Controlling the Visual Attention of Intelligent Vehicles

A. Barta, B. Takcs, and I. Vajk (Hungary)


Computer vision, visual attention, image processing, artificial intelligence, and neural networks


The paper presents a visual attention control mechanism for intelligent vehicles. The main problem of visual navigation is how to extract meaningful information from the huge amount of available data. Visual attention control reduces the processing requirement by adaptively searching the input images. The paper presents a network architecture that is capable of providing bottom up, top down and lateral information flow. The framework to accomplish the three-directional information flow is the Layered Dual Pyramid (LDP) architecture. A traffic sign recognition example is used to demonstrate the application of the architecture

Important Links:

Go Back