motor affordances are important for object knowledge. Semantic tasks on visual objects often show interactions with motor actions. Prior neuro-imaging studies suggested that motor affordances also play a role in visual working memory for objects. When participants remembered manipulable objects (e.g., hammer) greater premotor cortex activation was observed than when they remembered non-manipula...
متن کاملTowards a neural network model of the visual short-term memory
In this paper a neural network model of visual short-term memory (VSTM) is presented. The model aims at integrating a winners-take-all type of neural network (Usher & Cohen, 1999) with Bundesen’s (1990) well-established mathematical theory of visual attention. We evaluate the model’s ability to fit experimental data from a classical whole and partial report study. Previous statistic models have...
متن کاملAffordance Prediction via Learned Object Attributes
We present a novel method for learning and predicting the affordances of an object based on its physical and visual attributes. Affordance prediction is a key task in autonomous robot learning, as it allows a robot to reason about the actions it can perform in order to accomplish its goals. Previous approaches to affordance prediction have either learned direct mappings from visual features to ...
متن کاملAffordance based Part Recognition for Grasping and Manipulation
Affordances (unit utility, functional and topological relationships) and semantic scene understanding are key to building a generic, scalable and cognitive architecture for visual perception. ‘Affordance based object recognition’ or recognition based on affordance features is an important step in this regard. In this paper, we extend the scope of affordance features to define ‘Conceptual Equiva...
متن کامل