Learning to Attend to Salient Targets in Driving Videos Using Fully Convolutional RNN
Ashish Tawari, Praneeta Mallela, Sujitha Martin · 2018
Driving involves the processing of rich audio, visual and haptic signals to make safe and calculated decisions on the road. Human vision plays a crucial role in this task and analysis of the gaze behavior could provide some insights into the action the driver takes upon seeing an object/region. A typical representation of the gaze behavior is a saliency map. The work in this paper aims to predict this saliency map given a sequence of image frames. Strategies are developed to address important topics for video saliency including active gaze (i.e. gaze that is useful for driving), pixel- and object-level information, and suppression of non-negative pixels in the saliency maps. These strategies enabled the development of a novel pixel- and object-level saliency ground truth dataset using real-world driving data around traffic intersections. We further proposed a fully convolutional RNN architecture capable of handling time sequence image data to estimate saliency map. Our methodology shows promising results.